diff --git a/.asf.yaml b/.asf.yaml
index e96b43cf0..75b2262de 100644
--- a/.asf.yaml
+++ b/.asf.yaml
@@ -29,6 +29,10 @@ github:
     rebase: false
   features:
     issues: true
+  protected_branches:
+    main:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
 
 staging:
   whoami: asf-staging
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index acabad3ca..61896e43d 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -33,7 +33,7 @@ jobs:
         with:
           python-version: "3.12"
 
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
@@ -52,7 +52,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
@@ -94,7 +94,7 @@ jobs:
           version: "27.4"
           repo-token: ${{ secrets.GITHUB_TOKEN }}
 
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
@@ -150,7 +150,7 @@ jobs:
           version: "27.4"
           repo-token: ${{ secrets.GITHUB_TOKEN }}
 
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
diff --git a/.github/workflows/docs.yaml b/.github/workflows/docs.yaml
index 9037e0a5c..9341488a0 100644
--- a/.github/workflows/docs.yaml
+++ b/.github/workflows/docs.yaml
@@ -58,7 +58,7 @@ jobs:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Install dependencies and build
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
index da3582766..31c2febea 100644
--- a/.github/workflows/test.yaml
+++ b/.github/workflows/test.yaml
@@ -76,7 +76,7 @@ jobs:
         run: cargo clippy --all-targets --all-features -- -D clippy::all -D warnings -A clippy::redundant_closure
 
       - name: Install dependencies and build
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
             enable-cache: true
 
@@ -91,9 +91,9 @@ jobs:
 
       - name: FFI unit tests
         run: |
-          cd examples/ffi-table-provider
+          cd examples/datafusion-ffi-example
           uv run --no-project maturin develop --uv
-          uv run --no-project pytest python/tests/_test_table_provider.py
+          uv run --no-project pytest python/tests/_test*.py
 
       - name: Cache the generated dataset
         id: cache-tpch-dataset
diff --git a/Cargo.lock b/Cargo.lock
index 5c7f2bf3c..39489ed94 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -73,13 +73,13 @@ checksum = "aae1277d39aeec15cb388266ecc24b11c80469deae6067e17a1a7aa9e5c1f234"
 
 [[package]]
 name = "ahash"
-version = "0.8.11"
+version = "0.8.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
  "const-random",
- "getrandom 0.2.15",
+ "getrandom 0.3.3",
  "once_cell",
  "version_check",
  "zerocopy",
@@ -132,9 +132,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.95"
+version = "1.0.98"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34ac096ce696dc2fcabef30516bb13c0a68a11d30131d3df6f04711467681b04"
+checksum = "e16d2d3311acee920a9eb8d33b8cbc1787ce4a264e85f964c2404b969bdcd487"
 
 [[package]]
 name = "apache-avro"
@@ -150,7 +150,7 @@ dependencies = [
  "log",
  "num-bigint",
  "quad-rand",
- "rand",
+ "rand 0.8.5",
  "regex-lite",
  "serde",
  "serde_bytes",
@@ -179,9 +179,9 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
 
 [[package]]
 name = "arrow"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "755b6da235ac356a869393c23668c663720b8749dd6f15e52b6c214b4b964cc7"
+checksum = "b1bb018b6960c87fd9d025009820406f74e83281185a8bdcb44880d2aa5c9a87"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -201,9 +201,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-arith"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "64656a1e0b13ca766f8440752e9a93e11014eec7b67909986f83ed0ab1fe37b8"
+checksum = "44de76b51473aa888ecd6ad93ceb262fb8d40d1f1154a4df2f069b3590aa7575"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -215,9 +215,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-array"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57a4a6d2896083cfbdf84a71a863b22460d0708f8206a8373c52e326cc72ea1a"
+checksum = "29ed77e22744475a9a53d00026cf8e166fe73cf42d89c4c4ae63607ee1cfcc3f"
 dependencies = [
  "ahash",
  "arrow-buffer",
@@ -226,15 +226,15 @@ dependencies = [
  "chrono",
  "chrono-tz",
  "half",
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
  "num",
 ]
 
 [[package]]
 name = "arrow-buffer"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cef870583ce5e4f3b123c181706f2002fb134960f9a911900f64ba4830c7a43a"
+checksum = "b0391c96eb58bf7389171d1e103112d3fc3e5625ca6b372d606f2688f1ea4cce"
 dependencies = [
  "bytes",
  "half",
@@ -243,9 +243,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-cast"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ac7eba5a987f8b4a7d9629206ba48e19a1991762795bbe5d08497b7736017ee"
+checksum = "f39e1d774ece9292697fcbe06b5584401b26bd34be1bec25c33edae65c2420ff"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -264,9 +264,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-csv"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90f12542b8164398fc9ec595ff783c4cf6044daa89622c5a7201be920e4c0d4c"
+checksum = "9055c972a07bf12c2a827debfd34f88d3b93da1941d36e1d9fee85eebe38a12a"
 dependencies = [
  "arrow-array",
  "arrow-cast",
@@ -280,9 +280,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-data"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b095e8a4f3c309544935d53e04c3bfe4eea4e71c3de6fe0416d1f08bb4441a83"
+checksum = "cf75ac27a08c7f48b88e5c923f267e980f27070147ab74615ad85b5c5f90473d"
 dependencies = [
  "arrow-buffer",
  "arrow-schema",
@@ -292,9 +292,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-ipc"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65c63da4afedde2b25ef69825cd4663ca76f78f79ffe2d057695742099130ff6"
+checksum = "a222f0d93772bd058d1268f4c28ea421a603d66f7979479048c429292fac7b2e"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -306,9 +306,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-json"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9551d9400532f23a370cabbea1dc5a53c49230397d41f96c4c8eedf306199305"
+checksum = "9085342bbca0f75e8cb70513c0807cc7351f1fbf5cb98192a67d5e3044acb033"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -319,16 +319,18 @@ dependencies = [
  "half",
  "indexmap",
  "lexical-core",
+ "memchr",
  "num",
  "serde",
  "serde_json",
+ "simdutf8",
 ]
 
 [[package]]
 name = "arrow-ord"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c07223476f8219d1ace8cd8d85fa18c4ebd8d945013f25ef5c72e85085ca4ee"
+checksum = "ab2f1065a5cad7b9efa9e22ce5747ce826aa3855766755d4904535123ef431e7"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -339,9 +341,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-row"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91b194b38bfd89feabc23e798238989c6648b2506ad639be42ec8eb1658d82c4"
+checksum = "3703a0e3e92d23c3f756df73d2dc9476873f873a76ae63ef9d3de17fda83b2d8"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -352,18 +354,18 @@ dependencies = [
 
 [[package]]
 name = "arrow-schema"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0f40f6be8f78af1ab610db7d9b236e21d587b7168e368a36275d2e5670096735"
+checksum = "73a47aa0c771b5381de2b7f16998d351a6f4eb839f1e13d48353e17e873d969b"
 dependencies = [
- "bitflags 2.8.0",
+ "bitflags",
 ]
 
 [[package]]
 name = "arrow-select"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac265273864a820c4a179fc67182ccc41ea9151b97024e1be956f0f2369c2539"
+checksum = "24b7b85575702b23b85272b01bc1c25a01c9b9852305e5d0078c79ba25d995d4"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -375,9 +377,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-string"
-version = "54.2.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d44c8eed43be4ead49128370f7131f054839d3d6003e52aebf64322470b8fbd0"
+checksum = "9260fddf1cdf2799ace2b4c2fc0356a9789fa7551e0953e35435536fecefebbd"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -404,11 +406,11 @@ dependencies = [
 
 [[package]]
 name = "async-compression"
-version = "0.4.18"
+version = "0.4.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df895a515f70646414f4b45c0b79082783b80552b373a68283012928df56f522"
+checksum = "06575e6a9673580f52661c92107baabffbf41e2141373441cbcdc47cb733003c"
 dependencies = [
- "bzip2 0.4.4",
+ "bzip2 0.5.2",
  "flate2",
  "futures-core",
  "memchr",
@@ -436,18 +438,18 @@ checksum = "3b43422f69d8ff38f95f1b2bb76517c91589a924d1559a0e935d7c8ce0274c11"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "async-trait"
-version = "0.1.86"
+version = "0.1.88"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "644dd749086bf3771a2fbc5f256fdb982d53f011c7d5d560304eafeecebce79d"
+checksum = "e539d3fca749fcee5236ab05e93a52867dd549cc157c8cb7f99595f3cedffdb5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -473,9 +475,9 @@ checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
 
 [[package]]
 name = "backtrace"
-version = "0.3.74"
+version = "0.3.75"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a"
+checksum = "6806a6321ec58106fea15becdad98371e28d92ccbc7c8f1b3b6dd724fe8f1002"
 dependencies = [
  "addr2line",
  "cfg-if",
@@ -483,7 +485,7 @@ dependencies = [
  "miniz_oxide",
  "object",
  "rustc-demangle",
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -500,9 +502,9 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "bigdecimal"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f31f3af01c5c65a07985c804d3366560e6fa7883d640a122819b14ec327482c"
+checksum = "1a22f228ab7a1b23027ccc6c350b72868017af7ea8356fbdf19f8d991c690013"
 dependencies = [
  "autocfg",
  "libm",
@@ -514,15 +516,9 @@ dependencies = [
 
 [[package]]
 name = "bitflags"
-version = "1.3.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
-
-[[package]]
-name = "bitflags"
-version = "2.8.0"
+version = "2.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f68f53c83ab957f72c32642f3868eec03eb974d1fb82e453128456482613d36"
+checksum = "1b8e56985ec62d17e9c1001dc89c88ecd7dc08e47eba5ec7c29c7b5eeecde967"
 
 [[package]]
 name = "blake2"
@@ -535,9 +531,9 @@ dependencies = [
 
 [[package]]
 name = "blake3"
-version = "1.5.5"
+version = "1.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8ee0c1824c4dea5b5f81736aff91bae041d2c07ee1192bec91054e10e3e601e"
+checksum = "3888aaa89e4b2a40fca9848e400f6a658a5a3978de7be858e209cafa8be9a4a0"
 dependencies = [
  "arrayref",
  "arrayvec",
@@ -557,9 +553,9 @@ dependencies = [
 
 [[package]]
 name = "brotli"
-version = "7.0.0"
+version = "8.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc97b8f16f944bba54f0433f07e30be199b6dc2bd25937444bbad560bcea29bd"
+checksum = "9991eea70ea4f293524138648e41ee89b0b2b12ddef3b255effa43c8056e0e0d"
 dependencies = [
  "alloc-no-stdlib",
  "alloc-stdlib",
@@ -568,9 +564,9 @@ dependencies = [
 
 [[package]]
 name = "brotli-decompressor"
-version = "4.0.2"
+version = "5.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74fa05ad7d803d413eb8380983b092cbbaf9a85f151b871360e7b00cd7060b37"
+checksum = "874bb8112abecc98cbd6d81ea4fa7e94fb9449648c93cc89aa40c81c24d7de03"
 dependencies = [
  "alloc-no-stdlib",
  "alloc-stdlib",
@@ -590,9 +586,9 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
 
 [[package]]
 name = "bytes"
-version = "1.10.0"
+version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f61dac84819c6588b558454b194026eb1f09c293b9036ae9b159e74e73ab6cf9"
+checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
 
 [[package]]
 name = "bzip2"
@@ -606,29 +602,28 @@ dependencies = [
 
 [[package]]
 name = "bzip2"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75b89e7c29231c673a61a46e722602bcd138298f6b9e81e71119693534585f5c"
+checksum = "49ecfb22d906f800d4fe833b6282cf4dc1c298f5057ca0b5445e5c209735ca47"
 dependencies = [
  "bzip2-sys",
 ]
 
 [[package]]
 name = "bzip2-sys"
-version = "0.1.12+1.0.8"
+version = "0.1.13+1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72ebc2f1a417f01e1da30ef264ee86ae31d2dcd2d603ea283d3c244a883ca2a9"
+checksum = "225bff33b2141874fe80d71e07d6eec4f85c5c216453dd96388240f96e1acc14"
 dependencies = [
  "cc",
- "libc",
  "pkg-config",
 ]
 
 [[package]]
 name = "cc"
-version = "1.2.14"
+version = "1.2.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c3d1b2e905a3a7b00a6141adb0e4c0bb941d11caf55349d863942a1cc44e3c9"
+checksum = "5f4ac86a9e5bc1e2b3449ab9d7d3a6a405e3d1bb28d7b9be8614f55846ae3766"
 dependencies = [
  "jobserver",
  "libc",
@@ -649,22 +644,22 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrono"
-version = "0.4.39"
+version = "0.4.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e36cc9d416881d2e24f9a963be5fb1cd90966419ac844274161d10488b3e825"
+checksum = "c469d952047f47f91b68d1cba3f10d63c11d73e4636f24f08daf0278abf01c4d"
 dependencies = [
  "android-tzdata",
  "iana-time-zone",
  "num-traits",
  "serde",
- "windows-targets",
+ "windows-link",
 ]
 
 [[package]]
 name = "chrono-tz"
-version = "0.10.1"
+version = "0.10.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c6ac4f2c0bf0f44e9161aec9675e1050aa4a530663c4a9e37e108fa948bca9f"
+checksum = "efdce149c370f133a071ca8ef6ea340b7b88748ab0810097a9e2976eaa34b4f3"
 dependencies = [
  "chrono",
  "chrono-tz-build",
@@ -673,9 +668,9 @@ dependencies = [
 
 [[package]]
 name = "chrono-tz-build"
-version = "0.4.0"
+version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e94fea34d77a245229e7746bd2beb786cd2a896f306ff491fb8cecb3074b10a7"
+checksum = "8f10f8c9340e31fc120ff885fcdb54a0b48e474bbd77cab557f0c30a3e569402"
 dependencies = [
  "parse-zoneinfo",
  "phf_codegen",
@@ -715,7 +710,7 @@ version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
 dependencies = [
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
  "once_cell",
  "tiny-keccak",
 ]
@@ -792,9 +787,9 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-channel"
-version = "0.5.14"
+version = "0.5.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "06ba6d68e24814cb8de6bb986db8222d3a027d15872cabc0d18817bc3c0e4471"
+checksum = "82b8f8f868b36967f9606790d1903570de9ceaf870a7bf9fbbd3016d636a2cb2"
 dependencies = [
  "crossbeam-utils",
 ]
@@ -864,51 +859,54 @@ dependencies = [
 
 [[package]]
 name = "datafusion"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eae420e7a5b0b7f1c39364cc76cbcd0f5fdc416b2514ae3847c2676bbd60702a"
+checksum = "ffe060b978f74ab446be722adb8a274e052e005bf6dfd171caadc3abaad10080"
 dependencies = [
- "apache-avro",
  "arrow",
- "arrow-array",
  "arrow-ipc",
  "arrow-schema",
- "async-compression",
  "async-trait",
  "bytes",
- "bzip2 0.5.1",
+ "bzip2 0.5.2",
  "chrono",
  "datafusion-catalog",
+ "datafusion-catalog-listing",
  "datafusion-common",
  "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-datasource-avro",
+ "datafusion-datasource-csv",
+ "datafusion-datasource-json",
+ "datafusion-datasource-parquet",
  "datafusion-execution",
  "datafusion-expr",
+ "datafusion-expr-common",
  "datafusion-functions",
  "datafusion-functions-aggregate",
  "datafusion-functions-nested",
  "datafusion-functions-table",
  "datafusion-functions-window",
+ "datafusion-macros",
  "datafusion-optimizer",
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
  "datafusion-physical-optimizer",
  "datafusion-physical-plan",
+ "datafusion-session",
  "datafusion-sql",
  "flate2",
  "futures",
- "glob",
  "itertools 0.14.0",
  "log",
- "num-traits",
  "object_store",
  "parking_lot",
  "parquet",
- "rand",
+ "rand 0.8.5",
  "regex",
  "sqlparser",
  "tempfile",
  "tokio",
- "tokio-util",
  "url",
  "uuid",
  "xz2",
@@ -917,38 +915,63 @@ dependencies = [
 
 [[package]]
 name = "datafusion-catalog"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f27987bc22b810939e8dfecc55571e9d50355d6ea8ec1c47af8383a76a6d0e1"
+checksum = "61fe34f401bd03724a1f96d12108144f8cd495a3cdda2bf5e091822fb80b7e66"
 dependencies = [
  "arrow",
  "async-trait",
  "dashmap",
  "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
  "datafusion-execution",
  "datafusion-expr",
+ "datafusion-physical-expr",
  "datafusion-physical-plan",
+ "datafusion-session",
  "datafusion-sql",
  "futures",
  "itertools 0.14.0",
  "log",
+ "object_store",
  "parking_lot",
- "sqlparser",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-catalog-listing"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4411b8e3bce5e0fc7521e44f201def2e2d5d1b5f176fb56e8cdc9942c890f00"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "log",
+ "object_store",
+ "tokio",
 ]
 
 [[package]]
 name = "datafusion-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3f6d5b8c9408cc692f7c194b8aa0c0f9b253e065a8d960ad9cdc2a13e697602"
+checksum = "0734015d81c8375eb5d4869b7f7ecccc2ee8d6cb81948ef737cd0e7b743bd69c"
 dependencies = [
  "ahash",
  "apache-avro",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ipc",
- "arrow-schema",
  "base64 0.22.1",
  "half",
  "hashbrown 0.14.5",
@@ -966,25 +989,168 @@ dependencies = [
 
 [[package]]
 name = "datafusion-common-runtime"
-version = "45.0.0"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5167bb1d2ccbb87c6bc36c295274d7a0519b14afcfdaf401d53cbcaa4ef4968b"
+dependencies = [
+ "futures",
+ "log",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04e602dcdf2f50c2abf297cc2203c73531e6f48b29516af7695d338cf2a778b1"
+dependencies = [
+ "arrow",
+ "async-compression",
+ "async-trait",
+ "bytes",
+ "bzip2 0.5.2",
+ "chrono",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "flate2",
+ "futures",
+ "glob",
+ "itertools 0.14.0",
+ "log",
+ "object_store",
+ "parquet",
+ "rand 0.8.5",
+ "tempfile",
+ "tokio",
+ "tokio-util",
+ "url",
+ "xz2",
+ "zstd",
+]
+
+[[package]]
+name = "datafusion-datasource-avro"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4ea5111aab9d3f2a8bff570343cccb03ce4c203875ef5a566b7d6f1eb72559e"
+dependencies = [
+ "apache-avro",
+ "arrow",
+ "async-trait",
+ "bytes",
+ "chrono",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "num-traits",
+ "object_store",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource-csv"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3bb2253952dc32296ed5b84077cb2e0257fea4be6373e1c376426e17ead4ef6"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "object_store",
+ "regex",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource-json"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d4603c8e8a4baf77660ab7074cc66fc15cc8a18f2ce9dfadb755fc6ee294e48"
+checksum = "5b8c7f47a5d2fe03bfa521ec9bafdb8a5c82de8377f60967c3663f00c8790352"
 dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "object_store",
+ "serde_json",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource-parquet"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "27d15868ea39ed2dc266728b554f6304acd473de2142281ecfa1294bb7415923"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-functions-aggregate",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-optimizer",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "itertools 0.14.0",
  "log",
+ "object_store",
+ "parking_lot",
+ "parquet",
+ "rand 0.8.5",
  "tokio",
 ]
 
 [[package]]
 name = "datafusion-doc"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5bf4bc68623a5cf231eed601ed6eb41f46a37c4d15d11a0bff24cbc8396cd66"
+checksum = "a91f8c2c5788ef32f48ff56c68e5b545527b744822a284373ac79bba1ba47292"
 
 [[package]]
 name = "datafusion-execution"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88b491c012cdf8e051053426013429a76f74ee3c2db68496c79c323ca1084d27"
+checksum = "06f004d100f49a3658c9da6fb0c3a9b760062d96cd4ad82ccc3b7b69a9fb2f84"
 dependencies = [
  "arrow",
  "dashmap",
@@ -994,16 +1160,16 @@ dependencies = [
  "log",
  "object_store",
  "parking_lot",
- "rand",
+ "rand 0.8.5",
  "tempfile",
  "url",
 ]
 
 [[package]]
 name = "datafusion-expr"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5a181408d4fc5dc22f9252781a8f39f2d0e5d1b33ec9bde242844980a2689c1"
+checksum = "7a4e4ce3802609be38eeb607ee72f6fe86c3091460de9dbfae9e18db423b3964"
 dependencies = [
  "arrow",
  "chrono",
@@ -1022,25 +1188,25 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1129b48e8534d8c03c6543bcdccef0b55c8ac0c1272a15a56c67068b6eb1885"
+checksum = "422ac9cf3b22bbbae8cdf8ceb33039107fde1b5492693168f13bd566b1bcc839"
 dependencies = [
  "arrow",
  "datafusion-common",
+ "indexmap",
  "itertools 0.14.0",
  "paste",
 ]
 
 [[package]]
 name = "datafusion-ffi"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff47a79d442207c168c6e3e1d970c248589c148e4800e5b285ac1b2cb1a230f8"
+checksum = "5cf3fe9ab492c56daeb7beed526690d33622d388b8870472e0b7b7f55490338c"
 dependencies = [
  "abi_stable",
  "arrow",
- "arrow-array",
  "arrow-schema",
  "async-ffi",
  "async-trait",
@@ -1055,9 +1221,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6125874e4856dfb09b59886784fcb74cde5cfc5930b3a80a1a728ef7a010df6b"
+checksum = "2ddf0a0a2db5d2918349c978d42d80926c6aa2459cd8a3c533a84ec4bb63479e"
 dependencies = [
  "arrow",
  "arrow-buffer",
@@ -1071,12 +1237,11 @@ dependencies = [
  "datafusion-expr",
  "datafusion-expr-common",
  "datafusion-macros",
- "hashbrown 0.14.5",
  "hex",
  "itertools 0.14.0",
  "log",
  "md-5",
- "rand",
+ "rand 0.8.5",
  "regex",
  "sha2",
  "unicode-segmentation",
@@ -1085,14 +1250,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3add7b1d3888e05e7c95f2b281af900ca69ebdcb21069ba679b33bde8b3b9d6"
+checksum = "408a05dafdc70d05a38a29005b8b15e21b0238734dab1e98483fcb58038c5aba"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -1108,9 +1271,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e18baa4cfc3d2f144f74148ed68a1f92337f5072b6dde204a0dbbdf3324989c"
+checksum = "756d21da2dd6c9bef97af1504970ff56cbf35d03fbd4ffd62827f02f4d2279d4"
 dependencies = [
  "ahash",
  "arrow",
@@ -1121,15 +1284,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-nested"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3ec5ee8cecb0dc370291279673097ddabec03a011f73f30d7f1096457127e03e"
+checksum = "8d8d50f6334b378930d992d801a10ac5b3e93b846b39e4a05085742572844537"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -1145,9 +1305,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-table"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c403ddd473bbb0952ba880008428b3c7febf0ed3ce1eec35a205db20efb2a36"
+checksum = "cc9a97220736c8fff1446e936be90d57216c06f28969f9ffd3b72ac93c958c8a"
 dependencies = [
  "arrow",
  "async-trait",
@@ -1161,9 +1321,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ab18c2fb835614d06a75f24a9e09136d3a8c12a92d97c95a6af316a1787a9c5"
+checksum = "cefc2d77646e1aadd1d6a9c40088937aedec04e68c5f0465939912e1291f8193"
 dependencies = [
  "datafusion-common",
  "datafusion-doc",
@@ -1178,9 +1338,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a77b73bc15e7d1967121fdc7a55d819bfb9d6c03766a6c322247dce9094a53a4"
+checksum = "dd4aff082c42fa6da99ce0698c85addd5252928c908eb087ca3cfa64ff16b313"
 dependencies = [
  "datafusion-common",
  "datafusion-physical-expr-common",
@@ -1188,20 +1348,20 @@ dependencies = [
 
 [[package]]
 name = "datafusion-macros"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09369b8d962291e808977cf94d495fd8b5b38647232d7ef562c27ac0f495b0af"
+checksum = "df6f88d7ee27daf8b108ba910f9015176b36fbc72902b1ca5c2a5f1d1717e1a1"
 dependencies = [
  "datafusion-expr",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "datafusion-optimizer"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2403a7e4a84637f3de7d8d4d7a9ccc0cc4be92d89b0161ba3ee5be82f0531c54"
+checksum = "084d9f979c4b155346d3c34b18f4256e6904ded508e9554d90fed416415c3515"
 dependencies = [
  "arrow",
  "chrono",
@@ -1218,15 +1378,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86ff72ac702b62dbf2650c4e1d715ebd3e4aab14e3885e72e8549e250307347c"
+checksum = "64c536062b0076f4e30084065d805f389f9fe38af0ca75bcbac86bc5e9fbab65"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-expr",
  "datafusion-expr-common",
@@ -1243,13 +1400,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60982b7d684e25579ee29754b4333057ed62e2cc925383c5f0bd8cab7962f435"
+checksum = "f8a92b53b3193fac1916a1c5b8e3f4347c526f6822e56b71faa5fb372327a863"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
  "datafusion-common",
  "datafusion-expr-common",
  "hashbrown 0.14.5",
@@ -1258,12 +1414,11 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-optimizer"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac5e85c189d5238a5cf181a624e450c4cd4c66ac77ca551d6f3ff9080bac90bb"
+checksum = "6fa0a5ac94c7cf3da97bedabd69d6bbca12aef84b9b37e6e9e8c25286511b5e2"
 dependencies = [
  "arrow",
- "arrow-schema",
  "datafusion-common",
  "datafusion-execution",
  "datafusion-expr",
@@ -1271,23 +1426,19 @@ dependencies = [
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
  "datafusion-physical-plan",
- "futures",
  "itertools 0.14.0",
  "log",
  "recursive",
- "url",
 ]
 
 [[package]]
 name = "datafusion-physical-plan"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c36bf163956d7e2542657c78b3383fdc78f791317ef358a359feffcdb968106f"
+checksum = "690c615db468c2e5fe5085b232d8b1c088299a6c63d87fd960a354a71f7acb55"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
  "arrow-schema",
  "async-trait",
@@ -1312,9 +1463,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-proto"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2db5d79f0c974041787b899d24dc91bdab2ff112d1942dd71356a4ce3b407e6c"
+checksum = "a4a1afb2bdb05de7ff65be6883ebfd4ec027bd9f1f21c46aa3afd01927160a83"
 dependencies = [
  "arrow",
  "chrono",
@@ -1328,9 +1479,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-proto-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de21bde1603aac0ff32cf478e47081be6e3583c6861fe8f57034da911efe7578"
+checksum = "35b7a5876ebd6b564fb9a1fd2c3a2a9686b787071a256b47e4708f0916f9e46f"
 dependencies = [
  "arrow",
  "datafusion-common",
@@ -1339,7 +1490,7 @@ dependencies = [
 
 [[package]]
 name = "datafusion-python"
-version = "45.2.0"
+version = "47.0.0"
 dependencies = [
  "arrow",
  "async-trait",
@@ -1360,15 +1511,37 @@ dependencies = [
  "uuid",
 ]
 
+[[package]]
+name = "datafusion-session"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad229a134c7406c057ece00c8743c0c34b97f4e72f78b475fe17b66c5e14fa4f"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "dashmap",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-plan",
+ "datafusion-sql",
+ "futures",
+ "itertools 0.14.0",
+ "log",
+ "object_store",
+ "parking_lot",
+ "tokio",
+]
+
 [[package]]
 name = "datafusion-sql"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13caa4daede211ecec53c78b13c503b592794d125f9a3cc3afe992edf9e7f43"
+checksum = "64f6ab28b72b664c21a27b22a2ff815fd390ed224c26e89a93b5a8154a4e8607"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-schema",
  "bigdecimal",
  "datafusion-common",
  "datafusion-expr",
@@ -1381,11 +1554,10 @@ dependencies = [
 
 [[package]]
 name = "datafusion-substrait"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1634405abd8bd3c64c352f2da2f2aec6d80a815930257e0db0ce4ff5daf00944"
+checksum = "061efc0937f0ce3abb37ed0d56cfa01dd0e654b90e408656d05e846c8b7599fe"
 dependencies = [
- "arrow-buffer",
  "async-recursion",
  "async-trait",
  "chrono",
@@ -1395,6 +1567,7 @@ dependencies = [
  "pbjson-types",
  "prost",
  "substrait",
+ "tokio",
  "url",
 ]
 
@@ -1417,20 +1590,20 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "dyn-clone"
-version = "1.0.18"
+version = "1.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "feeef44e73baff3a26d371801df019877a9866a8c493d315ab00177843314f35"
+checksum = "1c7a8fb8a9fbf66c1f703fe16184d10ca0ee9d23be5b4436400408ba54a95005"
 
 [[package]]
 name = "either"
-version = "1.13.0"
+version = "1.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
 
 [[package]]
 name = "equivalent"
@@ -1440,9 +1613,9 @@ checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
 
 [[package]]
 name = "errno"
-version = "0.3.10"
+version = "0.3.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "33d852cb9b869c2a9b3df2f71a3074817f01e1844f839a144f5fcef059a4eb5d"
+checksum = "cea14ef9355e3beab063703aa9dab15afd25f0667c341310c1e5274bb1d0da18"
 dependencies = [
  "libc",
  "windows-sys 0.59.0",
@@ -1462,21 +1635,22 @@ checksum = "1d674e81391d1e1ab681a28d99df07927c6d4aa5b027d7da16ba32d1d21ecd99"
 
 [[package]]
 name = "flatbuffers"
-version = "24.12.23"
+version = "25.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f1baf0dbf96932ec9a3038d57900329c015b0bfb7b63d904f3bc27e2b02a096"
+checksum = "1045398c1bfd89168b5fd3f1fc11f6e70b34f6f66300c87d44d3de849463abf1"
 dependencies = [
- "bitflags 1.3.2",
+ "bitflags",
  "rustc_version",
 ]
 
 [[package]]
 name = "flate2"
-version = "1.0.35"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c936bfdafb507ebbf50b8074c54fa31c5be9a1e7e5f467dd659697041407d07c"
+checksum = "7ced92e76e966ca2fd84c8f7aa01a4aea65b0eb6648d72f7c8f3e2764a67fece"
 dependencies = [
  "crc32fast",
+ "libz-rs-sys",
  "miniz_oxide",
 ]
 
@@ -1488,9 +1662,9 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
 name = "foldhash"
-version = "0.1.4"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0d2fde1f7b3d48b8395d5f2de76c18a528bd6a9cdde438df747bfcba3e05d6f"
+checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"
 
 [[package]]
 name = "form_urlencoded"
@@ -1557,7 +1731,7 @@ checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -1611,9 +1785,9 @@ dependencies = [
 
 [[package]]
 name = "getrandom"
-version = "0.2.15"
+version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
+checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
 dependencies = [
  "cfg-if",
  "js-sys",
@@ -1624,14 +1798,16 @@ dependencies = [
 
 [[package]]
 name = "getrandom"
-version = "0.3.1"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43a49c392881ce6d5c3b8cb70f98717b7c07aabbdff06687b9030dbfbe2725f8"
+checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
 dependencies = [
  "cfg-if",
+ "js-sys",
  "libc",
- "wasi 0.13.3+wasi-0.2.2",
- "windows-targets",
+ "r-efi",
+ "wasi 0.14.2+wasi-0.2.4",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -1648,9 +1824,9 @@ checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"
 
 [[package]]
 name = "h2"
-version = "0.4.7"
+version = "0.4.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ccae279728d634d083c00f6099cb58f01cc99c145b84b8be2f6c74618d79922e"
+checksum = "a9421a676d1b147b16b82c9225157dc629087ef8ec4d5e2960f9437a90dac0a5"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -1667,9 +1843,9 @@ dependencies = [
 
 [[package]]
 name = "half"
-version = "2.4.1"
+version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6dd08c532ae367adf81c312a4580bc67f1d0fe8bc9c460520283f4c0ff277888"
+checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9"
 dependencies = [
  "cfg-if",
  "crunchy",
@@ -1688,9 +1864,9 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.15.2"
+version = "0.15.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289"
+checksum = "84b26c544d002229e640969970a2e74021aadf6e2f96372b9c58eff97de08eb3"
 dependencies = [
  "allocator-api2",
  "equivalent",
@@ -1711,9 +1887,9 @@ checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "http"
-version = "1.2.0"
+version = "1.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f16ca2af56261c99fba8bac40a10251ce8188205a4c448fbb745a2e4daa76fea"
+checksum = "f4a85d31aea989eead29a3aaf9e1115a180df8282431156e533de47660892565"
 dependencies = [
  "bytes",
  "fnv",
@@ -1732,12 +1908,12 @@ dependencies = [
 
 [[package]]
 name = "http-body-util"
-version = "0.1.2"
+version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "793429d76616a256bcb62c2a2ec2bed781c8307e797e2598c50010f2bee2544f"
+checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
 dependencies = [
  "bytes",
- "futures-util",
+ "futures-core",
  "http",
  "http-body",
  "pin-project-lite",
@@ -1745,15 +1921,15 @@ dependencies = [
 
 [[package]]
 name = "httparse"
-version = "1.10.0"
+version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2d708df4e7140240a16cd6ab0ab65c972d7433ab77819ea693fde9c43811e2a"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
 
 [[package]]
 name = "humantime"
-version = "2.1.0"
+version = "2.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4"
+checksum = "9b112acc8b3adf4b107a8ec20977da0273a8c386765a3ec0229bd500a1443f9f"
 
 [[package]]
 name = "hyper"
@@ -1795,9 +1971,9 @@ dependencies = [
 
 [[package]]
 name = "hyper-util"
-version = "0.1.10"
+version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df2dcfbe0677734ab2f3ffa7fa7bfd4706bfdc1ef393f2ee30184aed67e631b4"
+checksum = "497bbc33a26fdd4af9ed9c70d63f61cf56a938375fbb32df34db9b1cd6d643f2"
 dependencies = [
  "bytes",
  "futures-channel",
@@ -1805,6 +1981,7 @@ dependencies = [
  "http",
  "http-body",
  "hyper",
+ "libc",
  "pin-project-lite",
  "socket2",
  "tokio",
@@ -1814,14 +1991,15 @@ dependencies = [
 
 [[package]]
 name = "iana-time-zone"
-version = "0.1.61"
+version = "0.1.63"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "235e081f3925a06703c2d0117ea8b91f042756fd6e7a6e5d901e8ca1a996b220"
+checksum = "b0c919e5debc312ad217002b8048a17b7d83f80703865bbfcfebb0458b0b27d8"
 dependencies = [
  "android_system_properties",
  "core-foundation-sys",
  "iana-time-zone-haiku",
  "js-sys",
+ "log",
  "wasm-bindgen",
  "windows-core",
 ]
@@ -1837,21 +2015,22 @@ dependencies = [
 
 [[package]]
 name = "icu_collections"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "db2fa452206ebee18c4b5c2274dbf1de17008e874b4dc4f0aea9d01ca79e4526"
+checksum = "200072f5d0e3614556f94a9930d5dc3e0662a652823904c3a75dc3b0af7fee47"
 dependencies = [
  "displaydoc",
+ "potential_utf",
  "yoke",
  "zerofrom",
  "zerovec",
 ]
 
 [[package]]
-name = "icu_locid"
-version = "1.5.0"
+name = "icu_locale_core"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "13acbb8371917fc971be86fc8057c41a64b521c184808a698c02acc242dbf637"
+checksum = "0cde2700ccaed3872079a65fb1a78f6c0a36c91570f28755dda67bc8f7d9f00a"
 dependencies = [
  "displaydoc",
  "litemap",
@@ -1860,31 +2039,11 @@ dependencies = [
  "zerovec",
 ]
 
-[[package]]
-name = "icu_locid_transform"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "01d11ac35de8e40fdeda00d9e1e9d92525f3f9d887cdd7aa81d727596788b54e"
-dependencies = [
- "displaydoc",
- "icu_locid",
- "icu_locid_transform_data",
- "icu_provider",
- "tinystr",
- "zerovec",
-]
-
-[[package]]
-name = "icu_locid_transform_data"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fdc8ff3388f852bede6b579ad4e978ab004f139284d7b28715f773507b946f6e"
-
 [[package]]
 name = "icu_normalizer"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "19ce3e0da2ec68599d193c93d088142efd7f9c5d6fc9b803774855747dc6a84f"
+checksum = "436880e8e18df4d7bbc06d58432329d6458cc84531f7ac5f024e93deadb37979"
 dependencies = [
  "displaydoc",
  "icu_collections",
@@ -1892,67 +2051,54 @@ dependencies = [
  "icu_properties",
  "icu_provider",
  "smallvec",
- "utf16_iter",
- "utf8_iter",
- "write16",
  "zerovec",
 ]
 
 [[package]]
 name = "icu_normalizer_data"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8cafbf7aa791e9b22bec55a167906f9e1215fd475cd22adfcf660e03e989516"
+checksum = "00210d6893afc98edb752b664b8890f0ef174c8adbb8d0be9710fa66fbbf72d3"
 
 [[package]]
 name = "icu_properties"
-version = "1.5.1"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93d6020766cfc6302c15dbbc9c8778c37e62c14427cb7f6e601d849e092aeef5"
+checksum = "2549ca8c7241c82f59c80ba2a6f415d931c5b58d24fb8412caa1a1f02c49139a"
 dependencies = [
  "displaydoc",
  "icu_collections",
- "icu_locid_transform",
+ "icu_locale_core",
  "icu_properties_data",
  "icu_provider",
- "tinystr",
+ "potential_utf",
+ "zerotrie",
  "zerovec",
 ]
 
 [[package]]
 name = "icu_properties_data"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67a8effbc3dd3e4ba1afa8ad918d5684b8868b3b26500753effea8d2eed19569"
+checksum = "8197e866e47b68f8f7d95249e172903bec06004b18b2937f1095d40a0c57de04"
 
 [[package]]
 name = "icu_provider"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ed421c8a8ef78d3e2dbc98a973be2f3770cb42b606e3ab18d6237c4dfde68d9"
+checksum = "03c80da27b5f4187909049ee2d72f276f0d9f99a42c306bd0131ecfe04d8e5af"
 dependencies = [
  "displaydoc",
- "icu_locid",
- "icu_provider_macros",
+ "icu_locale_core",
  "stable_deref_trait",
  "tinystr",
  "writeable",
  "yoke",
  "zerofrom",
+ "zerotrie",
  "zerovec",
 ]
 
-[[package]]
-name = "icu_provider_macros"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.98",
-]
-
 [[package]]
 name = "idna"
 version = "1.0.3"
@@ -1966,9 +2112,9 @@ dependencies = [
 
 [[package]]
 name = "idna_adapter"
-version = "1.2.0"
+version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "daca1df1c957320b2cf139ac61e7bd64fed304c5040df000a745aa1de3b4ef71"
+checksum = "3acae9609540aa318d1bc588455225fb2085b9ed0c4f6bd0d9d5bcd86f1a0344"
 dependencies = [
  "icu_normalizer",
  "icu_properties",
@@ -1976,19 +2122,19 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.7.1"
+version = "2.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8c9c992b02b5b4c94ea26e32fe5bccb7aa7d9f390ab5c1221ff895bc7ea8b652"
+checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e"
 dependencies = [
  "equivalent",
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
 ]
 
 [[package]]
 name = "indoc"
-version = "2.0.5"
+version = "2.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b248f5224d1d606005e02c97f5aa4e88eeb230488bcc03bc9ca4d7991399f2b5"
+checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
 
 [[package]]
 name = "integer-encoding"
@@ -2022,16 +2168,17 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.14"
+version = "1.0.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d75a2a4b1b190afb6f5425f10f6a8f959d2ea0b9c2b1d79553551850539e4674"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
 
 [[package]]
 name = "jobserver"
-version = "0.1.32"
+version = "0.1.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48d1dbcbbeb6a7fec7e059840aa538bd62aaccf972c7346c4d9d2059312853d0"
+checksum = "38f262f097c174adebe41eb73d66ae9c06b2844fb0da69969647bbddd9b0538a"
 dependencies = [
+ "getrandom 0.3.3",
  "libc",
 ]
 
@@ -2117,9 +2264,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.169"
+version = "0.2.172"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
+checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
 
 [[package]]
 name = "libflate"
@@ -2157,31 +2304,40 @@ dependencies = [
 
 [[package]]
 name = "libm"
-version = "0.2.11"
+version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8355be11b20d696c8f18f6cc018c4e372165b1fa8126cef092399c9951984ffa"
+checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
 
 [[package]]
 name = "libmimalloc-sys"
-version = "0.1.39"
+version = "0.1.42"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23aa6811d3bd4deb8a84dde645f943476d13b248d818edcf8ce0b2f37f036b44"
+checksum = "ec9d6fac27761dabcd4ee73571cdb06b7022dc99089acbe5435691edffaac0f4"
 dependencies = [
  "cc",
  "libc",
 ]
 
+[[package]]
+name = "libz-rs-sys"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6489ca9bd760fe9642d7644e827b0c9add07df89857b0416ee15c1cc1a3b8c5a"
+dependencies = [
+ "zlib-rs",
+]
+
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.15"
+version = "0.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d26c52dbd32dccf2d10cac7725f8eae5296885fb5703b261f7d0a0739ec807ab"
+checksum = "cd945864f07fe9f5371a27ad7b52a172b4b499999f1d97574c9fa68373937e12"
 
 [[package]]
 name = "litemap"
-version = "0.7.4"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104"
+checksum = "241eaef5fd12c88705a01fc1066c48c4b36e0dd4377dcdc7ec3942cea7a69956"
 
 [[package]]
 name = "lock_api"
@@ -2195,9 +2351,15 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.25"
+version = "0.4.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "04cbf5b083de1c7e0222a7a51dbfdba1cbe1c6ab0b15e29fff3f6c077fd9cd9f"
+checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
+
+[[package]]
+name = "lru-slab"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154"
 
 [[package]]
 name = "lz4_flex"
@@ -2205,7 +2367,7 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "75761162ae2b0e580d7e7c390558127e5f01b4194debd6221fd8c207fc80e3f5"
 dependencies = [
- "twox-hash",
+ "twox-hash 1.6.3",
 ]
 
 [[package]]
@@ -2246,9 +2408,9 @@ dependencies = [
 
 [[package]]
 name = "mimalloc"
-version = "0.1.43"
+version = "0.1.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "68914350ae34959d83f732418d51e2427a794055d0b9529f48259ac07af65633"
+checksum = "995942f432bbb4822a7e9c3faa87a695185b0d09273ba85f097b54f4e458f2af"
 dependencies = [
  "libmimalloc-sys",
 ]
@@ -2261,9 +2423,9 @@ checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
 
 [[package]]
 name = "miniz_oxide"
-version = "0.8.4"
+version = "0.8.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b3b1c9bd4fe1f0f8b387f6eb9eb3b4a1aa26185e5750efb9140301703f62cd1b"
+checksum = "3be647b768db090acb35d5ec5db2b0e1f1de11133ca123b9eacf5137868f892a"
 dependencies = [
  "adler2",
 ]
@@ -2281,9 +2443,9 @@ dependencies = [
 
 [[package]]
 name = "multimap"
-version = "0.10.0"
+version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "defc4c55412d89136f966bbb339008b474350e5e6e78d2714439c386b3137a03"
+checksum = "1d87ecb2933e8aeadb3e3a02b828fed80a7528047e68b4f424523a0981a3a084"
 
 [[package]]
 name = "num"
@@ -2371,41 +2533,47 @@ dependencies = [
 
 [[package]]
 name = "object_store"
-version = "0.11.2"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3cfccb68961a56facde1163f9319e0d15743352344e7808a11795fb99698dcaf"
+checksum = "d94ac16b433c0ccf75326388c893d2835ab7457ea35ab8ba5d745c053ef5fa16"
 dependencies = [
  "async-trait",
  "base64 0.22.1",
  "bytes",
  "chrono",
+ "form_urlencoded",
  "futures",
+ "http",
+ "http-body-util",
  "httparse",
  "humantime",
  "hyper",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "md-5",
  "parking_lot",
  "percent-encoding",
  "quick-xml",
- "rand",
+ "rand 0.9.1",
  "reqwest",
  "ring",
  "rustls-pemfile",
  "serde",
  "serde_json",
- "snafu",
+ "serde_urlencoded",
+ "thiserror 2.0.12",
  "tokio",
  "tracing",
  "url",
  "walkdir",
+ "wasm-bindgen-futures",
+ "web-time",
 ]
 
 [[package]]
 name = "once_cell"
-version = "1.20.3"
+version = "1.21.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "945462a4b81e43c4e3ba96bd7b49d834c6f61198356aa858733bc4acf3cbe62e"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
 
 [[package]]
 name = "openssl-probe"
@@ -2442,14 +2610,14 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
 name = "parquet"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a01a0efa30bbd601ae85b375c728efdb211ade54390281628a7b16708beb235"
+checksum = "be7b2d778f6b841d37083ebdf32e33a524acde1266b5884a8ca29bf00dfa1231"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -2466,7 +2634,7 @@ dependencies = [
  "flate2",
  "futures",
  "half",
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
  "lz4_flex",
  "num",
  "num-bigint",
@@ -2477,9 +2645,8 @@ dependencies = [
  "snap",
  "thrift",
  "tokio",
- "twox-hash",
+ "twox-hash 2.1.0",
  "zstd",
- "zstd-sys",
 ]
 
 [[package]]
@@ -2576,7 +2743,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
 dependencies = [
  "phf_shared",
- "rand",
+ "rand 0.8.5",
 ]
 
 [[package]]
@@ -2602,40 +2769,49 @@ checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
 [[package]]
 name = "pkg-config"
-version = "0.3.31"
+version = "0.3.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2"
+checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
 
 [[package]]
 name = "portable-atomic"
-version = "1.10.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "280dc24453071f1b63954171985a0b0d30058d287960968b9b2aca264c8d4ee6"
+checksum = "350e9b48cbc6b0e028b0473b114454c6316e57336ee184ceab6e53f72c178b3e"
+
+[[package]]
+name = "potential_utf"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5a7c30837279ca13e7c867e9e40053bc68740f988cb07f7ca6df43cc734b585"
+dependencies = [
+ "zerovec",
+]
 
 [[package]]
 name = "ppv-lite86"
-version = "0.2.20"
+version = "0.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
 dependencies = [
  "zerocopy",
 ]
 
 [[package]]
 name = "prettyplease"
-version = "0.2.29"
+version = "0.2.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6924ced06e1f7dfe3fa48d57b9f74f55d8915f5036121bef647ef4b204895fac"
+checksum = "664ec5419c51e34154eec046ebcba56312d5a2fc3b09a06da188e1ad21afadf6"
 dependencies = [
  "proc-macro2",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.93"
+version = "1.0.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60946a68e5f9d28b0dc1c21bb8a97ee7d018a8b322fa57838ba31cc878e22d99"
+checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
 dependencies = [
  "unicode-ident",
 ]
@@ -2666,7 +2842,7 @@ dependencies = [
  "prost",
  "prost-types",
  "regex",
- "syn 2.0.98",
+ "syn 2.0.101",
  "tempfile",
 ]
 
@@ -2680,7 +2856,7 @@ dependencies = [
  "itertools 0.14.0",
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -2703,18 +2879,18 @@ dependencies = [
 
 [[package]]
 name = "psm"
-version = "0.1.25"
+version = "0.1.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f58e5423e24c18cc840e1c98370b3993c6649cd1678b4d24318bcf0a083cbe88"
+checksum = "6e944464ec8536cd1beb0bbfd96987eb5e3b72f2ecdafdc5c769a37f1fa2ae1f"
 dependencies = [
  "cc",
 ]
 
 [[package]]
 name = "pyo3"
-version = "0.23.4"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57fe09249128b3173d092de9523eaa75136bf7ba85e0d69eca241c7939c933cc"
+checksum = "e5203598f366b11a02b13aa20cab591229ff0a89fd121a308a5df751d5fc9219"
 dependencies = [
  "cfg-if",
  "indoc",
@@ -2730,9 +2906,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-async-runtimes"
-version = "0.23.0"
+version = "0.24.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "977dc837525cfd22919ba6a831413854beb7c99a256c03bf8624ad707e45810e"
+checksum = "dd0b83dc42f9d41f50d38180dad65f0c99763b65a3ff2a81bf351dd35a1df8bf"
 dependencies = [
  "futures",
  "once_cell",
@@ -2743,9 +2919,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.23.4"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1cd3927b5a78757a0d71aa9dff669f903b1eb64b54142a9bd9f757f8fde65fd7"
+checksum = "99636d423fa2ca130fa5acde3059308006d46f98caac629418e53f7ebb1e9999"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -2753,9 +2929,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.23.4"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dab6bb2102bd8f991e7749f130a70d05dd557613e39ed2deeee8e9ca0c4d548d"
+checksum = "78f9cf92ba9c409279bc3305b5409d90db2d2c22392d443a87df3a1adad59e33"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -2763,27 +2939,27 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.23.4"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91871864b353fd5ffcb3f91f2f703a22a9797c91b9ab497b1acac7b07ae509c7"
+checksum = "0b999cb1a6ce21f9a6b147dcf1be9ffedf02e0043aec74dc390f3007047cecd9"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.23.4"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43abc3b80bc20f3facd86cd3c60beed58c3e2aa26213f3cda368de39c60a27e4"
+checksum = "822ece1c7e1012745607d5cf0bcb2874769f0f7cb34c4cde03b9358eb9ef911a"
 dependencies = [
  "heck",
  "proc-macro2",
  "pyo3-build-config",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -2794,9 +2970,9 @@ checksum = "5a651516ddc9168ebd67b24afd085a718be02f8858fe406591b013d101ce2f40"
 
 [[package]]
 name = "quick-xml"
-version = "0.37.2"
+version = "0.37.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "165859e9e55f79d67b96c5d96f4e88b6f2695a1972849c15a6a3f5c59fc2c003"
+checksum = "331e97a1af0bf59823e6eadffe373d7b27f485be8748f71471c662c1f269b7fb"
 dependencies = [
  "memchr",
  "serde",
@@ -2804,37 +2980,40 @@ dependencies = [
 
 [[package]]
 name = "quinn"
-version = "0.11.6"
+version = "0.11.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "62e96808277ec6f97351a2380e6c25114bc9e67037775464979f3037c92d05ef"
+checksum = "626214629cda6781b6dc1d316ba307189c85ba657213ce642d9c77670f8202c8"
 dependencies = [
  "bytes",
+ "cfg_aliases",
  "pin-project-lite",
  "quinn-proto",
  "quinn-udp",
  "rustc-hash",
  "rustls",
  "socket2",
- "thiserror 2.0.11",
+ "thiserror 2.0.12",
  "tokio",
  "tracing",
+ "web-time",
 ]
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.9"
+version = "0.11.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a2fe5ef3495d7d2e377ff17b1a8ce2ee2ec2a18cde8b6ad6619d65d0701c135d"
+checksum = "49df843a9161c85bb8aae55f101bc0bac8bcafd637a620d9122fd7e0b2f7422e"
 dependencies = [
  "bytes",
- "getrandom 0.2.15",
- "rand",
+ "getrandom 0.3.3",
+ "lru-slab",
+ "rand 0.9.1",
  "ring",
  "rustc-hash",
  "rustls",
  "rustls-pki-types",
  "slab",
- "thiserror 2.0.11",
+ "thiserror 2.0.12",
  "tinyvec",
  "tracing",
  "web-time",
@@ -2842,9 +3021,9 @@ dependencies = [
 
 [[package]]
 name = "quinn-udp"
-version = "0.5.10"
+version = "0.5.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e46f3055866785f6b92bc6164b76be02ca8f2eb4b002c0354b28cf4c119e5944"
+checksum = "ee4e529991f949c5e25755532370b8af5d114acae52326361d68d47af64aa842"
 dependencies = [
  "cfg_aliases",
  "libc",
@@ -2856,13 +3035,19 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.38"
+version = "1.0.40"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e4dccaaaf89514f546c693ddc140f729f958c247918a13380cccc6078391acc"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
 dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "r-efi"
+version = "5.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
+
 [[package]]
 name = "rand"
 version = "0.8.5"
@@ -2870,8 +3055,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
 dependencies = [
  "libc",
- "rand_chacha",
- "rand_core",
+ "rand_chacha 0.3.1",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9fbfd9d094a40bf3ae768db9361049ace4c0e04a4fd6b359518bd7b73a73dd97"
+dependencies = [
+ "rand_chacha 0.9.0",
+ "rand_core 0.9.3",
 ]
 
 [[package]]
@@ -2881,7 +3076,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
 dependencies = [
  "ppv-lite86",
- "rand_core",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core 0.9.3",
 ]
 
 [[package]]
@@ -2890,7 +3095,16 @@ version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
 dependencies = [
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
+dependencies = [
+ "getrandom 0.3.3",
 ]
 
 [[package]]
@@ -2910,16 +3124,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76009fbe0614077fc1a2ce255e3a1881a2e3a3527097d5dc6d8212c585e7e38b"
 dependencies = [
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.8"
+version = "0.5.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03a862b389f93e68874fbf580b9de08dd02facb9a788ebadaf4a3fd33cf58834"
+checksum = "928fca9cf2aa042393a8325b9ead81d2f0df4cb12e1e24cef072922ccd99c5af"
 dependencies = [
- "bitflags 2.8.0",
+ "bitflags",
 ]
 
 [[package]]
@@ -2963,7 +3177,7 @@ version = "0.10.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "78ef7fa9ed0256d64a688a3747d0fef7a88851c18a5e1d57f115f38ec2e09366"
 dependencies = [
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
  "memchr",
 ]
 
@@ -2978,9 +3192,9 @@ dependencies = [
 
 [[package]]
 name = "reqwest"
-version = "0.12.12"
+version = "0.12.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43e734407157c3c2034e0258f5e4473ddb361b1e85f95a66690d67264d7cd1da"
+checksum = "d19c46a6fdd48bc4dab94b6103fccc55d34c67cc0ad04653aad4ea2a07cd7bbb"
 dependencies = [
  "base64 0.22.1",
  "bytes",
@@ -3024,13 +3238,13 @@ dependencies = [
 
 [[package]]
 name = "ring"
-version = "0.17.9"
+version = "0.17.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e75ec5e92c4d8aede845126adc388046234541629e76029599ed35a003c7ed24"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
 dependencies = [
  "cc",
  "cfg-if",
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
  "libc",
  "untrusted",
  "windows-sys 0.52.0",
@@ -3065,11 +3279,11 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.38.44"
+version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fdb5bc1ae2baa591800df16c9ca78619bf65c0488b41b96ccec5d11220d8c154"
+checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
 dependencies = [
- "bitflags 2.8.0",
+ "bitflags",
  "errno",
  "libc",
  "linux-raw-sys",
@@ -3078,9 +3292,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.23"
+version = "0.23.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47796c98c480fce5406ef69d1c76378375492c3b0a0de587be0c1d9feb12f395"
+checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
 dependencies = [
  "once_cell",
  "ring",
@@ -3113,18 +3327,19 @@ dependencies = [
 
 [[package]]
 name = "rustls-pki-types"
-version = "1.11.0"
+version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "917ce264624a4b4db1c364dcc35bfca9ded014d0a958cd47ad3e960e988ea51c"
+checksum = "229a4a4c221013e7e1f1a043678c5cc39fe5171437c88fb47151a21e6f5b5c79"
 dependencies = [
  "web-time",
+ "zeroize",
 ]
 
 [[package]]
 name = "rustls-webpki"
-version = "0.102.8"
+version = "0.103.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "64ca1bc8749bd4cf37b5ce386cc146580777b4e8572c7b97baf22c83f444bee9"
+checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435"
 dependencies = [
  "ring",
  "rustls-pki-types",
@@ -3133,15 +3348,15 @@ dependencies = [
 
 [[package]]
 name = "rustversion"
-version = "1.0.19"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7c45b9784283f1b2e7fb61b42047c2fd678ef0960d4f6f1eba131594cc369d4"
+checksum = "eded382c5f5f786b989652c49544c4877d9f015cc22e145a5ea8ea66c2921cd2"
 
 [[package]]
 name = "ryu"
-version = "1.0.19"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ea1a2d0a644769cc99faa24c3ad26b379b786fe7c36fd3c546254801650e6dd"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
 
 [[package]]
 name = "same-file"
@@ -3163,9 +3378,9 @@ dependencies = [
 
 [[package]]
 name = "schemars"
-version = "0.8.21"
+version = "0.8.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09c024468a378b7e36765cd36702b7a90cc3cba11654f6685c8f233408e89e92"
+checksum = "3fbf2ae1b8bc8e02df939598064d22402220cd5bbcca1c76f7d6a310974d5615"
 dependencies = [
  "dyn-clone",
  "schemars_derive",
@@ -3175,14 +3390,14 @@ dependencies = [
 
 [[package]]
 name = "schemars_derive"
-version = "0.8.21"
+version = "0.8.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b1eee588578aff73f856ab961cd2f79e36bc45d7ded33a7562adba4667aecc0e"
+checksum = "32e265784ad618884abaea0600a9adf15393368d840e0222d101a072f3f7534d"
 dependencies = [
  "proc-macro2",
  "quote",
  "serde_derive_internals",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3197,7 +3412,7 @@ version = "3.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "271720403f46ca04f7ba6f55d438f8bd878d6b8ca0a1046e8228c4145bcbb316"
 dependencies = [
- "bitflags 2.8.0",
+ "bitflags",
  "core-foundation",
  "core-foundation-sys",
  "libc",
@@ -3216,46 +3431,46 @@ dependencies = [
 
 [[package]]
 name = "semver"
-version = "1.0.25"
+version = "1.0.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f79dfe2d285b0488816f30e700a7438c5a73d816b5b7d3ac72fbc48b0d185e03"
+checksum = "56e6fa9c48d24d85fb3de5ad847117517440f6beceb7798af16b4a87d616b8d0"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "seq-macro"
-version = "0.3.5"
+version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
 
 [[package]]
 name = "serde"
-version = "1.0.217"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02fc4265df13d6fa1d00ecff087228cc0a2b5f3c0e87e258d8b94a156e984c70"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_bytes"
-version = "0.11.15"
+version = "0.11.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "387cc504cb06bb40a96c8e04e951fe01854cf6bc921053c954e4a606d9675c6a"
+checksum = "8437fd221bde2d4ca316d61b90e337e9e702b3820b87d63caa9ba6c02bd06d96"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.217"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a9bf7cf98d04a2b28aead066b7496853d4779c9cc183c440dbac457641e19a0"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3266,14 +3481,14 @@ checksum = "18d26a20a969b9e3fdf2fc2d9f21eda6c40e2de84c9408bb5d3b05d499aae711"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.138"
+version = "1.0.140"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d434192e7da787e94a6ea7e9670b26a036d0ca41e0b7efb2676dd32bae872949"
+checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
 dependencies = [
  "itoa",
  "memchr",
@@ -3290,7 +3505,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "serde",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3320,9 +3535,9 @@ dependencies = [
 
 [[package]]
 name = "sha2"
-version = "0.10.8"
+version = "0.10.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
  "cpufeatures",
@@ -3358,30 +3573,9 @@ dependencies = [
 
 [[package]]
 name = "smallvec"
-version = "1.14.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7fcf8323ef1faaee30a44a340193b1ac6814fd9b7b4e88e9d4519a3e4abe1cfd"
-
-[[package]]
-name = "snafu"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "223891c85e2a29c3fe8fb900c1fae5e69c2e42415e3177752e8718475efa5019"
-dependencies = [
- "snafu-derive",
-]
-
-[[package]]
-name = "snafu-derive"
-version = "0.8.5"
+version = "1.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03c3c6b7927ffe7ecaa769ee0e3994da3b8cafc8f444578982c83ecb161af917"
-dependencies = [
- "heck",
- "proc-macro2",
- "quote",
- "syn 2.0.98",
-]
+checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9"
 
 [[package]]
 name = "snap"
@@ -3391,9 +3585,9 @@ checksum = "1b6b67fb9a61334225b5b790716f609cd58395f895b3fe8b328786812a40bc3b"
 
 [[package]]
 name = "socket2"
-version = "0.5.8"
+version = "0.5.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c970269d99b64e60ec3bd6ad27270092a5394c4e309314b18ae3fe575695fbe8"
+checksum = "4f5fd57c80058a56cf5c777ab8a126398ece8e442983605d280a44ce79d0edef"
 dependencies = [
  "libc",
  "windows-sys 0.52.0",
@@ -3401,11 +3595,12 @@ dependencies = [
 
 [[package]]
 name = "sqlparser"
-version = "0.53.0"
+version = "0.55.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05a528114c392209b3264855ad491fcce534b94a38771b0a0b97a79379275ce8"
+checksum = "c4521174166bac1ff04fe16ef4524c70144cd29682a45978978ca3d7f4e0be11"
 dependencies = [
  "log",
+ "recursive",
  "sqlparser_derive",
 ]
 
@@ -3417,7 +3612,7 @@ checksum = "da5fc6819faabb412da764b99d3b713bb55083c11e7e0c00144d386cd6a1939c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3428,9 +3623,9 @@ checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
 
 [[package]]
 name = "stacker"
-version = "0.1.18"
+version = "0.1.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1d08feb8f695b465baed819b03c128dc23f57a694510ab1f06c77f763975685e"
+checksum = "cddb07e32ddb770749da91081d8d0ac3a16f1a569a18b20348cd371f5dead06b"
 dependencies = [
  "cc",
  "cfg-if",
@@ -3461,14 +3656,14 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "substrait"
-version = "0.52.3"
+version = "0.55.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5db15789cecbfdf6b1fcf2db807e767c92273bdc407ac057c2194b070c597756"
+checksum = "048fe52a3664881ccdfdc9bdb0f4e8805f3444ee64abf299d365c54f6a2ffabb"
 dependencies = [
  "heck",
  "pbjson",
@@ -3485,7 +3680,7 @@ dependencies = [
  "serde",
  "serde_json",
  "serde_yaml",
- "syn 2.0.98",
+ "syn 2.0.101",
  "typify",
  "walkdir",
 ]
@@ -3509,9 +3704,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.98"
+version = "2.0.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36147f1a48ae0ec2b5b3bc5b537d267457555a10dc06f3dbc8cb11ba3006d3b1"
+checksum = "8ce2b7fc941b3a24138a0a7cf8e858bfc6a992e7978a068a5c760deb0ed43caf"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -3529,30 +3724,29 @@ dependencies = [
 
 [[package]]
 name = "synstructure"
-version = "0.13.1"
+version = "0.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "target-lexicon"
-version = "0.12.16"
+version = "0.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
+checksum = "e502f78cdbb8ba4718f566c418c52bc729126ffd16baee5baa718cf25dd5a69a"
 
 [[package]]
 name = "tempfile"
-version = "3.16.0"
+version = "3.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38c246215d7d24f48ae091a2902398798e05d978b24315d6efbc00ede9a8bb91"
+checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1"
 dependencies = [
- "cfg-if",
  "fastrand",
- "getrandom 0.3.1",
+ "getrandom 0.3.3",
  "once_cell",
  "rustix",
  "windows-sys 0.59.0",
@@ -3569,11 +3763,11 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "2.0.11"
+version = "2.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d452f284b73e6d76dd36758a0c8684b1d5be31f92b89d07fd5822175732206fc"
+checksum = "567b8a2dae586314f7be2a752ec7474332959c6460e02bde30d702a66d488708"
 dependencies = [
- "thiserror-impl 2.0.11",
+ "thiserror-impl 2.0.12",
 ]
 
 [[package]]
@@ -3584,18 +3778,18 @@ checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "2.0.11"
+version = "2.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26afc1baea8a989337eeb52b6e72a039780ce45c3edfcc9c5b9d112feeb173c2"
+checksum = "7f7cf42b4507d8ea322120659672cf1b9dbb93f8f2d4ecfd6e51350ff5b17a1d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3620,9 +3814,9 @@ dependencies = [
 
 [[package]]
 name = "tinystr"
-version = "0.7.6"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9117f5d4db391c1cf6927e7bea3db74b9a1c1add8f7eda9ffd5364f40f57b82f"
+checksum = "5d4f6d1145dcb577acf783d4e601bc1d76a13337bb54e6233add580b07344c8b"
 dependencies = [
  "displaydoc",
  "zerovec",
@@ -3630,9 +3824,9 @@ dependencies = [
 
 [[package]]
 name = "tinyvec"
-version = "1.8.1"
+version = "1.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "022db8904dfa342efe721985167e9fcd16c29b226db4397ed752a761cfce81e8"
+checksum = "09b3661f17e86524eccd4371ab0429194e0d7c008abb45f7a7495b1719463c71"
 dependencies = [
  "tinyvec_macros",
 ]
@@ -3645,9 +3839,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 
 [[package]]
 name = "tokio"
-version = "1.43.0"
+version = "1.45.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d61fa4ffa3de412bfea335c6ecff681de2b609ba3c77ef3e00e521813a9ed9e"
+checksum = "2513ca694ef9ede0fb23fe71a4ee4107cb102b9dc1930f6d0fd77aae068ae165"
 dependencies = [
  "backtrace",
  "bytes",
@@ -3667,14 +3861,14 @@ checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "tokio-rustls"
-version = "0.26.1"
+version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f6d0975eaace0cf0fcadee4e4aaa5da15b5c079146f2cffb67c113be122bf37"
+checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
 dependencies = [
  "rustls",
  "tokio",
@@ -3682,9 +3876,9 @@ dependencies = [
 
 [[package]]
 name = "tokio-util"
-version = "0.7.13"
+version = "0.7.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d7fcaa8d55a2bdd6b83ace262b016eca0d79ee02818c5c1bcdf0305114081078"
+checksum = "66a539a9ad6d5d281510d5bd368c973d636c02dbf8a67300bfb6b950696ad7df"
 dependencies = [
  "bytes",
  "futures-core",
@@ -3739,7 +3933,7 @@ checksum = "395ae124c09f9e6918a2310af6038fba074bcf474ac352496d5910dd59a2226d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -3782,6 +3976,12 @@ dependencies = [
  "static_assertions",
 ]
 
+[[package]]
+name = "twox-hash"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e7b17f197b3050ba473acf9181f7b1d3b66d1cf7356c6cc57886662276e65908"
+
 [[package]]
 name = "typed-arena"
 version = "2.0.2"
@@ -3805,14 +4005,14 @@ checksum = "f9534daa9fd3ed0bd911d462a37f172228077e7abf18c18a5f67199d959205f8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "typenum"
-version = "1.17.0"
+version = "1.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
+checksum = "1dccffe3ce07af9386bfd29e80c0ab1a8205a2fc34e4bcd40364df902cfa8f3f"
 
 [[package]]
 name = "typify"
@@ -3839,8 +4039,8 @@ dependencies = [
  "semver",
  "serde",
  "serde_json",
- "syn 2.0.98",
- "thiserror 2.0.11",
+ "syn 2.0.101",
+ "thiserror 2.0.12",
  "unicode-ident",
 ]
 
@@ -3857,15 +4057,15 @@ dependencies = [
  "serde",
  "serde_json",
  "serde_tokenstream",
- "syn 2.0.98",
+ "syn 2.0.101",
  "typify-impl",
 ]
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.16"
+version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a210d160f08b701c8721ba1c726c11662f877ea6b7094007e1ca9a1041945034"
+checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
 
 [[package]]
 name = "unicode-segmentation"
@@ -3881,9 +4081,9 @@ checksum = "1fc81956842c57dac11422a97c3b8195a1ff727f06e85c84ed2e8aa277c9a0fd"
 
 [[package]]
 name = "unindent"
-version = "0.2.3"
+version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
+checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
 
 [[package]]
 name = "unsafe-libyaml"
@@ -3908,12 +4108,6 @@ dependencies = [
  "percent-encoding",
 ]
 
-[[package]]
-name = "utf16_iter"
-version = "1.0.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246"
-
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -3922,12 +4116,14 @@ checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
 
 [[package]]
 name = "uuid"
-version = "1.13.1"
+version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ced87ca4be083373936a67f8de945faa23b6b42384bd5b64434850802c6dccd0"
+checksum = "458f7a779bf54acc9f347480ac654f68407d3aab21269a6e3c9f922acd9e2da9"
 dependencies = [
- "getrandom 0.3.1",
+ "getrandom 0.3.3",
+ "js-sys",
  "serde",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -3963,9 +4159,9 @@ checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
 [[package]]
 name = "wasi"
-version = "0.13.3+wasi-0.2.2"
+version = "0.14.2+wasi-0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26816d2e1a4a36a2940b96c5296ce403917633dff8f3440e9b236ed6f6bacad2"
+checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
 dependencies = [
  "wit-bindgen-rt",
 ]
@@ -3992,7 +4188,7 @@ dependencies = [
  "log",
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
  "wasm-bindgen-shared",
 ]
 
@@ -4027,7 +4223,7 @@ checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -4107,41 +4303,81 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
 name = "windows-core"
-version = "0.52.0"
+version = "0.61.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "33ab640c8d7e35bf8ba19b884ba838ceb4fba93a4e8c65a9059d08afcfc683d9"
+checksum = "46ec44dc15085cea82cf9c78f85a9114c463a369786585ad2882d1ff0b0acf40"
 dependencies = [
- "windows-targets",
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings 0.4.1",
 ]
 
+[[package]]
+name = "windows-implement"
+version = "0.60.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a47fddd13af08290e67f4acabf4b459f647552718f683a7b415d290ac744a836"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bd9211b69f8dcdfa817bfd14bf1c97c9188afa36f4750130fcdf3f400eca9fa8"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76840935b766e1b0a05c0066835fb9ec80071d4c09a16f6bd5f7e655e3c14c38"
+
 [[package]]
 name = "windows-registry"
-version = "0.2.0"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e400001bb720a623c1c69032f8e3e4cf09984deec740f007dd2b03ec864804b0"
+checksum = "4286ad90ddb45071efd1a66dfa43eb02dd0dfbae1545ad6cc3c51cf34d7e8ba3"
 dependencies = [
  "windows-result",
- "windows-strings",
- "windows-targets",
+ "windows-strings 0.3.1",
+ "windows-targets 0.53.0",
 ]
 
 [[package]]
 name = "windows-result"
-version = "0.2.0"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1d1043d8214f791817bab27572aaa8af63732e11bf84aa21a45a78d6c317ae0e"
+checksum = "4b895b5356fc36103d0f64dd1e94dfa7ac5633f1c9dd6e80fe9ec4adef69e09d"
 dependencies = [
- "windows-targets",
+ "windows-link",
 ]
 
 [[package]]
 name = "windows-strings"
-version = "0.1.0"
+version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4cd9b125c486025df0eabcb585e62173c6c9eddcec5d117d3b6e8c30e2ee4d10"
+checksum = "87fa48cc5d406560701792be122a10132491cff9d0aeb23583cc2dcafc847319"
 dependencies = [
- "windows-result",
- "windows-targets",
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a7ab927b2637c19b3dbe0965e75d8f2d30bdd697a1516191cad2ec4df8fb28a"
+dependencies = [
+ "windows-link",
 ]
 
 [[package]]
@@ -4150,7 +4386,7 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -4159,7 +4395,7 @@ version = "0.59.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -4168,14 +4404,30 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
 dependencies = [
- "windows_aarch64_gnullvm",
- "windows_aarch64_msvc",
- "windows_i686_gnu",
- "windows_i686_gnullvm",
- "windows_i686_msvc",
- "windows_x86_64_gnu",
- "windows_x86_64_gnullvm",
- "windows_x86_64_msvc",
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
+ "windows_i686_gnullvm 0.52.6",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1e4c7e8ceaaf9cb7d7507c974735728ab453b67ef8f18febdd7c11fe59dca8b"
+dependencies = [
+ "windows_aarch64_gnullvm 0.53.0",
+ "windows_aarch64_msvc 0.53.0",
+ "windows_i686_gnu 0.53.0",
+ "windows_i686_gnullvm 0.53.0",
+ "windows_i686_msvc 0.53.0",
+ "windows_x86_64_gnu 0.53.0",
+ "windows_x86_64_gnullvm 0.53.0",
+ "windows_x86_64_msvc 0.53.0",
 ]
 
 [[package]]
@@ -4184,42 +4436,84 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86b8d5f90ddd19cb4a147a5fa63ca848db3df085e25fee3cc10b39b6eebae764"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7651a1f62a11b8cbd5e0d42526e55f2c99886c77e007179efff86c2b137e66c"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1dc67659d35f387f5f6c479dc4e28f1d4bb90ddd1a5d3da2e5d97b42d6272c3"
+
 [[package]]
 name = "windows_i686_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
 
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ce6ccbdedbf6d6354471319e781c0dfef054c81fbc7cf83f338a4296c0cae11"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "581fee95406bb13382d2f65cd4a908ca7b1e4c2f1917f143ba16efe98a589b5d"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2e55b5ac9ea33f2fc1716d1742db15574fd6fc8dadc51caab1c16a3d3b4190ba"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0a6e035dd0599267ce1ee132e51c27dd29437f63325753051e71dd9e42406c57"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.6"
@@ -4227,25 +4521,25 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
 [[package]]
-name = "wit-bindgen-rt"
-version = "0.33.0"
+name = "windows_x86_64_msvc"
+version = "0.53.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3268f3d866458b787f390cf61f4bbb563b922d091359f9608842999eaee3943c"
-dependencies = [
- "bitflags 2.8.0",
-]
+checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
 
 [[package]]
-name = "write16"
-version = "1.0.0"
+name = "wit-bindgen-rt"
+version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1890f4022759daae28ed4fe62859b1236caebfc61ede2f63ed4e695f3f6d936"
+checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
+dependencies = [
+ "bitflags",
+]
 
 [[package]]
 name = "writeable"
-version = "0.5.5"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51"
+checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
 
 [[package]]
 name = "xz2"
@@ -4258,9 +4552,9 @@ dependencies = [
 
 [[package]]
 name = "yoke"
-version = "0.7.5"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40"
+checksum = "5f41bb01b8226ef4bfd589436a297c53d118f65921786300e427be8d487695cc"
 dependencies = [
  "serde",
  "stable_deref_trait",
@@ -4270,55 +4564,54 @@ dependencies = [
 
 [[package]]
 name = "yoke-derive"
-version = "0.7.5"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
+checksum = "38da3c9736e16c5d3c8c597a9aaa5d1fa565d0532ae05e27c24aa62fb32c0ab6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
  "synstructure",
 ]
 
 [[package]]
 name = "zerocopy"
-version = "0.7.35"
+version = "0.8.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
+checksum = "a1702d9583232ddb9174e01bb7c15a2ab8fb1bc6f227aa1233858c351a3ba0cb"
 dependencies = [
- "byteorder",
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.7.35"
+version = "0.8.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
+checksum = "28a6e20d751156648aa063f3800b706ee209a32c0b4d9f24be3d980b01be55ef"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "zerofrom"
-version = "0.1.5"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cff3ee08c995dee1859d998dea82f7374f2826091dd9cd47def953cae446cd2e"
+checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5"
 dependencies = [
  "zerofrom-derive",
 ]
 
 [[package]]
 name = "zerofrom-derive"
-version = "0.1.5"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808"
+checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
  "synstructure",
 ]
 
@@ -4328,11 +4621,22 @@ version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"
 
+[[package]]
+name = "zerotrie"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "36f0bbd478583f79edad978b407914f61b2972f5af6fa089686016be8f9af595"
+dependencies = [
+ "displaydoc",
+ "yoke",
+ "zerofrom",
+]
+
 [[package]]
 name = "zerovec"
-version = "0.10.4"
+version = "0.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079"
+checksum = "4a05eb080e015ba39cc9e23bbe5e7fb04d5fb040350f99f34e338d5fdd294428"
 dependencies = [
  "yoke",
  "zerofrom",
@@ -4341,38 +4645,44 @@ dependencies = [
 
 [[package]]
 name = "zerovec-derive"
-version = "0.10.3"
+version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
+checksum = "5b96237efa0c878c64bd89c436f661be4e46b2f3eff1ebb976f7ef2321d2f58f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.98",
+ "syn 2.0.101",
 ]
 
+[[package]]
+name = "zlib-rs"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "868b928d7949e09af2f6086dfc1e01936064cc7a819253bce650d4e2a2d63ba8"
+
 [[package]]
 name = "zstd"
-version = "0.13.2"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fcf2b778a664581e31e389454a7072dab1647606d44f7feea22cd5abb9c9f3f9"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
 dependencies = [
  "zstd-safe",
 ]
 
 [[package]]
 name = "zstd-safe"
-version = "7.2.1"
+version = "7.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "54a3ab4db68cea366acc5c897c7b4d4d1b8994a9cd6e6f841f8964566a419059"
+checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
 dependencies = [
  "zstd-sys",
 ]
 
 [[package]]
 name = "zstd-sys"
-version = "2.0.13+zstd.1.5.6"
+version = "2.0.15+zstd.1.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38ff0f21cfee8f97d94cef41359e0c89aa6113028ab0291aa8ca0038995a95aa"
+checksum = "eb81183ddd97d0c74cedf1d50d85c8d08c1b8b68ee863bdee9e706eedba1a237"
 dependencies = [
  "cc",
  "pkg-config",
diff --git a/Cargo.toml b/Cargo.toml
index 50967a219..8107d76d3 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -17,7 +17,7 @@
 
 [package]
 name = "datafusion-python"
-version = "45.2.0"
+version = "47.0.0"
 homepage = "https://datafusion.apache.org/python"
 repository = "https://github.com/apache/datafusion-python"
 authors = ["Apache DataFusion <dev@datafusion.apache.org>"]
@@ -34,25 +34,25 @@ protoc = [ "datafusion-substrait/protoc" ]
 substrait = ["dep:datafusion-substrait"]
 
 [dependencies]
-tokio = { version = "1.42", features = ["macros", "rt", "rt-multi-thread", "sync"] }
-pyo3 = { version = "0.23", features = ["extension-module", "abi3", "abi3-py39"] }
-pyo3-async-runtimes = { version = "0.23", features = ["tokio-runtime"]}
-arrow = { version = "54", features = ["pyarrow"] }
-datafusion = { version = "45.0.0", features = ["avro", "unicode_expressions"] }
-datafusion-substrait = { version = "45.0.0", optional = true }
-datafusion-proto = { version = "45.0.0" }
-datafusion-ffi = { version = "45.0.0" }
-prost = "0.13" # keep in line with `datafusion-substrait`
-uuid = { version = "1.12", features = ["v4"] }
+tokio = { version = "1.45", features = ["macros", "rt", "rt-multi-thread", "sync"] }
+pyo3 = { version = "0.24", features = ["extension-module", "abi3", "abi3-py39"] }
+pyo3-async-runtimes = { version = "0.24", features = ["tokio-runtime"]}
+arrow = { version = "55.0.0", features = ["pyarrow"] }
+datafusion = { version = "47.0.0", features = ["avro", "unicode_expressions"] }
+datafusion-substrait = { version = "47.0.0", optional = true }
+datafusion-proto = { version = "47.0.0" }
+datafusion-ffi = { version = "47.0.0" }
+prost = "0.13.1" # keep in line with `datafusion-substrait`
+uuid = { version = "1.16", features = ["v4"] }
 mimalloc = { version = "0.1", optional = true, default-features = false, features = ["local_dynamic_tls"] }
-async-trait = "0.1"
+async-trait = "0.1.88"
 futures = "0.3"
-object_store = { version = "0.11.0", features = ["aws", "gcp", "azure", "http"] }
+object_store = { version = "0.12.1", features = ["aws", "gcp", "azure", "http"] }
 url = "2"
 
 [build-dependencies]
-prost-types = "0.13" # keep in line with `datafusion-substrait`
-pyo3-build-config = "0.23"
+prost-types = "0.13.1" # keep in line with `datafusion-substrait`
+pyo3-build-config = "0.24"
 
 [lib]
 name = "datafusion_python"
diff --git a/dev/changelog/46.0.0.md b/dev/changelog/46.0.0.md
new file mode 100644
index 000000000..3e5768099
--- /dev/null
+++ b/dev/changelog/46.0.0.md
@@ -0,0 +1,73 @@
+<!--
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing,
+software distributed under the License is distributed on an
+"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied.  See the License for the
+specific language governing permissions and limitations
+under the License.
+-->
+
+# Apache DataFusion Python 46.0.0 Changelog
+
+This release consists of 21 commits from 11 contributors. See credits at the end of this changelog for more information.
+
+**Implemented enhancements:**
+
+- feat: reads using global ctx [#982](https://github.com/apache/datafusion-python/pull/982) (ion-elgreco)
+- feat: Implementation of udf and udaf decorator [#1040](https://github.com/apache/datafusion-python/pull/1040) (CrystalZhou0529)
+- feat: expose regex_count function [#1066](https://github.com/apache/datafusion-python/pull/1066) (nirnayroy)
+- feat: Update DataFusion dependency to 46 [#1079](https://github.com/apache/datafusion-python/pull/1079) (timsaucer)
+
+**Fixed bugs:**
+
+- fix: add to_timestamp_nanos [#1020](https://github.com/apache/datafusion-python/pull/1020) (chenkovsky)
+- fix: type checking [#993](https://github.com/apache/datafusion-python/pull/993) (chenkovsky)
+
+**Other:**
+
+- [infra] Fail Clippy on rust build warnings [#1029](https://github.com/apache/datafusion-python/pull/1029) (kevinjqliu)
+- Add user documentation for the FFI approach [#1031](https://github.com/apache/datafusion-python/pull/1031) (timsaucer)
+- build(deps): bump arrow from 54.1.0 to 54.2.0 [#1035](https://github.com/apache/datafusion-python/pull/1035) (dependabot[bot])
+- Chore: Release datafusion-python 45 [#1024](https://github.com/apache/datafusion-python/pull/1024) (timsaucer)
+- Enable Dataframe to be converted into views which can be used in register_table [#1016](https://github.com/apache/datafusion-python/pull/1016) (kosiew)
+- Add ruff check for missing futures import [#1052](https://github.com/apache/datafusion-python/pull/1052) (timsaucer)
+- Enable take comments to assign issues to users [#1058](https://github.com/apache/datafusion-python/pull/1058) (timsaucer)
+- Update python min version to 3.9 [#1043](https://github.com/apache/datafusion-python/pull/1043) (kevinjqliu)
+- feat/improve ruff test coverage [#1055](https://github.com/apache/datafusion-python/pull/1055) (timsaucer)
+- feat/making global context accessible for users [#1060](https://github.com/apache/datafusion-python/pull/1060) (jsai28)
+- Renaming Internal Structs [#1059](https://github.com/apache/datafusion-python/pull/1059) (Spaarsh)
+- test: add pytest asyncio tests [#1063](https://github.com/apache/datafusion-python/pull/1063) (jsai28)
+- Add decorator for udwf [#1061](https://github.com/apache/datafusion-python/pull/1061) (kosiew)
+- Add additional ruff suggestions [#1062](https://github.com/apache/datafusion-python/pull/1062) (Spaarsh)
+- Improve collection during repr and repr_html [#1036](https://github.com/apache/datafusion-python/pull/1036) (timsaucer)
+
+## Credits
+
+Thank you to everyone who contributed to this release. Here is a breakdown of commits (PRs merged) per contributor.
+
+```
+     7	Tim Saucer
+     2	Kevin Liu
+     2	Spaarsh
+     2	jsai28
+     2	kosiew
+     1	Chen Chongchen
+     1	Chongchen Chen
+     1	Crystal Zhou
+     1	Ion Koutsouris
+     1	Nirnay Roy
+     1	dependabot[bot]
+```
+
+Thank you also to everyone who contributed in other ways such as filing issues, reviewing PRs, and providing feedback on this release.
+
diff --git a/dev/changelog/47.0.0.md b/dev/changelog/47.0.0.md
new file mode 100644
index 000000000..a7ed90313
--- /dev/null
+++ b/dev/changelog/47.0.0.md
@@ -0,0 +1,64 @@
+<!--
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing,
+software distributed under the License is distributed on an
+"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied.  See the License for the
+specific language governing permissions and limitations
+under the License.
+-->
+
+# Apache DataFusion Python 47.0.0 Changelog
+
+This release consists of 23 commits from 5 contributors. See credits at the end of this changelog for more information.
+
+**Implemented enhancements:**
+
+- feat: support unparser [#1088](https://github.com/apache/datafusion-python/pull/1088) (chenkovsky)
+- feat: update datafusion dependency 47 [#1107](https://github.com/apache/datafusion-python/pull/1107) (timsaucer)
+- feat: alias with metadata [#1111](https://github.com/apache/datafusion-python/pull/1111) (chenkovsky)
+- feat: add missing PyLogicalPlan to_variant [#1085](https://github.com/apache/datafusion-python/pull/1085) (chenkovsky)
+- feat: add user defined table function support [#1113](https://github.com/apache/datafusion-python/pull/1113) (timsaucer)
+
+**Fixed bugs:**
+
+- fix: recursive import [#1117](https://github.com/apache/datafusion-python/pull/1117) (chenkovsky)
+
+**Other:**
+
+- Update changelog and version number [#1089](https://github.com/apache/datafusion-python/pull/1089) (timsaucer)
+- Documentation updates: mention correct dataset on basics page [#1081](https://github.com/apache/datafusion-python/pull/1081) (floscha)
+- Add Configurable HTML Table Formatter for DataFusion DataFrames in Python [#1100](https://github.com/apache/datafusion-python/pull/1100) (kosiew)
+- Add DataFrame usage guide with HTML rendering customization options [#1108](https://github.com/apache/datafusion-python/pull/1108) (kosiew)
+- 1075/enhancement/Make col class with __getattr__ [#1076](https://github.com/apache/datafusion-python/pull/1076) (deanm0000)
+- 1064/enhancement/add functions to Expr class [#1074](https://github.com/apache/datafusion-python/pull/1074) (deanm0000)
+- ci: require approving review [#1122](https://github.com/apache/datafusion-python/pull/1122) (timsaucer)
+- Partial fix for 1078: Enhance DataFrame Formatter Configuration with Memory and Display Controls [#1119](https://github.com/apache/datafusion-python/pull/1119) (kosiew)
+- Add fill_null method to DataFrame API for handling missing values [#1019](https://github.com/apache/datafusion-python/pull/1019) (kosiew)
+- minor: reduce error size [#1126](https://github.com/apache/datafusion-python/pull/1126) (timsaucer)
+- Move the udf module to user_defined [#1112](https://github.com/apache/datafusion-python/pull/1112) (timsaucer)
+- add unit tests for expression functions [#1121](https://github.com/apache/datafusion-python/pull/1121) (timsaucer)
+
+## Credits
+
+Thank you to everyone who contributed to this release. Here is a breakdown of commits (PRs merged) per contributor.
+
+```
+    12	Tim Saucer
+     4	Chen Chongchen
+     4	kosiew
+     2	deanm0000
+     1	Florian Schäfer
+```
+
+Thank you also to everyone who contributed in other ways such as filing issues, reviewing PRs, and providing feedback on this release.
+
diff --git a/dev/release/README.md b/dev/release/README.md
index f0b333999..692473930 100644
--- a/dev/release/README.md
+++ b/dev/release/README.md
@@ -56,6 +56,8 @@ Before creating a new release:
 - a PR should be created and merged to update the major version number of the project
 - A new release branch should be created, such as `branch-0.8`
 
+## Preparing a Release Candidate
+
 ### Change Log
 
 We maintain a `CHANGELOG.md` so our users know what has been changed between releases.
@@ -76,21 +78,17 @@ Categorizing pull requests
 Generating changelog content
 ```
 
-This process is not fully automated, so there are some additional manual steps:
-
-- Add the ASF header to the generated file
-- Add a link to this changelog from the top-level `/datafusion/CHANGELOG.md`
-- Add the following content (copy from the previous version's changelog and update as appropriate:
+### Update the version number
 
-```
-## [24.0.0](https://github.com/apache/datafusion-python/tree/24.0.0) (2023-05-06)
+The only place you should need to update the version is in the root `Cargo.toml`.
 
-[Full Changelog](https://github.com/apache/datafusion-python/compare/23.0.0...24.0.0)
-```
+### Tag the Repository
 
-### Preparing a Release Candidate
+Commit the changes to the changelog and version.
 
-### Tag the Repository
+Assuming you have set up a remote to the `apache` repository rather than your personal fork,
+you need to push a tag to start the CI process for release candidates. The following assumes
+the upstream repository is called `apache`.
 
 ```bash
 git tag 0.8.0-rc1
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 0be03d81d..0ca124fd1 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -71,6 +71,7 @@
 autoapi_member_order = "groupwise"
 suppress_warnings = ["autoapi.python_import_resolution"]
 autoapi_python_class_content = "both"
+autoapi_keep_files = False  # set to True for debugging generated files
 
 
 def autoapi_skip_member_fn(app, what, name, obj, skip, options) -> bool:  # noqa: ARG001
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 558b2d572..c18793822 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -72,6 +72,7 @@ Example
    user-guide/introduction
    user-guide/basics
    user-guide/data-sources
+   user-guide/dataframe
    user-guide/common-operations/index
    user-guide/io/index
    user-guide/configuration
diff --git a/docs/source/user-guide/basics.rst b/docs/source/user-guide/basics.rst
index f37378a41..2975d9a6b 100644
--- a/docs/source/user-guide/basics.rst
+++ b/docs/source/user-guide/basics.rst
@@ -20,8 +20,9 @@
 Concepts
 ========
 
-In this section, we will cover a basic example to introduce a few key concepts. We will use the same
-source file as described in the :ref:`Introduction <guide>`, the Pokemon data set.
+In this section, we will cover a basic example to introduce a few key concepts. We will use the
+2021 Yellow Taxi Trip Records (`download <https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2021-01.parquet>`_),
+from the `TLC Trip Record Data <https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page>`_.
 
 .. ipython:: python
 
@@ -72,6 +73,8 @@ DataFrames are typically created by calling a method on :py:class:`~datafusion.c
 calling the transformation methods, such as :py:func:`~datafusion.dataframe.DataFrame.filter`, :py:func:`~datafusion.dataframe.DataFrame.select`, :py:func:`~datafusion.dataframe.DataFrame.aggregate`,
 and :py:func:`~datafusion.dataframe.DataFrame.limit` to build up a query definition.
 
+For more details on working with DataFrames, including visualization options and conversion to other formats, see :doc:`dataframe`.
+
 Expressions
 -----------
 
diff --git a/docs/source/user-guide/common-operations/functions.rst b/docs/source/user-guide/common-operations/functions.rst
index 12097be8f..d458d3eb0 100644
--- a/docs/source/user-guide/common-operations/functions.rst
+++ b/docs/source/user-guide/common-operations/functions.rst
@@ -129,3 +129,24 @@ The function :py:func:`~datafusion.functions.in_list` allows to check a column f
           .limit(20)
           .to_pandas()
     )
+
+
+Handling Missing Values 
+=====================
+
+DataFusion provides methods to handle missing values in DataFrames:
+
+fill_null
+---------
+
+The ``fill_null()`` method replaces NULL values in specified columns with a provided value:
+
+.. code-block:: python
+
+    # Fill all NULL values with 0 where possible
+    df = df.fill_null(0)
+
+    # Fill NULL values only in specific string columns
+    df = df.fill_null("missing", subset=["name", "category"]) 
+
+The fill value will be cast to match each column's type. If casting fails for a column, that column remains unchanged.
diff --git a/docs/source/user-guide/common-operations/udf-and-udfa.rst b/docs/source/user-guide/common-operations/udf-and-udfa.rst
index ffd7a05cb..0830fa81c 100644
--- a/docs/source/user-guide/common-operations/udf-and-udfa.rst
+++ b/docs/source/user-guide/common-operations/udf-and-udfa.rst
@@ -26,7 +26,7 @@ Scalar Functions
 
 When writing a user-defined function that can operate on a row by row basis, these are called Scalar
 Functions. You can define your own scalar function by calling
-:py:func:`~datafusion.udf.ScalarUDF.udf` .
+:py:func:`~datafusion.user_defined.ScalarUDF.udf` .
 
 The basic definition of a scalar UDF is a python function that takes one or more
 `pyarrow <https://arrow.apache.org/docs/python/index.html>`_ arrays and returns a single array as
@@ -93,9 +93,9 @@ converting to Python objects to do the evaluation.
 Aggregate Functions
 -------------------
 
-The :py:func:`~datafusion.udf.AggregateUDF.udaf` function allows you to define User-Defined
+The :py:func:`~datafusion.user_defined.AggregateUDF.udaf` function allows you to define User-Defined
 Aggregate Functions (UDAFs). To use this you must implement an
-:py:class:`~datafusion.udf.Accumulator` that determines how the aggregation is performed.
+:py:class:`~datafusion.user_defined.Accumulator` that determines how the aggregation is performed.
 
 When defining a UDAF there are four methods you need to implement. The ``update`` function takes the
 array(s) of input and updates the internal state of the accumulator. You should define this function
@@ -153,8 +153,8 @@ Window Functions
 ----------------
 
 To implement a User-Defined Window Function (UDWF) you must call the
-:py:func:`~datafusion.udf.WindowUDF.udwf` function using a class that implements the abstract
-class :py:class:`~datafusion.udf.WindowEvaluator`.
+:py:func:`~datafusion.user_defined.WindowUDF.udwf` function using a class that implements the abstract
+class :py:class:`~datafusion.user_defined.WindowEvaluator`.
 
 There are three methods of evaluation of UDWFs.
 
@@ -207,7 +207,7 @@ determine which evaluate functions are called.
 
     import pyarrow as pa
     from datafusion import udwf, col, SessionContext
-    from datafusion.udf import WindowEvaluator
+    from datafusion.user_defined import WindowEvaluator
 
     class ExponentialSmooth(WindowEvaluator):
         def __init__(self, alpha: float) -> None:
@@ -242,3 +242,35 @@ determine which evaluate functions are called.
     })
 
     df.select("a", exp_smooth(col("a")).alias("smooth_a")).show()
+
+Table Functions
+---------------
+
+User Defined Table Functions are slightly different than the other functions
+described here. These functions take any number of `Expr` arguments, but only
+literal expressions are supported. Table functions must return a Table
+Provider as described in the ref:`_io_custom_table_provider` page.
+
+Once you have a table function, you can register it with the session context
+by using :py:func:`datafusion.context.SessionContext.register_udtf`.
+
+There are examples of both rust backed and python based table functions in the
+examples folder of the repository. If you have a rust backed table function
+that you wish to expose via PyO3, you need to expose it as a ``PyCapsule``.
+
+.. code-block:: rust
+
+    #[pymethods]
+    impl MyTableFunction {
+        fn __datafusion_table_function__<'py>(
+            &self,
+            py: Python<'py>,
+        ) -> PyResult<Bound<'py, PyCapsule>> {
+            let name = cr"datafusion_table_function".into();
+
+            let func = self.clone();
+            let provider = FFI_TableFunction::new(Arc::new(func), None);
+
+            PyCapsule::new(py, provider, Some(name))
+        }
+    }
diff --git a/docs/source/user-guide/dataframe.rst b/docs/source/user-guide/dataframe.rst
new file mode 100644
index 000000000..11e3d7e72
--- /dev/null
+++ b/docs/source/user-guide/dataframe.rst
@@ -0,0 +1,217 @@
+.. Licensed to the Apache Software Foundation (ASF) under one
+.. or more contributor license agreements.  See the NOTICE file
+.. distributed with this work for additional information
+.. regarding copyright ownership.  The ASF licenses this file
+.. to you under the Apache License, Version 2.0 (the
+.. "License"); you may not use this file except in compliance
+.. with the License.  You may obtain a copy of the License at
+
+..   http://www.apache.org/licenses/LICENSE-2.0
+
+.. Unless required by applicable law or agreed to in writing,
+.. software distributed under the License is distributed on an
+.. "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+.. KIND, either express or implied.  See the License for the
+.. specific language governing permissions and limitations
+.. under the License.
+
+DataFrames
+==========
+
+Overview
+--------
+
+DataFusion's DataFrame API provides a powerful interface for building and executing queries against data sources. 
+It offers a familiar API similar to pandas and other DataFrame libraries, but with the performance benefits of Rust 
+and Arrow.
+
+A DataFrame represents a logical plan that can be composed through operations like filtering, projection, and aggregation.
+The actual execution happens when terminal operations like ``collect()`` or ``show()`` are called.
+
+Basic Usage
+-----------
+
+.. code-block:: python
+
+    import datafusion
+    from datafusion import col, lit
+
+    # Create a context and register a data source
+    ctx = datafusion.SessionContext()
+    ctx.register_csv("my_table", "path/to/data.csv")
+    
+    # Create and manipulate a DataFrame
+    df = ctx.sql("SELECT * FROM my_table")
+    
+    # Or use the DataFrame API directly
+    df = (ctx.table("my_table")
+          .filter(col("age") > lit(25))
+          .select([col("name"), col("age")]))
+    
+    # Execute and collect results
+    result = df.collect()
+    
+    # Display the first few rows
+    df.show()
+
+HTML Rendering
+--------------
+
+When working in Jupyter notebooks or other environments that support HTML rendering, DataFrames will
+automatically display as formatted HTML tables, making it easier to visualize your data.
+
+The ``_repr_html_`` method is called automatically by Jupyter to render a DataFrame. This method 
+controls how DataFrames appear in notebook environments, providing a richer visualization than
+plain text output.
+
+Customizing HTML Rendering
+--------------------------
+
+You can customize how DataFrames are rendered in HTML by configuring the formatter:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import configure_formatter
+    
+    # Change the default styling
+    configure_formatter(
+        max_cell_length=25,        # Maximum characters in a cell before truncation
+        max_width=1000,            # Maximum width in pixels
+        max_height=300,            # Maximum height in pixels
+        max_memory_bytes=2097152,  # Maximum memory for rendering (2MB)
+        min_rows_display=20,       # Minimum number of rows to display
+        repr_rows=10,              # Number of rows to display in __repr__
+        enable_cell_expansion=True,# Allow expanding truncated cells
+        custom_css=None,           # Additional custom CSS
+        show_truncation_message=True, # Show message when data is truncated
+        style_provider=None,       # Custom styling provider
+        use_shared_styles=True     # Share styles across tables
+    )
+
+The formatter settings affect all DataFrames displayed after configuration.
+
+Custom Style Providers
+----------------------
+
+For advanced styling needs, you can create a custom style provider:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import StyleProvider, configure_formatter
+    
+    class MyStyleProvider(StyleProvider):
+        def get_table_styles(self):
+            return {
+                "table": "border-collapse: collapse; width: 100%;",
+                "th": "background-color: #007bff; color: white; padding: 8px; text-align: left;",
+                "td": "border: 1px solid #ddd; padding: 8px;",
+                "tr:nth-child(even)": "background-color: #f2f2f2;",
+            }
+            
+        def get_value_styles(self, dtype, value):
+            """Return custom styles for specific values"""
+            if dtype == "float" and value < 0:
+                return "color: red;"
+            return None
+    
+    # Apply the custom style provider
+    configure_formatter(style_provider=MyStyleProvider())
+
+Performance Optimization with Shared Styles
+-------------------------------------------
+The ``use_shared_styles`` parameter (enabled by default) optimizes performance when displaying 
+multiple DataFrames in notebook environments:
+
+ .. code-block:: python
+    from datafusion.html_formatter import StyleProvider, configure_formatter
+    # Default: Use shared styles (recommended for notebooks)
+    configure_formatter(use_shared_styles=True)
+
+    # Disable shared styles (each DataFrame includes its own styles)
+    configure_formatter(use_shared_styles=False)
+
+When ``use_shared_styles=True``:
+- CSS styles and JavaScript are included only once per notebook session
+- This reduces HTML output size and prevents style duplication
+- Improves rendering performance with many DataFrames
+- Applies consistent styling across all DataFrames
+
+Creating a Custom Formatter
+---------------------------
+
+For complete control over rendering, you can implement a custom formatter:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import Formatter, get_formatter
+    
+    class MyFormatter(Formatter):
+        def format_html(self, batches, schema, has_more=False, table_uuid=None):
+            # Create your custom HTML here
+            html = "<div class='my-custom-table'>"
+            # ... formatting logic ...
+            html += "</div>"
+            return html
+    
+    # Set as the global formatter
+    configure_formatter(formatter_class=MyFormatter)
+    
+    # Or use the formatter just for specific operations
+    formatter = get_formatter()
+    custom_html = formatter.format_html(batches, schema)
+
+Managing Formatters
+-------------------
+
+Reset to default formatting:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import reset_formatter
+    
+    # Reset to default settings
+    reset_formatter()
+
+Get the current formatter settings:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import get_formatter
+    
+    formatter = get_formatter()
+    print(formatter.max_rows)
+    print(formatter.theme)
+
+Contextual Formatting
+---------------------
+
+You can also use a context manager to temporarily change formatting settings:
+
+.. code-block:: python
+
+    from datafusion.html_formatter import formatting_context
+    
+    # Default formatting
+    df.show()
+    
+    # Temporarily use different formatting
+    with formatting_context(max_rows=100, theme="dark"):
+        df.show()  # Will use the temporary settings
+    
+    # Back to default formatting
+    df.show()
+
+Memory and Display Controls
+---------------------------
+
+You can control how much data is displayed and how much memory is used for rendering:
+
+ .. code-block:: python
+ 
+    configure_formatter(
+        max_memory_bytes=4 * 1024 * 1024,  # 4MB maximum memory for display
+        min_rows_display=50,               # Always show at least 50 rows
+        repr_rows=20                       # Show 20 rows in __repr__ output
+    )
+
+These parameters help balance comprehensive data display against performance considerations.
\ No newline at end of file
diff --git a/examples/ffi-table-provider/.cargo/config.toml b/examples/datafusion-ffi-example/.cargo/config.toml
similarity index 100%
rename from examples/ffi-table-provider/.cargo/config.toml
rename to examples/datafusion-ffi-example/.cargo/config.toml
diff --git a/examples/ffi-table-provider/Cargo.lock b/examples/datafusion-ffi-example/Cargo.lock
similarity index 71%
rename from examples/ffi-table-provider/Cargo.lock
rename to examples/datafusion-ffi-example/Cargo.lock
index 8d0edd515..075ebd5a1 100644
--- a/examples/ffi-table-provider/Cargo.lock
+++ b/examples/datafusion-ffi-example/Cargo.lock
@@ -67,13 +67,13 @@ checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627"
 
 [[package]]
 name = "ahash"
-version = "0.8.11"
+version = "0.8.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
  "const-random",
- "getrandom",
+ "getrandom 0.3.3",
  "once_cell",
  "version_check",
  "zerocopy",
@@ -105,9 +105,9 @@ dependencies = [
 
 [[package]]
 name = "allocator-api2"
-version = "0.2.20"
+version = "0.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45862d1c77f2228b9e10bc609d5bc203d86ebc9b87ad8d5d5167a6c9abf739d9"
+checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
 
 [[package]]
 name = "android-tzdata"
@@ -126,9 +126,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.93"
+version = "1.0.98"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c95c10ba0b00a02636238b814946408b1322d5ac4760326e6fb8ec956d85775"
+checksum = "e16d2d3311acee920a9eb8d33b8cbc1787ce4a264e85f964c2404b969bdcd487"
 
 [[package]]
 name = "arrayref"
@@ -144,9 +144,9 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
 
 [[package]]
 name = "arrow"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6422e12ac345a0678d7a17e316238e3a40547ae7f92052b77bd86d5e0239f3fc"
+checksum = "b1bb018b6960c87fd9d025009820406f74e83281185a8bdcb44880d2aa5c9a87"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -165,9 +165,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-arith"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23cf34bb1f48c41d3475927bcc7be498665b8e80b379b88f62a840337f8b8248"
+checksum = "44de76b51473aa888ecd6ad93ceb262fb8d40d1f1154a4df2f069b3590aa7575"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -179,9 +179,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-array"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb4a06d507f54b70a277be22a127c8ffe0cec6cd98c0ad8a48e77779bbda8223"
+checksum = "29ed77e22744475a9a53d00026cf8e166fe73cf42d89c4c4ae63607ee1cfcc3f"
 dependencies = [
  "ahash",
  "arrow-buffer",
@@ -190,15 +190,15 @@ dependencies = [
  "chrono",
  "chrono-tz",
  "half",
- "hashbrown 0.15.1",
+ "hashbrown 0.15.3",
  "num",
 ]
 
 [[package]]
 name = "arrow-buffer"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d69d326d5ad1cb82dcefa9ede3fee8fdca98f9982756b16f9cb142f4aa6edc89"
+checksum = "b0391c96eb58bf7389171d1e103112d3fc3e5625ca6b372d606f2688f1ea4cce"
 dependencies = [
  "bytes",
  "half",
@@ -207,9 +207,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-cast"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "626e65bd42636a84a238bed49d09c8777e3d825bf81f5087a70111c2831d9870"
+checksum = "f39e1d774ece9292697fcbe06b5584401b26bd34be1bec25c33edae65c2420ff"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -228,9 +228,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-csv"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "71c8f959f7a1389b1dbd883cdcd37c3ed12475329c111912f7f69dad8195d8c6"
+checksum = "9055c972a07bf12c2a827debfd34f88d3b93da1941d36e1d9fee85eebe38a12a"
 dependencies = [
  "arrow-array",
  "arrow-cast",
@@ -244,9 +244,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-data"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1858e7c7d01c44cf71c21a85534fd1a54501e8d60d1195d0d6fbcc00f4b10754"
+checksum = "cf75ac27a08c7f48b88e5c923f267e980f27070147ab74615ad85b5c5f90473d"
 dependencies = [
  "arrow-buffer",
  "arrow-schema",
@@ -256,9 +256,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-ipc"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6bb3f727f049884c7603f0364bc9315363f356b59e9f605ea76541847e06a1e"
+checksum = "a222f0d93772bd058d1268f4c28ea421a603d66f7979479048c429292fac7b2e"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -270,9 +270,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-json"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35de94f165ed8830aede72c35f238763794f0d49c69d30c44d49c9834267ff8c"
+checksum = "9085342bbca0f75e8cb70513c0807cc7351f1fbf5cb98192a67d5e3044acb033"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -283,16 +283,18 @@ dependencies = [
  "half",
  "indexmap",
  "lexical-core",
+ "memchr",
  "num",
  "serde",
  "serde_json",
+ "simdutf8",
 ]
 
 [[package]]
 name = "arrow-ord"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8aa06e5f267dc53efbacb933485c79b6fc1685d3ffbe870a16ce4e696fb429da"
+checksum = "ab2f1065a5cad7b9efa9e22ce5747ce826aa3855766755d4904535123ef431e7"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -303,9 +305,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-row"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "66f1144bb456a2f9d82677bd3abcea019217e572fc8f07de5a7bac4b2c56eb2c"
+checksum = "3703a0e3e92d23c3f756df73d2dc9476873f873a76ae63ef9d3de17fda83b2d8"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -316,18 +318,18 @@ dependencies = [
 
 [[package]]
 name = "arrow-schema"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "105f01ec0090259e9a33a9263ec18ff223ab91a0ea9fbc18042f7e38005142f6"
+checksum = "73a47aa0c771b5381de2b7f16998d351a6f4eb839f1e13d48353e17e873d969b"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags",
 ]
 
 [[package]]
 name = "arrow-select"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f690752fdbd2dee278b5f1636fefad8f2f7134c85e20fd59c4199e15a39a6807"
+checksum = "24b7b85575702b23b85272b01bc1c25a01c9b9852305e5d0078c79ba25d995d4"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -339,9 +341,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-string"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d0fff9cd745a7039b66c47ecaf5954460f9fa12eed628f65170117ea93e64ee0"
+checksum = "9260fddf1cdf2799ace2b4c2fc0356a9789fa7551e0953e35435536fecefebbd"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -368,11 +370,11 @@ dependencies = [
 
 [[package]]
 name = "async-compression"
-version = "0.4.17"
+version = "0.4.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0cb8f1d480b0ea3783ab015936d2a55c87e219676f0c0b7dec61494043f21857"
+checksum = "06575e6a9673580f52661c92107baabffbf41e2141373441cbcdc47cb733003c"
 dependencies = [
- "bzip2 0.4.4",
+ "bzip2",
  "flate2",
  "futures-core",
  "memchr",
@@ -394,13 +396,13 @@ dependencies = [
 
 [[package]]
 name = "async-trait"
-version = "0.1.83"
+version = "0.1.88"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "721cae7de5c34fbb2acd27e21e6d2cf7b886dce0c27388d46c4e6c47ea4318dd"
+checksum = "e539d3fca749fcee5236ab05e93a52867dd549cc157c8cb7f99595f3cedffdb5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -420,9 +422,9 @@ checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
 
 [[package]]
 name = "backtrace"
-version = "0.3.74"
+version = "0.3.75"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a"
+checksum = "6806a6321ec58106fea15becdad98371e28d92ccbc7c8f1b3b6dd724fe8f1002"
 dependencies = [
  "addr2line",
  "cfg-if",
@@ -441,9 +443,9 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "bigdecimal"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f31f3af01c5c65a07985c804d3366560e6fa7883d640a122819b14ec327482c"
+checksum = "1a22f228ab7a1b23027ccc6c350b72868017af7ea8356fbdf19f8d991c690013"
 dependencies = [
  "autocfg",
  "libm",
@@ -454,15 +456,9 @@ dependencies = [
 
 [[package]]
 name = "bitflags"
-version = "1.3.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
-
-[[package]]
-name = "bitflags"
-version = "2.6.0"
+version = "2.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+checksum = "1b8e56985ec62d17e9c1001dc89c88ecd7dc08e47eba5ec7c29c7b5eeecde967"
 
 [[package]]
 name = "blake2"
@@ -475,9 +471,9 @@ dependencies = [
 
 [[package]]
 name = "blake3"
-version = "1.5.4"
+version = "1.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d82033247fd8e890df8f740e407ad4d038debb9eb1f40533fffb32e7d17dc6f7"
+checksum = "3888aaa89e4b2a40fca9848e400f6a658a5a3978de7be858e209cafa8be9a4a0"
 dependencies = [
  "arrayref",
  "arrayvec",
@@ -497,9 +493,9 @@ dependencies = [
 
 [[package]]
 name = "brotli"
-version = "7.0.0"
+version = "8.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc97b8f16f944bba54f0433f07e30be199b6dc2bd25937444bbad560bcea29bd"
+checksum = "9991eea70ea4f293524138648e41ee89b0b2b12ddef3b255effa43c8056e0e0d"
 dependencies = [
  "alloc-no-stdlib",
  "alloc-stdlib",
@@ -508,9 +504,9 @@ dependencies = [
 
 [[package]]
 name = "brotli-decompressor"
-version = "4.0.1"
+version = "5.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a45bd2e4095a8b518033b128020dd4a55aab1c0a381ba4404a472630f4bc362"
+checksum = "874bb8112abecc98cbd6d81ea4fa7e94fb9449648c93cc89aa40c81c24d7de03"
 dependencies = [
  "alloc-no-stdlib",
  "alloc-stdlib",
@@ -518,9 +514,9 @@ dependencies = [
 
 [[package]]
 name = "bumpalo"
-version = "3.16.0"
+version = "3.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
+checksum = "1628fb46dfa0b37568d12e5edd512553eccf6a22a78e8bde00bb4aed84d5bdbf"
 
 [[package]]
 name = "byteorder"
@@ -530,46 +526,34 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
 
 [[package]]
 name = "bytes"
-version = "1.8.0"
+version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ac0150caa2ae65ca5bd83f25c7de183dea78d4d366469f148435e2acfbad0da"
-
-[[package]]
-name = "bzip2"
-version = "0.4.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bdb116a6ef3f6c3698828873ad02c3014b3c85cadb88496095628e3ef1e347f8"
-dependencies = [
- "bzip2-sys",
- "libc",
-]
+checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
 
 [[package]]
 name = "bzip2"
-version = "0.5.0"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bafdbf26611df8c14810e268ddceda071c297570a5fb360ceddf617fe417ef58"
+checksum = "49ecfb22d906f800d4fe833b6282cf4dc1c298f5057ca0b5445e5c209735ca47"
 dependencies = [
  "bzip2-sys",
- "libc",
 ]
 
 [[package]]
 name = "bzip2-sys"
-version = "0.1.11+1.0.8"
+version = "0.1.13+1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc"
+checksum = "225bff33b2141874fe80d71e07d6eec4f85c5c216453dd96388240f96e1acc14"
 dependencies = [
  "cc",
- "libc",
  "pkg-config",
 ]
 
 [[package]]
 name = "cc"
-version = "1.1.37"
+version = "1.2.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "40545c26d092346d8a8dab71ee48e7685a7a9cba76e634790c215b41a4a7b4cf"
+checksum = "5f4ac86a9e5bc1e2b3449ab9d7d3a6a405e3d1bb28d7b9be8614f55846ae3766"
 dependencies = [
  "jobserver",
  "libc",
@@ -584,21 +568,21 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "chrono"
-version = "0.4.38"
+version = "0.4.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a21f936df1771bf62b77f047b726c4625ff2e8aa607c01ec06e5a05bd8463401"
+checksum = "c469d952047f47f91b68d1cba3f10d63c11d73e4636f24f08daf0278abf01c4d"
 dependencies = [
  "android-tzdata",
  "iana-time-zone",
  "num-traits",
- "windows-targets",
+ "windows-link",
 ]
 
 [[package]]
 name = "chrono-tz"
-version = "0.10.0"
+version = "0.10.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd6dd8046d00723a59a2f8c5f295c515b9bb9a331ee4f8f3d4dd49e428acd3b6"
+checksum = "efdce149c370f133a071ca8ef6ea340b7b88748ab0810097a9e2976eaa34b4f3"
 dependencies = [
  "chrono",
  "chrono-tz-build",
@@ -607,9 +591,9 @@ dependencies = [
 
 [[package]]
 name = "chrono-tz-build"
-version = "0.4.0"
+version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e94fea34d77a245229e7746bd2beb786cd2a896f306ff491fb8cecb3074b10a7"
+checksum = "8f10f8c9340e31fc120ff885fcdb54a0b48e474bbd77cab557f0c30a3e569402"
 dependencies = [
  "parse-zoneinfo",
  "phf_codegen",
@@ -617,12 +601,11 @@ dependencies = [
 
 [[package]]
 name = "comfy-table"
-version = "7.1.1"
+version = "7.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b34115915337defe99b2aff5c2ce6771e5fbc4079f4b506301f5cf394c8452f7"
+checksum = "4a65ebfec4fb190b6f90e944a817d60499ee0744e582530e2c9900a22e591d9a"
 dependencies = [
- "strum",
- "strum_macros",
+ "unicode-segmentation",
  "unicode-width",
 ]
 
@@ -641,16 +624,16 @@ version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.16",
  "once_cell",
  "tiny-keccak",
 ]
 
 [[package]]
 name = "const_panic"
-version = "0.2.10"
+version = "0.2.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "013b6c2c3a14d678f38cd23994b02da3a1a1b6a5d1eedddfe63a5a5f11b13a81"
+checksum = "2459fc9262a1aa204eb4b5764ad4f189caec88aea9634389c0a25f8be7f6265e"
 
 [[package]]
 name = "constant_time_eq"
@@ -681,9 +664,9 @@ checksum = "69f3b219d28b6e3b4ac87bc1fc522e0803ab22e055da177bff0068c4150c61a6"
 
 [[package]]
 name = "cpufeatures"
-version = "0.2.14"
+version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "608697df725056feaccfa42cffdaeeec3fccc4ffc38358ecd19b243e716a78e0"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
 dependencies = [
  "libc",
 ]
@@ -699,24 +682,24 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-channel"
-version = "0.5.13"
+version = "0.5.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "33480d6946193aa8033910124896ca395333cae7e2d1113d1fef6c3272217df2"
+checksum = "82b8f8f868b36967f9606790d1903570de9ceaf870a7bf9fbbd3016d636a2cb2"
 dependencies = [
  "crossbeam-utils",
 ]
 
 [[package]]
 name = "crossbeam-utils"
-version = "0.8.20"
+version = "0.8.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
 [[package]]
 name = "crunchy"
-version = "0.2.2"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
+checksum = "43da5946c66ffcc7745f48db692ffbb10a83bfe0afd96235c5c2a4fb23994929"
 
 [[package]]
 name = "crypto-common"
@@ -742,9 +725,9 @@ dependencies = [
 
 [[package]]
 name = "csv-core"
-version = "0.1.11"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5efa2b3d7902f4b634a20cae3c9c4e6209dc4779feb6863329607560143efa70"
+checksum = "7d02f3b0da4c6504f86e9cd789d8dbafab48c2321be74e9987593de5a894d93d"
 dependencies = [
  "memchr",
 ]
@@ -765,39 +748,44 @@ dependencies = [
 
 [[package]]
 name = "datafusion"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eae420e7a5b0b7f1c39364cc76cbcd0f5fdc416b2514ae3847c2676bbd60702a"
+checksum = "ffe060b978f74ab446be722adb8a274e052e005bf6dfd171caadc3abaad10080"
 dependencies = [
  "arrow",
- "arrow-array",
  "arrow-ipc",
  "arrow-schema",
- "async-compression",
  "async-trait",
  "bytes",
- "bzip2 0.5.0",
+ "bzip2",
  "chrono",
  "datafusion-catalog",
+ "datafusion-catalog-listing",
  "datafusion-common",
  "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-datasource-csv",
+ "datafusion-datasource-json",
+ "datafusion-datasource-parquet",
  "datafusion-execution",
  "datafusion-expr",
+ "datafusion-expr-common",
  "datafusion-functions",
  "datafusion-functions-aggregate",
  "datafusion-functions-nested",
  "datafusion-functions-table",
  "datafusion-functions-window",
+ "datafusion-macros",
  "datafusion-optimizer",
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
  "datafusion-physical-optimizer",
  "datafusion-physical-plan",
+ "datafusion-session",
  "datafusion-sql",
  "flate2",
  "futures",
- "glob",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "object_store",
  "parking_lot",
@@ -807,7 +795,6 @@ dependencies = [
  "sqlparser",
  "tempfile",
  "tokio",
- "tokio-util",
  "url",
  "uuid",
  "xz2",
@@ -816,37 +803,62 @@ dependencies = [
 
 [[package]]
 name = "datafusion-catalog"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f27987bc22b810939e8dfecc55571e9d50355d6ea8ec1c47af8383a76a6d0e1"
+checksum = "61fe34f401bd03724a1f96d12108144f8cd495a3cdda2bf5e091822fb80b7e66"
 dependencies = [
  "arrow",
  "async-trait",
  "dashmap",
  "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
  "datafusion-execution",
  "datafusion-expr",
+ "datafusion-physical-expr",
  "datafusion-physical-plan",
+ "datafusion-session",
  "datafusion-sql",
  "futures",
- "itertools 0.14.0",
+ "itertools",
  "log",
+ "object_store",
  "parking_lot",
- "sqlparser",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-catalog-listing"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4411b8e3bce5e0fc7521e44f201def2e2d5d1b5f176fb56e8cdc9942c890f00"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "log",
+ "object_store",
+ "tokio",
 ]
 
 [[package]]
 name = "datafusion-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3f6d5b8c9408cc692f7c194b8aa0c0f9b253e065a8d960ad9cdc2a13e697602"
+checksum = "0734015d81c8375eb5d4869b7f7ecccc2ee8d6cb81948ef737cd0e7b743bd69c"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ipc",
- "arrow-schema",
  "base64",
  "half",
  "hashbrown 0.14.5",
@@ -864,25 +876,143 @@ dependencies = [
 
 [[package]]
 name = "datafusion-common-runtime"
-version = "45.0.0"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5167bb1d2ccbb87c6bc36c295274d7a0519b14afcfdaf401d53cbcaa4ef4968b"
+dependencies = [
+ "futures",
+ "log",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04e602dcdf2f50c2abf297cc2203c73531e6f48b29516af7695d338cf2a778b1"
+dependencies = [
+ "arrow",
+ "async-compression",
+ "async-trait",
+ "bytes",
+ "bzip2",
+ "chrono",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "flate2",
+ "futures",
+ "glob",
+ "itertools",
+ "log",
+ "object_store",
+ "parquet",
+ "rand",
+ "tempfile",
+ "tokio",
+ "tokio-util",
+ "url",
+ "xz2",
+ "zstd",
+]
+
+[[package]]
+name = "datafusion-datasource-csv"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3bb2253952dc32296ed5b84077cb2e0257fea4be6373e1c376426e17ead4ef6"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "object_store",
+ "regex",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource-json"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b8c7f47a5d2fe03bfa521ec9bafdb8a5c82de8377f60967c3663f00c8790352"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "object_store",
+ "serde_json",
+ "tokio",
+]
+
+[[package]]
+name = "datafusion-datasource-parquet"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d4603c8e8a4baf77660ab7074cc66fc15cc8a18f2ce9dfadb755fc6ee294e48"
+checksum = "27d15868ea39ed2dc266728b554f6304acd473de2142281ecfa1294bb7415923"
 dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-functions-aggregate",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-optimizer",
+ "datafusion-physical-plan",
+ "datafusion-session",
+ "futures",
+ "itertools",
  "log",
+ "object_store",
+ "parking_lot",
+ "parquet",
+ "rand",
  "tokio",
 ]
 
 [[package]]
 name = "datafusion-doc"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5bf4bc68623a5cf231eed601ed6eb41f46a37c4d15d11a0bff24cbc8396cd66"
+checksum = "a91f8c2c5788ef32f48ff56c68e5b545527b744822a284373ac79bba1ba47292"
 
 [[package]]
 name = "datafusion-execution"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88b491c012cdf8e051053426013429a76f74ee3c2db68496c79c323ca1084d27"
+checksum = "06f004d100f49a3658c9da6fb0c3a9b760062d96cd4ad82ccc3b7b69a9fb2f84"
 dependencies = [
  "arrow",
  "dashmap",
@@ -899,9 +1029,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5a181408d4fc5dc22f9252781a8f39f2d0e5d1b33ec9bde242844980a2689c1"
+checksum = "7a4e4ce3802609be38eeb607ee72f6fe86c3091460de9dbfae9e18db423b3964"
 dependencies = [
  "arrow",
  "chrono",
@@ -920,25 +1050,25 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1129b48e8534d8c03c6543bcdccef0b55c8ac0c1272a15a56c67068b6eb1885"
+checksum = "422ac9cf3b22bbbae8cdf8ceb33039107fde1b5492693168f13bd566b1bcc839"
 dependencies = [
  "arrow",
  "datafusion-common",
- "itertools 0.14.0",
+ "indexmap",
+ "itertools",
  "paste",
 ]
 
 [[package]]
 name = "datafusion-ffi"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff47a79d442207c168c6e3e1d970c248589c148e4800e5b285ac1b2cb1a230f8"
+checksum = "5cf3fe9ab492c56daeb7beed526690d33622d388b8870472e0b7b7f55490338c"
 dependencies = [
  "abi_stable",
  "arrow",
- "arrow-array",
  "arrow-schema",
  "async-ffi",
  "async-trait",
@@ -953,9 +1083,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6125874e4856dfb09b59886784fcb74cde5cfc5930b3a80a1a728ef7a010df6b"
+checksum = "2ddf0a0a2db5d2918349c978d42d80926c6aa2459cd8a3c533a84ec4bb63479e"
 dependencies = [
  "arrow",
  "arrow-buffer",
@@ -969,9 +1099,8 @@ dependencies = [
  "datafusion-expr",
  "datafusion-expr-common",
  "datafusion-macros",
- "hashbrown 0.14.5",
  "hex",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "md-5",
  "rand",
@@ -983,14 +1112,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3add7b1d3888e05e7c95f2b281af900ca69ebdcb21069ba679b33bde8b3b9d6"
+checksum = "408a05dafdc70d05a38a29005b8b15e21b0238734dab1e98483fcb58038c5aba"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -1006,9 +1133,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e18baa4cfc3d2f144f74148ed68a1f92337f5072b6dde204a0dbbdf3324989c"
+checksum = "756d21da2dd6c9bef97af1504970ff56cbf35d03fbd4ffd62827f02f4d2279d4"
 dependencies = [
  "ahash",
  "arrow",
@@ -1019,15 +1146,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-nested"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3ec5ee8cecb0dc370291279673097ddabec03a011f73f30d7f1096457127e03e"
+checksum = "8d8d50f6334b378930d992d801a10ac5b3e93b846b39e4a05085742572844537"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -1036,16 +1160,16 @@ dependencies = [
  "datafusion-functions-aggregate",
  "datafusion-macros",
  "datafusion-physical-expr-common",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "paste",
 ]
 
 [[package]]
 name = "datafusion-functions-table"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c403ddd473bbb0952ba880008428b3c7febf0ed3ce1eec35a205db20efb2a36"
+checksum = "cc9a97220736c8fff1446e936be90d57216c06f28969f9ffd3b72ac93c958c8a"
 dependencies = [
  "arrow",
  "async-trait",
@@ -1059,9 +1183,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ab18c2fb835614d06a75f24a9e09136d3a8c12a92d97c95a6af316a1787a9c5"
+checksum = "cefc2d77646e1aadd1d6a9c40088937aedec04e68c5f0465939912e1291f8193"
 dependencies = [
  "datafusion-common",
  "datafusion-doc",
@@ -1076,9 +1200,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a77b73bc15e7d1967121fdc7a55d819bfb9d6c03766a6c322247dce9094a53a4"
+checksum = "dd4aff082c42fa6da99ce0698c85addd5252928c908eb087ca3cfa64ff16b313"
 dependencies = [
  "datafusion-common",
  "datafusion-physical-expr-common",
@@ -1086,20 +1210,20 @@ dependencies = [
 
 [[package]]
 name = "datafusion-macros"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09369b8d962291e808977cf94d495fd8b5b38647232d7ef562c27ac0f495b0af"
+checksum = "df6f88d7ee27daf8b108ba910f9015176b36fbc72902b1ca5c2a5f1d1717e1a1"
 dependencies = [
  "datafusion-expr",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "datafusion-optimizer"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2403a7e4a84637f3de7d8d4d7a9ccc0cc4be92d89b0161ba3ee5be82f0531c54"
+checksum = "084d9f979c4b155346d3c34b18f4256e6904ded508e9554d90fed416415c3515"
 dependencies = [
  "arrow",
  "chrono",
@@ -1107,7 +1231,7 @@ dependencies = [
  "datafusion-expr",
  "datafusion-physical-expr",
  "indexmap",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "recursive",
  "regex",
@@ -1116,15 +1240,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86ff72ac702b62dbf2650c4e1d715ebd3e4aab14e3885e72e8549e250307347c"
+checksum = "64c536062b0076f4e30084065d805f389f9fe38af0ca75bcbac86bc5e9fbab65"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-expr",
  "datafusion-expr-common",
@@ -1133,7 +1254,7 @@ dependencies = [
  "half",
  "hashbrown 0.14.5",
  "indexmap",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "paste",
  "petgraph",
@@ -1141,27 +1262,25 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60982b7d684e25579ee29754b4333057ed62e2cc925383c5f0bd8cab7962f435"
+checksum = "f8a92b53b3193fac1916a1c5b8e3f4347c526f6822e56b71faa5fb372327a863"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
  "datafusion-common",
  "datafusion-expr-common",
  "hashbrown 0.14.5",
- "itertools 0.14.0",
+ "itertools",
 ]
 
 [[package]]
 name = "datafusion-physical-optimizer"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac5e85c189d5238a5cf181a624e450c4cd4c66ac77ca551d6f3ff9080bac90bb"
+checksum = "6fa0a5ac94c7cf3da97bedabd69d6bbca12aef84b9b37e6e9e8c25286511b5e2"
 dependencies = [
  "arrow",
- "arrow-schema",
  "datafusion-common",
  "datafusion-execution",
  "datafusion-expr",
@@ -1169,23 +1288,19 @@ dependencies = [
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
  "datafusion-physical-plan",
- "futures",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "recursive",
- "url",
 ]
 
 [[package]]
 name = "datafusion-physical-plan"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c36bf163956d7e2542657c78b3383fdc78f791317ef358a359feffcdb968106f"
+checksum = "690c615db468c2e5fe5085b232d8b1c088299a6c63d87fd960a354a71f7acb55"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
  "arrow-schema",
  "async-trait",
@@ -1201,7 +1316,7 @@ dependencies = [
  "half",
  "hashbrown 0.14.5",
  "indexmap",
- "itertools 0.14.0",
+ "itertools",
  "log",
  "parking_lot",
  "pin-project-lite",
@@ -1210,9 +1325,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-proto"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2db5d79f0c974041787b899d24dc91bdab2ff112d1942dd71356a4ce3b407e6c"
+checksum = "a4a1afb2bdb05de7ff65be6883ebfd4ec027bd9f1f21c46aa3afd01927160a83"
 dependencies = [
  "arrow",
  "chrono",
@@ -1226,24 +1341,46 @@ dependencies = [
 
 [[package]]
 name = "datafusion-proto-common"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de21bde1603aac0ff32cf478e47081be6e3583c6861fe8f57034da911efe7578"
+checksum = "35b7a5876ebd6b564fb9a1fd2c3a2a9686b787071a256b47e4708f0916f9e46f"
 dependencies = [
  "arrow",
  "datafusion-common",
  "prost",
 ]
 
+[[package]]
+name = "datafusion-session"
+version = "47.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad229a134c7406c057ece00c8743c0c34b97f4e72f78b475fe17b66c5e14fa4f"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "dashmap",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-plan",
+ "datafusion-sql",
+ "futures",
+ "itertools",
+ "log",
+ "object_store",
+ "parking_lot",
+ "tokio",
+]
+
 [[package]]
 name = "datafusion-sql"
-version = "45.0.0"
+version = "47.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13caa4daede211ecec53c78b13c503b592794d125f9a3cc3afe992edf9e7f43"
+checksum = "64f6ab28b72b664c21a27b22a2ff815fd390ed224c26e89a93b5a8154a4e8607"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-schema",
  "bigdecimal",
  "datafusion-common",
  "datafusion-expr",
@@ -1273,36 +1410,36 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "either"
-version = "1.13.0"
+version = "1.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
 
 [[package]]
 name = "equivalent"
-version = "1.0.1"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
 
 [[package]]
 name = "errno"
-version = "0.3.9"
+version = "0.3.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba"
+checksum = "cea14ef9355e3beab063703aa9dab15afd25f0667c341310c1e5274bb1d0da18"
 dependencies = [
  "libc",
- "windows-sys 0.52.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "fastrand"
-version = "2.2.0"
+version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "486f806e73c5707928240ddc295403b1b93c96a02038563881c4a2fd84b81ac4"
+checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
 [[package]]
 name = "ffi-table-provider"
@@ -1325,24 +1462,31 @@ checksum = "1d674e81391d1e1ab681a28d99df07927c6d4aa5b027d7da16ba32d1d21ecd99"
 
 [[package]]
 name = "flatbuffers"
-version = "24.12.23"
+version = "25.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f1baf0dbf96932ec9a3038d57900329c015b0bfb7b63d904f3bc27e2b02a096"
+checksum = "1045398c1bfd89168b5fd3f1fc11f6e70b34f6f66300c87d44d3de849463abf1"
 dependencies = [
- "bitflags 1.3.2",
+ "bitflags",
  "rustc_version",
 ]
 
 [[package]]
 name = "flate2"
-version = "1.0.34"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1b589b4dc103969ad3cf85c950899926ec64300a1a46d76c03a6072957036f0"
+checksum = "7ced92e76e966ca2fd84c8f7aa01a4aea65b0eb6648d72f7c8f3e2764a67fece"
 dependencies = [
  "crc32fast",
+ "libz-rs-sys",
  "miniz_oxide",
 ]
 
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
 [[package]]
 name = "form_urlencoded"
 version = "1.2.1"
@@ -1408,7 +1552,7 @@ checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -1462,13 +1606,25 @@ dependencies = [
 
 [[package]]
 name = "getrandom"
-version = "0.2.15"
+version = "0.2.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi 0.11.0+wasi-snapshot-preview1",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
+checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
 dependencies = [
  "cfg-if",
  "libc",
- "wasi",
+ "r-efi",
+ "wasi 0.14.2+wasi-0.2.4",
 ]
 
 [[package]]
@@ -1479,15 +1635,15 @@ checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f"
 
 [[package]]
 name = "glob"
-version = "0.3.1"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"
 
 [[package]]
 name = "half"
-version = "2.4.1"
+version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6dd08c532ae367adf81c312a4580bc67f1d0fe8bc9c460520283f4c0ff277888"
+checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9"
 dependencies = [
  "cfg-if",
  "crunchy",
@@ -1506,9 +1662,9 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.15.1"
+version = "0.15.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3a9bfc1af68b1726ea47d3d5109de126281def866b33970e10fbab11b5dafab3"
+checksum = "84b26c544d002229e640969970a2e74021aadf6e2f96372b9c58eff97de08eb3"
 
 [[package]]
 name = "heck"
@@ -1522,22 +1678,34 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
+[[package]]
+name = "http"
+version = "1.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4a85d31aea989eead29a3aaf9e1115a180df8282431156e533de47660892565"
+dependencies = [
+ "bytes",
+ "fnv",
+ "itoa",
+]
+
 [[package]]
 name = "humantime"
-version = "2.1.0"
+version = "2.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4"
+checksum = "9b112acc8b3adf4b107a8ec20977da0273a8c386765a3ec0229bd500a1443f9f"
 
 [[package]]
 name = "iana-time-zone"
-version = "0.1.61"
+version = "0.1.63"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "235e081f3925a06703c2d0117ea8b91f042756fd6e7a6e5d901e8ca1a996b220"
+checksum = "b0c919e5debc312ad217002b8048a17b7d83f80703865bbfcfebb0458b0b27d8"
 dependencies = [
  "android_system_properties",
  "core-foundation-sys",
  "iana-time-zone-haiku",
  "js-sys",
+ "log",
  "wasm-bindgen",
  "windows-core",
 ]
@@ -1553,21 +1721,22 @@ dependencies = [
 
 [[package]]
 name = "icu_collections"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "db2fa452206ebee18c4b5c2274dbf1de17008e874b4dc4f0aea9d01ca79e4526"
+checksum = "200072f5d0e3614556f94a9930d5dc3e0662a652823904c3a75dc3b0af7fee47"
 dependencies = [
  "displaydoc",
+ "potential_utf",
  "yoke",
  "zerofrom",
  "zerovec",
 ]
 
 [[package]]
-name = "icu_locid"
-version = "1.5.0"
+name = "icu_locale_core"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "13acbb8371917fc971be86fc8057c41a64b521c184808a698c02acc242dbf637"
+checksum = "0cde2700ccaed3872079a65fb1a78f6c0a36c91570f28755dda67bc8f7d9f00a"
 dependencies = [
  "displaydoc",
  "litemap",
@@ -1576,31 +1745,11 @@ dependencies = [
  "zerovec",
 ]
 
-[[package]]
-name = "icu_locid_transform"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "01d11ac35de8e40fdeda00d9e1e9d92525f3f9d887cdd7aa81d727596788b54e"
-dependencies = [
- "displaydoc",
- "icu_locid",
- "icu_locid_transform_data",
- "icu_provider",
- "tinystr",
- "zerovec",
-]
-
-[[package]]
-name = "icu_locid_transform_data"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fdc8ff3388f852bede6b579ad4e978ab004f139284d7b28715f773507b946f6e"
-
 [[package]]
 name = "icu_normalizer"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "19ce3e0da2ec68599d193c93d088142efd7f9c5d6fc9b803774855747dc6a84f"
+checksum = "436880e8e18df4d7bbc06d58432329d6458cc84531f7ac5f024e93deadb37979"
 dependencies = [
  "displaydoc",
  "icu_collections",
@@ -1608,67 +1757,54 @@ dependencies = [
  "icu_properties",
  "icu_provider",
  "smallvec",
- "utf16_iter",
- "utf8_iter",
- "write16",
  "zerovec",
 ]
 
 [[package]]
 name = "icu_normalizer_data"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8cafbf7aa791e9b22bec55a167906f9e1215fd475cd22adfcf660e03e989516"
+checksum = "00210d6893afc98edb752b664b8890f0ef174c8adbb8d0be9710fa66fbbf72d3"
 
 [[package]]
 name = "icu_properties"
-version = "1.5.1"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93d6020766cfc6302c15dbbc9c8778c37e62c14427cb7f6e601d849e092aeef5"
+checksum = "2549ca8c7241c82f59c80ba2a6f415d931c5b58d24fb8412caa1a1f02c49139a"
 dependencies = [
  "displaydoc",
  "icu_collections",
- "icu_locid_transform",
+ "icu_locale_core",
  "icu_properties_data",
  "icu_provider",
- "tinystr",
+ "potential_utf",
+ "zerotrie",
  "zerovec",
 ]
 
 [[package]]
 name = "icu_properties_data"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67a8effbc3dd3e4ba1afa8ad918d5684b8868b3b26500753effea8d2eed19569"
+checksum = "8197e866e47b68f8f7d95249e172903bec06004b18b2937f1095d40a0c57de04"
 
 [[package]]
 name = "icu_provider"
-version = "1.5.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ed421c8a8ef78d3e2dbc98a973be2f3770cb42b606e3ab18d6237c4dfde68d9"
+checksum = "03c80da27b5f4187909049ee2d72f276f0d9f99a42c306bd0131ecfe04d8e5af"
 dependencies = [
  "displaydoc",
- "icu_locid",
- "icu_provider_macros",
+ "icu_locale_core",
  "stable_deref_trait",
  "tinystr",
  "writeable",
  "yoke",
  "zerofrom",
+ "zerotrie",
  "zerovec",
 ]
 
-[[package]]
-name = "icu_provider_macros"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.87",
-]
-
 [[package]]
 name = "idna"
 version = "1.0.3"
@@ -1682,9 +1818,9 @@ dependencies = [
 
 [[package]]
 name = "idna_adapter"
-version = "1.2.0"
+version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "daca1df1c957320b2cf139ac61e7bd64fed304c5040df000a745aa1de3b4ef71"
+checksum = "3acae9609540aa318d1bc588455225fb2085b9ed0c4f6bd0d9d5bcd86f1a0344"
 dependencies = [
  "icu_normalizer",
  "icu_properties",
@@ -1692,19 +1828,19 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.7.1"
+version = "2.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8c9c992b02b5b4c94ea26e32fe5bccb7aa7d9f390ab5c1221ff895bc7ea8b652"
+checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e"
 dependencies = [
  "equivalent",
- "hashbrown 0.15.1",
+ "hashbrown 0.15.3",
 ]
 
 [[package]]
 name = "indoc"
-version = "2.0.5"
+version = "2.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b248f5224d1d606005e02c97f5aa4e88eeb230488bcc03bc9ca4d7991399f2b5"
+checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
 
 [[package]]
 name = "integer-encoding"
@@ -1712,15 +1848,6 @@ version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8bb03732005da905c88227371639bf1ad885cc712789c011c31c5fb3ab3ccf02"
 
-[[package]]
-name = "itertools"
-version = "0.13.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
-dependencies = [
- "either",
-]
-
 [[package]]
 name = "itertools"
 version = "0.14.0"
@@ -1732,25 +1859,27 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.11"
+version = "1.0.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
 
 [[package]]
 name = "jobserver"
-version = "0.1.32"
+version = "0.1.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48d1dbcbbeb6a7fec7e059840aa538bd62aaccf972c7346c4d9d2059312853d0"
+checksum = "38f262f097c174adebe41eb73d66ae9c06b2844fb0da69969647bbddd9b0538a"
 dependencies = [
+ "getrandom 0.3.3",
  "libc",
 ]
 
 [[package]]
 name = "js-sys"
-version = "0.3.72"
+version = "0.3.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a88f1bda2bd75b0452a14784937d796722fdebfe50df998aeb3f0b7603019a9"
+checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f"
 dependencies = [
+ "once_cell",
  "wasm-bindgen",
 ]
 
@@ -1762,9 +1891,9 @@ checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
 
 [[package]]
 name = "lexical-core"
-version = "1.0.2"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0431c65b318a590c1de6b8fd6e72798c92291d27762d94c9e6c37ed7a73d8458"
+checksum = "b765c31809609075565a70b4b71402281283aeda7ecaf4818ac14a7b2ade8958"
 dependencies = [
  "lexical-parse-float",
  "lexical-parse-integer",
@@ -1775,9 +1904,9 @@ dependencies = [
 
 [[package]]
 name = "lexical-parse-float"
-version = "1.0.2"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eb17a4bdb9b418051aa59d41d65b1c9be5affab314a872e5ad7f06231fb3b4e0"
+checksum = "de6f9cb01fb0b08060209a057c048fcbab8717b4c1ecd2eac66ebfe39a65b0f2"
 dependencies = [
  "lexical-parse-integer",
  "lexical-util",
@@ -1786,9 +1915,9 @@ dependencies = [
 
 [[package]]
 name = "lexical-parse-integer"
-version = "1.0.2"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5df98f4a4ab53bf8b175b363a34c7af608fe31f93cc1fb1bf07130622ca4ef61"
+checksum = "72207aae22fc0a121ba7b6d479e42cbfea549af1479c3f3a4f12c70dd66df12e"
 dependencies = [
  "lexical-util",
  "static_assertions",
@@ -1796,18 +1925,18 @@ dependencies = [
 
 [[package]]
 name = "lexical-util"
-version = "1.0.3"
+version = "1.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85314db53332e5c192b6bca611fb10c114a80d1b831ddac0af1e9be1b9232ca0"
+checksum = "5a82e24bf537fd24c177ffbbdc6ebcc8d54732c35b50a3f28cc3f4e4c949a0b3"
 dependencies = [
  "static_assertions",
 ]
 
 [[package]]
 name = "lexical-write-float"
-version = "1.0.2"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e7c3ad4e37db81c1cbe7cf34610340adc09c322871972f74877a712abc6c809"
+checksum = "c5afc668a27f460fb45a81a757b6bf2f43c2d7e30cb5a2dcd3abf294c78d62bd"
 dependencies = [
  "lexical-util",
  "lexical-write-integer",
@@ -1816,9 +1945,9 @@ dependencies = [
 
 [[package]]
 name = "lexical-write-integer"
-version = "1.0.2"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eb89e9f6958b83258afa3deed90b5de9ef68eef090ad5086c791cd2345610162"
+checksum = "629ddff1a914a836fb245616a7888b62903aae58fa771e1d83943035efa0f978"
 dependencies = [
  "lexical-util",
  "static_assertions",
@@ -1826,9 +1955,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.162"
+version = "0.2.172"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18d287de67fe55fd7e1581fe933d965a5a9477b38e949cfa9f8574ef01506398"
+checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
 
 [[package]]
 name = "libloading"
@@ -1842,21 +1971,30 @@ dependencies = [
 
 [[package]]
 name = "libm"
-version = "0.2.11"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
+
+[[package]]
+name = "libz-rs-sys"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8355be11b20d696c8f18f6cc018c4e372165b1fa8126cef092399c9951984ffa"
+checksum = "6489ca9bd760fe9642d7644e827b0c9add07df89857b0416ee15c1cc1a3b8c5a"
+dependencies = [
+ "zlib-rs",
+]
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.14"
+version = "0.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
+checksum = "cd945864f07fe9f5371a27ad7b52a172b4b499999f1d97574c9fa68373937e12"
 
 [[package]]
 name = "litemap"
-version = "0.7.3"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "643cb0b8d4fcc284004d5fd0d67ccf61dfffadb7f75e1e71bc420f4688a3a704"
+checksum = "241eaef5fd12c88705a01fc1066c48c4b36e0dd4377dcdc7ec3942cea7a69956"
 
 [[package]]
 name = "lock_api"
@@ -1870,9 +2008,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.22"
+version = "0.4.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24"
+checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
 
 [[package]]
 name = "lz4_flex"
@@ -1880,7 +2018,7 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "75761162ae2b0e580d7e7c390558127e5f01b4194debd6221fd8c207fc80e3f5"
 dependencies = [
- "twox-hash",
+ "twox-hash 1.6.3",
 ]
 
 [[package]]
@@ -1921,9 +2059,9 @@ dependencies = [
 
 [[package]]
 name = "miniz_oxide"
-version = "0.8.0"
+version = "0.8.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
+checksum = "3be647b768db090acb35d5ec5db2b0e1f1de11133ca123b9eacf5137868f892a"
 dependencies = [
  "adler2",
 ]
@@ -2004,39 +2142,42 @@ dependencies = [
 
 [[package]]
 name = "object"
-version = "0.36.5"
+version = "0.36.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aedf0a2d09c573ed1d8d85b30c119153926a2b36dce0ab28322c09a117a4683e"
+checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
 name = "object_store"
-version = "0.11.1"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6eb4c22c6154a1e759d7099f9ffad7cc5ef8245f9efbab4a41b92623079c82f3"
+checksum = "d94ac16b433c0ccf75326388c893d2835ab7457ea35ab8ba5d745c053ef5fa16"
 dependencies = [
  "async-trait",
  "bytes",
  "chrono",
  "futures",
+ "http",
  "humantime",
- "itertools 0.13.0",
+ "itertools",
  "parking_lot",
  "percent-encoding",
- "snafu",
+ "thiserror",
  "tokio",
  "tracing",
  "url",
  "walkdir",
+ "wasm-bindgen-futures",
+ "web-time",
 ]
 
 [[package]]
 name = "once_cell"
-version = "1.20.2"
+version = "1.21.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1261fe7e33c73b354eab43b1273a57c8f967d0391e80353e51f764ac02cf6775"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
 
 [[package]]
 name = "ordered-float"
@@ -2072,9 +2213,9 @@ dependencies = [
 
 [[package]]
 name = "parquet"
-version = "54.1.0"
+version = "55.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a01a0efa30bbd601ae85b375c728efdb211ade54390281628a7b16708beb235"
+checksum = "be7b2d778f6b841d37083ebdf32e33a524acde1266b5884a8ca29bf00dfa1231"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -2091,7 +2232,7 @@ dependencies = [
  "flate2",
  "futures",
  "half",
- "hashbrown 0.15.1",
+ "hashbrown 0.15.3",
  "lz4_flex",
  "num",
  "num-bigint",
@@ -2102,9 +2243,8 @@ dependencies = [
  "snap",
  "thrift",
  "tokio",
- "twox-hash",
+ "twox-hash 2.1.0",
  "zstd",
- "zstd-sys",
 ]
 
 [[package]]
@@ -2140,18 +2280,18 @@ dependencies = [
 
 [[package]]
 name = "phf"
-version = "0.11.2"
+version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
+checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
 dependencies = [
  "phf_shared",
 ]
 
 [[package]]
 name = "phf_codegen"
-version = "0.11.2"
+version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
+checksum = "aef8048c789fa5e851558d709946d6d79a8ff88c0440c587967f8e94bfb1216a"
 dependencies = [
  "phf_generator",
  "phf_shared",
@@ -2159,9 +2299,9 @@ dependencies = [
 
 [[package]]
 name = "phf_generator"
-version = "0.11.2"
+version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
+checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
 dependencies = [
  "phf_shared",
  "rand",
@@ -2169,18 +2309,18 @@ dependencies = [
 
 [[package]]
 name = "phf_shared"
-version = "0.11.2"
+version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
+checksum = "67eabc2ef2a60eb7faa00097bd1ffdb5bd28e62bf39990626a582201b7a754e5"
 dependencies = [
  "siphasher",
 ]
 
 [[package]]
 name = "pin-project-lite"
-version = "0.2.15"
+version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "915a1e146535de9163f3987b8944ed8cf49a18bb0056bcebcdcece385cece4ff"
+checksum = "3b3cff922bd51709b605d9ead9aa71031d81447142d828eb4a6eba76fe619f9b"
 
 [[package]]
 name = "pin-utils"
@@ -2190,39 +2330,48 @@ checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
 [[package]]
 name = "pkg-config"
-version = "0.3.31"
+version = "0.3.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2"
+checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
 
 [[package]]
 name = "portable-atomic"
-version = "1.9.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc9c68a3f6da06753e9335d63e27f6b9754dd1920d941135b7ea8224f141adb2"
+checksum = "350e9b48cbc6b0e028b0473b114454c6316e57336ee184ceab6e53f72c178b3e"
+
+[[package]]
+name = "potential_utf"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5a7c30837279ca13e7c867e9e40053bc68740f988cb07f7ca6df43cc734b585"
+dependencies = [
+ "zerovec",
+]
 
 [[package]]
 name = "ppv-lite86"
-version = "0.2.20"
+version = "0.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
 dependencies = [
  "zerocopy",
 ]
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.89"
+version = "1.0.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f139b0662de085916d1fb67d2b4169d1addddda1919e696f3252b740b629986e"
+checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "prost"
-version = "0.13.3"
+version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b0487d90e047de87f984913713b85c601c05609aad5b0df4b4573fbf69aa13f"
+checksum = "2796faa41db3ec313a31f7624d9286acf277b52de526150b7e69f3debf891ee5"
 dependencies = [
  "bytes",
  "prost-derive",
@@ -2230,31 +2379,31 @@ dependencies = [
 
 [[package]]
 name = "prost-derive"
-version = "0.13.3"
+version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e9552f850d5f0964a4e4d0bf306459ac29323ddfbae05e35a7c0d35cb0803cc5"
+checksum = "8a56d757972c98b346a9b766e3f02746cde6dd1cd1d1d563472929fdd74bec4d"
 dependencies = [
  "anyhow",
- "itertools 0.13.0",
+ "itertools",
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "psm"
-version = "0.1.24"
+version = "0.1.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "200b9ff220857e53e184257720a14553b2f4aa02577d2ed9842d45d4b9654810"
+checksum = "6e944464ec8536cd1beb0bbfd96987eb5e3b72f2ecdafdc5c769a37f1fa2ae1f"
 dependencies = [
  "cc",
 ]
 
 [[package]]
 name = "pyo3"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57fe09249128b3173d092de9523eaa75136bf7ba85e0d69eca241c7939c933cc"
+checksum = "7778bffd85cf38175ac1f545509665d0b9b92a198ca7941f131f85f7a4f9a872"
 dependencies = [
  "cfg-if",
  "indoc",
@@ -2270,9 +2419,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1cd3927b5a78757a0d71aa9dff669f903b1eb64b54142a9bd9f757f8fde65fd7"
+checksum = "94f6cbe86ef3bf18998d9df6e0f3fc1050a8c5efa409bf712e661a4366e010fb"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -2280,9 +2429,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dab6bb2102bd8f991e7749f130a70d05dd557613e39ed2deeee8e9ca0c4d548d"
+checksum = "e9f1b4c431c0bb1c8fb0a338709859eed0d030ff6daa34368d3b152a63dfdd8d"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -2290,38 +2439,44 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91871864b353fd5ffcb3f91f2f703a22a9797c91b9ab497b1acac7b07ae509c7"
+checksum = "fbc2201328f63c4710f68abdf653c89d8dbc2858b88c5d88b0ff38a75288a9da"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43abc3b80bc20f3facd86cd3c60beed58c3e2aa26213f3cda368de39c60a27e4"
+checksum = "fca6726ad0f3da9c9de093d6f116a93c1a38e417ed73bf138472cf4064f72028"
 dependencies = [
  "heck",
  "proc-macro2",
  "pyo3-build-config",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.37"
+version = "1.0.40"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
 dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "r-efi"
+version = "5.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
+
 [[package]]
 name = "rand"
 version = "0.8.5"
@@ -2349,7 +2504,7 @@ version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.16",
 ]
 
 [[package]]
@@ -2369,16 +2524,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76009fbe0614077fc1a2ce255e3a1881a2e3a3527097d5dc6d8212c585e7e38b"
 dependencies = [
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.7"
+version = "0.5.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b6dfecf2c74bce2466cabf93f6664d6998a69eb21e39f4207930065b27b771f"
+checksum = "928fca9cf2aa042393a8325b9ead81d2f0df4cb12e1e24cef072922ccd99c5af"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags",
 ]
 
 [[package]]
@@ -2395,9 +2550,9 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.4.8"
+version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "368758f23274712b504848e9d5a6f010445cc8b87a7cdb4d7cbee666c1288da3"
+checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -2436,28 +2591,28 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.38.40"
+version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "99e4ea3e1cdc4b559b8e5650f9c8e5998e3e5c1343b4eaf034565f32318d63c0"
+checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags",
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.52.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "rustversion"
-version = "1.0.18"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e819f2bc632f285be6d7cd36e25940d45b2391dd6d9b939e79de557f7014248"
+checksum = "eded382c5f5f786b989652c49544c4877d9f015cc22e145a5ea8ea66c2921cd2"
 
 [[package]]
 name = "ryu"
-version = "1.0.18"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
 
 [[package]]
 name = "same-file"
@@ -2476,41 +2631,41 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
 [[package]]
 name = "semver"
-version = "1.0.25"
+version = "1.0.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f79dfe2d285b0488816f30e700a7438c5a73d816b5b7d3ac72fbc48b0d185e03"
+checksum = "56e6fa9c48d24d85fb3de5ad847117517440f6beceb7798af16b4a87d616b8d0"
 
 [[package]]
 name = "seq-macro"
-version = "0.3.5"
+version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
 
 [[package]]
 name = "serde"
-version = "1.0.214"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f55c3193aca71c12ad7890f1785d2b73e1b9f63a0bbc353c08ef26fe03fc56b5"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.214"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de523f781f095e28fa605cdce0f8307e451cc0fd14e2eb4cd2e98a355b147766"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.132"
+version = "1.0.140"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d726bfaff4b320266d395898905d0eba0345aae23b54aee3a737e260fd46db03"
+checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
 dependencies = [
  "itoa",
  "memchr",
@@ -2520,9 +2675,9 @@ dependencies = [
 
 [[package]]
 name = "sha2"
-version = "0.10.8"
+version = "0.10.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
  "cpufeatures",
@@ -2543,9 +2698,9 @@ checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e"
 
 [[package]]
 name = "siphasher"
-version = "0.3.11"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d"
+checksum = "56199f7ddabf13fe5074ce809e7d3f42b42ae711800501b5b16ea82ad029c39d"
 
 [[package]]
 name = "slab"
@@ -2558,30 +2713,9 @@ dependencies = [
 
 [[package]]
 name = "smallvec"
-version = "1.13.2"
+version = "1.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
-
-[[package]]
-name = "snafu"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "223891c85e2a29c3fe8fb900c1fae5e69c2e42415e3177752e8718475efa5019"
-dependencies = [
- "snafu-derive",
-]
-
-[[package]]
-name = "snafu-derive"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03c3c6b7927ffe7ecaa769ee0e3994da3b8cafc8f444578982c83ecb161af917"
-dependencies = [
- "heck",
- "proc-macro2",
- "quote",
- "syn 2.0.87",
-]
+checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9"
 
 [[package]]
 name = "snap"
@@ -2591,11 +2725,12 @@ checksum = "1b6b67fb9a61334225b5b790716f609cd58395f895b3fe8b328786812a40bc3b"
 
 [[package]]
 name = "sqlparser"
-version = "0.53.0"
+version = "0.55.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05a528114c392209b3264855ad491fcce534b94a38771b0a0b97a79379275ce8"
+checksum = "c4521174166bac1ff04fe16ef4524c70144cd29682a45978978ca3d7f4e0be11"
 dependencies = [
  "log",
+ "recursive",
  "sqlparser_derive",
 ]
 
@@ -2607,7 +2742,7 @@ checksum = "da5fc6819faabb412da764b99d3b713bb55083c11e7e0c00144d386cd6a1939c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -2618,15 +2753,15 @@ checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
 
 [[package]]
 name = "stacker"
-version = "0.1.17"
+version = "0.1.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "799c883d55abdb5e98af1a7b3f23b9b6de8ecada0ecac058672d7635eb48ca7b"
+checksum = "cddb07e32ddb770749da91081d8d0ac3a16f1a569a18b20348cd371f5dead06b"
 dependencies = [
  "cc",
  "cfg-if",
  "libc",
  "psm",
- "windows-sys 0.59.0",
+ "windows-sys",
 ]
 
 [[package]]
@@ -2635,25 +2770,6 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
-[[package]]
-name = "strum"
-version = "0.26.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06"
-
-[[package]]
-name = "strum_macros"
-version = "0.26.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
-dependencies = [
- "heck",
- "proc-macro2",
- "quote",
- "rustversion",
- "syn 2.0.87",
-]
-
 [[package]]
 name = "subtle"
 version = "2.6.1"
@@ -2673,9 +2789,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.87"
+version = "2.0.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "25aa4ce346d03a6dcd68dd8b4010bcb74e54e62c90c573f394c46eae99aba32d"
+checksum = "8ce2b7fc941b3a24138a0a7cf8e858bfc6a992e7978a068a5c760deb0ed43caf"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2684,13 +2800,13 @@ dependencies = [
 
 [[package]]
 name = "synstructure"
-version = "0.13.1"
+version = "0.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -2701,15 +2817,35 @@ checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
 
 [[package]]
 name = "tempfile"
-version = "3.14.0"
+version = "3.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28cce251fcbc87fac86a866eeb0d6c2d536fc16d06f184bb61aeae11aa4cee0c"
+checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1"
 dependencies = [
- "cfg-if",
  "fastrand",
+ "getrandom 0.3.3",
  "once_cell",
  "rustix",
- "windows-sys 0.59.0",
+ "windows-sys",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "567b8a2dae586314f7be2a752ec7474332959c6460e02bde30d702a66d488708"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f7cf42b4507d8ea322120659672cf1b9dbb93f8f2d4ecfd6e51350ff5b17a1d"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
 ]
 
 [[package]]
@@ -2734,9 +2870,9 @@ dependencies = [
 
 [[package]]
 name = "tinystr"
-version = "0.7.6"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9117f5d4db391c1cf6927e7bea3db74b9a1c1add8f7eda9ffd5364f40f57b82f"
+checksum = "5d4f6d1145dcb577acf783d4e601bc1d76a13337bb54e6233add580b07344c8b"
 dependencies = [
  "displaydoc",
  "zerovec",
@@ -2744,9 +2880,9 @@ dependencies = [
 
 [[package]]
 name = "tokio"
-version = "1.41.1"
+version = "1.45.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22cfb5bee7a6a52939ca9224d6ac897bb669134078daa8735560897f69de4d33"
+checksum = "2513ca694ef9ede0fb23fe71a4ee4107cb102b9dc1930f6d0fd77aae068ae165"
 dependencies = [
  "backtrace",
  "bytes",
@@ -2756,20 +2892,20 @@ dependencies = [
 
 [[package]]
 name = "tokio-macros"
-version = "2.4.0"
+version = "2.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "693d596312e88961bc67d7f1f97af8a70227d9f90c31bba5806eec004978d752"
+checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "tokio-util"
-version = "0.7.12"
+version = "0.7.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61e7c3654c13bcd040d4a03abee2c75b1d14a37b423cf5a813ceae1cc903ec6a"
+checksum = "66a539a9ad6d5d281510d5bd368c973d636c02dbf8a67300bfb6b950696ad7df"
 dependencies = [
  "bytes",
  "futures-core",
@@ -2780,9 +2916,9 @@ dependencies = [
 
 [[package]]
 name = "tracing"
-version = "0.1.40"
+version = "0.1.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef"
+checksum = "784e0ac535deb450455cbfa28a6f0df145ea1bb7ae51b821cf5e7927fdcfbdd0"
 dependencies = [
  "pin-project-lite",
  "tracing-attributes",
@@ -2791,20 +2927,20 @@ dependencies = [
 
 [[package]]
 name = "tracing-attributes"
-version = "0.1.27"
+version = "0.1.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
+checksum = "395ae124c09f9e6918a2310af6038fba074bcf474ac352496d5910dd59a2226d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "tracing-core"
-version = "0.1.32"
+version = "0.1.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54"
+checksum = "e672c95779cf947c5311f83787af4fa8fffd12fb27e4993211a84bdfd9610f9c"
 dependencies = [
  "once_cell",
 ]
@@ -2834,6 +2970,12 @@ dependencies = [
  "static_assertions",
 ]
 
+[[package]]
+name = "twox-hash"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e7b17f197b3050ba473acf9181f7b1d3b66d1cf7356c6cc57886662276e65908"
+
 [[package]]
 name = "typed-arena"
 version = "2.0.2"
@@ -2842,15 +2984,15 @@ checksum = "6af6ae20167a9ece4bcb41af5b80f8a1f1df981f6391189ce00fd257af04126a"
 
 [[package]]
 name = "typenum"
-version = "1.17.0"
+version = "1.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
+checksum = "1dccffe3ce07af9386bfd29e80c0ab1a8205a2fc34e4bcd40364df902cfa8f3f"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.13"
+version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e91b56cd4cadaeb79bbf1a5645f6b4f8dc5bde8834ad5894a8db35fda9efa1fe"
+checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
 
 [[package]]
 name = "unicode-segmentation"
@@ -2860,15 +3002,15 @@ checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
 
 [[package]]
 name = "unicode-width"
-version = "0.1.14"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7dd6e30e90baa6f72411720665d41d89b9a3d039dc45b8faea1ddd07f617f6af"
+checksum = "1fc81956842c57dac11422a97c3b8195a1ff727f06e85c84ed2e8aa277c9a0fd"
 
 [[package]]
 name = "unindent"
-version = "0.2.3"
+version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
+checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
 
 [[package]]
 name = "url"
@@ -2881,12 +3023,6 @@ dependencies = [
  "percent-encoding",
 ]
 
-[[package]]
-name = "utf16_iter"
-version = "1.0.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246"
-
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -2895,11 +3031,13 @@ checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
 
 [[package]]
 name = "uuid"
-version = "1.11.0"
+version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8c5f0a0af699448548ad1a2fbf920fb4bee257eae39953ba95cb84891a0446a"
+checksum = "458f7a779bf54acc9f347480ac654f68407d3aab21269a6e3c9f922acd9e2da9"
 dependencies = [
- "getrandom",
+ "getrandom 0.3.3",
+ "js-sys",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -2924,37 +3062,59 @@ version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
+[[package]]
+name = "wasi"
+version = "0.14.2+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "128d1e363af62632b8eb57219c8fd7877144af57558fb2ef0368d0087bddeb2e"
+checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5"
 dependencies = [
  "cfg-if",
  "once_cell",
+ "rustversion",
  "wasm-bindgen-macro",
 ]
 
 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb6dd4d3ca0ddffd1dd1c9c04f94b868c37ff5fac97c30b97cff2d74fce3a358"
+checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6"
 dependencies = [
  "bumpalo",
  "log",
- "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
  "wasm-bindgen-shared",
 ]
 
+[[package]]
+name = "wasm-bindgen-futures"
+version = "0.4.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "555d470ec0bc3bb57890405e5d4322cc9ea83cebb085523ced7be4144dac1e61"
+dependencies = [
+ "cfg-if",
+ "js-sys",
+ "once_cell",
+ "wasm-bindgen",
+ "web-sys",
+]
+
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e79384be7f8f5a9dd5d7167216f022090cf1f9ec128e6e6a482a2cb5c5422c56"
+checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -2962,22 +3122,35 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26c6ab57572f7a24a4985830b120de1594465e5d500f24afe89e16b4e833ef68"
+checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.95"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "web-sys"
+version = "0.3.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d"
+checksum = "33b6dd2ef9186f1f2072e409e99cd22a975331a6b3591b12c764e0e55c60d5d2"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
 
 [[package]]
 name = "web-time"
@@ -3011,7 +3184,7 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys",
 ]
 
 [[package]]
@@ -3022,20 +3195,61 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
 name = "windows-core"
-version = "0.52.0"
+version = "0.61.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "33ab640c8d7e35bf8ba19b884ba838ceb4fba93a4e8c65a9059d08afcfc683d9"
+checksum = "46ec44dc15085cea82cf9c78f85a9114c463a369786585ad2882d1ff0b0acf40"
 dependencies = [
- "windows-targets",
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
 ]
 
 [[package]]
-name = "windows-sys"
-version = "0.52.0"
+name = "windows-implement"
+version = "0.60.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+checksum = "a47fddd13af08290e67f4acabf4b459f647552718f683a7b415d290ac744a836"
 dependencies = [
- "windows-targets",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bd9211b69f8dcdfa817bfd14bf1c97c9188afa36f4750130fcdf3f400eca9fa8"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76840935b766e1b0a05c0066835fb9ec80071d4c09a16f6bd5f7e655e3c14c38"
+
+[[package]]
+name = "windows-result"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b895b5356fc36103d0f64dd1e94dfa7ac5633f1c9dd6e80fe9ec4adef69e09d"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a7ab927b2637c19b3dbe0965e75d8f2d30bdd697a1516191cad2ec4df8fb28a"
+dependencies = [
+ "windows-link",
 ]
 
 [[package]]
@@ -3112,16 +3326,19 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
 [[package]]
-name = "write16"
-version = "1.0.0"
+name = "wit-bindgen-rt"
+version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1890f4022759daae28ed4fe62859b1236caebfc61ede2f63ed4e695f3f6d936"
+checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
+dependencies = [
+ "bitflags",
+]
 
 [[package]]
 name = "writeable"
-version = "0.5.5"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51"
+checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
 
 [[package]]
 name = "xz2"
@@ -3134,9 +3351,9 @@ dependencies = [
 
 [[package]]
 name = "yoke"
-version = "0.7.4"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c5b1314b079b0930c31e3af543d8ee1757b1951ae1e1565ec704403a7240ca5"
+checksum = "5f41bb01b8226ef4bfd589436a297c53d118f65921786300e427be8d487695cc"
 dependencies = [
  "serde",
  "stable_deref_trait",
@@ -3146,63 +3363,73 @@ dependencies = [
 
 [[package]]
 name = "yoke-derive"
-version = "0.7.4"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28cc31741b18cb6f1d5ff12f5b7523e3d6eb0852bbbad19d73905511d9849b95"
+checksum = "38da3c9736e16c5d3c8c597a9aaa5d1fa565d0532ae05e27c24aa62fb32c0ab6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
  "synstructure",
 ]
 
 [[package]]
 name = "zerocopy"
-version = "0.7.35"
+version = "0.8.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
+checksum = "a1702d9583232ddb9174e01bb7c15a2ab8fb1bc6f227aa1233858c351a3ba0cb"
 dependencies = [
- "byteorder",
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.7.35"
+version = "0.8.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
+checksum = "28a6e20d751156648aa063f3800b706ee209a32c0b4d9f24be3d980b01be55ef"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
 [[package]]
 name = "zerofrom"
-version = "0.1.4"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91ec111ce797d0e0784a1116d0ddcdbea84322cd79e5d5ad173daeba4f93ab55"
+checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5"
 dependencies = [
  "zerofrom-derive",
 ]
 
 [[package]]
 name = "zerofrom-derive"
-version = "0.1.4"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ea7b4a3637ea8669cedf0f1fd5c286a17f3de97b8dd5a70a6c167a1730e63a5"
+checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
  "synstructure",
 ]
 
+[[package]]
+name = "zerotrie"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "36f0bbd478583f79edad978b407914f61b2972f5af6fa089686016be8f9af595"
+dependencies = [
+ "displaydoc",
+ "yoke",
+ "zerofrom",
+]
+
 [[package]]
 name = "zerovec"
-version = "0.10.4"
+version = "0.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079"
+checksum = "4a05eb080e015ba39cc9e23bbe5e7fb04d5fb040350f99f34e338d5fdd294428"
 dependencies = [
  "yoke",
  "zerofrom",
@@ -3211,38 +3438,44 @@ dependencies = [
 
 [[package]]
 name = "zerovec-derive"
-version = "0.10.3"
+version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
+checksum = "5b96237efa0c878c64bd89c436f661be4e46b2f3eff1ebb976f7ef2321d2f58f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.87",
+ "syn 2.0.101",
 ]
 
+[[package]]
+name = "zlib-rs"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "868b928d7949e09af2f6086dfc1e01936064cc7a819253bce650d4e2a2d63ba8"
+
 [[package]]
 name = "zstd"
-version = "0.13.2"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fcf2b778a664581e31e389454a7072dab1647606d44f7feea22cd5abb9c9f3f9"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
 dependencies = [
  "zstd-safe",
 ]
 
 [[package]]
 name = "zstd-safe"
-version = "7.2.1"
+version = "7.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "54a3ab4db68cea366acc5c897c7b4d4d1b8994a9cd6e6f841f8964566a419059"
+checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
 dependencies = [
  "zstd-sys",
 ]
 
 [[package]]
 name = "zstd-sys"
-version = "2.0.13+zstd.1.5.6"
+version = "2.0.15+zstd.1.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38ff0f21cfee8f97d94cef41359e0c89aa6113028ab0291aa8ca0038995a95aa"
+checksum = "eb81183ddd97d0c74cedf1d50d85c8d08c1b8b68ee863bdee9e706eedba1a237"
 dependencies = [
  "cc",
  "pkg-config",
diff --git a/examples/ffi-table-provider/Cargo.toml b/examples/datafusion-ffi-example/Cargo.toml
similarity index 83%
rename from examples/ffi-table-provider/Cargo.toml
rename to examples/datafusion-ffi-example/Cargo.toml
index f4e4fda79..0e17567b9 100644
--- a/examples/ffi-table-provider/Cargo.toml
+++ b/examples/datafusion-ffi-example/Cargo.toml
@@ -21,16 +21,16 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-datafusion = { version = "45.0.0" }
-datafusion-ffi = { version = "45.0.0" }
+datafusion = { version = "47.0.0" }
+datafusion-ffi = { version = "47.0.0" }
 pyo3 = { version = "0.23", features = ["extension-module", "abi3", "abi3-py39"] }
-arrow = { version = "54" }
-arrow-array = { version = "54" }
-arrow-schema = { version = "54" }
+arrow = { version = "55.0.0" }
+arrow-array = { version = "55.0.0" }
+arrow-schema = { version = "55.0.0" }
 
 [build-dependencies]
 pyo3-build-config = "0.23"
 
 [lib]
-name = "ffi_table_provider"
+name = "datafusion_ffi_example"
 crate-type = ["cdylib", "rlib"]
diff --git a/examples/ffi-table-provider/build.rs b/examples/datafusion-ffi-example/build.rs
similarity index 100%
rename from examples/ffi-table-provider/build.rs
rename to examples/datafusion-ffi-example/build.rs
diff --git a/examples/ffi-table-provider/pyproject.toml b/examples/datafusion-ffi-example/pyproject.toml
similarity index 97%
rename from examples/ffi-table-provider/pyproject.toml
rename to examples/datafusion-ffi-example/pyproject.toml
index 9cd25b423..0c54df95c 100644
--- a/examples/ffi-table-provider/pyproject.toml
+++ b/examples/datafusion-ffi-example/pyproject.toml
@@ -20,7 +20,7 @@ requires = ["maturin>=1.6,<2.0"]
 build-backend = "maturin"
 
 [project]
-name = "ffi_table_provider"
+name = "datafusion_ffi_example"
 requires-python = ">=3.9"
 classifiers = [
     "Programming Language :: Rust",
diff --git a/examples/datafusion-ffi-example/python/tests/_test_table_function.py b/examples/datafusion-ffi-example/python/tests/_test_table_function.py
new file mode 100644
index 000000000..f3c56a90a
--- /dev/null
+++ b/examples/datafusion-ffi-example/python/tests/_test_table_function.py
@@ -0,0 +1,134 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pyarrow as pa
+from datafusion import Expr, SessionContext, udtf
+from datafusion_ffi_example import MyTableFunction, MyTableProvider
+
+if TYPE_CHECKING:
+    from datafusion.context import TableProviderExportable
+
+
+def test_ffi_table_function_register():
+    ctx = SessionContext()
+    table_func = MyTableFunction()
+    table_udtf = udtf(table_func, "my_table_func")
+    ctx.register_udtf(table_udtf)
+    result = ctx.sql("select * from my_table_func()").collect()
+
+    assert len(result) == 2
+    assert result[0].num_columns == 4
+    print(result)
+
+    result = [r.column(0) for r in result]
+    expected = [
+        pa.array([0, 1, 2], type=pa.int32()),
+        pa.array([3, 4, 5, 6], type=pa.int32()),
+    ]
+
+    assert result == expected
+
+
+def test_ffi_table_function_call_directly():
+    ctx = SessionContext()
+    table_func = MyTableFunction()
+    table_udtf = udtf(table_func, "my_table_func")
+
+    my_table = table_udtf()
+    ctx.register_table_provider("t", my_table)
+    result = ctx.table("t").collect()
+
+    assert len(result) == 2
+    assert result[0].num_columns == 4
+    print(result)
+
+    result = [r.column(0) for r in result]
+    expected = [
+        pa.array([0, 1, 2], type=pa.int32()),
+        pa.array([3, 4, 5, 6], type=pa.int32()),
+    ]
+
+    assert result == expected
+
+
+class PythonTableFunction:
+    """Python based table function.
+
+    This class is used as a Python implementation of a table function.
+    We use the existing TableProvider to create the underlying
+    provider, and this function takes no arguments
+    """
+
+    def __call__(
+        self, num_cols: Expr, num_rows: Expr, num_batches: Expr
+    ) -> TableProviderExportable:
+        args = [
+            num_cols.to_variant().value_i64(),
+            num_rows.to_variant().value_i64(),
+            num_batches.to_variant().value_i64(),
+        ]
+        return MyTableProvider(*args)
+
+
+def common_table_function_test(test_ctx: SessionContext) -> None:
+    result = test_ctx.sql("select * from my_table_func(3,2,4)").collect()
+
+    assert len(result) == 4
+    assert result[0].num_columns == 3
+    print(result)
+
+    result = [r.column(0) for r in result]
+    expected = [
+        pa.array([0, 1], type=pa.int32()),
+        pa.array([2, 3, 4], type=pa.int32()),
+        pa.array([4, 5, 6, 7], type=pa.int32()),
+        pa.array([6, 7, 8, 9, 10], type=pa.int32()),
+    ]
+
+    assert result == expected
+
+
+def test_python_table_function():
+    ctx = SessionContext()
+    table_func = PythonTableFunction()
+    table_udtf = udtf(table_func, "my_table_func")
+    ctx.register_udtf(table_udtf)
+
+    common_table_function_test(ctx)
+
+
+def test_python_table_function_decorator():
+    ctx = SessionContext()
+
+    @udtf("my_table_func")
+    def my_udtf(
+        num_cols: Expr, num_rows: Expr, num_batches: Expr
+    ) -> TableProviderExportable:
+        args = [
+            num_cols.to_variant().value_i64(),
+            num_rows.to_variant().value_i64(),
+            num_batches.to_variant().value_i64(),
+        ]
+        return MyTableProvider(*args)
+
+    ctx.register_udtf(my_udtf)
+
+    common_table_function_test(ctx)
diff --git a/examples/ffi-table-provider/python/tests/_test_table_provider.py b/examples/datafusion-ffi-example/python/tests/_test_table_provider.py
similarity index 94%
rename from examples/ffi-table-provider/python/tests/_test_table_provider.py
rename to examples/datafusion-ffi-example/python/tests/_test_table_provider.py
index 0db3ec561..6b24da06c 100644
--- a/examples/ffi-table-provider/python/tests/_test_table_provider.py
+++ b/examples/datafusion-ffi-example/python/tests/_test_table_provider.py
@@ -15,9 +15,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+from __future__ import annotations
+
 import pyarrow as pa
 from datafusion import SessionContext
-from ffi_table_provider import MyTableProvider
+from datafusion_ffi_example import MyTableProvider
 
 
 def test_table_loading():
diff --git a/examples/datafusion-ffi-example/src/lib.rs b/examples/datafusion-ffi-example/src/lib.rs
new file mode 100644
index 000000000..ae08c3b65
--- /dev/null
+++ b/examples/datafusion-ffi-example/src/lib.rs
@@ -0,0 +1,30 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use crate::table_function::MyTableFunction;
+use crate::table_provider::MyTableProvider;
+use pyo3::prelude::*;
+
+pub(crate) mod table_function;
+pub(crate) mod table_provider;
+
+#[pymodule]
+fn datafusion_ffi_example(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_class::<MyTableProvider>()?;
+    m.add_class::<MyTableFunction>()?;
+    Ok(())
+}
diff --git a/examples/datafusion-ffi-example/src/table_function.rs b/examples/datafusion-ffi-example/src/table_function.rs
new file mode 100644
index 000000000..2d7b356e3
--- /dev/null
+++ b/examples/datafusion-ffi-example/src/table_function.rs
@@ -0,0 +1,56 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use crate::table_provider::MyTableProvider;
+use datafusion::catalog::{TableFunctionImpl, TableProvider};
+use datafusion::error::Result as DataFusionResult;
+use datafusion::prelude::Expr;
+use datafusion_ffi::udtf::FFI_TableFunction;
+use pyo3::types::PyCapsule;
+use pyo3::{pyclass, pymethods, Bound, PyResult, Python};
+use std::sync::Arc;
+
+#[pyclass(name = "MyTableFunction", module = "datafusion_ffi_example", subclass)]
+#[derive(Debug, Clone)]
+pub(crate) struct MyTableFunction {}
+
+#[pymethods]
+impl MyTableFunction {
+    #[new]
+    fn new() -> Self {
+        Self {}
+    }
+
+    fn __datafusion_table_function__<'py>(
+        &self,
+        py: Python<'py>,
+    ) -> PyResult<Bound<'py, PyCapsule>> {
+        let name = cr"datafusion_table_function".into();
+
+        let func = self.clone();
+        let provider = FFI_TableFunction::new(Arc::new(func), None);
+
+        PyCapsule::new(py, provider, Some(name))
+    }
+}
+
+impl TableFunctionImpl for MyTableFunction {
+    fn call(&self, _args: &[Expr]) -> DataFusionResult<Arc<dyn TableProvider>> {
+        let provider = MyTableProvider::new(4, 3, 2).create_table()?;
+        Ok(Arc::new(provider))
+    }
+}
diff --git a/examples/ffi-table-provider/src/lib.rs b/examples/datafusion-ffi-example/src/table_provider.rs
similarity index 71%
rename from examples/ffi-table-provider/src/lib.rs
rename to examples/datafusion-ffi-example/src/table_provider.rs
index 88deeece2..e884585b5 100644
--- a/examples/ffi-table-provider/src/lib.rs
+++ b/examples/datafusion-ffi-example/src/table_provider.rs
@@ -15,25 +15,21 @@
 // specific language governing permissions and limitations
 // under the License.
 
-use std::{ffi::CString, sync::Arc};
-
-use arrow_array::ArrayRef;
-use datafusion::{
-    arrow::{
-        array::RecordBatch,
-        datatypes::{DataType, Field, Schema},
-    },
-    datasource::MemTable,
-    error::{DataFusionError, Result},
-};
+use arrow_array::{ArrayRef, RecordBatch};
+use arrow_schema::{DataType, Field, Schema};
+use datafusion::catalog::MemTable;
+use datafusion::error::{DataFusionError, Result as DataFusionResult};
 use datafusion_ffi::table_provider::FFI_TableProvider;
-use pyo3::{exceptions::PyRuntimeError, prelude::*, types::PyCapsule};
+use pyo3::exceptions::PyRuntimeError;
+use pyo3::types::PyCapsule;
+use pyo3::{pyclass, pymethods, Bound, PyResult, Python};
+use std::sync::Arc;
 
 /// In order to provide a test that demonstrates different sized record batches,
 /// the first batch will have num_rows, the second batch num_rows+1, and so on.
-#[pyclass(name = "MyTableProvider", module = "ffi_table_provider", subclass)]
+#[pyclass(name = "MyTableProvider", module = "datafusion_ffi_example", subclass)]
 #[derive(Clone)]
-struct MyTableProvider {
+pub(crate) struct MyTableProvider {
     num_cols: usize,
     num_rows: usize,
     num_batches: usize,
@@ -44,21 +40,19 @@ fn create_record_batch(
     num_cols: usize,
     start_value: i32,
     num_values: usize,
-) -> Result<RecordBatch> {
+) -> DataFusionResult<RecordBatch> {
     let end_value = start_value + num_values as i32;
     let row_values: Vec<i32> = (start_value..end_value).collect();
 
     let columns: Vec<_> = (0..num_cols)
-        .map(|_| {
-            std::sync::Arc::new(arrow::array::Int32Array::from(row_values.clone())) as ArrayRef
-        })
+        .map(|_| Arc::new(arrow::array::Int32Array::from(row_values.clone())) as ArrayRef)
         .collect();
 
     RecordBatch::try_new(Arc::clone(schema), columns).map_err(DataFusionError::from)
 }
 
 impl MyTableProvider {
-    fn create_table(&self) -> Result<MemTable> {
+    pub fn create_table(&self) -> DataFusionResult<MemTable> {
         let fields: Vec<_> = (0..self.num_cols)
             .map(|idx| (b'A' + idx as u8) as char)
             .map(|col_name| Field::new(col_name, DataType::Int32, true))
@@ -66,7 +60,7 @@ impl MyTableProvider {
 
         let schema = Arc::new(Schema::new(fields));
 
-        let batches: Result<Vec<_>> = (0..self.num_batches)
+        let batches: DataFusionResult<Vec<_>> = (0..self.num_batches)
             .map(|batch_idx| {
                 let start_value = batch_idx * self.num_rows;
                 create_record_batch(
@@ -85,7 +79,7 @@ impl MyTableProvider {
 #[pymethods]
 impl MyTableProvider {
     #[new]
-    fn new(num_cols: usize, num_rows: usize, num_batches: usize) -> Self {
+    pub fn new(num_cols: usize, num_rows: usize, num_batches: usize) -> Self {
         Self {
             num_cols,
             num_rows,
@@ -93,23 +87,17 @@ impl MyTableProvider {
         }
     }
 
-    fn __datafusion_table_provider__<'py>(
+    pub fn __datafusion_table_provider__<'py>(
         &self,
         py: Python<'py>,
     ) -> PyResult<Bound<'py, PyCapsule>> {
-        let name = CString::new("datafusion_table_provider").unwrap();
+        let name = cr"datafusion_table_provider".into();
 
         let provider = self
             .create_table()
             .map_err(|e| PyRuntimeError::new_err(e.to_string()))?;
         let provider = FFI_TableProvider::new(Arc::new(provider), false, None);
 
-        PyCapsule::new_bound(py, provider, Some(name.clone()))
+        PyCapsule::new(py, provider, Some(name))
     }
 }
-
-#[pymodule]
-fn ffi_table_provider(m: &Bound<'_, PyModule>) -> PyResult<()> {
-    m.add_class::<MyTableProvider>()?;
-    Ok(())
-}
diff --git a/examples/python-udwf.py b/examples/python-udwf.py
index 98d118bf2..645ded188 100644
--- a/examples/python-udwf.py
+++ b/examples/python-udwf.py
@@ -22,7 +22,7 @@
 from datafusion import col, lit, udwf
 from datafusion import functions as f
 from datafusion.expr import WindowFrame
-from datafusion.udf import WindowEvaluator
+from datafusion.user_defined import WindowEvaluator
 
 # This example creates five different examples of user defined window functions in order
 # to demonstrate the variety of ways a user may need to implement.
diff --git a/pyproject.toml b/pyproject.toml
index d86b657ec..728cedb2d 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -63,6 +63,10 @@ exclude = [".github/**", "ci/**", ".asf.yaml"]
 locked = true
 features = ["substrait"]
 
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+
 # Enable docstring linting using the google style guide
 [tool.ruff.lint]
 select = ["ALL" ]
diff --git a/python/datafusion/__init__.py b/python/datafusion/__init__.py
index d871fdb71..c3468eb4a 100644
--- a/python/datafusion/__init__.py
+++ b/python/datafusion/__init__.py
@@ -26,7 +26,9 @@
 except ImportError:
     import importlib_metadata
 
-from . import functions, object_store, substrait
+from datafusion.col import col, column
+
+from . import functions, object_store, substrait, unparser
 
 # The following imports are okay to remain as opaque to the user.
 from ._internal import Config
@@ -45,10 +47,21 @@
     Expr,
     WindowFrame,
 )
+from .html_formatter import configure_formatter
 from .io import read_avro, read_csv, read_json, read_parquet
 from .plan import ExecutionPlan, LogicalPlan
 from .record_batch import RecordBatch, RecordBatchStream
-from .udf import Accumulator, AggregateUDF, ScalarUDF, WindowUDF, udaf, udf, udwf
+from .user_defined import (
+    Accumulator,
+    AggregateUDF,
+    ScalarUDF,
+    TableFunction,
+    WindowUDF,
+    udaf,
+    udf,
+    udtf,
+    udwf,
+)
 
 __version__ = importlib_metadata.version(__name__)
 
@@ -71,11 +84,13 @@
     "SessionConfig",
     "SessionContext",
     "Table",
+    "TableFunction",
     "WindowFrame",
     "WindowUDF",
     "col",
     "column",
     "common",
+    "configure_formatter",
     "expr",
     "functions",
     "lit",
@@ -88,20 +103,12 @@
     "substrait",
     "udaf",
     "udf",
+    "udtf",
     "udwf",
+    "unparser",
 ]
 
 
-def column(value: str) -> Expr:
-    """Create a column expression."""
-    return Expr.column(value)
-
-
-def col(value: str) -> Expr:
-    """Create a column expression."""
-    return Expr.column(value)
-
-
 def literal(value) -> Expr:
     """Create a literal expression."""
     return Expr.literal(value)
diff --git a/python/datafusion/col.py b/python/datafusion/col.py
new file mode 100644
index 000000000..1141dc092
--- /dev/null
+++ b/python/datafusion/col.py
@@ -0,0 +1,45 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Col class."""
+
+from datafusion.expr import Expr
+
+
+class Col:
+    """Create a column expression.
+
+    This helper class allows an extra syntax of creating columns using the __getattr__
+    method.
+    """
+
+    def __call__(self, value: str) -> Expr:
+        """Create a column expression."""
+        return Expr.column(value)
+
+    def __getattr__(self, value: str) -> Expr:
+        """Create a column using attribute syntax."""
+        # For autocomplete to work with IPython
+        if value.startswith("__wrapped__"):
+            return getattr(type(self), value)
+
+        return Expr.column(value)
+
+
+col: Col = Col()
+column: Col = Col()
+__all__ = ["col", "column"]
diff --git a/python/datafusion/common.py b/python/datafusion/common.py
index e762a993b..c689a816d 100644
--- a/python/datafusion/common.py
+++ b/python/datafusion/common.py
@@ -33,8 +33,12 @@
 SqlTable = common_internal.SqlTable
 SqlType = common_internal.SqlType
 SqlView = common_internal.SqlView
+TableType = common_internal.TableType
+TableSource = common_internal.TableSource
+Constraints = common_internal.Constraints
 
 __all__ = [
+    "Constraints",
     "DFSchema",
     "DataType",
     "DataTypeMap",
@@ -47,6 +51,8 @@
     "SqlTable",
     "SqlType",
     "SqlView",
+    "TableSource",
+    "TableType",
 ]
 
 
diff --git a/python/datafusion/context.py b/python/datafusion/context.py
index 1429a4975..26c3d2e22 100644
--- a/python/datafusion/context.py
+++ b/python/datafusion/context.py
@@ -30,7 +30,7 @@
 from datafusion.dataframe import DataFrame
 from datafusion.expr import Expr, SortExpr, sort_list_to_raw_sort_list
 from datafusion.record_batch import RecordBatchStream
-from datafusion.udf import AggregateUDF, ScalarUDF, WindowUDF
+from datafusion.user_defined import AggregateUDF, ScalarUDF, TableFunction, WindowUDF
 
 from ._internal import RuntimeEnvBuilder as RuntimeEnvBuilderInternal
 from ._internal import SessionConfig as SessionConfigInternal
@@ -752,6 +752,10 @@ def register_table_provider(
         """
         self.ctx.register_table_provider(name, provider)
 
+    def register_udtf(self, func: TableFunction) -> None:
+        """Register a user defined table function."""
+        self.ctx.register_udtf(func._udtf)
+
     def register_record_batches(
         self, name: str, partitions: list[list[pa.RecordBatch]]
     ) -> None:
diff --git a/python/datafusion/dataframe.py b/python/datafusion/dataframe.py
index 26fe8f453..a1df7e080 100644
--- a/python/datafusion/dataframe.py
+++ b/python/datafusion/dataframe.py
@@ -37,6 +37,8 @@
 except ImportError:
     from typing_extensions import deprecated  # Python 3.12
 
+from datafusion._internal import DataFrame as DataFrameInternal
+from datafusion.expr import Expr, SortExpr, sort_or_default
 from datafusion.plan import ExecutionPlan, LogicalPlan
 from datafusion.record_batch import RecordBatchStream
 
@@ -53,8 +55,6 @@
 
 from enum import Enum
 
-from datafusion.expr import Expr, SortExpr, sort_or_default
-
 
 # excerpt from deltalake
 # https://github.com/apache/datafusion-python/pull/981#discussion_r1905619163
@@ -869,3 +869,25 @@ def within_limit(df: DataFrame, limit: int) -> DataFrame:
             DataFrame: After applying func to the original dataframe.
         """
         return func(self, *args)
+
+    def fill_null(self, value: Any, subset: list[str] | None = None) -> DataFrame:
+        """Fill null values in specified columns with a value.
+
+        Args:
+            value: Value to replace nulls with. Will be cast to match column type.
+            subset: Optional list of column names to fill. If None, fills all columns.
+
+        Returns:
+            DataFrame with null values replaced where type casting is possible
+
+        Examples:
+            >>> df = df.fill_null(0)  # Fill all nulls with 0 where possible
+            >>> # Fill nulls in specific string columns
+            >>> df = df.fill_null("missing", subset=["name", "category"])
+
+        Notes:
+            - Only fills nulls in columns where the value can be cast to the column type
+            - For columns where casting fails, the original column is kept unchanged
+            - For columns not in subset, the original column is kept unchanged
+        """
+        return DataFrame(self.df.fill_null(value, subset))
diff --git a/python/datafusion/expr.py b/python/datafusion/expr.py
index 2697d8143..9e58873d0 100644
--- a/python/datafusion/expr.py
+++ b/python/datafusion/expr.py
@@ -54,14 +54,29 @@
 Case = expr_internal.Case
 Cast = expr_internal.Cast
 Column = expr_internal.Column
+CopyTo = expr_internal.CopyTo
+CreateCatalog = expr_internal.CreateCatalog
+CreateCatalogSchema = expr_internal.CreateCatalogSchema
+CreateExternalTable = expr_internal.CreateExternalTable
+CreateFunction = expr_internal.CreateFunction
+CreateFunctionBody = expr_internal.CreateFunctionBody
+CreateIndex = expr_internal.CreateIndex
 CreateMemoryTable = expr_internal.CreateMemoryTable
 CreateView = expr_internal.CreateView
+Deallocate = expr_internal.Deallocate
+DescribeTable = expr_internal.DescribeTable
 Distinct = expr_internal.Distinct
+DmlStatement = expr_internal.DmlStatement
+DropCatalogSchema = expr_internal.DropCatalogSchema
+DropFunction = expr_internal.DropFunction
 DropTable = expr_internal.DropTable
+DropView = expr_internal.DropView
 EmptyRelation = expr_internal.EmptyRelation
+Execute = expr_internal.Execute
 Exists = expr_internal.Exists
 Explain = expr_internal.Explain
 Extension = expr_internal.Extension
+FileType = expr_internal.FileType
 Filter = expr_internal.Filter
 GroupingSet = expr_internal.GroupingSet
 Join = expr_internal.Join
@@ -83,21 +98,31 @@
 Literal = expr_internal.Literal
 Negative = expr_internal.Negative
 Not = expr_internal.Not
+OperateFunctionArg = expr_internal.OperateFunctionArg
 Partitioning = expr_internal.Partitioning
 Placeholder = expr_internal.Placeholder
+Prepare = expr_internal.Prepare
 Projection = expr_internal.Projection
+RecursiveQuery = expr_internal.RecursiveQuery
 Repartition = expr_internal.Repartition
 ScalarSubquery = expr_internal.ScalarSubquery
 ScalarVariable = expr_internal.ScalarVariable
+SetVariable = expr_internal.SetVariable
 SimilarTo = expr_internal.SimilarTo
 Sort = expr_internal.Sort
 Subquery = expr_internal.Subquery
 SubqueryAlias = expr_internal.SubqueryAlias
 TableScan = expr_internal.TableScan
+TransactionAccessMode = expr_internal.TransactionAccessMode
+TransactionConclusion = expr_internal.TransactionConclusion
+TransactionEnd = expr_internal.TransactionEnd
+TransactionIsolationLevel = expr_internal.TransactionIsolationLevel
+TransactionStart = expr_internal.TransactionStart
 TryCast = expr_internal.TryCast
 Union = expr_internal.Union
 Unnest = expr_internal.Unnest
 UnnestExpr = expr_internal.UnnestExpr
+Values = expr_internal.Values
 WindowExpr = expr_internal.WindowExpr
 
 __all__ = [
@@ -111,15 +136,30 @@
     "CaseBuilder",
     "Cast",
     "Column",
+    "CopyTo",
+    "CreateCatalog",
+    "CreateCatalogSchema",
+    "CreateExternalTable",
+    "CreateFunction",
+    "CreateFunctionBody",
+    "CreateIndex",
     "CreateMemoryTable",
     "CreateView",
+    "Deallocate",
+    "DescribeTable",
     "Distinct",
+    "DmlStatement",
+    "DropCatalogSchema",
+    "DropFunction",
     "DropTable",
+    "DropView",
     "EmptyRelation",
+    "Execute",
     "Exists",
     "Explain",
     "Expr",
     "Extension",
+    "FileType",
     "Filter",
     "GroupingSet",
     "ILike",
@@ -142,22 +182,32 @@
     "Literal",
     "Negative",
     "Not",
+    "OperateFunctionArg",
     "Partitioning",
     "Placeholder",
+    "Prepare",
     "Projection",
+    "RecursiveQuery",
     "Repartition",
     "ScalarSubquery",
     "ScalarVariable",
+    "SetVariable",
     "SimilarTo",
     "Sort",
     "SortExpr",
     "Subquery",
     "SubqueryAlias",
     "TableScan",
+    "TransactionAccessMode",
+    "TransactionConclusion",
+    "TransactionEnd",
+    "TransactionIsolationLevel",
+    "TransactionStart",
     "TryCast",
     "Union",
     "Unnest",
     "UnnestExpr",
+    "Values",
     "Window",
     "WindowExpr",
     "WindowFrame",
@@ -406,9 +456,17 @@ def column(value: str) -> Expr:
         """Creates a new expression representing a column."""
         return Expr(expr_internal.RawExpr.column(value))
 
-    def alias(self, name: str) -> Expr:
-        """Assign a name to the expression."""
-        return Expr(self.expr.alias(name))
+    def alias(self, name: str, metadata: Optional[dict[str, str]] = None) -> Expr:
+        """Assign a name to the expression.
+
+        Args:
+            name: The name to assign to the expression.
+            metadata: Optional metadata to attach to the expression.
+
+        Returns:
+            A new expression with the assigned name.
+        """
+        return Expr(self.expr.alias(name, metadata))
 
     def sort(self, ascending: bool = True, nulls_first: bool = True) -> SortExpr:
         """Creates a sort :py:class:`Expr` from an existing :py:class:`Expr`.
@@ -603,6 +661,424 @@ def over(self, window: Window) -> Expr:
             )
         )
 
+    def asin(self) -> Expr:
+        """Returns the arc sine or inverse sine of a number."""
+        from . import functions as F
+
+        return F.asin(self)
+
+    def array_pop_back(self) -> Expr:
+        """Returns the array without the last element."""
+        from . import functions as F
+
+        return F.array_pop_back(self)
+
+    def reverse(self) -> Expr:
+        """Reverse the string argument."""
+        from . import functions as F
+
+        return F.reverse(self)
+
+    def bit_length(self) -> Expr:
+        """Returns the number of bits in the string argument."""
+        from . import functions as F
+
+        return F.bit_length(self)
+
+    def array_length(self) -> Expr:
+        """Returns the length of the array."""
+        from . import functions as F
+
+        return F.array_length(self)
+
+    def array_ndims(self) -> Expr:
+        """Returns the number of dimensions of the array."""
+        from . import functions as F
+
+        return F.array_ndims(self)
+
+    def to_hex(self) -> Expr:
+        """Converts an integer to a hexadecimal string."""
+        from . import functions as F
+
+        return F.to_hex(self)
+
+    def array_dims(self) -> Expr:
+        """Returns an array of the array's dimensions."""
+        from . import functions as F
+
+        return F.array_dims(self)
+
+    def from_unixtime(self) -> Expr:
+        """Converts an integer to RFC3339 timestamp format string."""
+        from . import functions as F
+
+        return F.from_unixtime(self)
+
+    def array_empty(self) -> Expr:
+        """Returns a boolean indicating whether the array is empty."""
+        from . import functions as F
+
+        return F.array_empty(self)
+
+    def sin(self) -> Expr:
+        """Returns the sine of the argument."""
+        from . import functions as F
+
+        return F.sin(self)
+
+    def log10(self) -> Expr:
+        """Base 10 logarithm of the argument."""
+        from . import functions as F
+
+        return F.log10(self)
+
+    def initcap(self) -> Expr:
+        """Set the initial letter of each word to capital.
+
+        Converts the first letter of each word in ``string`` to uppercase and the
+        remaining characters to lowercase.
+        """
+        from . import functions as F
+
+        return F.initcap(self)
+
+    def list_distinct(self) -> Expr:
+        """Returns distinct values from the array after removing duplicates.
+
+        This is an alias for :py:func:`array_distinct`.
+        """
+        from . import functions as F
+
+        return F.list_distinct(self)
+
+    def iszero(self) -> Expr:
+        """Returns true if a given number is +0.0 or -0.0 otherwise returns false."""
+        from . import functions as F
+
+        return F.iszero(self)
+
+    def array_distinct(self) -> Expr:
+        """Returns distinct values from the array after removing duplicates."""
+        from . import functions as F
+
+        return F.array_distinct(self)
+
+    def arrow_typeof(self) -> Expr:
+        """Returns the Arrow type of the expression."""
+        from . import functions as F
+
+        return F.arrow_typeof(self)
+
+    def length(self) -> Expr:
+        """The number of characters in the ``string``."""
+        from . import functions as F
+
+        return F.length(self)
+
+    def lower(self) -> Expr:
+        """Converts a string to lowercase."""
+        from . import functions as F
+
+        return F.lower(self)
+
+    def acos(self) -> Expr:
+        """Returns the arc cosine or inverse cosine of a number.
+
+        Returns:
+        --------
+        Expr
+            A new expression representing the arc cosine of the input expression.
+        """
+        from . import functions as F
+
+        return F.acos(self)
+
+    def ascii(self) -> Expr:
+        """Returns the numeric code of the first character of the argument."""
+        from . import functions as F
+
+        return F.ascii(self)
+
+    def sha384(self) -> Expr:
+        """Computes the SHA-384 hash of a binary string."""
+        from . import functions as F
+
+        return F.sha384(self)
+
+    def isnan(self) -> Expr:
+        """Returns true if a given number is +NaN or -NaN otherwise returns false."""
+        from . import functions as F
+
+        return F.isnan(self)
+
+    def degrees(self) -> Expr:
+        """Converts the argument from radians to degrees."""
+        from . import functions as F
+
+        return F.degrees(self)
+
+    def cardinality(self) -> Expr:
+        """Returns the total number of elements in the array."""
+        from . import functions as F
+
+        return F.cardinality(self)
+
+    def sha224(self) -> Expr:
+        """Computes the SHA-224 hash of a binary string."""
+        from . import functions as F
+
+        return F.sha224(self)
+
+    def asinh(self) -> Expr:
+        """Returns inverse hyperbolic sine."""
+        from . import functions as F
+
+        return F.asinh(self)
+
+    def flatten(self) -> Expr:
+        """Flattens an array of arrays into a single array."""
+        from . import functions as F
+
+        return F.flatten(self)
+
+    def exp(self) -> Expr:
+        """Returns the exponential of the argument."""
+        from . import functions as F
+
+        return F.exp(self)
+
+    def abs(self) -> Expr:
+        """Return the absolute value of a given number.
+
+        Returns:
+        --------
+        Expr
+            A new expression representing the absolute value of the input expression.
+        """
+        from . import functions as F
+
+        return F.abs(self)
+
+    def btrim(self) -> Expr:
+        """Removes all characters, spaces by default, from both sides of a string."""
+        from . import functions as F
+
+        return F.btrim(self)
+
+    def md5(self) -> Expr:
+        """Computes an MD5 128-bit checksum for a string expression."""
+        from . import functions as F
+
+        return F.md5(self)
+
+    def octet_length(self) -> Expr:
+        """Returns the number of bytes of a string."""
+        from . import functions as F
+
+        return F.octet_length(self)
+
+    def cosh(self) -> Expr:
+        """Returns the hyperbolic cosine of the argument."""
+        from . import functions as F
+
+        return F.cosh(self)
+
+    def radians(self) -> Expr:
+        """Converts the argument from degrees to radians."""
+        from . import functions as F
+
+        return F.radians(self)
+
+    def sqrt(self) -> Expr:
+        """Returns the square root of the argument."""
+        from . import functions as F
+
+        return F.sqrt(self)
+
+    def character_length(self) -> Expr:
+        """Returns the number of characters in the argument."""
+        from . import functions as F
+
+        return F.character_length(self)
+
+    def tanh(self) -> Expr:
+        """Returns the hyperbolic tangent of the argument."""
+        from . import functions as F
+
+        return F.tanh(self)
+
+    def atan(self) -> Expr:
+        """Returns inverse tangent of a number."""
+        from . import functions as F
+
+        return F.atan(self)
+
+    def rtrim(self) -> Expr:
+        """Removes all characters, spaces by default, from the end of a string."""
+        from . import functions as F
+
+        return F.rtrim(self)
+
+    def atanh(self) -> Expr:
+        """Returns inverse hyperbolic tangent."""
+        from . import functions as F
+
+        return F.atanh(self)
+
+    def list_dims(self) -> Expr:
+        """Returns an array of the array's dimensions.
+
+        This is an alias for :py:func:`array_dims`.
+        """
+        from . import functions as F
+
+        return F.list_dims(self)
+
+    def sha256(self) -> Expr:
+        """Computes the SHA-256 hash of a binary string."""
+        from . import functions as F
+
+        return F.sha256(self)
+
+    def factorial(self) -> Expr:
+        """Returns the factorial of the argument."""
+        from . import functions as F
+
+        return F.factorial(self)
+
+    def acosh(self) -> Expr:
+        """Returns inverse hyperbolic cosine."""
+        from . import functions as F
+
+        return F.acosh(self)
+
+    def floor(self) -> Expr:
+        """Returns the nearest integer less than or equal to the argument."""
+        from . import functions as F
+
+        return F.floor(self)
+
+    def ceil(self) -> Expr:
+        """Returns the nearest integer greater than or equal to argument."""
+        from . import functions as F
+
+        return F.ceil(self)
+
+    def list_length(self) -> Expr:
+        """Returns the length of the array.
+
+        This is an alias for :py:func:`array_length`.
+        """
+        from . import functions as F
+
+        return F.list_length(self)
+
+    def upper(self) -> Expr:
+        """Converts a string to uppercase."""
+        from . import functions as F
+
+        return F.upper(self)
+
+    def chr(self) -> Expr:
+        """Converts the Unicode code point to a UTF8 character."""
+        from . import functions as F
+
+        return F.chr(self)
+
+    def ln(self) -> Expr:
+        """Returns the natural logarithm (base e) of the argument."""
+        from . import functions as F
+
+        return F.ln(self)
+
+    def tan(self) -> Expr:
+        """Returns the tangent of the argument."""
+        from . import functions as F
+
+        return F.tan(self)
+
+    def array_pop_front(self) -> Expr:
+        """Returns the array without the first element."""
+        from . import functions as F
+
+        return F.array_pop_front(self)
+
+    def cbrt(self) -> Expr:
+        """Returns the cube root of a number."""
+        from . import functions as F
+
+        return F.cbrt(self)
+
+    def sha512(self) -> Expr:
+        """Computes the SHA-512 hash of a binary string."""
+        from . import functions as F
+
+        return F.sha512(self)
+
+    def char_length(self) -> Expr:
+        """The number of characters in the ``string``."""
+        from . import functions as F
+
+        return F.char_length(self)
+
+    def list_ndims(self) -> Expr:
+        """Returns the number of dimensions of the array.
+
+        This is an alias for :py:func:`array_ndims`.
+        """
+        from . import functions as F
+
+        return F.list_ndims(self)
+
+    def trim(self) -> Expr:
+        """Removes all characters, spaces by default, from both sides of a string."""
+        from . import functions as F
+
+        return F.trim(self)
+
+    def cos(self) -> Expr:
+        """Returns the cosine of the argument."""
+        from . import functions as F
+
+        return F.cos(self)
+
+    def sinh(self) -> Expr:
+        """Returns the hyperbolic sine of the argument."""
+        from . import functions as F
+
+        return F.sinh(self)
+
+    def empty(self) -> Expr:
+        """This is an alias for :py:func:`array_empty`."""
+        from . import functions as F
+
+        return F.empty(self)
+
+    def ltrim(self) -> Expr:
+        """Removes all characters, spaces by default, from the beginning of a string."""
+        from . import functions as F
+
+        return F.ltrim(self)
+
+    def signum(self) -> Expr:
+        """Returns the sign of the argument (-1, 0, +1)."""
+        from . import functions as F
+
+        return F.signum(self)
+
+    def log2(self) -> Expr:
+        """Base 2 logarithm of the argument."""
+        from . import functions as F
+
+        return F.log2(self)
+
+    def cot(self) -> Expr:
+        """Returns the cotangent of the argument."""
+        from . import functions as F
+
+        return F.cot(self)
+
 
 class ExprFuncBuilder:
     def __init__(self, builder: expr_internal.ExprFuncBuilder) -> None:
diff --git a/python/datafusion/functions.py b/python/datafusion/functions.py
index 5cf914e16..f430cdf4b 100644
--- a/python/datafusion/functions.py
+++ b/python/datafusion/functions.py
@@ -372,9 +372,18 @@ def order_by(expr: Expr, ascending: bool = True, nulls_first: bool = True) -> So
     return SortExpr(expr, ascending=ascending, nulls_first=nulls_first)
 
 
-def alias(expr: Expr, name: str) -> Expr:
-    """Creates an alias expression."""
-    return Expr(f.alias(expr.expr, name))
+def alias(expr: Expr, name: str, metadata: Optional[dict[str, str]] = None) -> Expr:
+    """Creates an alias expression with an optional metadata dictionary.
+
+    Args:
+        expr: The expression to alias
+        name: The alias name
+        metadata: Optional metadata to attach to the column
+
+    Returns:
+        An expression with the given alias
+    """
+    return Expr(f.alias(expr.expr, name, metadata))
 
 
 def col(name: str) -> Expr:
diff --git a/python/datafusion/html_formatter.py b/python/datafusion/html_formatter.py
new file mode 100644
index 000000000..12a7e4553
--- /dev/null
+++ b/python/datafusion/html_formatter.py
@@ -0,0 +1,711 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+"""HTML formatting utilities for DataFusion DataFrames."""
+
+from __future__ import annotations
+
+from typing import (
+    Any,
+    Callable,
+    Optional,
+    Protocol,
+    runtime_checkable,
+)
+
+
+def _validate_positive_int(value: Any, param_name: str) -> None:
+    """Validate that a parameter is a positive integer.
+
+    Args:
+        value: The value to validate
+        param_name: Name of the parameter (used in error message)
+
+    Raises:
+        ValueError: If the value is not a positive integer
+    """
+    if not isinstance(value, int) or value <= 0:
+        msg = f"{param_name} must be a positive integer"
+        raise ValueError(msg)
+
+
+def _validate_bool(value: Any, param_name: str) -> None:
+    """Validate that a parameter is a boolean.
+
+    Args:
+        value: The value to validate
+        param_name: Name of the parameter (used in error message)
+
+    Raises:
+        TypeError: If the value is not a boolean
+    """
+    if not isinstance(value, bool):
+        msg = f"{param_name} must be a boolean"
+        raise TypeError(msg)
+
+
+@runtime_checkable
+class CellFormatter(Protocol):
+    """Protocol for cell value formatters."""
+
+    def __call__(self, value: Any) -> str:
+        """Format a cell value to string representation."""
+        ...
+
+
+@runtime_checkable
+class StyleProvider(Protocol):
+    """Protocol for HTML style providers."""
+
+    def get_cell_style(self) -> str:
+        """Get the CSS style for table cells."""
+        ...
+
+    def get_header_style(self) -> str:
+        """Get the CSS style for header cells."""
+        ...
+
+
+class DefaultStyleProvider:
+    """Default implementation of StyleProvider."""
+
+    def get_cell_style(self) -> str:
+        """Get the CSS style for table cells.
+
+        Returns:
+            CSS style string
+        """
+        return (
+            "border: 1px solid black; padding: 8px; text-align: left; "
+            "white-space: nowrap;"
+        )
+
+    def get_header_style(self) -> str:
+        """Get the CSS style for header cells.
+
+        Returns:
+            CSS style string
+        """
+        return (
+            "border: 1px solid black; padding: 8px; text-align: left; "
+            "background-color: #f2f2f2; white-space: nowrap; min-width: fit-content; "
+            "max-width: fit-content;"
+        )
+
+
+class DataFrameHtmlFormatter:
+    """Configurable HTML formatter for DataFusion DataFrames.
+
+    This class handles the HTML rendering of DataFrames for display in
+    Jupyter notebooks and other rich display contexts.
+
+    This class supports extension through composition. Key extension points:
+    - Provide a custom StyleProvider for styling cells and headers
+    - Register custom formatters for specific types
+    - Provide custom cell builders for specialized cell rendering
+
+    Args:
+        max_cell_length: Maximum characters to display in a cell before truncation
+        max_width: Maximum width of the HTML table in pixels
+        max_height: Maximum height of the HTML table in pixels
+        max_memory_bytes: Maximum memory in bytes for rendered data (default: 2MB)
+        min_rows_display: Minimum number of rows to display
+        repr_rows: Default number of rows to display in repr output
+        enable_cell_expansion: Whether to add expand/collapse buttons for long cell
+          values
+        custom_css: Additional CSS to include in the HTML output
+        show_truncation_message: Whether to display a message when data is truncated
+        style_provider: Custom provider for cell and header styles
+        use_shared_styles: Whether to load styles and scripts only once per notebook
+          session
+    """
+
+    # Class variable to track if styles have been loaded in the notebook
+    _styles_loaded = False
+
+    def __init__(
+        self,
+        max_cell_length: int = 25,
+        max_width: int = 1000,
+        max_height: int = 300,
+        max_memory_bytes: int = 2 * 1024 * 1024,  # 2 MB
+        min_rows_display: int = 20,
+        repr_rows: int = 10,
+        enable_cell_expansion: bool = True,
+        custom_css: Optional[str] = None,
+        show_truncation_message: bool = True,
+        style_provider: Optional[StyleProvider] = None,
+        use_shared_styles: bool = True,
+    ) -> None:
+        """Initialize the HTML formatter.
+
+        Parameters
+        ----------
+        max_cell_length : int, default 25
+            Maximum length of cell content before truncation.
+        max_width : int, default 1000
+            Maximum width of the displayed table in pixels.
+        max_height : int, default 300
+            Maximum height of the displayed table in pixels.
+        max_memory_bytes : int, default 2097152 (2MB)
+            Maximum memory in bytes for rendered data.
+        min_rows_display : int, default 20
+            Minimum number of rows to display.
+        repr_rows : int, default 10
+            Default number of rows to display in repr output.
+        enable_cell_expansion : bool, default True
+            Whether to allow cells to expand when clicked.
+        custom_css : str, optional
+            Custom CSS to apply to the HTML table.
+        show_truncation_message : bool, default True
+            Whether to show a message indicating that content has been truncated.
+        style_provider : StyleProvider, optional
+            Provider of CSS styles for the HTML table. If None, DefaultStyleProvider
+            is used.
+        use_shared_styles : bool, default True
+            Whether to use shared styles across multiple tables.
+
+        Raises:
+        ------
+        ValueError
+            If max_cell_length, max_width, max_height, max_memory_bytes,
+            min_rows_display, or repr_rows is not a positive integer.
+        TypeError
+            If enable_cell_expansion, show_truncation_message, or use_shared_styles is
+            not a boolean,
+            or if custom_css is provided but is not a string,
+            or if style_provider is provided but does not implement the StyleProvider
+            protocol.
+        """
+        # Validate numeric parameters
+        _validate_positive_int(max_cell_length, "max_cell_length")
+        _validate_positive_int(max_width, "max_width")
+        _validate_positive_int(max_height, "max_height")
+        _validate_positive_int(max_memory_bytes, "max_memory_bytes")
+        _validate_positive_int(min_rows_display, "min_rows_display")
+        _validate_positive_int(repr_rows, "repr_rows")
+
+        # Validate boolean parameters
+        _validate_bool(enable_cell_expansion, "enable_cell_expansion")
+        _validate_bool(show_truncation_message, "show_truncation_message")
+        _validate_bool(use_shared_styles, "use_shared_styles")
+
+        # Validate custom_css
+        if custom_css is not None and not isinstance(custom_css, str):
+            msg = "custom_css must be None or a string"
+            raise TypeError(msg)
+
+        # Validate style_provider
+        if style_provider is not None and not isinstance(style_provider, StyleProvider):
+            msg = "style_provider must implement the StyleProvider protocol"
+            raise TypeError(msg)
+
+        self.max_cell_length = max_cell_length
+        self.max_width = max_width
+        self.max_height = max_height
+        self.max_memory_bytes = max_memory_bytes
+        self.min_rows_display = min_rows_display
+        self.repr_rows = repr_rows
+        self.enable_cell_expansion = enable_cell_expansion
+        self.custom_css = custom_css
+        self.show_truncation_message = show_truncation_message
+        self.style_provider = style_provider or DefaultStyleProvider()
+        self.use_shared_styles = use_shared_styles
+        # Registry for custom type formatters
+        self._type_formatters: dict[type, CellFormatter] = {}
+        # Custom cell builders
+        self._custom_cell_builder: Optional[Callable[[Any, int, int, str], str]] = None
+        self._custom_header_builder: Optional[Callable[[Any], str]] = None
+
+    def register_formatter(self, type_class: type, formatter: CellFormatter) -> None:
+        """Register a custom formatter for a specific data type.
+
+        Args:
+            type_class: The type to register a formatter for
+            formatter: Function that takes a value of the given type and returns
+                a formatted string
+        """
+        self._type_formatters[type_class] = formatter
+
+    def set_custom_cell_builder(
+        self, builder: Callable[[Any, int, int, str], str]
+    ) -> None:
+        """Set a custom cell builder function.
+
+        Args:
+            builder: Function that takes (value, row, col, table_id) and returns HTML
+        """
+        self._custom_cell_builder = builder
+
+    def set_custom_header_builder(self, builder: Callable[[Any], str]) -> None:
+        """Set a custom header builder function.
+
+        Args:
+            builder: Function that takes a field and returns HTML
+        """
+        self._custom_header_builder = builder
+
+    @classmethod
+    def is_styles_loaded(cls) -> bool:
+        """Check if HTML styles have been loaded in the current session.
+
+        This method is primarily intended for debugging UI rendering issues
+        related to style loading.
+
+        Returns:
+            True if styles have been loaded, False otherwise
+
+        Example:
+            >>> from datafusion.html_formatter import DataFrameHtmlFormatter
+            >>> DataFrameHtmlFormatter.is_styles_loaded()
+            False
+        """
+        return cls._styles_loaded
+
+    def format_html(
+        self,
+        batches: list,
+        schema: Any,
+        has_more: bool = False,
+        table_uuid: str | None = None,
+    ) -> str:
+        """Format record batches as HTML.
+
+        This method is used by DataFrame's _repr_html_ implementation and can be
+        called directly when custom HTML rendering is needed.
+
+        Args:
+            batches: List of Arrow RecordBatch objects
+            schema: Arrow Schema object
+            has_more: Whether there are more batches not shown
+            table_uuid: Unique ID for the table, used for JavaScript interactions
+
+        Returns:
+            HTML string representation of the data
+
+        Raises:
+            TypeError: If schema is invalid and no batches are provided
+        """
+        if not batches:
+            return "No data to display"
+
+        # Validate schema
+        if schema is None or not hasattr(schema, "__iter__"):
+            msg = "Schema must be provided"
+            raise TypeError(msg)
+
+        # Generate a unique ID if none provided
+        table_uuid = table_uuid or f"df-{id(batches)}"
+
+        # Build HTML components
+        html = []
+
+        # Only include styles and scripts if:
+        # 1. Not using shared styles, OR
+        # 2. Using shared styles but they haven't been loaded yet
+        include_styles = (
+            not self.use_shared_styles or not DataFrameHtmlFormatter._styles_loaded
+        )
+
+        if include_styles:
+            html.extend(self._build_html_header())
+            # If we're using shared styles, mark them as loaded
+            if self.use_shared_styles:
+                DataFrameHtmlFormatter._styles_loaded = True
+
+        html.extend(self._build_table_container_start())
+
+        # Add table header and body
+        html.extend(self._build_table_header(schema))
+        html.extend(self._build_table_body(batches, table_uuid))
+
+        html.append("</table>")
+        html.append("</div>")
+
+        # Add footer (JavaScript and messages)
+        if include_styles and self.enable_cell_expansion:
+            html.append(self._get_javascript())
+
+        # Always add truncation message if needed (independent of styles)
+        if has_more and self.show_truncation_message:
+            html.append("<div>Data truncated due to size.</div>")
+
+        return "\n".join(html)
+
+    def _build_html_header(self) -> list[str]:
+        """Build the HTML header with CSS styles."""
+        html = []
+        html.append("<style>")
+        # Only include expandable CSS if cell expansion is enabled
+        if self.enable_cell_expansion:
+            html.append(self._get_default_css())
+        if self.custom_css:
+            html.append(self.custom_css)
+        html.append("</style>")
+        return html
+
+    def _build_table_container_start(self) -> list[str]:
+        """Build the opening tags for the table container."""
+        html = []
+        html.append(
+            f'<div style="width: 100%; max-width: {self.max_width}px; '
+            f"max-height: {self.max_height}px; overflow: auto; border: "
+            '1px solid #ccc;">'
+        )
+        html.append('<table style="border-collapse: collapse; min-width: 100%">')
+        return html
+
+    def _build_table_header(self, schema: Any) -> list[str]:
+        """Build the HTML table header with column names."""
+        html = []
+        html.append("<thead>")
+        html.append("<tr>")
+        for field in schema:
+            if self._custom_header_builder:
+                html.append(self._custom_header_builder(field))
+            else:
+                html.append(
+                    f"<th style='{self.style_provider.get_header_style()}'>"
+                    f"{field.name}</th>"
+                )
+        html.append("</tr>")
+        html.append("</thead>")
+        return html
+
+    def _build_table_body(self, batches: list, table_uuid: str) -> list[str]:
+        """Build the HTML table body with data rows."""
+        html = []
+        html.append("<tbody>")
+
+        row_count = 0
+        for batch in batches:
+            for row_idx in range(batch.num_rows):
+                row_count += 1
+                html.append("<tr>")
+
+                for col_idx, column in enumerate(batch.columns):
+                    # Get the raw value from the column
+                    raw_value = self._get_cell_value(column, row_idx)
+
+                    # Always check for type formatters first to format the value
+                    formatted_value = self._format_cell_value(raw_value)
+
+                    # Then apply either custom cell builder or standard cell formatting
+                    if self._custom_cell_builder:
+                        # Pass both the raw value and formatted value to let the
+                        # builder decide
+                        cell_html = self._custom_cell_builder(
+                            raw_value, row_count, col_idx, table_uuid
+                        )
+                        html.append(cell_html)
+                    else:
+                        # Standard cell formatting with formatted value
+                        if (
+                            len(str(raw_value)) > self.max_cell_length
+                            and self.enable_cell_expansion
+                        ):
+                            cell_html = self._build_expandable_cell(
+                                formatted_value, row_count, col_idx, table_uuid
+                            )
+                        else:
+                            cell_html = self._build_regular_cell(formatted_value)
+                        html.append(cell_html)
+
+                html.append("</tr>")
+
+        html.append("</tbody>")
+        return html
+
+    def _get_cell_value(self, column: Any, row_idx: int) -> Any:
+        """Extract a cell value from a column.
+
+        Args:
+            column: Arrow array
+            row_idx: Row index
+
+        Returns:
+            The raw cell value
+        """
+        try:
+            value = column[row_idx]
+
+            if hasattr(value, "as_py"):
+                return value.as_py()
+        except (AttributeError, TypeError):
+            pass
+        else:
+            return value
+
+    def _format_cell_value(self, value: Any) -> str:
+        """Format a cell value for display.
+
+        Uses registered type formatters if available.
+
+        Args:
+            value: The cell value to format
+
+        Returns:
+            Formatted cell value as string
+        """
+        # Check for custom type formatters
+        for type_cls, formatter in self._type_formatters.items():
+            if isinstance(value, type_cls):
+                return formatter(value)
+
+        # If no formatter matched, return string representation
+        return str(value)
+
+    def _build_expandable_cell(
+        self, formatted_value: str, row_count: int, col_idx: int, table_uuid: str
+    ) -> str:
+        """Build an expandable cell for long content."""
+        short_value = str(formatted_value)[: self.max_cell_length]
+        return (
+            f"<td style='{self.style_provider.get_cell_style()}'>"
+            f"<div class='expandable-container'>"
+            "<span class='expandable' "
+            f"id='{table_uuid}-min-text-{row_count}-{col_idx}'>"
+            f"{short_value}</span>"
+            "<span class='full-text' "
+            f"id='{table_uuid}-full-text-{row_count}-{col_idx}'>"
+            f"{formatted_value}</span>"
+            f"<button class='expand-btn' "
+            f"onclick=\"toggleDataFrameCellText('{table_uuid}',{row_count},{col_idx})\">"
+            f"...</button>"
+            f"</div>"
+            f"</td>"
+        )
+
+    def _build_regular_cell(self, formatted_value: str) -> str:
+        """Build a regular table cell."""
+        return (
+            f"<td style='{self.style_provider.get_cell_style()}'>{formatted_value}</td>"
+        )
+
+    def _build_html_footer(self, has_more: bool) -> list[str]:
+        """Build the HTML footer with JavaScript and messages."""
+        html = []
+
+        # Add JavaScript for interactivity only if cell expansion is enabled
+        # and we're not using the shared styles approach
+        if self.enable_cell_expansion and not self.use_shared_styles:
+            html.append(self._get_javascript())
+
+        # Add truncation message if needed
+        if has_more and self.show_truncation_message:
+            html.append("<div>Data truncated due to size.</div>")
+
+        return html
+
+    def _get_default_css(self) -> str:
+        """Get default CSS styles for the HTML table."""
+        return """
+            .expandable-container {
+                display: inline-block;
+                max-width: 200px;
+            }
+            .expandable {
+                white-space: nowrap;
+                overflow: hidden;
+                text-overflow: ellipsis;
+                display: block;
+            }
+            .full-text {
+                display: none;
+                white-space: normal;
+            }
+            .expand-btn {
+                cursor: pointer;
+                color: blue;
+                text-decoration: underline;
+                border: none;
+                background: none;
+                font-size: inherit;
+                display: block;
+                margin-top: 5px;
+            }
+        """
+
+    def _get_javascript(self) -> str:
+        """Get JavaScript code for interactive elements."""
+        return """
+            <script>
+            function toggleDataFrameCellText(table_uuid, row, col) {
+                var shortText = document.getElementById(
+                    table_uuid + "-min-text-" + row + "-" + col
+                );
+                var fullText = document.getElementById(
+                    table_uuid + "-full-text-" + row + "-" + col
+                );
+                var button = event.target;
+
+                if (fullText.style.display === "none") {
+                    shortText.style.display = "none";
+                    fullText.style.display = "inline";
+                    button.textContent = "(less)";
+                } else {
+                    shortText.style.display = "inline";
+                    fullText.style.display = "none";
+                    button.textContent = "...";
+                }
+            }
+            </script>
+        """
+
+
+class FormatterManager:
+    """Manager class for the global DataFrame HTML formatter instance."""
+
+    _default_formatter: DataFrameHtmlFormatter = DataFrameHtmlFormatter()
+
+    @classmethod
+    def set_formatter(cls, formatter: DataFrameHtmlFormatter) -> None:
+        """Set the global DataFrame HTML formatter.
+
+        Args:
+            formatter: The formatter instance to use globally
+        """
+        cls._default_formatter = formatter
+        _refresh_formatter_reference()
+
+    @classmethod
+    def get_formatter(cls) -> DataFrameHtmlFormatter:
+        """Get the current global DataFrame HTML formatter.
+
+        Returns:
+            The global HTML formatter instance
+        """
+        return cls._default_formatter
+
+
+def get_formatter() -> DataFrameHtmlFormatter:
+    """Get the current global DataFrame HTML formatter.
+
+    This function is used by the DataFrame._repr_html_ implementation to access
+    the shared formatter instance. It can also be used directly when custom
+    HTML rendering is needed.
+
+    Returns:
+        The global HTML formatter instance
+
+    Example:
+        >>> from datafusion.html_formatter import get_formatter
+        >>> formatter = get_formatter()
+        >>> formatter.max_cell_length = 50  # Increase cell length
+    """
+    return FormatterManager.get_formatter()
+
+
+def set_formatter(formatter: DataFrameHtmlFormatter) -> None:
+    """Set the global DataFrame HTML formatter.
+
+    Args:
+        formatter: The formatter instance to use globally
+
+    Example:
+        >>> from datafusion.html_formatter import get_formatter, set_formatter
+        >>> custom_formatter = DataFrameHtmlFormatter(max_cell_length=100)
+        >>> set_formatter(custom_formatter)
+    """
+    FormatterManager.set_formatter(formatter)
+
+
+def configure_formatter(**kwargs: Any) -> None:
+    """Configure the global DataFrame HTML formatter.
+
+    This function creates a new formatter with the provided configuration
+    and sets it as the global formatter for all DataFrames.
+
+    Args:
+        **kwargs: Formatter configuration parameters like max_cell_length,
+                 max_width, max_height, enable_cell_expansion, etc.
+
+    Raises:
+        ValueError: If any invalid parameters are provided
+
+    Example:
+        >>> from datafusion.html_formatter import configure_formatter
+        >>> configure_formatter(
+        ...     max_cell_length=50,
+        ...     max_height=500,
+        ...     enable_cell_expansion=True,
+        ...     use_shared_styles=True
+        ... )
+    """
+    # Valid parameters accepted by DataFrameHtmlFormatter
+    valid_params = {
+        "max_cell_length",
+        "max_width",
+        "max_height",
+        "max_memory_bytes",
+        "min_rows_display",
+        "repr_rows",
+        "enable_cell_expansion",
+        "custom_css",
+        "show_truncation_message",
+        "style_provider",
+        "use_shared_styles",
+    }
+
+    # Check for invalid parameters
+    invalid_params = set(kwargs) - valid_params
+    if invalid_params:
+        msg = (
+            f"Invalid formatter parameters: {', '.join(invalid_params)}. "
+            f"Valid parameters are: {', '.join(valid_params)}"
+        )
+        raise ValueError(msg)
+
+    # Create and set formatter with validated parameters
+    set_formatter(DataFrameHtmlFormatter(**kwargs))
+
+
+def reset_formatter() -> None:
+    """Reset the global DataFrame HTML formatter to default settings.
+
+    This function creates a new formatter with default configuration
+    and sets it as the global formatter for all DataFrames.
+
+    Example:
+        >>> from datafusion.html_formatter import reset_formatter
+        >>> reset_formatter()  # Reset formatter to default settings
+    """
+    formatter = DataFrameHtmlFormatter()
+    # Reset the styles_loaded flag to ensure styles will be reloaded
+    DataFrameHtmlFormatter._styles_loaded = False
+    set_formatter(formatter)
+
+
+def reset_styles_loaded_state() -> None:
+    """Reset the styles loaded state to force reloading of styles.
+
+    This can be useful when switching between notebook sessions or
+    when styles need to be refreshed.
+
+    Example:
+        >>> from datafusion.html_formatter import reset_styles_loaded_state
+        >>> reset_styles_loaded_state()  # Force styles to reload in next render
+    """
+    DataFrameHtmlFormatter._styles_loaded = False
+
+
+def _refresh_formatter_reference() -> None:
+    """Refresh formatter reference in any modules using it.
+
+    This helps ensure that changes to the formatter are reflected in existing
+    DataFrames that might be caching the formatter reference.
+    """
+    # This is a no-op but signals modules to refresh their reference
diff --git a/python/datafusion/udf.py b/python/datafusion/udf.py
index e93a34ca5..c7265fa09 100644
--- a/python/datafusion/udf.py
+++ b/python/datafusion/udf.py
@@ -15,753 +15,15 @@
 # specific language governing permissions and limitations
 # under the License.
 
-"""Provides the user-defined functions for evaluation of dataframes."""
+"""Deprecated module for user defined functions."""
 
-from __future__ import annotations
+import warnings
 
-import functools
-from abc import ABCMeta, abstractmethod
-from enum import Enum
-from typing import TYPE_CHECKING, Any, Callable, Optional, TypeVar, overload
+from datafusion.user_defined import *  # noqa: F403
 
-import pyarrow as pa
-
-import datafusion._internal as df_internal
-from datafusion.expr import Expr
-
-if TYPE_CHECKING:
-    _R = TypeVar("_R", bound=pa.DataType)
-
-
-class Volatility(Enum):
-    """Defines how stable or volatile a function is.
-
-    When setting the volatility of a function, you can either pass this
-    enumeration or a ``str``. The ``str`` equivalent is the lower case value of the
-    name (`"immutable"`, `"stable"`, or `"volatile"`).
-    """
-
-    Immutable = 1
-    """An immutable function will always return the same output when given the
-    same input.
-
-    DataFusion will attempt to inline immutable functions during planning.
-    """
-
-    Stable = 2
-    """
-    Returns the same value for a given input within a single queries.
-
-    A stable function may return different values given the same input across
-    different queries but must return the same value for a given input within a
-    query. An example of this is the ``Now`` function. DataFusion will attempt to
-    inline ``Stable`` functions during planning, when possible. For query
-    ``select col1, now() from t1``, it might take a while to execute but ``now()``
-    column will be the same for each output row, which is evaluated during
-    planning.
-    """
-
-    Volatile = 3
-    """A volatile function may change the return value from evaluation to
-    evaluation.
-
-    Multiple invocations of a volatile function may return different results
-    when used in the same query. An example of this is the random() function.
-    DataFusion can not evaluate such functions during planning. In the query
-    ``select col1, random() from t1``, ``random()`` function will be evaluated
-    for each output row, resulting in a unique random value for each row.
-    """
-
-    def __str__(self) -> str:
-        """Returns the string equivalent."""
-        return self.name.lower()
-
-
-class ScalarUDF:
-    """Class for performing scalar user-defined functions (UDF).
-
-    Scalar UDFs operate on a row by row basis. See also :py:class:`AggregateUDF` for
-    operating on a group of rows.
-    """
-
-    def __init__(
-        self,
-        name: str,
-        func: Callable[..., _R],
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: _R,
-        volatility: Volatility | str,
-    ) -> None:
-        """Instantiate a scalar user-defined function (UDF).
-
-        See helper method :py:func:`udf` for argument details.
-        """
-        if isinstance(input_types, pa.DataType):
-            input_types = [input_types]
-        self._udf = df_internal.ScalarUDF(
-            name, func, input_types, return_type, str(volatility)
-        )
-
-    def __call__(self, *args: Expr) -> Expr:
-        """Execute the UDF.
-
-        This function is not typically called by an end user. These calls will
-        occur during the evaluation of the dataframe.
-        """
-        args_raw = [arg.expr for arg in args]
-        return Expr(self._udf.__call__(*args_raw))
-
-    @overload
-    @staticmethod
-    def udf(
-        input_types: list[pa.DataType],
-        return_type: _R,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> Callable[..., ScalarUDF]: ...
-
-    @overload
-    @staticmethod
-    def udf(
-        func: Callable[..., _R],
-        input_types: list[pa.DataType],
-        return_type: _R,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> ScalarUDF: ...
-
-    @staticmethod
-    def udf(*args: Any, **kwargs: Any):  # noqa: D417
-        """Create a new User-Defined Function (UDF).
-
-        This class can be used both as a **function** and as a **decorator**.
-
-        Usage:
-            - **As a function**: Call `udf(func, input_types, return_type, volatility,
-              name)`.
-            - **As a decorator**: Use `@udf(input_types, return_type, volatility,
-              name)`. In this case, do **not** pass `func` explicitly.
-
-        Args:
-            func (Callable, optional): **Only needed when calling as a function.**
-                Skip this argument when using `udf` as a decorator.
-            input_types (list[pa.DataType]): The data types of the arguments
-                to `func`. This list must be of the same length as the number of
-                arguments.
-            return_type (_R): The data type of the return value from the function.
-            volatility (Volatility | str): See `Volatility` for allowed values.
-            name (Optional[str]): A descriptive name for the function.
-
-        Returns:
-            A user-defined function that can be used in SQL expressions,
-            data aggregation, or window function calls.
-
-        Example:
-            **Using `udf` as a function:**
-            ```
-            def double_func(x):
-                return x * 2
-            double_udf = udf(double_func, [pa.int32()], pa.int32(),
-            "volatile", "double_it")
-            ```
-
-            **Using `udf` as a decorator:**
-            ```
-            @udf([pa.int32()], pa.int32(), "volatile", "double_it")
-            def double_udf(x):
-                return x * 2
-            ```
-        """
-
-        def _function(
-            func: Callable[..., _R],
-            input_types: list[pa.DataType],
-            return_type: _R,
-            volatility: Volatility | str,
-            name: Optional[str] = None,
-        ) -> ScalarUDF:
-            if not callable(func):
-                msg = "`func` argument must be callable"
-                raise TypeError(msg)
-            if name is None:
-                if hasattr(func, "__qualname__"):
-                    name = func.__qualname__.lower()
-                else:
-                    name = func.__class__.__name__.lower()
-            return ScalarUDF(
-                name=name,
-                func=func,
-                input_types=input_types,
-                return_type=return_type,
-                volatility=volatility,
-            )
-
-        def _decorator(
-            input_types: list[pa.DataType],
-            return_type: _R,
-            volatility: Volatility | str,
-            name: Optional[str] = None,
-        ) -> Callable:
-            def decorator(func: Callable):
-                udf_caller = ScalarUDF.udf(
-                    func, input_types, return_type, volatility, name
-                )
-
-                @functools.wraps(func)
-                def wrapper(*args: Any, **kwargs: Any):
-                    return udf_caller(*args, **kwargs)
-
-                return wrapper
-
-            return decorator
-
-        if args and callable(args[0]):
-            # Case 1: Used as a function, require the first parameter to be callable
-            return _function(*args, **kwargs)
-        # Case 2: Used as a decorator with parameters
-        return _decorator(*args, **kwargs)
-
-
-class Accumulator(metaclass=ABCMeta):
-    """Defines how an :py:class:`AggregateUDF` accumulates values."""
-
-    @abstractmethod
-    def state(self) -> list[pa.Scalar]:
-        """Return the current state."""
-
-    @abstractmethod
-    def update(self, *values: pa.Array) -> None:
-        """Evaluate an array of values and update state."""
-
-    @abstractmethod
-    def merge(self, states: list[pa.Array]) -> None:
-        """Merge a set of states."""
-
-    @abstractmethod
-    def evaluate(self) -> pa.Scalar:
-        """Return the resultant value."""
-
-
-class AggregateUDF:
-    """Class for performing scalar user-defined functions (UDF).
-
-    Aggregate UDFs operate on a group of rows and return a single value. See
-    also :py:class:`ScalarUDF` for operating on a row by row basis.
-    """
-
-    def __init__(
-        self,
-        name: str,
-        accumulator: Callable[[], Accumulator],
-        input_types: list[pa.DataType],
-        return_type: pa.DataType,
-        state_type: list[pa.DataType],
-        volatility: Volatility | str,
-    ) -> None:
-        """Instantiate a user-defined aggregate function (UDAF).
-
-        See :py:func:`udaf` for a convenience function and argument
-        descriptions.
-        """
-        self._udaf = df_internal.AggregateUDF(
-            name,
-            accumulator,
-            input_types,
-            return_type,
-            state_type,
-            str(volatility),
-        )
-
-    def __call__(self, *args: Expr) -> Expr:
-        """Execute the UDAF.
-
-        This function is not typically called by an end user. These calls will
-        occur during the evaluation of the dataframe.
-        """
-        args_raw = [arg.expr for arg in args]
-        return Expr(self._udaf.__call__(*args_raw))
-
-    @overload
-    @staticmethod
-    def udaf(
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        state_type: list[pa.DataType],
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> Callable[..., AggregateUDF]: ...
-
-    @overload
-    @staticmethod
-    def udaf(
-        accum: Callable[[], Accumulator],
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        state_type: list[pa.DataType],
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> AggregateUDF: ...
-
-    @staticmethod
-    def udaf(*args: Any, **kwargs: Any):  # noqa: D417
-        """Create a new User-Defined Aggregate Function (UDAF).
-
-        This class allows you to define an **aggregate function** that can be used in
-        data aggregation or window function calls.
-
-        Usage:
-            - **As a function**: Call `udaf(accum, input_types, return_type, state_type,
-                volatility, name)`.
-            - **As a decorator**: Use `@udaf(input_types, return_type, state_type,
-                volatility, name)`.
-            When using `udaf` as a decorator, **do not pass `accum` explicitly**.
-
-        **Function example:**
-
-            If your `:py:class:Accumulator` can be instantiated with no arguments, you
-            can simply pass it's type as `accum`. If you need to pass additional
-            arguments to it's constructor, you can define a lambda or a factory method.
-            During runtime the `:py:class:Accumulator` will be constructed for every
-            instance in which this UDAF is used. The following examples are all valid.
-            ```
-            import pyarrow as pa
-            import pyarrow.compute as pc
-
-            class Summarize(Accumulator):
-                def __init__(self, bias: float = 0.0):
-                    self._sum = pa.scalar(bias)
-
-                def state(self) -> list[pa.Scalar]:
-                    return [self._sum]
-
-                def update(self, values: pa.Array) -> None:
-                    self._sum = pa.scalar(self._sum.as_py() + pc.sum(values).as_py())
-
-                def merge(self, states: list[pa.Array]) -> None:
-                    self._sum = pa.scalar(self._sum.as_py() + pc.sum(states[0]).as_py())
-
-                def evaluate(self) -> pa.Scalar:
-                    return self._sum
-
-            def sum_bias_10() -> Summarize:
-                return Summarize(10.0)
-
-            udaf1 = udaf(Summarize, pa.float64(), pa.float64(), [pa.float64()],
-                "immutable")
-            udaf2 = udaf(sum_bias_10, pa.float64(), pa.float64(), [pa.float64()],
-                "immutable")
-            udaf3 = udaf(lambda: Summarize(20.0), pa.float64(), pa.float64(),
-                [pa.float64()], "immutable")
-            ```
-
-        **Decorator example:**
-            ```
-            @udaf(pa.float64(), pa.float64(), [pa.float64()], "immutable")
-            def udf4() -> Summarize:
-                return Summarize(10.0)
-            ```
-
-        Args:
-            accum: The accumulator python function. **Only needed when calling as a
-                function. Skip this argument when using `udaf` as a decorator.**
-            input_types: The data types of the arguments to ``accum``.
-            return_type: The data type of the return value.
-            state_type: The data types of the intermediate accumulation.
-            volatility: See :py:class:`Volatility` for allowed values.
-            name: A descriptive name for the function.
-
-        Returns:
-            A user-defined aggregate function, which can be used in either data
-            aggregation or window function calls.
-        """
-
-        def _function(
-            accum: Callable[[], Accumulator],
-            input_types: pa.DataType | list[pa.DataType],
-            return_type: pa.DataType,
-            state_type: list[pa.DataType],
-            volatility: Volatility | str,
-            name: Optional[str] = None,
-        ) -> AggregateUDF:
-            if not callable(accum):
-                msg = "`func` must be callable."
-                raise TypeError(msg)
-            if not isinstance(accum(), Accumulator):
-                msg = "Accumulator must implement the abstract base class Accumulator"
-                raise TypeError(msg)
-            if name is None:
-                name = accum().__class__.__qualname__.lower()
-            if isinstance(input_types, pa.DataType):
-                input_types = [input_types]
-            return AggregateUDF(
-                name=name,
-                accumulator=accum,
-                input_types=input_types,
-                return_type=return_type,
-                state_type=state_type,
-                volatility=volatility,
-            )
-
-        def _decorator(
-            input_types: pa.DataType | list[pa.DataType],
-            return_type: pa.DataType,
-            state_type: list[pa.DataType],
-            volatility: Volatility | str,
-            name: Optional[str] = None,
-        ) -> Callable[..., Callable[..., Expr]]:
-            def decorator(accum: Callable[[], Accumulator]) -> Callable[..., Expr]:
-                udaf_caller = AggregateUDF.udaf(
-                    accum, input_types, return_type, state_type, volatility, name
-                )
-
-                @functools.wraps(accum)
-                def wrapper(*args: Any, **kwargs: Any) -> Expr:
-                    return udaf_caller(*args, **kwargs)
-
-                return wrapper
-
-            return decorator
-
-        if args and callable(args[0]):
-            # Case 1: Used as a function, require the first parameter to be callable
-            return _function(*args, **kwargs)
-        # Case 2: Used as a decorator with parameters
-        return _decorator(*args, **kwargs)
-
-
-class WindowEvaluator:
-    """Evaluator class for user-defined window functions (UDWF).
-
-    It is up to the user to decide which evaluate function is appropriate.
-
-    +------------------------+--------------------------------+------------------+---------------------------+
-    | ``uses_window_frame``  | ``supports_bounded_execution`` | ``include_rank`` | function_to_implement     |
-    +========================+================================+==================+===========================+
-    | False (default)        | False (default)                | False (default)  | ``evaluate_all``          |
-    +------------------------+--------------------------------+------------------+---------------------------+
-    | False                  | True                           | False            | ``evaluate``              |
-    +------------------------+--------------------------------+------------------+---------------------------+
-    | False                  | True/False                     | True             | ``evaluate_all_with_rank``|
-    +------------------------+--------------------------------+------------------+---------------------------+
-    | True                   | True/False                     | True/False       | ``evaluate``              |
-    +------------------------+--------------------------------+------------------+---------------------------+
-    """  # noqa: W505, E501
-
-    def memoize(self) -> None:
-        """Perform a memoize operation to improve performance.
-
-        When the window frame has a fixed beginning (e.g UNBOUNDED
-        PRECEDING), some functions such as FIRST_VALUE and
-        NTH_VALUE do not need the (unbounded) input once they have
-        seen a certain amount of input.
-
-        `memoize` is called after each input batch is processed, and
-        such functions can save whatever they need
-        """
-
-    def get_range(self, idx: int, num_rows: int) -> tuple[int, int]:  # noqa: ARG002
-        """Return the range for the window fuction.
-
-        If `uses_window_frame` flag is `false`. This method is used to
-        calculate required range for the window function during
-        stateful execution.
-
-        Generally there is no required range, hence by default this
-        returns smallest range(current row). e.g seeing current row is
-        enough to calculate window result (such as row_number, rank,
-        etc)
-
-        Args:
-            idx:: Current index
-            num_rows: Number of rows.
-        """
-        return (idx, idx + 1)
-
-    def is_causal(self) -> bool:
-        """Get whether evaluator needs future data for its result."""
-        return False
-
-    def evaluate_all(self, values: list[pa.Array], num_rows: int) -> pa.Array:
-        """Evaluate a window function on an entire input partition.
-
-        This function is called once per input *partition* for window functions that
-        *do not use* values from the window frame, such as
-        :py:func:`~datafusion.functions.row_number`,
-        :py:func:`~datafusion.functions.rank`,
-        :py:func:`~datafusion.functions.dense_rank`,
-        :py:func:`~datafusion.functions.percent_rank`,
-        :py:func:`~datafusion.functions.cume_dist`,
-        :py:func:`~datafusion.functions.lead`,
-        and :py:func:`~datafusion.functions.lag`.
-
-        It produces the result of all rows in a single pass. It
-        expects to receive the entire partition as the ``value`` and
-        must produce an output column with one output row for every
-        input row.
-
-        ``num_rows`` is required to correctly compute the output in case
-        ``len(values) == 0``
-
-        Implementing this function is an optimization. Certain window
-        functions are not affected by the window frame definition or
-        the query doesn't have a frame, and ``evaluate`` skips the
-        (costly) window frame boundary calculation and the overhead of
-        calling ``evaluate`` for each output row.
-
-        For example, the `LAG` built in window function does not use
-        the values of its window frame (it can be computed in one shot
-        on the entire partition with ``Self::evaluate_all`` regardless of the
-        window defined in the ``OVER`` clause)
-
-        .. code-block:: text
-
-            lag(x, 1) OVER (ORDER BY z ROWS BETWEEN 2 PRECEDING AND 3 FOLLOWING)
-
-        However, ``avg()`` computes the average in the window and thus
-        does use its window frame.
-
-        .. code-block:: text
-
-            avg(x) OVER (PARTITION BY y ORDER BY z ROWS BETWEEN 2 PRECEDING AND 3 FOLLOWING)
-        """  # noqa: W505, E501
-
-    def evaluate(
-        self, values: list[pa.Array], eval_range: tuple[int, int]
-    ) -> pa.Scalar:
-        """Evaluate window function on a range of rows in an input partition.
-
-        This is the simplest and most general function to implement
-        but also the least performant as it creates output one row at
-        a time. It is typically much faster to implement stateful
-        evaluation using one of the other specialized methods on this
-        trait.
-
-        Returns a [`ScalarValue`] that is the value of the window
-        function within `range` for the entire partition. Argument
-        `values` contains the evaluation result of function arguments
-        and evaluation results of ORDER BY expressions. If function has a
-        single argument, `values[1..]` will contain ORDER BY expression results.
-        """
-
-    def evaluate_all_with_rank(
-        self, num_rows: int, ranks_in_partition: list[tuple[int, int]]
-    ) -> pa.Array:
-        """Called for window functions that only need the rank of a row.
-
-        Evaluate the partition evaluator against the partition using
-        the row ranks. For example, ``rank(col("a"))`` produces
-
-        .. code-block:: text
-
-            a | rank
-            - + ----
-            A | 1
-            A | 1
-            C | 3
-            D | 4
-            D | 4
-
-        For this case, `num_rows` would be `5` and the
-        `ranks_in_partition` would be called with
-
-        .. code-block:: text
-
-            [
-                (0,1),
-                (2,2),
-                (3,4),
-            ]
-
-        The user must implement this method if ``include_rank`` returns True.
-        """
-
-    def supports_bounded_execution(self) -> bool:
-        """Can the window function be incrementally computed using bounded memory?"""
-        return False
-
-    def uses_window_frame(self) -> bool:
-        """Does the window function use the values from the window frame?"""
-        return False
-
-    def include_rank(self) -> bool:
-        """Can this function be evaluated with (only) rank?"""
-        return False
-
-
-class WindowUDF:
-    """Class for performing window user-defined functions (UDF).
-
-    Window UDFs operate on a partition of rows. See
-    also :py:class:`ScalarUDF` for operating on a row by row basis.
-    """
-
-    def __init__(
-        self,
-        name: str,
-        func: Callable[[], WindowEvaluator],
-        input_types: list[pa.DataType],
-        return_type: pa.DataType,
-        volatility: Volatility | str,
-    ) -> None:
-        """Instantiate a user-defined window function (UDWF).
-
-        See :py:func:`udwf` for a convenience function and argument
-        descriptions.
-        """
-        self._udwf = df_internal.WindowUDF(
-            name, func, input_types, return_type, str(volatility)
-        )
-
-    def __call__(self, *args: Expr) -> Expr:
-        """Execute the UDWF.
-
-        This function is not typically called by an end user. These calls will
-        occur during the evaluation of the dataframe.
-        """
-        args_raw = [arg.expr for arg in args]
-        return Expr(self._udwf.__call__(*args_raw))
-
-    @overload
-    @staticmethod
-    def udwf(
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> Callable[..., WindowUDF]: ...
-
-    @overload
-    @staticmethod
-    def udwf(
-        func: Callable[[], WindowEvaluator],
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> WindowUDF: ...
-
-    @staticmethod
-    def udwf(*args: Any, **kwargs: Any):  # noqa: D417
-        """Create a new User-Defined Window Function (UDWF).
-
-        This class can be used both as a **function** and as a **decorator**.
-
-        Usage:
-            - **As a function**: Call `udwf(func, input_types, return_type, volatility,
-              name)`.
-            - **As a decorator**: Use `@udwf(input_types, return_type, volatility,
-              name)`. When using `udwf` as a decorator, **do not pass `func`
-              explicitly**.
-
-        **Function example:**
-            ```
-            import pyarrow as pa
-
-            class BiasedNumbers(WindowEvaluator):
-                def __init__(self, start: int = 0) -> None:
-                    self.start = start
-
-                def evaluate_all(self, values: list[pa.Array],
-                    num_rows: int) -> pa.Array:
-                    return pa.array([self.start + i for i in range(num_rows)])
-
-            def bias_10() -> BiasedNumbers:
-                return BiasedNumbers(10)
-
-            udwf1 = udwf(BiasedNumbers, pa.int64(), pa.int64(), "immutable")
-            udwf2 = udwf(bias_10, pa.int64(), pa.int64(), "immutable")
-            udwf3 = udwf(lambda: BiasedNumbers(20), pa.int64(), pa.int64(), "immutable")
-
-            ```
-
-        **Decorator example:**
-            ```
-            @udwf(pa.int64(), pa.int64(), "immutable")
-            def biased_numbers() -> BiasedNumbers:
-                return BiasedNumbers(10)
-            ```
-
-        Args:
-            func: **Only needed when calling as a function. Skip this argument when
-                using `udwf` as a decorator.**
-            input_types: The data types of the arguments.
-            return_type: The data type of the return value.
-            volatility: See :py:class:`Volatility` for allowed values.
-            name: A descriptive name for the function.
-
-        Returns:
-            A user-defined window function that can be used in window function calls.
-        """
-        if args and callable(args[0]):
-            # Case 1: Used as a function, require the first parameter to be callable
-            return WindowUDF._create_window_udf(*args, **kwargs)
-        # Case 2: Used as a decorator with parameters
-        return WindowUDF._create_window_udf_decorator(*args, **kwargs)
-
-    @staticmethod
-    def _create_window_udf(
-        func: Callable[[], WindowEvaluator],
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> WindowUDF:
-        """Create a WindowUDF instance from function arguments."""
-        if not callable(func):
-            msg = "`func` must be callable."
-            raise TypeError(msg)
-        if not isinstance(func(), WindowEvaluator):
-            msg = "`func` must implement the abstract base class WindowEvaluator"
-            raise TypeError(msg)
-
-        name = name or func.__qualname__.lower()
-        input_types = (
-            [input_types] if isinstance(input_types, pa.DataType) else input_types
-        )
-
-        return WindowUDF(name, func, input_types, return_type, volatility)
-
-    @staticmethod
-    def _get_default_name(func: Callable) -> str:
-        """Get the default name for a function based on its attributes."""
-        if hasattr(func, "__qualname__"):
-            return func.__qualname__.lower()
-        return func.__class__.__name__.lower()
-
-    @staticmethod
-    def _normalize_input_types(
-        input_types: pa.DataType | list[pa.DataType],
-    ) -> list[pa.DataType]:
-        """Convert a single DataType to a list if needed."""
-        if isinstance(input_types, pa.DataType):
-            return [input_types]
-        return input_types
-
-    @staticmethod
-    def _create_window_udf_decorator(
-        input_types: pa.DataType | list[pa.DataType],
-        return_type: pa.DataType,
-        volatility: Volatility | str,
-        name: Optional[str] = None,
-    ) -> Callable[[Callable[[], WindowEvaluator]], Callable[..., Expr]]:
-        """Create a decorator for a WindowUDF."""
-
-        def decorator(func: Callable[[], WindowEvaluator]) -> Callable[..., Expr]:
-            udwf_caller = WindowUDF._create_window_udf(
-                func, input_types, return_type, volatility, name
-            )
-
-            @functools.wraps(func)
-            def wrapper(*args: Any, **kwargs: Any) -> Expr:
-                return udwf_caller(*args, **kwargs)
-
-            return wrapper
-
-        return decorator
-
-
-# Convenience exports so we can import instead of treating as
-# variables at the package root
-udf = ScalarUDF.udf
-udaf = AggregateUDF.udaf
-udwf = WindowUDF.udwf
+warnings.warn(
+    "The module 'udf' is deprecated and will be removed in the next release. "
+    "Please use 'user_defined' instead.",
+    DeprecationWarning,
+    stacklevel=2,
+)
diff --git a/python/datafusion/unparser.py b/python/datafusion/unparser.py
new file mode 100644
index 000000000..7ca5b9190
--- /dev/null
+++ b/python/datafusion/unparser.py
@@ -0,0 +1,80 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""This module provides support for unparsing datafusion plans to SQL.
+
+For additional information about unparsing, see https://docs.rs/datafusion-sql/latest/datafusion_sql/unparser/index.html
+"""
+
+from ._internal import unparser as unparser_internal
+from .plan import LogicalPlan
+
+
+class Dialect:
+    """DataFusion data catalog."""
+
+    def __init__(self, dialect: unparser_internal.Dialect) -> None:
+        """This constructor is not typically called by the end user."""
+        self.dialect = dialect
+
+    @staticmethod
+    def default() -> "Dialect":
+        """Create a new default dialect."""
+        return Dialect(unparser_internal.Dialect.default())
+
+    @staticmethod
+    def mysql() -> "Dialect":
+        """Create a new MySQL dialect."""
+        return Dialect(unparser_internal.Dialect.mysql())
+
+    @staticmethod
+    def postgres() -> "Dialect":
+        """Create a new PostgreSQL dialect."""
+        return Dialect(unparser_internal.Dialect.postgres())
+
+    @staticmethod
+    def sqlite() -> "Dialect":
+        """Create a new SQLite dialect."""
+        return Dialect(unparser_internal.Dialect.sqlite())
+
+    @staticmethod
+    def duckdb() -> "Dialect":
+        """Create a new DuckDB dialect."""
+        return Dialect(unparser_internal.Dialect.duckdb())
+
+
+class Unparser:
+    """DataFusion unparser."""
+
+    def __init__(self, dialect: Dialect) -> None:
+        """This constructor is not typically called by the end user."""
+        self.unparser = unparser_internal.Unparser(dialect.dialect)
+
+    def plan_to_sql(self, plan: LogicalPlan) -> str:
+        """Convert a logical plan to a SQL string."""
+        return self.unparser.plan_to_sql(plan._raw_plan)
+
+    def with_pretty(self, pretty: bool) -> "Unparser":
+        """Set the pretty flag."""
+        self.unparser = self.unparser.with_pretty(pretty)
+        return self
+
+
+__all__ = [
+    "Dialect",
+    "Unparser",
+]
diff --git a/python/datafusion/user_defined.py b/python/datafusion/user_defined.py
new file mode 100644
index 000000000..9ec3679a6
--- /dev/null
+++ b/python/datafusion/user_defined.py
@@ -0,0 +1,833 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Provides the user-defined functions for evaluation of dataframes."""
+
+from __future__ import annotations
+
+import functools
+from abc import ABCMeta, abstractmethod
+from enum import Enum
+from typing import TYPE_CHECKING, Any, Callable, Optional, TypeVar, overload
+
+import pyarrow as pa
+
+import datafusion._internal as df_internal
+from datafusion.expr import Expr
+
+if TYPE_CHECKING:
+    _R = TypeVar("_R", bound=pa.DataType)
+
+
+class Volatility(Enum):
+    """Defines how stable or volatile a function is.
+
+    When setting the volatility of a function, you can either pass this
+    enumeration or a ``str``. The ``str`` equivalent is the lower case value of the
+    name (`"immutable"`, `"stable"`, or `"volatile"`).
+    """
+
+    Immutable = 1
+    """An immutable function will always return the same output when given the
+    same input.
+
+    DataFusion will attempt to inline immutable functions during planning.
+    """
+
+    Stable = 2
+    """
+    Returns the same value for a given input within a single queries.
+
+    A stable function may return different values given the same input across
+    different queries but must return the same value for a given input within a
+    query. An example of this is the ``Now`` function. DataFusion will attempt to
+    inline ``Stable`` functions during planning, when possible. For query
+    ``select col1, now() from t1``, it might take a while to execute but ``now()``
+    column will be the same for each output row, which is evaluated during
+    planning.
+    """
+
+    Volatile = 3
+    """A volatile function may change the return value from evaluation to
+    evaluation.
+
+    Multiple invocations of a volatile function may return different results
+    when used in the same query. An example of this is the random() function.
+    DataFusion can not evaluate such functions during planning. In the query
+    ``select col1, random() from t1``, ``random()`` function will be evaluated
+    for each output row, resulting in a unique random value for each row.
+    """
+
+    def __str__(self) -> str:
+        """Returns the string equivalent."""
+        return self.name.lower()
+
+
+class ScalarUDF:
+    """Class for performing scalar user-defined functions (UDF).
+
+    Scalar UDFs operate on a row by row basis. See also :py:class:`AggregateUDF` for
+    operating on a group of rows.
+    """
+
+    def __init__(
+        self,
+        name: str,
+        func: Callable[..., _R],
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: _R,
+        volatility: Volatility | str,
+    ) -> None:
+        """Instantiate a scalar user-defined function (UDF).
+
+        See helper method :py:func:`udf` for argument details.
+        """
+        if isinstance(input_types, pa.DataType):
+            input_types = [input_types]
+        self._udf = df_internal.ScalarUDF(
+            name, func, input_types, return_type, str(volatility)
+        )
+
+    def __call__(self, *args: Expr) -> Expr:
+        """Execute the UDF.
+
+        This function is not typically called by an end user. These calls will
+        occur during the evaluation of the dataframe.
+        """
+        args_raw = [arg.expr for arg in args]
+        return Expr(self._udf.__call__(*args_raw))
+
+    @overload
+    @staticmethod
+    def udf(
+        input_types: list[pa.DataType],
+        return_type: _R,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> Callable[..., ScalarUDF]: ...
+
+    @overload
+    @staticmethod
+    def udf(
+        func: Callable[..., _R],
+        input_types: list[pa.DataType],
+        return_type: _R,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> ScalarUDF: ...
+
+    @staticmethod
+    def udf(*args: Any, **kwargs: Any):  # noqa: D417
+        """Create a new User-Defined Function (UDF).
+
+        This class can be used both as either a function or a decorator.
+
+        Usage:
+            - As a function: ``udf(func, input_types, return_type, volatility, name)``.
+            - As a decorator: ``@udf(input_types, return_type, volatility, name)``.
+              When used a decorator, do **not** pass ``func`` explicitly.
+
+        Args:
+            func (Callable, optional): Only needed when calling as a function.
+                Skip this argument when using ``udf`` as a decorator.
+            input_types (list[pa.DataType]): The data types of the arguments
+                to ``func``. This list must be of the same length as the number of
+                arguments.
+            return_type (_R): The data type of the return value from the function.
+            volatility (Volatility | str): See `Volatility` for allowed values.
+            name (Optional[str]): A descriptive name for the function.
+
+        Returns:
+            A user-defined function that can be used in SQL expressions,
+            data aggregation, or window function calls.
+
+        Example: Using ``udf`` as a function::
+
+            def double_func(x):
+                return x * 2
+            double_udf = udf(double_func, [pa.int32()], pa.int32(),
+            "volatile", "double_it")
+
+        Example: Using ``udf`` as a decorator::
+
+            @udf([pa.int32()], pa.int32(), "volatile", "double_it")
+            def double_udf(x):
+                return x * 2
+        """
+
+        def _function(
+            func: Callable[..., _R],
+            input_types: list[pa.DataType],
+            return_type: _R,
+            volatility: Volatility | str,
+            name: Optional[str] = None,
+        ) -> ScalarUDF:
+            if not callable(func):
+                msg = "`func` argument must be callable"
+                raise TypeError(msg)
+            if name is None:
+                if hasattr(func, "__qualname__"):
+                    name = func.__qualname__.lower()
+                else:
+                    name = func.__class__.__name__.lower()
+            return ScalarUDF(
+                name=name,
+                func=func,
+                input_types=input_types,
+                return_type=return_type,
+                volatility=volatility,
+            )
+
+        def _decorator(
+            input_types: list[pa.DataType],
+            return_type: _R,
+            volatility: Volatility | str,
+            name: Optional[str] = None,
+        ) -> Callable:
+            def decorator(func: Callable):
+                udf_caller = ScalarUDF.udf(
+                    func, input_types, return_type, volatility, name
+                )
+
+                @functools.wraps(func)
+                def wrapper(*args: Any, **kwargs: Any):
+                    return udf_caller(*args, **kwargs)
+
+                return wrapper
+
+            return decorator
+
+        if args and callable(args[0]):
+            # Case 1: Used as a function, require the first parameter to be callable
+            return _function(*args, **kwargs)
+        # Case 2: Used as a decorator with parameters
+        return _decorator(*args, **kwargs)
+
+
+class Accumulator(metaclass=ABCMeta):
+    """Defines how an :py:class:`AggregateUDF` accumulates values."""
+
+    @abstractmethod
+    def state(self) -> list[pa.Scalar]:
+        """Return the current state."""
+
+    @abstractmethod
+    def update(self, *values: pa.Array) -> None:
+        """Evaluate an array of values and update state."""
+
+    @abstractmethod
+    def merge(self, states: list[pa.Array]) -> None:
+        """Merge a set of states."""
+
+    @abstractmethod
+    def evaluate(self) -> pa.Scalar:
+        """Return the resultant value."""
+
+
+class AggregateUDF:
+    """Class for performing scalar user-defined functions (UDF).
+
+    Aggregate UDFs operate on a group of rows and return a single value. See
+    also :py:class:`ScalarUDF` for operating on a row by row basis.
+    """
+
+    def __init__(
+        self,
+        name: str,
+        accumulator: Callable[[], Accumulator],
+        input_types: list[pa.DataType],
+        return_type: pa.DataType,
+        state_type: list[pa.DataType],
+        volatility: Volatility | str,
+    ) -> None:
+        """Instantiate a user-defined aggregate function (UDAF).
+
+        See :py:func:`udaf` for a convenience function and argument
+        descriptions.
+        """
+        self._udaf = df_internal.AggregateUDF(
+            name,
+            accumulator,
+            input_types,
+            return_type,
+            state_type,
+            str(volatility),
+        )
+
+    def __call__(self, *args: Expr) -> Expr:
+        """Execute the UDAF.
+
+        This function is not typically called by an end user. These calls will
+        occur during the evaluation of the dataframe.
+        """
+        args_raw = [arg.expr for arg in args]
+        return Expr(self._udaf.__call__(*args_raw))
+
+    @overload
+    @staticmethod
+    def udaf(
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        state_type: list[pa.DataType],
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> Callable[..., AggregateUDF]: ...
+
+    @overload
+    @staticmethod
+    def udaf(
+        accum: Callable[[], Accumulator],
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        state_type: list[pa.DataType],
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> AggregateUDF: ...
+
+    @staticmethod
+    def udaf(*args: Any, **kwargs: Any):  # noqa: D417
+        """Create a new User-Defined Aggregate Function (UDAF).
+
+        This class allows you to define an aggregate function that can be used in
+        data aggregation or window function calls.
+
+        Usage:
+            - As a function: ``udaf(accum, input_types, return_type, state_type, volatility, name)``.
+            - As a decorator: ``@udaf(input_types, return_type, state_type, volatility, name)``.
+              When using ``udaf`` as a decorator, do not pass ``accum`` explicitly.
+
+        Function example:
+
+        If your :py:class:`Accumulator` can be instantiated with no arguments, you
+        can simply pass it's type as `accum`. If you need to pass additional
+        arguments to it's constructor, you can define a lambda or a factory method.
+        During runtime the :py:class:`Accumulator` will be constructed for every
+        instance in which this UDAF is used. The following examples are all valid::
+
+            import pyarrow as pa
+            import pyarrow.compute as pc
+
+            class Summarize(Accumulator):
+                def __init__(self, bias: float = 0.0):
+                    self._sum = pa.scalar(bias)
+
+                def state(self) -> list[pa.Scalar]:
+                    return [self._sum]
+
+                def update(self, values: pa.Array) -> None:
+                    self._sum = pa.scalar(self._sum.as_py() + pc.sum(values).as_py())
+
+                def merge(self, states: list[pa.Array]) -> None:
+                    self._sum = pa.scalar(self._sum.as_py() + pc.sum(states[0]).as_py())
+
+                def evaluate(self) -> pa.Scalar:
+                    return self._sum
+
+            def sum_bias_10() -> Summarize:
+                return Summarize(10.0)
+
+            udaf1 = udaf(Summarize, pa.float64(), pa.float64(), [pa.float64()],
+                "immutable")
+            udaf2 = udaf(sum_bias_10, pa.float64(), pa.float64(), [pa.float64()],
+                "immutable")
+            udaf3 = udaf(lambda: Summarize(20.0), pa.float64(), pa.float64(),
+                [pa.float64()], "immutable")
+
+        Decorator example:::
+
+            @udaf(pa.float64(), pa.float64(), [pa.float64()], "immutable")
+            def udf4() -> Summarize:
+                return Summarize(10.0)
+
+        Args:
+            accum: The accumulator python function. Only needed when calling as a
+                function. Skip this argument when using ``udaf`` as a decorator.
+            input_types: The data types of the arguments to ``accum``.
+            return_type: The data type of the return value.
+            state_type: The data types of the intermediate accumulation.
+            volatility: See :py:class:`Volatility` for allowed values.
+            name: A descriptive name for the function.
+
+        Returns:
+            A user-defined aggregate function, which can be used in either data
+            aggregation or window function calls.
+        """  # noqa: E501 W505
+
+        def _function(
+            accum: Callable[[], Accumulator],
+            input_types: pa.DataType | list[pa.DataType],
+            return_type: pa.DataType,
+            state_type: list[pa.DataType],
+            volatility: Volatility | str,
+            name: Optional[str] = None,
+        ) -> AggregateUDF:
+            if not callable(accum):
+                msg = "`func` must be callable."
+                raise TypeError(msg)
+            if not isinstance(accum(), Accumulator):
+                msg = "Accumulator must implement the abstract base class Accumulator"
+                raise TypeError(msg)
+            if name is None:
+                name = accum().__class__.__qualname__.lower()
+            if isinstance(input_types, pa.DataType):
+                input_types = [input_types]
+            return AggregateUDF(
+                name=name,
+                accumulator=accum,
+                input_types=input_types,
+                return_type=return_type,
+                state_type=state_type,
+                volatility=volatility,
+            )
+
+        def _decorator(
+            input_types: pa.DataType | list[pa.DataType],
+            return_type: pa.DataType,
+            state_type: list[pa.DataType],
+            volatility: Volatility | str,
+            name: Optional[str] = None,
+        ) -> Callable[..., Callable[..., Expr]]:
+            def decorator(accum: Callable[[], Accumulator]) -> Callable[..., Expr]:
+                udaf_caller = AggregateUDF.udaf(
+                    accum, input_types, return_type, state_type, volatility, name
+                )
+
+                @functools.wraps(accum)
+                def wrapper(*args: Any, **kwargs: Any) -> Expr:
+                    return udaf_caller(*args, **kwargs)
+
+                return wrapper
+
+            return decorator
+
+        if args and callable(args[0]):
+            # Case 1: Used as a function, require the first parameter to be callable
+            return _function(*args, **kwargs)
+        # Case 2: Used as a decorator with parameters
+        return _decorator(*args, **kwargs)
+
+
+class WindowEvaluator:
+    """Evaluator class for user-defined window functions (UDWF).
+
+    It is up to the user to decide which evaluate function is appropriate.
+
+    +------------------------+--------------------------------+------------------+---------------------------+
+    | ``uses_window_frame``  | ``supports_bounded_execution`` | ``include_rank`` | function_to_implement     |
+    +========================+================================+==================+===========================+
+    | False (default)        | False (default)                | False (default)  | ``evaluate_all``          |
+    +------------------------+--------------------------------+------------------+---------------------------+
+    | False                  | True                           | False            | ``evaluate``              |
+    +------------------------+--------------------------------+------------------+---------------------------+
+    | False                  | True/False                     | True             | ``evaluate_all_with_rank``|
+    +------------------------+--------------------------------+------------------+---------------------------+
+    | True                   | True/False                     | True/False       | ``evaluate``              |
+    +------------------------+--------------------------------+------------------+---------------------------+
+    """  # noqa: W505, E501
+
+    def memoize(self) -> None:
+        """Perform a memoize operation to improve performance.
+
+        When the window frame has a fixed beginning (e.g UNBOUNDED
+        PRECEDING), some functions such as FIRST_VALUE and
+        NTH_VALUE do not need the (unbounded) input once they have
+        seen a certain amount of input.
+
+        `memoize` is called after each input batch is processed, and
+        such functions can save whatever they need
+        """
+
+    def get_range(self, idx: int, num_rows: int) -> tuple[int, int]:  # noqa: ARG002
+        """Return the range for the window fuction.
+
+        If `uses_window_frame` flag is `false`. This method is used to
+        calculate required range for the window function during
+        stateful execution.
+
+        Generally there is no required range, hence by default this
+        returns smallest range(current row). e.g seeing current row is
+        enough to calculate window result (such as row_number, rank,
+        etc)
+
+        Args:
+            idx:: Current index
+            num_rows: Number of rows.
+        """
+        return (idx, idx + 1)
+
+    def is_causal(self) -> bool:
+        """Get whether evaluator needs future data for its result."""
+        return False
+
+    def evaluate_all(self, values: list[pa.Array], num_rows: int) -> pa.Array:
+        """Evaluate a window function on an entire input partition.
+
+        This function is called once per input *partition* for window functions that
+        *do not use* values from the window frame, such as
+        :py:func:`~datafusion.functions.row_number`,
+        :py:func:`~datafusion.functions.rank`,
+        :py:func:`~datafusion.functions.dense_rank`,
+        :py:func:`~datafusion.functions.percent_rank`,
+        :py:func:`~datafusion.functions.cume_dist`,
+        :py:func:`~datafusion.functions.lead`,
+        and :py:func:`~datafusion.functions.lag`.
+
+        It produces the result of all rows in a single pass. It
+        expects to receive the entire partition as the ``value`` and
+        must produce an output column with one output row for every
+        input row.
+
+        ``num_rows`` is required to correctly compute the output in case
+        ``len(values) == 0``
+
+        Implementing this function is an optimization. Certain window
+        functions are not affected by the window frame definition or
+        the query doesn't have a frame, and ``evaluate`` skips the
+        (costly) window frame boundary calculation and the overhead of
+        calling ``evaluate`` for each output row.
+
+        For example, the `LAG` built in window function does not use
+        the values of its window frame (it can be computed in one shot
+        on the entire partition with ``Self::evaluate_all`` regardless of the
+        window defined in the ``OVER`` clause)
+
+        .. code-block:: text
+
+            lag(x, 1) OVER (ORDER BY z ROWS BETWEEN 2 PRECEDING AND 3 FOLLOWING)
+
+        However, ``avg()`` computes the average in the window and thus
+        does use its window frame.
+
+        .. code-block:: text
+
+            avg(x) OVER (PARTITION BY y ORDER BY z ROWS BETWEEN 2 PRECEDING AND 3 FOLLOWING)
+        """  # noqa: W505, E501
+
+    def evaluate(
+        self, values: list[pa.Array], eval_range: tuple[int, int]
+    ) -> pa.Scalar:
+        """Evaluate window function on a range of rows in an input partition.
+
+        This is the simplest and most general function to implement
+        but also the least performant as it creates output one row at
+        a time. It is typically much faster to implement stateful
+        evaluation using one of the other specialized methods on this
+        trait.
+
+        Returns a [`ScalarValue`] that is the value of the window
+        function within `range` for the entire partition. Argument
+        `values` contains the evaluation result of function arguments
+        and evaluation results of ORDER BY expressions. If function has a
+        single argument, `values[1..]` will contain ORDER BY expression results.
+        """
+
+    def evaluate_all_with_rank(
+        self, num_rows: int, ranks_in_partition: list[tuple[int, int]]
+    ) -> pa.Array:
+        """Called for window functions that only need the rank of a row.
+
+        Evaluate the partition evaluator against the partition using
+        the row ranks. For example, ``rank(col("a"))`` produces
+
+        .. code-block:: text
+
+            a | rank
+            - + ----
+            A | 1
+            A | 1
+            C | 3
+            D | 4
+            D | 4
+
+        For this case, `num_rows` would be `5` and the
+        `ranks_in_partition` would be called with
+
+        .. code-block:: text
+
+            [
+                (0,1),
+                (2,2),
+                (3,4),
+            ]
+
+        The user must implement this method if ``include_rank`` returns True.
+        """
+
+    def supports_bounded_execution(self) -> bool:
+        """Can the window function be incrementally computed using bounded memory?"""
+        return False
+
+    def uses_window_frame(self) -> bool:
+        """Does the window function use the values from the window frame?"""
+        return False
+
+    def include_rank(self) -> bool:
+        """Can this function be evaluated with (only) rank?"""
+        return False
+
+
+class WindowUDF:
+    """Class for performing window user-defined functions (UDF).
+
+    Window UDFs operate on a partition of rows. See
+    also :py:class:`ScalarUDF` for operating on a row by row basis.
+    """
+
+    def __init__(
+        self,
+        name: str,
+        func: Callable[[], WindowEvaluator],
+        input_types: list[pa.DataType],
+        return_type: pa.DataType,
+        volatility: Volatility | str,
+    ) -> None:
+        """Instantiate a user-defined window function (UDWF).
+
+        See :py:func:`udwf` for a convenience function and argument
+        descriptions.
+        """
+        self._udwf = df_internal.WindowUDF(
+            name, func, input_types, return_type, str(volatility)
+        )
+
+    def __call__(self, *args: Expr) -> Expr:
+        """Execute the UDWF.
+
+        This function is not typically called by an end user. These calls will
+        occur during the evaluation of the dataframe.
+        """
+        args_raw = [arg.expr for arg in args]
+        return Expr(self._udwf.__call__(*args_raw))
+
+    @overload
+    @staticmethod
+    def udwf(
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> Callable[..., WindowUDF]: ...
+
+    @overload
+    @staticmethod
+    def udwf(
+        func: Callable[[], WindowEvaluator],
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> WindowUDF: ...
+
+    @staticmethod
+    def udwf(*args: Any, **kwargs: Any):  # noqa: D417
+        """Create a new User-Defined Window Function (UDWF).
+
+        This class can be used both as either a function or a decorator.
+
+        Usage:
+            - As a function: ``udwf(func, input_types, return_type, volatility, name)``.
+            - As a decorator: ``@udwf(input_types, return_type, volatility, name)``.
+              When using ``udwf`` as a decorator, do not pass ``func`` explicitly.
+
+        Function example::
+
+            import pyarrow as pa
+
+            class BiasedNumbers(WindowEvaluator):
+                def __init__(self, start: int = 0) -> None:
+                    self.start = start
+
+                def evaluate_all(self, values: list[pa.Array],
+                    num_rows: int) -> pa.Array:
+                    return pa.array([self.start + i for i in range(num_rows)])
+
+            def bias_10() -> BiasedNumbers:
+                return BiasedNumbers(10)
+
+            udwf1 = udwf(BiasedNumbers, pa.int64(), pa.int64(), "immutable")
+            udwf2 = udwf(bias_10, pa.int64(), pa.int64(), "immutable")
+            udwf3 = udwf(lambda: BiasedNumbers(20), pa.int64(), pa.int64(), "immutable")
+
+
+        Decorator example::
+
+            @udwf(pa.int64(), pa.int64(), "immutable")
+            def biased_numbers() -> BiasedNumbers:
+                return BiasedNumbers(10)
+
+        Args:
+            func: Only needed when calling as a function. Skip this argument when
+                using ``udwf`` as a decorator.
+            input_types: The data types of the arguments.
+            return_type: The data type of the return value.
+            volatility: See :py:class:`Volatility` for allowed values.
+            name: A descriptive name for the function.
+
+        Returns:
+            A user-defined window function that can be used in window function calls.
+        """
+        if args and callable(args[0]):
+            # Case 1: Used as a function, require the first parameter to be callable
+            return WindowUDF._create_window_udf(*args, **kwargs)
+        # Case 2: Used as a decorator with parameters
+        return WindowUDF._create_window_udf_decorator(*args, **kwargs)
+
+    @staticmethod
+    def _create_window_udf(
+        func: Callable[[], WindowEvaluator],
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> WindowUDF:
+        """Create a WindowUDF instance from function arguments."""
+        if not callable(func):
+            msg = "`func` must be callable."
+            raise TypeError(msg)
+        if not isinstance(func(), WindowEvaluator):
+            msg = "`func` must implement the abstract base class WindowEvaluator"
+            raise TypeError(msg)
+
+        name = name or func.__qualname__.lower()
+        input_types = (
+            [input_types] if isinstance(input_types, pa.DataType) else input_types
+        )
+
+        return WindowUDF(name, func, input_types, return_type, volatility)
+
+    @staticmethod
+    def _get_default_name(func: Callable) -> str:
+        """Get the default name for a function based on its attributes."""
+        if hasattr(func, "__qualname__"):
+            return func.__qualname__.lower()
+        return func.__class__.__name__.lower()
+
+    @staticmethod
+    def _normalize_input_types(
+        input_types: pa.DataType | list[pa.DataType],
+    ) -> list[pa.DataType]:
+        """Convert a single DataType to a list if needed."""
+        if isinstance(input_types, pa.DataType):
+            return [input_types]
+        return input_types
+
+    @staticmethod
+    def _create_window_udf_decorator(
+        input_types: pa.DataType | list[pa.DataType],
+        return_type: pa.DataType,
+        volatility: Volatility | str,
+        name: Optional[str] = None,
+    ) -> Callable[[Callable[[], WindowEvaluator]], Callable[..., Expr]]:
+        """Create a decorator for a WindowUDF."""
+
+        def decorator(func: Callable[[], WindowEvaluator]) -> Callable[..., Expr]:
+            udwf_caller = WindowUDF._create_window_udf(
+                func, input_types, return_type, volatility, name
+            )
+
+            @functools.wraps(func)
+            def wrapper(*args: Any, **kwargs: Any) -> Expr:
+                return udwf_caller(*args, **kwargs)
+
+            return wrapper
+
+        return decorator
+
+
+class TableFunction:
+    """Class for performing user-defined table functions (UDTF).
+
+    Table functions generate new table providers based on the
+    input expressions.
+    """
+
+    def __init__(
+        self,
+        name: str,
+        func: Callable[[], any],
+    ) -> None:
+        """Instantiate a user-defined table function (UDTF).
+
+        See :py:func:`udtf` for a convenience function and argument
+        descriptions.
+        """
+        self._udtf = df_internal.TableFunction(name, func)
+
+    def __call__(self, *args: Expr) -> Any:
+        """Execute the UDTF and return a table provider."""
+        args_raw = [arg.expr for arg in args]
+        return self._udtf.__call__(*args_raw)
+
+    @overload
+    @staticmethod
+    def udtf(
+        name: str,
+    ) -> Callable[..., Any]: ...
+
+    @overload
+    @staticmethod
+    def udtf(
+        func: Callable[[], Any],
+        name: str,
+    ) -> TableFunction: ...
+
+    @staticmethod
+    def udtf(*args: Any, **kwargs: Any):
+        """Create a new User-Defined Table Function (UDTF)."""
+        if args and callable(args[0]):
+            # Case 1: Used as a function, require the first parameter to be callable
+            return TableFunction._create_table_udf(*args, **kwargs)
+        if args and hasattr(args[0], "__datafusion_table_function__"):
+            # Case 2: We have a datafusion FFI provided function
+            return TableFunction(args[1], args[0])
+        # Case 3: Used as a decorator with parameters
+        return TableFunction._create_table_udf_decorator(*args, **kwargs)
+
+    @staticmethod
+    def _create_table_udf(
+        func: Callable[..., Any],
+        name: str,
+    ) -> TableFunction:
+        """Create a TableFunction instance from function arguments."""
+        if not callable(func):
+            msg = "`func` must be callable."
+            raise TypeError(msg)
+
+        return TableFunction(name, func)
+
+    @staticmethod
+    def _create_table_udf_decorator(
+        name: Optional[str] = None,
+    ) -> Callable[[Callable[[], WindowEvaluator]], Callable[..., Expr]]:
+        """Create a decorator for a WindowUDF."""
+
+        def decorator(func: Callable[[], WindowEvaluator]) -> Callable[..., Expr]:
+            return TableFunction._create_table_udf(func, name)
+
+        return decorator
+
+    def __repr__(self) -> str:
+        """User printable representation."""
+        return self._udtf.__repr__()
+
+
+# Convenience exports so we can import instead of treating as
+# variables at the package root
+udf = ScalarUDF.udf
+udaf = AggregateUDF.udaf
+udwf = WindowUDF.udwf
+udtf = TableFunction.udtf
diff --git a/python/tests/test_aggregation.py b/python/tests/test_aggregation.py
index 61b1c7d80..49dfb38cf 100644
--- a/python/tests/test_aggregation.py
+++ b/python/tests/test_aggregation.py
@@ -338,7 +338,6 @@ def test_bit_and_bool_fns(df, name, expr, result):
             ),
             [7, 9],
         ),
-        ("last_value", f.last_value(column("a")), [3, 6]),
         (
             "last_value_ordered",
             f.last_value(column("a"), order_by=[column("a").sort(ascending=False)]),
diff --git a/python/tests/test_dataframe.py b/python/tests/test_dataframe.py
index 384b17878..dd5f962b2 100644
--- a/python/tests/test_dataframe.py
+++ b/python/tests/test_dataframe.py
@@ -14,7 +14,9 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+import datetime
 import os
+import re
 from typing import Any
 
 import pyarrow as pa
@@ -27,10 +29,21 @@
     column,
     literal,
 )
-from datafusion import functions as f
+from datafusion import (
+    functions as f,
+)
 from datafusion.expr import Window
+from datafusion.html_formatter import (
+    DataFrameHtmlFormatter,
+    configure_formatter,
+    get_formatter,
+    reset_formatter,
+    reset_styles_loaded_state,
+)
 from pyarrow.csv import write_csv
 
+MB = 1024 * 1024
+
 
 @pytest.fixture
 def ctx():
@@ -101,6 +114,69 @@ def partitioned_df():
     return ctx.create_dataframe([[batch]])
 
 
+@pytest.fixture
+def clean_formatter_state():
+    """Reset the HTML formatter after each test."""
+    reset_formatter()
+
+
+@pytest.fixture
+def null_df():
+    """Create a DataFrame with null values of different types."""
+    ctx = SessionContext()
+
+    # Create a RecordBatch with nulls across different types
+    batch = pa.RecordBatch.from_arrays(
+        [
+            pa.array([1, None, 3, None], type=pa.int64()),
+            pa.array([4.5, 6.7, None, None], type=pa.float64()),
+            pa.array(["a", None, "c", None], type=pa.string()),
+            pa.array([True, None, False, None], type=pa.bool_()),
+            pa.array(
+                [10957, None, 18993, None], type=pa.date32()
+            ),  # 2000-01-01, null, 2022-01-01, null
+            pa.array(
+                [946684800000, None, 1640995200000, None], type=pa.date64()
+            ),  # 2000-01-01, null, 2022-01-01, null
+        ],
+        names=[
+            "int_col",
+            "float_col",
+            "str_col",
+            "bool_col",
+            "date32_col",
+            "date64_col",
+        ],
+    )
+
+    return ctx.create_dataframe([[batch]])
+
+
+# custom style for testing with html formatter
+class CustomStyleProvider:
+    def get_cell_style(self) -> str:
+        return (
+            "background-color: #f5f5f5; color: #333; padding: 8px; border: "
+            "1px solid #ddd;"
+        )
+
+    def get_header_style(self) -> str:
+        return (
+            "background-color: #4285f4; color: white; font-weight: bold; "
+            "padding: 10px; border: 1px solid #3367d6;"
+        )
+
+
+def count_table_rows(html_content: str) -> int:
+    """Count the number of table rows in HTML content.
+    Args:
+        html_content: HTML string to analyze
+    Returns:
+        Number of table rows found (number of <tr> tags)
+    """
+    return len(re.findall(r"<tr", html_content))
+
+
 def test_select(df):
     df_1 = df.select(
         column("a") + column("b"),
@@ -655,6 +731,373 @@ def test_window_frame_defaults_match_postgres(partitioned_df):
     assert df_2.sort(col_a).to_pydict() == expected
 
 
+def test_html_formatter_cell_dimension(df, clean_formatter_state):
+    """Test configuring the HTML formatter with different options."""
+    # Configure with custom settings
+    configure_formatter(
+        max_width=500,
+        max_height=200,
+        enable_cell_expansion=False,
+    )
+
+    html_output = df._repr_html_()
+
+    # Verify our configuration was applied
+    assert "max-height: 200px" in html_output
+    assert "max-width: 500px" in html_output
+    # With cell expansion disabled, we shouldn't see expandable-container elements
+    assert "expandable-container" not in html_output
+
+
+def test_html_formatter_custom_style_provider(df, clean_formatter_state):
+    """Test using custom style providers with the HTML formatter."""
+
+    # Configure with custom style provider
+    configure_formatter(style_provider=CustomStyleProvider())
+
+    html_output = df._repr_html_()
+
+    # Verify our custom styles were applied
+    assert "background-color: #4285f4" in html_output
+    assert "color: white" in html_output
+    assert "background-color: #f5f5f5" in html_output
+
+
+def test_html_formatter_type_formatters(df, clean_formatter_state):
+    """Test registering custom type formatters for specific data types."""
+
+    # Get current formatter and register custom formatters
+    formatter = get_formatter()
+
+    # Format integers with color based on value
+    # Using int as the type for the formatter will work since we convert
+    # Arrow scalar values to Python native types in _get_cell_value
+    def format_int(value):
+        return f'<span style="color: {"red" if value > 2 else "blue"}">{value}</span>'
+
+    formatter.register_formatter(int, format_int)
+
+    html_output = df._repr_html_()
+
+    # Our test dataframe has values 1,2,3 so we should see:
+    assert '<span style="color: blue">1</span>' in html_output
+
+
+def test_html_formatter_custom_cell_builder(df, clean_formatter_state):
+    """Test using a custom cell builder function."""
+
+    # Create a custom cell builder with distinct styling for different value ranges
+    def custom_cell_builder(value, row, col, table_id):
+        try:
+            num_value = int(value)
+            if num_value > 5:  # Values > 5 get green background with indicator
+                return (
+                    '<td style="background-color: #d9f0d3" '
+                    f'data-test="high">{value}-high</td>'
+                )
+            if num_value < 3:  # Values < 3 get blue background with indicator
+                return (
+                    '<td style="background-color: #d3e9f0" '
+                    f'data-test="low">{value}-low</td>'
+                )
+        except (ValueError, TypeError):
+            pass
+
+        # Default styling for other cells (3, 4, 5)
+        return f'<td style="border: 1px solid #ddd" data-test="mid">{value}-mid</td>'
+
+    # Set our custom cell builder
+    formatter = get_formatter()
+    formatter.set_custom_cell_builder(custom_cell_builder)
+
+    html_output = df._repr_html_()
+
+    # Extract cells with specific styling using regex
+    low_cells = re.findall(
+        r'<td style="background-color: #d3e9f0"[^>]*>(\d+)-low</td>', html_output
+    )
+    mid_cells = re.findall(
+        r'<td style="border: 1px solid #ddd"[^>]*>(\d+)-mid</td>', html_output
+    )
+    high_cells = re.findall(
+        r'<td style="background-color: #d9f0d3"[^>]*>(\d+)-high</td>', html_output
+    )
+
+    # Sort the extracted values for consistent comparison
+    low_cells = sorted(map(int, low_cells))
+    mid_cells = sorted(map(int, mid_cells))
+    high_cells = sorted(map(int, high_cells))
+
+    # Verify specific values have the correct styling applied
+    assert low_cells == [1, 2]  # Values < 3
+    assert mid_cells == [3, 4, 5, 5]  # Values 3-5
+    assert high_cells == [6, 8, 8]  # Values > 5
+
+    # Verify the exact content with styling appears in the output
+    assert (
+        '<td style="background-color: #d3e9f0" data-test="low">1-low</td>'
+        in html_output
+    )
+    assert (
+        '<td style="background-color: #d3e9f0" data-test="low">2-low</td>'
+        in html_output
+    )
+    assert (
+        '<td style="border: 1px solid #ddd" data-test="mid">3-mid</td>' in html_output
+    )
+    assert (
+        '<td style="border: 1px solid #ddd" data-test="mid">4-mid</td>' in html_output
+    )
+    assert (
+        '<td style="background-color: #d9f0d3" data-test="high">6-high</td>'
+        in html_output
+    )
+    assert (
+        '<td style="background-color: #d9f0d3" data-test="high">8-high</td>'
+        in html_output
+    )
+
+    # Count occurrences to ensure all cells are properly styled
+    assert html_output.count("-low</td>") == 2  # Two low values (1, 2)
+    assert html_output.count("-mid</td>") == 4  # Four mid values (3, 4, 5, 5)
+    assert html_output.count("-high</td>") == 3  # Three high values (6, 8, 8)
+
+    # Create a custom cell builder that changes background color based on value
+    def custom_cell_builder(value, row, col, table_id):
+        # Handle numeric values regardless of their exact type
+        try:
+            num_value = int(value)
+            if num_value > 5:  # Values > 5 get green background
+                return f'<td style="background-color: #d9f0d3">{value}</td>'
+            if num_value < 3:  # Values < 3 get light blue background
+                return f'<td style="background-color: #d3e9f0">{value}</td>'
+        except (ValueError, TypeError):
+            pass
+
+        # Default styling for other cells
+        return f'<td style="border: 1px solid #ddd">{value}</td>'
+
+    # Set our custom cell builder
+    formatter = get_formatter()
+    formatter.set_custom_cell_builder(custom_cell_builder)
+
+    html_output = df._repr_html_()
+
+    # Verify our custom cell styling was applied
+    assert "background-color: #d3e9f0" in html_output  # For values 1,2
+
+
+def test_html_formatter_custom_header_builder(df, clean_formatter_state):
+    """Test using a custom header builder function."""
+
+    # Create a custom header builder with tooltips
+    def custom_header_builder(field):
+        tooltips = {
+            "a": "Primary key column",
+            "b": "Secondary values",
+            "c": "Additional data",
+        }
+        tooltip = tooltips.get(field.name, "")
+        return (
+            f'<th style="background-color: #333; color: white" '
+            f'title="{tooltip}">{field.name}</th>'
+        )
+
+    # Set our custom header builder
+    formatter = get_formatter()
+    formatter.set_custom_header_builder(custom_header_builder)
+
+    html_output = df._repr_html_()
+
+    # Verify our custom headers were applied
+    assert 'title="Primary key column"' in html_output
+    assert 'title="Secondary values"' in html_output
+    assert "background-color: #333; color: white" in html_output
+
+
+def test_html_formatter_complex_customization(df, clean_formatter_state):
+    """Test combining multiple customization options together."""
+
+    # Create a dark mode style provider
+    class DarkModeStyleProvider:
+        def get_cell_style(self) -> str:
+            return (
+                "background-color: #222; color: #eee; "
+                "padding: 8px; border: 1px solid #444;"
+            )
+
+        def get_header_style(self) -> str:
+            return (
+                "background-color: #111; color: #fff; padding: 10px; "
+                "border: 1px solid #333;"
+            )
+
+    # Configure with dark mode style
+    configure_formatter(
+        max_cell_length=10,
+        style_provider=DarkModeStyleProvider(),
+        custom_css="""
+            .datafusion-table {
+                font-family: monospace;
+                border-collapse: collapse;
+            }
+            .datafusion-table tr:hover td {
+                background-color: #444 !important;
+            }
+        """,
+    )
+
+    # Add type formatters for special formatting - now working with native int values
+    formatter = get_formatter()
+    formatter.register_formatter(
+        int,
+        lambda n: f'<span style="color: {"#5af" if n % 2 == 0 else "#f5a"}">{n}</span>',
+    )
+
+    html_output = df._repr_html_()
+
+    # Verify our customizations were applied
+    assert "background-color: #222" in html_output
+    assert "background-color: #111" in html_output
+    assert ".datafusion-table" in html_output
+    assert "color: #5af" in html_output  # Even numbers
+
+
+def test_html_formatter_memory(df, clean_formatter_state):
+    """Test the memory and row control parameters in DataFrameHtmlFormatter."""
+    configure_formatter(max_memory_bytes=10, min_rows_display=1)
+    html_output = df._repr_html_()
+
+    # Count the number of table rows in the output
+    tr_count = count_table_rows(html_output)
+    # With a tiny memory limit of 10 bytes, the formatter should display
+    # the minimum number of rows (1) plus a message about truncation
+    assert tr_count == 2  # 1 for header row, 1 for data row
+    assert "data truncated" in html_output.lower()
+
+    configure_formatter(max_memory_bytes=10 * MB, min_rows_display=1)
+    html_output = df._repr_html_()
+    # With larger memory limit and min_rows=2, should display all rows
+    tr_count = count_table_rows(html_output)
+    # Table should have header row (1) + 3 data rows = 4 rows
+    assert tr_count == 4
+    # No truncation message should appear
+    assert "data truncated" not in html_output.lower()
+
+
+def test_html_formatter_repr_rows(df, clean_formatter_state):
+    configure_formatter(min_rows_display=2, repr_rows=2)
+    html_output = df._repr_html_()
+
+    tr_count = count_table_rows(html_output)
+    # Tabe should have header row (1) + 2 data rows = 3 rows
+    assert tr_count == 3
+
+    configure_formatter(min_rows_display=2, repr_rows=3)
+    html_output = df._repr_html_()
+
+    tr_count = count_table_rows(html_output)
+    # Tabe should have header row (1) + 3 data rows = 4 rows
+    assert tr_count == 4
+
+
+def test_html_formatter_validation():
+    # Test validation for invalid parameters
+
+    with pytest.raises(ValueError, match="max_cell_length must be a positive integer"):
+        DataFrameHtmlFormatter(max_cell_length=0)
+
+    with pytest.raises(ValueError, match="max_width must be a positive integer"):
+        DataFrameHtmlFormatter(max_width=0)
+
+    with pytest.raises(ValueError, match="max_height must be a positive integer"):
+        DataFrameHtmlFormatter(max_height=0)
+
+    with pytest.raises(ValueError, match="max_memory_bytes must be a positive integer"):
+        DataFrameHtmlFormatter(max_memory_bytes=0)
+
+    with pytest.raises(ValueError, match="max_memory_bytes must be a positive integer"):
+        DataFrameHtmlFormatter(max_memory_bytes=-100)
+
+    with pytest.raises(ValueError, match="min_rows_display must be a positive integer"):
+        DataFrameHtmlFormatter(min_rows_display=0)
+
+    with pytest.raises(ValueError, match="min_rows_display must be a positive integer"):
+        DataFrameHtmlFormatter(min_rows_display=-5)
+
+    with pytest.raises(ValueError, match="repr_rows must be a positive integer"):
+        DataFrameHtmlFormatter(repr_rows=0)
+
+    with pytest.raises(ValueError, match="repr_rows must be a positive integer"):
+        DataFrameHtmlFormatter(repr_rows=-10)
+
+
+def test_configure_formatter(df, clean_formatter_state):
+    """Test using custom style providers with the HTML formatter and configured
+    parameters."""
+
+    # these are non-default values
+    max_cell_length = 10
+    max_width = 500
+    max_height = 30
+    max_memory_bytes = 3 * MB
+    min_rows_display = 2
+    repr_rows = 2
+    enable_cell_expansion = False
+    show_truncation_message = False
+    use_shared_styles = False
+
+    reset_formatter()
+    formatter_default = get_formatter()
+
+    assert formatter_default.max_cell_length != max_cell_length
+    assert formatter_default.max_width != max_width
+    assert formatter_default.max_height != max_height
+    assert formatter_default.max_memory_bytes != max_memory_bytes
+    assert formatter_default.min_rows_display != min_rows_display
+    assert formatter_default.repr_rows != repr_rows
+    assert formatter_default.enable_cell_expansion != enable_cell_expansion
+    assert formatter_default.show_truncation_message != show_truncation_message
+    assert formatter_default.use_shared_styles != use_shared_styles
+
+    # Configure with custom style provider and additional parameters
+    configure_formatter(
+        max_cell_length=max_cell_length,
+        max_width=max_width,
+        max_height=max_height,
+        max_memory_bytes=max_memory_bytes,
+        min_rows_display=min_rows_display,
+        repr_rows=repr_rows,
+        enable_cell_expansion=enable_cell_expansion,
+        show_truncation_message=show_truncation_message,
+        use_shared_styles=use_shared_styles,
+    )
+    formatter_custom = get_formatter()
+    assert formatter_custom.max_cell_length == max_cell_length
+    assert formatter_custom.max_width == max_width
+    assert formatter_custom.max_height == max_height
+    assert formatter_custom.max_memory_bytes == max_memory_bytes
+    assert formatter_custom.min_rows_display == min_rows_display
+    assert formatter_custom.repr_rows == repr_rows
+    assert formatter_custom.enable_cell_expansion == enable_cell_expansion
+    assert formatter_custom.show_truncation_message == show_truncation_message
+    assert formatter_custom.use_shared_styles == use_shared_styles
+
+
+def test_configure_formatter_invalid_params(clean_formatter_state):
+    """Test that configure_formatter rejects invalid parameters."""
+    with pytest.raises(ValueError, match="Invalid formatter parameters"):
+        configure_formatter(invalid_param=123)
+
+    # Test with multiple parameters, one valid and one invalid
+    with pytest.raises(ValueError, match="Invalid formatter parameters"):
+        configure_formatter(max_width=500, not_a_real_param="test")
+
+    # Test with multiple invalid parameters
+    with pytest.raises(ValueError, match="Invalid formatter parameters"):
+        configure_formatter(fake_param1="test", fake_param2=456)
+
+
 def test_get_dataframe(tmp_path):
     ctx = SessionContext()
 
@@ -752,7 +1195,8 @@ def test_execution_plan(aggregate_df):
     assert "AggregateExec:" in indent
     assert "CoalesceBatchesExec:" in indent
     assert "RepartitionExec:" in indent
-    assert "CsvExec:" in indent
+    assert "DataSourceExec:" in indent
+    assert "file_type=csv" in indent
 
     ctx = SessionContext()
     rows_returned = 0
@@ -1242,16 +1686,377 @@ def add_with_parameter(df_internal, value: Any) -> DataFrame:
     assert result["new_col"] == [3 for _i in range(3)]
 
 
-def test_dataframe_repr_html(df) -> None:
+def test_dataframe_repr_html_structure(df, clean_formatter_state) -> None:
+    """Test that DataFrame._repr_html_ produces expected HTML output structure."""
+
     output = df._repr_html_()
 
-    ref_html = """<table border='1'>
-        <tr><th>a</td><th>b</td><th>c</td></tr>
-        <tr><td>1</td><td>4</td><td>8</td></tr>
-        <tr><td>2</td><td>5</td><td>5</td></tr>
-        <tr><td>3</td><td>6</td><td>8</td></tr>
-        </table>
-        """
+    # Since we've added a fair bit of processing to the html output, lets just verify
+    # the values we are expecting in the table exist. Use regex and ignore everything
+    # between the <th></th> and <td></td>. We also don't want the closing > on the
+    # td and th segments because that is where the formatting data is written.
+
+    headers = ["a", "b", "c"]
+    headers = [f"<th(.*?)>{v}</th>" for v in headers]
+    header_pattern = "(.*?)".join(headers)
+    header_matches = re.findall(header_pattern, output, re.DOTALL)
+    assert len(header_matches) == 1
+
+    # Update the pattern to handle values that may be wrapped in spans
+    body_data = [[1, 4, 8], [2, 5, 5], [3, 6, 8]]
+
+    body_lines = [
+        f"<td(.*?)>(?:<span[^>]*?>)?{v}(?:</span>)?</td>"
+        for inner in body_data
+        for v in inner
+    ]
+    body_pattern = "(.*?)".join(body_lines)
+
+    body_matches = re.findall(body_pattern, output, re.DOTALL)
+
+    assert len(body_matches) == 1, "Expected pattern of values not found in HTML output"
+
+
+def test_dataframe_repr_html_values(df, clean_formatter_state):
+    """Test that DataFrame._repr_html_ contains the expected data values."""
+    html = df._repr_html_()
+    assert html is not None
+
+    # Create a more flexible pattern that handles values being wrapped in spans
+    # This pattern will match the sequence of values 1,4,8,2,5,5,3,6,8 regardless
+    # of formatting
+    pattern = re.compile(
+        r"<td[^>]*?>(?:<span[^>]*?>)?1(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?4(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?8(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?2(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?5(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?5(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?3(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?6(?:</span>)?</td>.*?"
+        r"<td[^>]*?>(?:<span[^>]*?>)?8(?:</span>)?</td>",
+        re.DOTALL,
+    )
+
+    # Print debug info if the test fails
+    matches = re.findall(pattern, html)
+    if not matches:
+        print(f"HTML output snippet: {html[:500]}...")  # noqa: T201
+
+    assert len(matches) > 0, "Expected pattern of values not found in HTML output"
+
+
+def test_html_formatter_shared_styles(df, clean_formatter_state):
+    """Test that shared styles work correctly across multiple tables."""
+
+    # First, ensure we're using shared styles
+    configure_formatter(use_shared_styles=True)
+
+    # Get HTML output for first table - should include styles
+    html_first = df._repr_html_()
+
+    # Verify styles are included in first render
+    assert "<style>" in html_first
+    assert ".expandable-container" in html_first
+
+    # Get HTML output for second table - should NOT include styles
+    html_second = df._repr_html_()
+
+    # Verify styles are NOT included in second render
+    assert "<style>" not in html_second
+    assert ".expandable-container" not in html_second
+
+    # Reset the styles loaded state and verify styles are included again
+    reset_styles_loaded_state()
+    html_after_reset = df._repr_html_()
+
+    # Verify styles are included after reset
+    assert "<style>" in html_after_reset
+    assert ".expandable-container" in html_after_reset
+
+
+def test_html_formatter_no_shared_styles(df, clean_formatter_state):
+    """Test that styles are always included when shared styles are disabled."""
+
+    # Configure formatter to NOT use shared styles
+    configure_formatter(use_shared_styles=False)
+
+    # Generate HTML multiple times
+    html_first = df._repr_html_()
+    html_second = df._repr_html_()
+
+    # Verify styles are included in both renders
+    assert "<style>" in html_first
+    assert "<style>" in html_second
+    assert ".expandable-container" in html_first
+    assert ".expandable-container" in html_second
+
+
+def test_html_formatter_manual_format_html(clean_formatter_state):
+    """Test direct usage of format_html method with shared styles."""
+
+    # Create sample data
+    batch = pa.RecordBatch.from_arrays(
+        [pa.array([1, 2, 3]), pa.array([4, 5, 6])],
+        names=["a", "b"],
+    )
+
+    formatter = get_formatter()
+
+    # First call should include styles
+    html_first = formatter.format_html([batch], batch.schema)
+    assert "<style>" in html_first
+
+    # Second call should not include styles (using shared styles by default)
+    html_second = formatter.format_html([batch], batch.schema)
+    assert "<style>" not in html_second
+
+    # Reset loaded state
+    reset_styles_loaded_state()
+
+    # After reset, styles should be included again
+    html_reset = formatter.format_html([batch], batch.schema)
+    assert "<style>" in html_reset
+
+    # Create a new formatter with shared_styles=False
+    local_formatter = DataFrameHtmlFormatter(use_shared_styles=False)
+
+    # Both calls should include styles
+    local_html_1 = local_formatter.format_html([batch], batch.schema)
+    local_html_2 = local_formatter.format_html([batch], batch.schema)
+
+    assert "<style>" in local_html_1
+    assert "<style>" in local_html_2
+
+
+def test_fill_null_basic(null_df):
+    """Test basic fill_null functionality with a single value."""
+    # Fill all nulls with 0
+    filled_df = null_df.fill_null(0)
+
+    result = filled_df.collect()[0]
+
+    # Check that nulls were filled with 0 (or equivalent)
+    assert result.column(0) == pa.array([1, 0, 3, 0])
+    assert result.column(1) == pa.array([4.5, 6.7, 0.0, 0.0])
+    # String column should be filled with "0"
+    assert result.column(2) == pa.array(["a", "0", "c", "0"])
+    # Boolean column should be filled with False (0 converted to bool)
+    assert result.column(3) == pa.array([True, False, False, False])
+
+
+def test_fill_null_subset(null_df):
+    """Test filling nulls only in a subset of columns."""
+    # Fill nulls only in numeric columns
+    filled_df = null_df.fill_null(0, subset=["int_col", "float_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check that nulls were filled only in specified columns
+    assert result.column(0) == pa.array([1, 0, 3, 0])
+    assert result.column(1) == pa.array([4.5, 6.7, 0.0, 0.0])
+    # These should still have nulls
+    assert None in result.column(2).to_pylist()
+    assert None in result.column(3).to_pylist()
+
+
+def test_fill_null_str_column(null_df):
+    """Test filling nulls in string columns with different values."""
+    # Fill string nulls with a replacement string
+    filled_df = null_df.fill_null("N/A", subset=["str_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check that string nulls were filled with "N/A"
+    assert result.column(2).to_pylist() == ["a", "N/A", "c", "N/A"]
+
+    # Other columns should be unchanged
+    assert None in result.column(0).to_pylist()
+    assert None in result.column(1).to_pylist()
+    assert None in result.column(3).to_pylist()
+
+    # Fill with an empty string
+    filled_df = null_df.fill_null("", subset=["str_col"])
+    result = filled_df.collect()[0]
+    assert result.column(2).to_pylist() == ["a", "", "c", ""]
+
+
+def test_fill_null_bool_column(null_df):
+    """Test filling nulls in boolean columns with different values."""
+    # Fill bool nulls with True
+    filled_df = null_df.fill_null(value=True, subset=["bool_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check that bool nulls were filled with True
+    assert result.column(3).to_pylist() == [True, True, False, True]
+
+    # Other columns should be unchanged
+    assert None in result.column(0).to_pylist()
+
+    # Fill bool nulls with False
+    filled_df = null_df.fill_null(value=False, subset=["bool_col"])
+    result = filled_df.collect()[0]
+    assert result.column(3).to_pylist() == [True, False, False, False]
+
+
+def test_fill_null_date32_column(null_df):
+    """Test filling nulls in date32 columns."""
+
+    # Fill date32 nulls with a specific date (1970-01-01)
+    epoch_date = datetime.date(1970, 1, 1)
+    filled_df = null_df.fill_null(epoch_date, subset=["date32_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check that date32 nulls were filled with epoch date
+    dates = result.column(4).to_pylist()
+    assert dates[0] == datetime.date(2000, 1, 1)  # Original value
+    assert dates[1] == epoch_date  # Filled value
+    assert dates[2] == datetime.date(2022, 1, 1)  # Original value
+    assert dates[3] == epoch_date  # Filled value
+
+    # Other date column should be unchanged
+    assert None in result.column(5).to_pylist()
+
+
+def test_fill_null_date64_column(null_df):
+    """Test filling nulls in date64 columns."""
+
+    # Fill date64 nulls with a specific date (1970-01-01)
+    epoch_date = datetime.date(1970, 1, 1)
+    filled_df = null_df.fill_null(epoch_date, subset=["date64_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check that date64 nulls were filled with epoch date
+    dates = result.column(5).to_pylist()
+    assert dates[0] == datetime.date(2000, 1, 1)  # Original value
+    assert dates[1] == epoch_date  # Filled value
+    assert dates[2] == datetime.date(2022, 1, 1)  # Original value
+    assert dates[3] == epoch_date  # Filled value
+
+    # Other date column should be unchanged
+    assert None in result.column(4).to_pylist()
+
+
+def test_fill_null_type_coercion(null_df):
+    """Test type coercion when filling nulls with values of different types."""
+    # Try to fill string nulls with a number
+    filled_df = null_df.fill_null(42, subset=["str_col"])
+
+    result = filled_df.collect()[0]
+
+    # String nulls should be filled with string representation of the number
+    assert result.column(2).to_pylist() == ["a", "42", "c", "42"]
+
+    # Try to fill bool nulls with a string that converts to True
+    filled_df = null_df.fill_null("true", subset=["bool_col"])
+    result = filled_df.collect()[0]
+
+    # This behavior depends on the implementation - check it works without error
+    # but don't make assertions about exact conversion behavior
+    assert None not in result.column(3).to_pylist()
+
+
+def test_fill_null_multiple_date_columns(null_df):
+    """Test filling nulls in both date column types simultaneously."""
+
+    # Fill both date column types with the same date
+    test_date = datetime.date(2023, 12, 31)
+    filled_df = null_df.fill_null(test_date, subset=["date32_col", "date64_col"])
+
+    result = filled_df.collect()[0]
+
+    # Check both date columns were filled correctly
+    date32_vals = result.column(4).to_pylist()
+    date64_vals = result.column(5).to_pylist()
+
+    assert None not in date32_vals
+    assert None not in date64_vals
+
+    assert date32_vals[1] == test_date
+    assert date32_vals[3] == test_date
+    assert date64_vals[1] == test_date
+    assert date64_vals[3] == test_date
+
+
+def test_fill_null_specific_types(null_df):
+    """Test filling nulls with type-appropriate values."""
+    # Fill with type-specific values
+    filled_df = null_df.fill_null("missing")
+
+    result = filled_df.collect()[0]
+
+    # Check that nulls were filled appropriately by type
+
+    assert result.column(0).to_pylist() == [1, None, 3, None]
+    assert result.column(1).to_pylist() == [4.5, 6.7, None, None]
+    assert result.column(2).to_pylist() == ["a", "missing", "c", "missing"]
+    assert result.column(3).to_pylist() == [True, None, False, None]  # Bool gets False
+    assert result.column(4).to_pylist() == [
+        datetime.date(2000, 1, 1),
+        None,
+        datetime.date(2022, 1, 1),
+        None,
+    ]
+    assert result.column(5).to_pylist() == [
+        datetime.date(2000, 1, 1),
+        None,
+        datetime.date(2022, 1, 1),
+        None,
+    ]
+
+
+def test_fill_null_immutability(null_df):
+    """Test that original DataFrame is unchanged after fill_null."""
+    # Get original values with nulls
+    original = null_df.collect()[0]
+    original_int_nulls = original.column(0).to_pylist().count(None)
+
+    # Apply fill_null
+    _filled_df = null_df.fill_null(0)
+
+    # Check that original is unchanged
+    new_original = null_df.collect()[0]
+    new_original_int_nulls = new_original.column(0).to_pylist().count(None)
+
+    assert original_int_nulls == new_original_int_nulls
+    assert original_int_nulls > 0  # Ensure we actually had nulls in the first place
+
+
+def test_fill_null_empty_df(ctx):
+    """Test fill_null on empty DataFrame."""
+    # Create an empty DataFrame with schema
+    batch = pa.RecordBatch.from_arrays(
+        [pa.array([], type=pa.int64()), pa.array([], type=pa.string())],
+        names=["a", "b"],
+    )
+    empty_df = ctx.create_dataframe([[batch]])
+
+    # Fill nulls (should work without errors)
+    filled_df = empty_df.fill_null(0)
+
+    # Should still be empty but with same schema
+    result = filled_df.collect()[0]
+    assert len(result.column(0)) == 0
+    assert len(result.column(1)) == 0
+    assert result.schema.field(0).name == "a"
+    assert result.schema.field(1).name == "b"
+
+
+def test_fill_null_all_null_column(ctx):
+    """Test fill_null on a column with all nulls."""
+    # Create DataFrame with a column of all nulls
+    batch = pa.RecordBatch.from_arrays(
+        [pa.array([1, 2, 3]), pa.array([None, None, None], type=pa.string())],
+        names=["a", "b"],
+    )
+    all_null_df = ctx.create_dataframe([[batch]])
+
+    # Fill nulls with a value
+    filled_df = all_null_df.fill_null("filled")
 
-    # Ignore whitespace just to make this test look cleaner
-    assert output.replace(" ", "") == ref_html.replace(" ", "")
+    # Check that all nulls were filled
+    result = filled_df.collect()[0]
+    assert result.column(1).to_pylist() == ["filled", "filled", "filled"]
diff --git a/python/tests/test_expr.py b/python/tests/test_expr.py
index 926e69845..adca783b5 100644
--- a/python/tests/test_expr.py
+++ b/python/tests/test_expr.py
@@ -15,20 +15,31 @@
 # specific language governing permissions and limitations
 # under the License.
 
+from datetime import datetime, timezone
+
 import pyarrow as pa
 import pytest
-from datafusion import SessionContext, col
+from datafusion import SessionContext, col, functions, lit
 from datafusion.expr import (
     Aggregate,
     AggregateFunction,
     BinaryExpr,
     Column,
+    CopyTo,
+    CreateIndex,
+    DescribeTable,
+    DmlStatement,
+    DropCatalogSchema,
     Filter,
     Limit,
     Literal,
     Projection,
+    RecursiveQuery,
     Sort,
     TableScan,
+    TransactionEnd,
+    TransactionStart,
+    Values,
 )
 
 
@@ -247,3 +258,569 @@ def test_fill_null(df):
     assert result.column(0) == pa.array([1, 2, 100])
     assert result.column(1) == pa.array([4, 25, 6])
     assert result.column(2) == pa.array([1234, 1234, 8])
+
+
+def test_copy_to():
+    ctx = SessionContext()
+    ctx.sql("CREATE TABLE foo (a int, b int)").collect()
+    df = ctx.sql("COPY foo TO bar STORED AS CSV")
+    plan = df.logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, CopyTo)
+
+
+def test_create_index():
+    ctx = SessionContext()
+    ctx.sql("CREATE TABLE foo (a int, b int)").collect()
+    plan = ctx.sql("create index idx on foo (a)").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, CreateIndex)
+
+
+def test_describe_table():
+    ctx = SessionContext()
+    ctx.sql("CREATE TABLE foo (a int, b int)").collect()
+    plan = ctx.sql("describe foo").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, DescribeTable)
+
+
+def test_dml_statement():
+    ctx = SessionContext()
+    ctx.sql("CREATE TABLE foo (a int, b int)").collect()
+    plan = ctx.sql("insert into foo values (1, 2)").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, DmlStatement)
+
+
+def drop_catalog_schema():
+    ctx = SessionContext()
+    plan = ctx.sql("drop schema cat").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, DropCatalogSchema)
+
+
+def test_recursive_query():
+    ctx = SessionContext()
+    plan = ctx.sql(
+        """
+        WITH RECURSIVE cte AS (
+        SELECT 1 as n
+        UNION ALL
+        SELECT n + 1 FROM cte WHERE n < 5
+        )
+        SELECT * FROM cte;
+        """
+    ).logical_plan()
+    plan = plan.inputs()[0].inputs()[0].to_variant()
+    assert isinstance(plan, RecursiveQuery)
+
+
+def test_values():
+    ctx = SessionContext()
+    plan = ctx.sql("values (1, 'foo'), (2, 'bar')").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, Values)
+
+
+def test_transaction_start():
+    ctx = SessionContext()
+    plan = ctx.sql("START TRANSACTION").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, TransactionStart)
+
+
+def test_transaction_end():
+    ctx = SessionContext()
+    plan = ctx.sql("COMMIT").logical_plan()
+    plan = plan.to_variant()
+    assert isinstance(plan, TransactionEnd)
+
+
+def test_col_getattr():
+    ctx = SessionContext()
+    data = {
+        "array_values": [[1, 2, 3], [4, 5], [6], []],
+        "struct_values": [
+            {"name": "Alice", "age": 15},
+            {"name": "Bob", "age": 14},
+            {"name": "Charlie", "age": 13},
+            {"name": None, "age": 12},
+        ],
+    }
+    df = ctx.from_pydict(data, name="table1")
+
+    names = df.select(col.struct_values["name"].alias("name")).collect()
+    names = [r.as_py() for rs in names for r in rs["name"]]
+
+    array_values = df.select(col.array_values[1].alias("value")).collect()
+    array_values = [r.as_py() for rs in array_values for r in rs["value"]]
+
+    assert names == ["Alice", "Bob", "Charlie", None]
+    assert array_values == [2, 5, None, None]
+
+
+def test_alias_with_metadata(df):
+    df = df.select(col("a").alias("b", {"key": "value"}))
+    assert df.schema().field("b").metadata == {b"key": b"value"}
+
+
+# These unit tests are to ensure the expression functions do not regress
+# For the math functions we will use `functions.round` so we can more
+# easily test for equivalence and not worry about floating point precision
+@pytest.mark.parametrize(
+    ("function", "expected_result"),
+    [
+        # Math Functions
+        pytest.param(
+            functions.round(col("a").asin(), lit(4)),
+            pa.array([-0.8481, 0.5236, 0.0, None], type=pa.float64()),
+            id="asin",
+        ),
+        pytest.param(
+            functions.round(col("a").sin(), lit(4)),
+            pa.array([-0.6816, 0.4794, 0.0, None], type=pa.float64()),
+            id="sin",
+        ),
+        pytest.param(
+            # Since log10 of negative returns NaN and you can't test NaN for
+            # equivalence, also do an abs() here.
+            functions.round(col("a").abs().log10(), lit(4)),
+            pa.array([-0.1249, -0.301, -float("inf"), None], type=pa.float64()),
+            id="log10",
+        ),
+        pytest.param(
+            col("a").iszero(),
+            pa.array([False, False, True, None], type=pa.bool_()),
+            id="iszero",
+        ),
+        pytest.param(
+            functions.round(col("a").acos(), lit(4)),
+            pa.array([2.4189, 1.0472, 1.5708, None], type=pa.float64()),
+            id="acos",
+        ),
+        pytest.param(
+            col("e").isnan(),
+            pa.array([False, True, False, None], type=pa.bool_()),
+            id="isnan",
+        ),
+        pytest.param(
+            functions.round(col("a").degrees(), lit(4)),
+            pa.array([-42.9718, 28.6479, 0.0, None], type=pa.float64()),
+            id="degrees",
+        ),
+        pytest.param(
+            functions.round(col("a").asinh(), lit(4)),
+            pa.array([-0.6931, 0.4812, 0.0, None], type=pa.float64()),
+            id="asinh",
+        ),
+        pytest.param(
+            col("a").abs(),
+            pa.array([0.75, 0.5, 0.0, None], type=pa.float64()),
+            id="abs",
+        ),
+        pytest.param(
+            functions.round(col("a").exp(), lit(4)),
+            pa.array([0.4724, 1.6487, 1.0, None], type=pa.float64()),
+            id="exp",
+        ),
+        pytest.param(
+            functions.round(col("a").cosh(), lit(4)),
+            pa.array([1.2947, 1.1276, 1.0, None], type=pa.float64()),
+            id="cosh",
+        ),
+        pytest.param(
+            functions.round(col("a").radians(), lit(4)),
+            pa.array([-0.0131, 0.0087, 0.0, None], type=pa.float64()),
+            id="radians",
+        ),
+        pytest.param(
+            functions.round(col("a").abs().sqrt(), lit(4)),
+            pa.array([0.866, 0.7071, 0.0, None], type=pa.float64()),
+            id="sqrt",
+        ),
+        pytest.param(
+            functions.round(col("a").tanh(), lit(4)),
+            pa.array([-0.6351, 0.4621, 0.0, None], type=pa.float64()),
+            id="tanh",
+        ),
+        pytest.param(
+            functions.round(col("a").atan(), lit(4)),
+            pa.array([-0.6435, 0.4636, 0.0, None], type=pa.float64()),
+            id="atan",
+        ),
+        pytest.param(
+            functions.round(col("a").atanh(), lit(4)),
+            pa.array([-0.973, 0.5493, 0.0, None], type=pa.float64()),
+            id="atanh",
+        ),
+        pytest.param(
+            # large numbers cause an integer overflow so divid to make smaller
+            (col("b") / lit(4)).factorial(),
+            pa.array([1, 3628800, 1, None], type=pa.int64()),
+            id="factorial",
+        ),
+        pytest.param(
+            # Valid values of acosh must be >= 1.0
+            functions.round((col("a").abs() + lit(1.0)).acosh(), lit(4)),
+            pa.array([1.1588, 0.9624, 0.0, None], type=pa.float64()),
+            id="acosh",
+        ),
+        pytest.param(
+            col("a").floor(),
+            pa.array([-1.0, 0.0, 0.0, None], type=pa.float64()),
+            id="floor",
+        ),
+        pytest.param(
+            col("a").ceil(),
+            pa.array([-0.0, 1.0, 0.0, None], type=pa.float64()),
+            id="ceil",
+        ),
+        pytest.param(
+            functions.round(col("a").abs().ln(), lit(4)),
+            pa.array([-0.2877, -0.6931, float("-inf"), None], type=pa.float64()),
+            id="ln",
+        ),
+        pytest.param(
+            functions.round(col("a").tan(), lit(4)),
+            pa.array([-0.9316, 0.5463, 0.0, None], type=pa.float64()),
+            id="tan",
+        ),
+        pytest.param(
+            functions.round(col("a").cbrt(), lit(4)),
+            pa.array([-0.9086, 0.7937, 0.0, None], type=pa.float64()),
+            id="cbrt",
+        ),
+        pytest.param(
+            functions.round(col("a").cos(), lit(4)),
+            pa.array([0.7317, 0.8776, 1.0, None], type=pa.float64()),
+            id="cos",
+        ),
+        pytest.param(
+            functions.round(col("a").sinh(), lit(4)),
+            pa.array([-0.8223, 0.5211, 0.0, None], type=pa.float64()),
+            id="sinh",
+        ),
+        pytest.param(
+            col("a").signum(),
+            pa.array([-1.0, 1.0, 0.0, None], type=pa.float64()),
+            id="signum",
+        ),
+        pytest.param(
+            functions.round(col("a").abs().log2(), lit(4)),
+            pa.array([-0.415, -1.0, float("-inf"), None], type=pa.float64()),
+            id="log2",
+        ),
+        pytest.param(
+            functions.round(col("a").cot(), lit(4)),
+            pa.array([-1.0734, 1.8305, float("inf"), None], type=pa.float64()),
+            id="cot",
+        ),
+        #
+        # String Functions
+        #
+        pytest.param(
+            col("c").reverse(),
+            pa.array(["olleH", " dlrow ", "!", None], type=pa.string()),
+            id="reverse",
+        ),
+        pytest.param(
+            col("c").bit_length(),
+            pa.array([40, 56, 8, None], type=pa.int32()),
+            id="bit_length",
+        ),
+        pytest.param(
+            col("b").to_hex(),
+            pa.array(["ffffffffffffffe2", "2a", "0", None], type=pa.string()),
+            id="to_hex",
+        ),
+        pytest.param(
+            col("c").length(),
+            pa.array([5, 7, 1, None], type=pa.int32()),
+            id="length",
+        ),
+        pytest.param(
+            col("c").lower(),
+            pa.array(["hello", " world ", "!", None], type=pa.string()),
+            id="lower",
+        ),
+        pytest.param(
+            col("c").ascii(),
+            pa.array([72, 32, 33, None], type=pa.int32()),
+            id="ascii",
+        ),
+        pytest.param(
+            col("c").sha512(),
+            pa.array(
+                [
+                    bytes.fromhex(
+                        "3615F80C9D293ED7402687F94B22D58E529B8CC7916F8FAC7FDDF7FBD5AF4CF777D3D795A7A00A16BF7E7F3FB9561EE9BAAE480DA9FE7A18769E71886B03F315"
+                    ),
+                    bytes.fromhex(
+                        "A6758FDA3C2F0B554084E18308EA99B94B54EEE8FDA72697CEA7844E524CC2F2F2EE4CC8BAC87D2E3E7222959FE3D0CA1A841761FDC0D1780F6FE9E39E369500"
+                    ),
+                    bytes.fromhex(
+                        "3831A6A6155E509DEE59A7F451EB35324D8F8F2DF6E3708894740F98FDEE23889F4DE5ADB0C5010DFB555CDA77C8AB5DC902094C52DE3278F35A75EBC25F093A"
+                    ),
+                    None,
+                ],
+                type=pa.binary(),
+            ),
+            id="sha512",
+        ),
+        pytest.param(
+            col("c").sha384(),
+            pa.array(
+                [
+                    bytes.fromhex(
+                        "3519FE5AD2C596EFE3E276A6F351B8FC0B03DB861782490D45F7598EBD0AB5FD5520ED102F38C4A5EC834E98668035FC"
+                    ),
+                    bytes.fromhex(
+                        "A6A38A9AE2CFD0D67F49989AD584632BF7D7A07DAD2277E92326A6A0B37F884A871D6173FB342CFE258E375258ACAAEC"
+                    ),
+                    bytes.fromhex(
+                        "1D0EC8C84EE9521E21F06774DE232367B64DE628474CB5B2E372B699A1F55AE335CC37193EF823E33324DFD9A70738A6"
+                    ),
+                    None,
+                ],
+                type=pa.binary(),
+            ),
+            id="sha384",
+        ),
+        pytest.param(
+            col("c").sha256(),
+            pa.array(
+                [
+                    bytes.fromhex(
+                        "185F8DB32271FE25F561A6FC938B2E264306EC304EDA518007D1764826381969"
+                    ),
+                    bytes.fromhex(
+                        "DE2EF0D77D456EC1CDE2C52F75996F6636A64079297213D548D875A488B03A75"
+                    ),
+                    bytes.fromhex(
+                        "BB7208BC9B5D7C04F1236A82A0093A5E33F40423D5BA8D4266F7092C3BA43B62"
+                    ),
+                    None,
+                ],
+                type=pa.binary(),
+            ),
+            id="sha256",
+        ),
+        pytest.param(
+            col("c").sha224(),
+            pa.array(
+                [
+                    bytes.fromhex(
+                        "4149DA18AA8BFC2B1E382C6C26556D01A92C261B6436DAD5E3BE3FCC"
+                    ),
+                    bytes.fromhex(
+                        "AD6DF6D9ECDDF50AF2A72D5E3144BA813EE954537572C0E8AB3066BE"
+                    ),
+                    bytes.fromhex(
+                        "6641A7E8278BCD49E476E7ACAE158F4105B2952D22AEB2E0B9A231A0"
+                    ),
+                    None,
+                ],
+                type=pa.binary(),
+            ),
+            id="sha224",
+        ),
+        pytest.param(
+            col("c").btrim(),
+            pa.array(["Hello", "world", "!", None], type=pa.string_view()),
+            id="btrim",
+        ),
+        pytest.param(
+            col("c").trim(),
+            pa.array(["Hello", "world", "!", None], type=pa.string_view()),
+            id="trim",
+        ),
+        pytest.param(
+            col("c").md5(),
+            pa.array(
+                [
+                    "8b1a9953c4611296a827abf8c47804d7",
+                    "de802497c24568d9a85d4eb8c2b6e8fe",
+                    "9033e0e305f247c0c3c80d0c7848c8b3",
+                    None,
+                ],
+                type=pa.string(),
+            ),
+            id="md5",
+        ),
+        pytest.param(
+            col("c").octet_length(),
+            pa.array([5, 7, 1, None], type=pa.int32()),
+            id="octet_length",
+        ),
+        pytest.param(
+            col("c").character_length(),
+            pa.array([5, 7, 1, None], type=pa.int32()),
+            id="character_length",
+        ),
+        pytest.param(
+            col("c").char_length(),
+            pa.array([5, 7, 1, None], type=pa.int32()),
+            id="char_length",
+        ),
+        pytest.param(
+            col("c").rtrim(),
+            pa.array(["Hello", " world", "!", None], type=pa.string_view()),
+            id="rtrim",
+        ),
+        pytest.param(
+            col("c").ltrim(),
+            pa.array(["Hello", "world ", "!", None], type=pa.string_view()),
+            id="ltrim",
+        ),
+        pytest.param(
+            col("c").upper(),
+            pa.array(["HELLO", " WORLD ", "!", None], type=pa.string()),
+            id="upper",
+        ),
+        pytest.param(
+            lit(65).chr(),
+            pa.array(["A", "A", "A", "A"], type=pa.string()),
+            id="chr",
+        ),
+        #
+        # Time Functions
+        #
+        pytest.param(
+            col("b").from_unixtime(),
+            pa.array(
+                [
+                    datetime(1969, 12, 31, 23, 59, 30, tzinfo=timezone.utc),
+                    datetime(1970, 1, 1, 0, 0, 42, tzinfo=timezone.utc),
+                    datetime(1970, 1, 1, 0, 0, 0, tzinfo=timezone.utc),
+                    None,
+                ],
+                type=pa.timestamp("s"),
+            ),
+            id="from_unixtime",
+        ),
+        pytest.param(
+            col("c").initcap(),
+            pa.array(["Hello", " World ", "!", None], type=pa.string_view()),
+            id="initcap",
+        ),
+        #
+        # Array Functions
+        #
+        pytest.param(
+            col("d").array_pop_back(),
+            pa.array([[-1, 1], [5, 10, 15], [], None], type=pa.list_(pa.int64())),
+            id="array_pop_back",
+        ),
+        pytest.param(
+            col("d").array_pop_front(),
+            pa.array([[1, 0], [10, 15, 20], [], None], type=pa.list_(pa.int64())),
+            id="array_pop_front",
+        ),
+        pytest.param(
+            col("d").array_length(),
+            pa.array([3, 4, 0, None], type=pa.uint64()),
+            id="array_length",
+        ),
+        pytest.param(
+            col("d").list_length(),
+            pa.array([3, 4, 0, None], type=pa.uint64()),
+            id="list_length",
+        ),
+        pytest.param(
+            col("d").array_ndims(),
+            pa.array([1, 1, 1, None], type=pa.uint64()),
+            id="array_ndims",
+        ),
+        pytest.param(
+            col("d").list_ndims(),
+            pa.array([1, 1, 1, None], type=pa.uint64()),
+            id="list_ndims",
+        ),
+        pytest.param(
+            col("d").array_dims(),
+            pa.array([[3], [4], None, None], type=pa.list_(pa.uint64())),
+            id="array_dims",
+        ),
+        pytest.param(
+            col("d").array_empty(),
+            pa.array([False, False, True, None], type=pa.bool_()),
+            id="array_empty",
+        ),
+        pytest.param(
+            col("d").list_distinct(),
+            pa.array(
+                [[-1, 0, 1], [5, 10, 15, 20], [], None], type=pa.list_(pa.int64())
+            ),
+            id="list_distinct",
+        ),
+        pytest.param(
+            col("d").array_distinct(),
+            pa.array(
+                [[-1, 0, 1], [5, 10, 15, 20], [], None], type=pa.list_(pa.int64())
+            ),
+            id="array_distinct",
+        ),
+        pytest.param(
+            col("d").cardinality(),
+            pa.array([3, 4, None, None], type=pa.uint64()),
+            id="cardinality",
+        ),
+        pytest.param(
+            col("f").flatten(),
+            pa.array(
+                [[-1, 1, 0, 4, 4], [5, 10, 15, 20, 3], [], []],
+                type=pa.list_(pa.int64()),
+            ),
+            id="flatten",
+        ),
+        pytest.param(
+            col("d").list_dims(),
+            pa.array([[3], [4], None, None], type=pa.list_(pa.uint64())),
+            id="list_dims",
+        ),
+        pytest.param(
+            col("d").empty(),
+            pa.array([False, False, True, None], type=pa.bool_()),
+            id="empty",
+        ),
+        #
+        # Other Tests
+        #
+        pytest.param(
+            col("d").arrow_typeof(),
+            pa.array(
+                [
+                    'List(Field { name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} })',  # noqa: E501
+                    'List(Field { name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} })',  # noqa: E501
+                    'List(Field { name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} })',  # noqa: E501
+                    'List(Field { name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} })',  # noqa: E501
+                ],
+                type=pa.string(),
+            ),
+            id="arrow_typeof",
+        ),
+    ],
+)
+def test_expr_functions(ctx, function, expected_result):
+    batch = pa.RecordBatch.from_arrays(
+        [
+            pa.array([-0.75, 0.5, 0.0, None], type=pa.float64()),
+            pa.array([-30, 42, 0, None], type=pa.int64()),
+            pa.array(["Hello", " world ", "!", None], type=pa.string_view()),
+            pa.array(
+                [[-1, 1, 0], [5, 10, 15, 20], [], None], type=pa.list_(pa.int64())
+            ),
+            pa.array([-0.75, float("nan"), 0.0, None], type=pa.float64()),
+            pa.array(
+                [[[-1, 1, 0], [4, 4]], [[5, 10, 15, 20], [3]], [[]], [None]],
+                type=pa.list_(pa.list_(pa.int64())),
+            ),
+        ],
+        names=["a", "b", "c", "d", "e", "f"],
+    )
+    df = ctx.create_dataframe([[batch]]).select(function)
+    result = df.collect()
+
+    assert len(result) == 1
+    assert result[0].column(0).equals(expected_result)
diff --git a/python/tests/test_functions.py b/python/tests/test_functions.py
index 37f2075f5..5189b651a 100644
--- a/python/tests/test_functions.py
+++ b/python/tests/test_functions.py
@@ -1231,3 +1231,69 @@ def test_between_default(df):
 
     actual = df.collect()[0].to_pydict()
     assert actual == expected
+
+
+def test_alias_with_metadata(df):
+    df = df.select(f.alias(f.col("a"), "b", {"key": "value"}))
+    assert df.schema().field("b").metadata == {b"key": b"value"}
+
+
+def test_coalesce(df):
+    # Create a DataFrame with null values
+    ctx = SessionContext()
+    batch = pa.RecordBatch.from_arrays(
+        [
+            pa.array(["Hello", None, "!"]),  # string column with null
+            pa.array([4, None, 6]),  # integer column with null
+            pa.array(["hello ", None, " !"]),  # string column with null
+            pa.array(
+                [
+                    datetime(2022, 12, 31, tzinfo=DEFAULT_TZ),
+                    None,
+                    datetime(2020, 7, 2, tzinfo=DEFAULT_TZ),
+                ]
+            ),  # datetime with null
+            pa.array([False, None, True]),  # boolean column with null
+        ],
+        names=["a", "b", "c", "d", "e"],
+    )
+    df_with_nulls = ctx.create_dataframe([[batch]])
+
+    # Test coalesce with different data types
+    result_df = df_with_nulls.select(
+        f.coalesce(column("a"), literal("default")).alias("a_coalesced"),
+        f.coalesce(column("b"), literal(0)).alias("b_coalesced"),
+        f.coalesce(column("c"), literal("default")).alias("c_coalesced"),
+        f.coalesce(column("d"), literal(datetime(2000, 1, 1, tzinfo=DEFAULT_TZ))).alias(
+            "d_coalesced"
+        ),
+        f.coalesce(column("e"), literal(value=False)).alias("e_coalesced"),
+    )
+
+    result = result_df.collect()[0]
+
+    # Verify results
+    assert result.column(0) == pa.array(
+        ["Hello", "default", "!"], type=pa.string_view()
+    )
+    assert result.column(1) == pa.array([4, 0, 6], type=pa.int64())
+    assert result.column(2) == pa.array(
+        ["hello ", "default", " !"], type=pa.string_view()
+    )
+    assert result.column(3).to_pylist() == [
+        datetime(2022, 12, 31, tzinfo=DEFAULT_TZ),
+        datetime(2000, 1, 1, tzinfo=DEFAULT_TZ),
+        datetime(2020, 7, 2, tzinfo=DEFAULT_TZ),
+    ]
+    assert result.column(4) == pa.array([False, False, True], type=pa.bool_())
+
+    # Test multiple arguments
+    result_df = df_with_nulls.select(
+        f.coalesce(column("a"), literal(None), literal("fallback")).alias(
+            "multi_coalesce"
+        )
+    )
+    result = result_df.collect()[0]
+    assert result.column(0) == pa.array(
+        ["Hello", "fallback", "!"], type=pa.string_view()
+    )
diff --git a/python/tests/test_imports.py b/python/tests/test_imports.py
index 9ef7ed89a..fca94b35a 100644
--- a/python/tests/test_imports.py
+++ b/python/tests/test_imports.py
@@ -107,7 +107,7 @@ def test_class_module_is_datafusion():
         AggregateUDF,
         ScalarUDF,
     ]:
-        assert klass.__module__ == "datafusion.udf"
+        assert klass.__module__ == "datafusion.user_defined"
 
     # expressions
     for klass in [Expr, Column, Literal, BinaryExpr, AggregateFunction]:
diff --git a/python/tests/test_udwf.py b/python/tests/test_udwf.py
index 4190e7d64..5aaf00664 100644
--- a/python/tests/test_udwf.py
+++ b/python/tests/test_udwf.py
@@ -22,7 +22,7 @@
 from datafusion import SessionContext, column, lit, udwf
 from datafusion import functions as f
 from datafusion.expr import WindowFrame
-from datafusion.udf import WindowEvaluator
+from datafusion.user_defined import WindowEvaluator
 
 
 class ExponentialSmoothDefault(WindowEvaluator):
diff --git a/python/tests/test_unparser.py b/python/tests/test_unparser.py
new file mode 100644
index 000000000..c4e05780c
--- /dev/null
+++ b/python/tests/test_unparser.py
@@ -0,0 +1,33 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+from datafusion.context import SessionContext
+from datafusion.unparser import Dialect, Unparser
+
+
+def test_unparser():
+    ctx = SessionContext()
+    df = ctx.sql("SELECT 1")
+    for dialect in [
+        Dialect.mysql(),
+        Dialect.postgres(),
+        Dialect.sqlite(),
+        Dialect.duckdb(),
+    ]:
+        unparser = Unparser(dialect)
+        sql = unparser.plan_to_sql(df.logical_plan())
+        assert sql == "SELECT 1"
diff --git a/src/common.rs b/src/common.rs
index 453bf67a4..88d2fdd5f 100644
--- a/src/common.rs
+++ b/src/common.rs
@@ -36,5 +36,8 @@ pub(crate) fn init_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<schema::SqlView>()?;
     m.add_class::<schema::SqlStatistics>()?;
     m.add_class::<function::SqlFunction>()?;
+    m.add_class::<schema::PyTableType>()?;
+    m.add_class::<schema::PyTableSource>()?;
+    m.add_class::<schema::PyConstraints>()?;
     Ok(())
 }
diff --git a/src/common/schema.rs b/src/common/schema.rs
index 66ce925ae..5a54fe333 100644
--- a/src/common/schema.rs
+++ b/src/common/schema.rs
@@ -15,14 +15,22 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use std::fmt::{self, Display, Formatter};
+use std::sync::Arc;
 use std::{any::Any, borrow::Cow};
 
+use arrow::datatypes::Schema;
+use arrow::pyarrow::PyArrowType;
 use datafusion::arrow::datatypes::SchemaRef;
+use datafusion::common::Constraints;
+use datafusion::datasource::TableType;
 use datafusion::logical_expr::{Expr, TableProviderFilterPushDown, TableSource};
 use pyo3::prelude::*;
 
 use datafusion::logical_expr::utils::split_conjunction;
 
+use crate::sql::logical::PyLogicalPlan;
+
 use super::{data_type::DataTypeMap, function::SqlFunction};
 
 #[pyclass(name = "SqlSchema", module = "datafusion.common", subclass)]
@@ -218,3 +226,84 @@ impl SqlStatistics {
         self.row_count
     }
 }
+
+#[pyclass(name = "Constraints", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyConstraints {
+    pub constraints: Constraints,
+}
+
+impl From<PyConstraints> for Constraints {
+    fn from(constraints: PyConstraints) -> Self {
+        constraints.constraints
+    }
+}
+
+impl From<Constraints> for PyConstraints {
+    fn from(constraints: Constraints) -> Self {
+        PyConstraints { constraints }
+    }
+}
+
+impl Display for PyConstraints {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "Constraints: {:?}", self.constraints)
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(eq, eq_int, name = "TableType", module = "datafusion.common")]
+pub enum PyTableType {
+    Base,
+    View,
+    Temporary,
+}
+
+impl From<PyTableType> for datafusion::logical_expr::TableType {
+    fn from(table_type: PyTableType) -> Self {
+        match table_type {
+            PyTableType::Base => datafusion::logical_expr::TableType::Base,
+            PyTableType::View => datafusion::logical_expr::TableType::View,
+            PyTableType::Temporary => datafusion::logical_expr::TableType::Temporary,
+        }
+    }
+}
+
+impl From<TableType> for PyTableType {
+    fn from(table_type: TableType) -> Self {
+        match table_type {
+            datafusion::logical_expr::TableType::Base => PyTableType::Base,
+            datafusion::logical_expr::TableType::View => PyTableType::View,
+            datafusion::logical_expr::TableType::Temporary => PyTableType::Temporary,
+        }
+    }
+}
+
+#[pyclass(name = "TableSource", module = "datafusion.common", subclass)]
+#[derive(Clone)]
+pub struct PyTableSource {
+    pub table_source: Arc<dyn TableSource>,
+}
+
+#[pymethods]
+impl PyTableSource {
+    pub fn schema(&self) -> PyArrowType<Schema> {
+        (*self.table_source.schema()).clone().into()
+    }
+
+    pub fn constraints(&self) -> Option<PyConstraints> {
+        self.table_source.constraints().map(|c| PyConstraints {
+            constraints: c.clone(),
+        })
+    }
+
+    pub fn table_type(&self) -> PyTableType {
+        self.table_source.table_type().into()
+    }
+
+    pub fn get_logical_plan(&self) -> Option<PyLogicalPlan> {
+        self.table_source
+            .get_logical_plan()
+            .map(|plan| PyLogicalPlan::new(plan.into_owned()))
+    }
+}
diff --git a/src/config.rs b/src/config.rs
index 667d5c590..20f22196c 100644
--- a/src/config.rs
+++ b/src/config.rs
@@ -18,10 +18,10 @@
 use pyo3::prelude::*;
 use pyo3::types::*;
 
-use datafusion::common::ScalarValue;
 use datafusion::config::ConfigOptions;
 
 use crate::errors::PyDataFusionResult;
+use crate::utils::py_obj_to_scalar_value;
 
 #[pyclass(name = "Config", module = "datafusion", subclass)]
 #[derive(Clone)]
@@ -59,7 +59,7 @@ impl PyConfig {
 
     /// Set a configuration option
     pub fn set(&mut self, key: &str, value: PyObject, py: Python) -> PyDataFusionResult<()> {
-        let scalar_value = py_obj_to_scalar_value(py, value);
+        let scalar_value = py_obj_to_scalar_value(py, value)?;
         self.config.set(key, scalar_value.to_string().as_str())?;
         Ok(())
     }
@@ -82,20 +82,3 @@ impl PyConfig {
         }
     }
 }
-
-/// Convert a python object to a ScalarValue
-fn py_obj_to_scalar_value(py: Python, obj: PyObject) -> ScalarValue {
-    if let Ok(value) = obj.extract::<bool>(py) {
-        ScalarValue::Boolean(Some(value))
-    } else if let Ok(value) = obj.extract::<i64>(py) {
-        ScalarValue::Int64(Some(value))
-    } else if let Ok(value) = obj.extract::<u64>(py) {
-        ScalarValue::UInt64(Some(value))
-    } else if let Ok(value) = obj.extract::<f64>(py) {
-        ScalarValue::Float64(Some(value))
-    } else if let Ok(value) = obj.extract::<String>(py) {
-        ScalarValue::Utf8(Some(value))
-    } else {
-        panic!("Unsupported value type")
-    }
-}
diff --git a/src/context.rs b/src/context.rs
index 0db0f4d7e..cc3d8e8e9 100644
--- a/src/context.rs
+++ b/src/context.rs
@@ -43,6 +43,7 @@ use crate::sql::logical::PyLogicalPlan;
 use crate::store::StorageContexts;
 use crate::udaf::PyAggregateUDF;
 use crate::udf::PyScalarUDF;
+use crate::udtf::PyTableFunction;
 use crate::udwf::PyWindowUDF;
 use crate::utils::{get_global_ctx, get_tokio_runtime, validate_pycapsule, wait_for_future};
 use datafusion::arrow::datatypes::{DataType, Schema, SchemaRef};
@@ -390,6 +391,12 @@ impl PySessionContext {
         Ok(())
     }
 
+    pub fn register_udtf(&mut self, func: PyTableFunction) {
+        let name = func.name.clone();
+        let func = Arc::new(func);
+        self.ctx.register_udtf(&name, func);
+    }
+
     /// Returns a PyDataFrame whose plan corresponds to the SQL statement.
     pub fn sql(&mut self, query: &str, py: Python) -> PyDataFusionResult<PyDataFrame> {
         let result = self.ctx.sql(query);
diff --git a/src/dataframe.rs b/src/dataframe.rs
index 243e2e14f..ece8c4e0f 100644
--- a/src/dataframe.rs
+++ b/src/dataframe.rs
@@ -23,7 +23,6 @@ use arrow::compute::can_cast_types;
 use arrow::error::ArrowError;
 use arrow::ffi::FFI_ArrowSchema;
 use arrow::ffi_stream::FFI_ArrowArrayStream;
-use arrow::util::display::{ArrayFormatter, FormatOptions};
 use datafusion::arrow::datatypes::Schema;
 use datafusion::arrow::pyarrow::{PyArrowType, ToPyArrow};
 use datafusion::arrow::util::pretty;
@@ -31,13 +30,16 @@ use datafusion::common::UnnestOptions;
 use datafusion::config::{CsvOptions, TableParquetOptions};
 use datafusion::dataframe::{DataFrame, DataFrameWriteOptions};
 use datafusion::datasource::TableProvider;
+use datafusion::error::DataFusionError;
 use datafusion::execution::SendableRecordBatchStream;
 use datafusion::parquet::basic::{BrotliLevel, Compression, GzipLevel, ZstdLevel};
 use datafusion::prelude::*;
+use datafusion_ffi::table_provider::FFI_TableProvider;
+use futures::{StreamExt, TryStreamExt};
 use pyo3::exceptions::PyValueError;
 use pyo3::prelude::*;
 use pyo3::pybacked::PyBackedStr;
-use pyo3::types::{PyCapsule, PyTuple, PyTupleMethods};
+use pyo3::types::{PyCapsule, PyList, PyTuple, PyTupleMethods};
 use tokio::task::JoinHandle;
 
 use crate::catalog::PyTable;
@@ -46,7 +48,9 @@ use crate::expr::sort_expr::to_sort_expressions;
 use crate::physical_plan::PyExecutionPlan;
 use crate::record_batch::PyRecordBatchStream;
 use crate::sql::logical::PyLogicalPlan;
-use crate::utils::{get_tokio_runtime, validate_pycapsule, wait_for_future};
+use crate::utils::{
+    get_tokio_runtime, py_obj_to_scalar_value, validate_pycapsule, wait_for_future,
+};
 use crate::{
     errors::PyDataFusionResult,
     expr::{sort_expr::PySortExpr, PyExpr},
@@ -57,7 +61,7 @@ use crate::{
 // this is an interim implementation
 #[pyclass(name = "TableProvider", module = "datafusion")]
 pub struct PyTableProvider {
-    provider: Arc<dyn TableProvider>,
+    provider: Arc<dyn TableProvider + Send>,
 }
 
 impl PyTableProvider {
@@ -71,6 +75,116 @@ impl PyTableProvider {
     }
 }
 
+#[pymethods]
+impl PyTableProvider {
+    fn __datafusion_table_provider__<'py>(
+        &self,
+        py: Python<'py>,
+    ) -> PyResult<Bound<'py, PyCapsule>> {
+        let name = CString::new("datafusion_table_provider").unwrap();
+
+        let runtime = get_tokio_runtime().0.handle().clone();
+        let provider = FFI_TableProvider::new(Arc::clone(&self.provider), false, Some(runtime));
+
+        PyCapsule::new(py, provider, Some(name.clone()))
+    }
+}
+
+/// Configuration for DataFrame display formatting
+#[derive(Debug, Clone)]
+pub struct FormatterConfig {
+    /// Maximum memory in bytes to use for display (default: 2MB)
+    pub max_bytes: usize,
+    /// Minimum number of rows to display (default: 20)
+    pub min_rows: usize,
+    /// Number of rows to include in __repr__ output (default: 10)
+    pub repr_rows: usize,
+}
+
+impl Default for FormatterConfig {
+    fn default() -> Self {
+        Self {
+            max_bytes: 2 * 1024 * 1024, // 2MB
+            min_rows: 20,
+            repr_rows: 10,
+        }
+    }
+}
+
+impl FormatterConfig {
+    /// Validates that all configuration values are positive integers.
+    ///
+    /// # Returns
+    ///
+    /// `Ok(())` if all values are valid, or an `Err` with a descriptive error message.
+    pub fn validate(&self) -> Result<(), String> {
+        if self.max_bytes == 0 {
+            return Err("max_bytes must be a positive integer".to_string());
+        }
+
+        if self.min_rows == 0 {
+            return Err("min_rows must be a positive integer".to_string());
+        }
+
+        if self.repr_rows == 0 {
+            return Err("repr_rows must be a positive integer".to_string());
+        }
+
+        Ok(())
+    }
+}
+
+/// Holds the Python formatter and its configuration
+struct PythonFormatter<'py> {
+    /// The Python formatter object
+    formatter: Bound<'py, PyAny>,
+    /// The formatter configuration
+    config: FormatterConfig,
+}
+
+/// Get the Python formatter and its configuration
+fn get_python_formatter_with_config(py: Python) -> PyResult<PythonFormatter> {
+    let formatter = import_python_formatter(py)?;
+    let config = build_formatter_config_from_python(&formatter)?;
+    Ok(PythonFormatter { formatter, config })
+}
+
+/// Get the Python formatter from the datafusion.html_formatter module
+fn import_python_formatter(py: Python) -> PyResult<Bound<'_, PyAny>> {
+    let formatter_module = py.import("datafusion.html_formatter")?;
+    let get_formatter = formatter_module.getattr("get_formatter")?;
+    get_formatter.call0()
+}
+
+// Helper function to extract attributes with fallback to default
+fn get_attr<'a, T>(py_object: &'a Bound<'a, PyAny>, attr_name: &str, default_value: T) -> T
+where
+    T: for<'py> pyo3::FromPyObject<'py> + Clone,
+{
+    py_object
+        .getattr(attr_name)
+        .and_then(|v| v.extract::<T>())
+        .unwrap_or_else(|_| default_value.clone())
+}
+
+/// Helper function to create a FormatterConfig from a Python formatter object
+fn build_formatter_config_from_python(formatter: &Bound<'_, PyAny>) -> PyResult<FormatterConfig> {
+    let default_config = FormatterConfig::default();
+    let max_bytes = get_attr(formatter, "max_memory_bytes", default_config.max_bytes);
+    let min_rows = get_attr(formatter, "min_rows_display", default_config.min_rows);
+    let repr_rows = get_attr(formatter, "repr_rows", default_config.repr_rows);
+
+    let config = FormatterConfig {
+        max_bytes,
+        min_rows,
+        repr_rows,
+    };
+
+    // Return the validated config, converting String error to PyErr
+    config.validate().map_err(PyValueError::new_err)?;
+    Ok(config)
+}
+
 /// A PyDataFrame is a representation of a logical plan and an API to compose statements.
 /// Use it to build a plan and `.collect()` to execute the plan and collect the result.
 /// The actual execution of a plan runs natively on Rust and Arrow on a multi-threaded environment.
@@ -111,56 +225,62 @@ impl PyDataFrame {
     }
 
     fn __repr__(&self, py: Python) -> PyDataFusionResult<String> {
-        let df = self.df.as_ref().clone().limit(0, Some(10))?;
-        let batches = wait_for_future(py, df.collect())?;
-        let batches_as_string = pretty::pretty_format_batches(&batches);
-        match batches_as_string {
-            Ok(batch) => Ok(format!("DataFrame()\n{batch}")),
-            Err(err) => Ok(format!("Error: {:?}", err.to_string())),
+        // Get the Python formatter config
+        let PythonFormatter {
+            formatter: _,
+            config,
+        } = get_python_formatter_with_config(py)?;
+        let (batches, has_more) = wait_for_future(
+            py,
+            collect_record_batches_to_display(self.df.as_ref().clone(), config),
+        )?;
+        if batches.is_empty() {
+            // This should not be reached, but do it for safety since we index into the vector below
+            return Ok("No data to display".to_string());
         }
-    }
 
-    fn _repr_html_(&self, py: Python) -> PyDataFusionResult<String> {
-        let mut html_str = "<table border='1'>\n".to_string();
+        let batches_as_displ =
+            pretty::pretty_format_batches(&batches).map_err(py_datafusion_err)?;
 
-        let df = self.df.as_ref().clone().limit(0, Some(10))?;
-        let batches = wait_for_future(py, df.collect())?;
+        let additional_str = match has_more {
+            true => "\nData truncated.",
+            false => "",
+        };
 
+        Ok(format!("DataFrame()\n{batches_as_displ}{additional_str}"))
+    }
+
+    fn _repr_html_(&self, py: Python) -> PyDataFusionResult<String> {
+        // Get the Python formatter and config
+        let PythonFormatter { formatter, config } = get_python_formatter_with_config(py)?;
+        let (batches, has_more) = wait_for_future(
+            py,
+            collect_record_batches_to_display(self.df.as_ref().clone(), config),
+        )?;
         if batches.is_empty() {
-            html_str.push_str("</table>\n");
-            return Ok(html_str);
+            // This should not be reached, but do it for safety since we index into the vector below
+            return Ok("No data to display".to_string());
         }
 
-        let schema = batches[0].schema();
+        let table_uuid = uuid::Uuid::new_v4().to_string();
 
-        let mut header = Vec::new();
-        for field in schema.fields() {
-            header.push(format!("<th>{}</td>", field.name()));
-        }
-        let header_str = header.join("");
-        html_str.push_str(&format!("<tr>{}</tr>\n", header_str));
+        // Convert record batches to PyObject list
+        let py_batches = batches
+            .into_iter()
+            .map(|rb| rb.to_pyarrow(py))
+            .collect::<PyResult<Vec<PyObject>>>()?;
 
-        for batch in batches {
-            let formatters = batch
-                .columns()
-                .iter()
-                .map(|c| ArrayFormatter::try_new(c.as_ref(), &FormatOptions::default()))
-                .map(|c| {
-                    c.map_err(|e| PyValueError::new_err(format!("Error: {:?}", e.to_string())))
-                })
-                .collect::<Result<Vec<_>, _>>()?;
-
-            for row in 0..batch.num_rows() {
-                let mut cells = Vec::new();
-                for formatter in &formatters {
-                    cells.push(format!("<td>{}</td>", formatter.value(row)));
-                }
-                let row_str = cells.join("");
-                html_str.push_str(&format!("<tr>{}</tr>\n", row_str));
-            }
-        }
+        let py_schema = self.schema().into_pyobject(py)?;
 
-        html_str.push_str("</table>\n");
+        let kwargs = pyo3::types::PyDict::new(py);
+        let py_batches_list = PyList::new(py, py_batches.as_slice())?;
+        kwargs.set_item("batches", py_batches_list)?;
+        kwargs.set_item("schema", py_schema)?;
+        kwargs.set_item("has_more", has_more)?;
+        kwargs.set_item("table_uuid", table_uuid)?;
+
+        let html_result = formatter.call_method("format_html", (), Some(&kwargs))?;
+        let html_str: String = html_result.extract()?;
 
         Ok(html_str)
     }
@@ -204,7 +324,7 @@ impl PyDataFrame {
 
     #[pyo3(signature = (*args))]
     fn select(&self, args: Vec<PyExpr>) -> PyDataFusionResult<Self> {
-        let expr = args.into_iter().map(|e| e.into()).collect();
+        let expr: Vec<Expr> = args.into_iter().map(|e| e.into()).collect();
         let df = self.df.as_ref().clone().select(expr)?;
         Ok(Self::new(df))
     }
@@ -697,6 +817,25 @@ impl PyDataFrame {
     fn count(&self, py: Python) -> PyDataFusionResult<usize> {
         Ok(wait_for_future(py, self.df.as_ref().clone().count())?)
     }
+
+    /// Fill null values with a specified value for specific columns
+    #[pyo3(signature = (value, columns=None))]
+    fn fill_null(
+        &self,
+        value: PyObject,
+        columns: Option<Vec<PyBackedStr>>,
+        py: Python,
+    ) -> PyDataFusionResult<Self> {
+        let scalar_value = py_obj_to_scalar_value(py, value)?;
+
+        let cols = match columns {
+            Some(col_names) => col_names.iter().map(|c| c.to_string()).collect(),
+            None => Vec::new(), // Empty vector means fill null for all columns
+        };
+
+        let df = self.df.as_ref().clone().fill_null(scalar_value, cols)?;
+        Ok(Self::new(df))
+    }
 }
 
 /// Print DataFrame
@@ -735,7 +874,7 @@ fn record_batch_into_schema(
 ) -> Result<RecordBatch, ArrowError> {
     let schema = Arc::new(schema.clone());
     let base_schema = record_batch.schema();
-    if base_schema.fields().len() == 0 {
+    if base_schema.fields().is_empty() {
         // Nothing to project
         return Ok(RecordBatch::new_empty(schema));
     }
@@ -771,3 +910,87 @@ fn record_batch_into_schema(
 
     RecordBatch::try_new(schema, data_arrays)
 }
+
+/// This is a helper function to return the first non-empty record batch from executing a DataFrame.
+/// It additionally returns a bool, which indicates if there are more record batches available.
+/// We do this so we can determine if we should indicate to the user that the data has been
+/// truncated. This collects until we have achived both of these two conditions
+///
+/// - We have collected our minimum number of rows
+/// - We have reached our limit, either data size or maximum number of rows
+///
+/// Otherwise it will return when the stream has exhausted. If you want a specific number of
+/// rows, set min_rows == max_rows.
+async fn collect_record_batches_to_display(
+    df: DataFrame,
+    config: FormatterConfig,
+) -> Result<(Vec<RecordBatch>, bool), DataFusionError> {
+    let FormatterConfig {
+        max_bytes,
+        min_rows,
+        repr_rows,
+    } = config;
+
+    let partitioned_stream = df.execute_stream_partitioned().await?;
+    let mut stream = futures::stream::iter(partitioned_stream).flatten();
+    let mut size_estimate_so_far = 0;
+    let mut rows_so_far = 0;
+    let mut record_batches = Vec::default();
+    let mut has_more = false;
+
+    // ensure minimum rows even if memory/row limits are hit
+    while (size_estimate_so_far < max_bytes && rows_so_far < repr_rows) || rows_so_far < min_rows {
+        let mut rb = match stream.next().await {
+            None => {
+                break;
+            }
+            Some(Ok(r)) => r,
+            Some(Err(e)) => return Err(e),
+        };
+
+        let mut rows_in_rb = rb.num_rows();
+        if rows_in_rb > 0 {
+            size_estimate_so_far += rb.get_array_memory_size();
+
+            if size_estimate_so_far > max_bytes {
+                let ratio = max_bytes as f32 / size_estimate_so_far as f32;
+                let total_rows = rows_in_rb + rows_so_far;
+
+                let mut reduced_row_num = (total_rows as f32 * ratio).round() as usize;
+                if reduced_row_num < min_rows {
+                    reduced_row_num = min_rows.min(total_rows);
+                }
+
+                let limited_rows_this_rb = reduced_row_num - rows_so_far;
+                if limited_rows_this_rb < rows_in_rb {
+                    rows_in_rb = limited_rows_this_rb;
+                    rb = rb.slice(0, limited_rows_this_rb);
+                    has_more = true;
+                }
+            }
+
+            if rows_in_rb + rows_so_far > repr_rows {
+                rb = rb.slice(0, repr_rows - rows_so_far);
+                has_more = true;
+            }
+
+            rows_so_far += rb.num_rows();
+            record_batches.push(rb);
+        }
+    }
+
+    if record_batches.is_empty() {
+        return Ok((Vec::default(), false));
+    }
+
+    if !has_more {
+        // Data was not already truncated, so check to see if more record batches remain
+        has_more = match stream.try_next().await {
+            Ok(None) => false, // reached end
+            Ok(Some(_)) => true,
+            Err(_) => false, // Stream disconnected
+        };
+    }
+
+    Ok((record_batches, has_more))
+}
diff --git a/src/dataset_exec.rs b/src/dataset_exec.rs
index 445e4fe74..aab8d7566 100644
--- a/src/dataset_exec.rs
+++ b/src/dataset_exec.rs
@@ -275,7 +275,9 @@ impl DisplayAs for DatasetExec {
         Python::with_gil(|py| {
             let number_of_fragments = self.fragments.bind(py).len();
             match t {
-                DisplayFormatType::Default | DisplayFormatType::Verbose => {
+                DisplayFormatType::Default
+                | DisplayFormatType::Verbose
+                | DisplayFormatType::TreeRender => {
                     let projected_columns: Vec<String> = self
                         .schema
                         .fields()
diff --git a/src/errors.rs b/src/errors.rs
index f1d5aeb23..d4f4f221d 100644
--- a/src/errors.rs
+++ b/src/errors.rs
@@ -28,7 +28,7 @@ pub type PyDataFusionResult<T> = std::result::Result<T, PyDataFusionError>;
 
 #[derive(Debug)]
 pub enum PyDataFusionError {
-    ExecutionError(InnerDataFusionError),
+    ExecutionError(Box<InnerDataFusionError>),
     ArrowError(ArrowError),
     Common(String),
     PythonError(PyErr),
@@ -55,7 +55,7 @@ impl From<ArrowError> for PyDataFusionError {
 
 impl From<InnerDataFusionError> for PyDataFusionError {
     fn from(err: InnerDataFusionError) -> PyDataFusionError {
-        PyDataFusionError::ExecutionError(err)
+        PyDataFusionError::ExecutionError(Box::new(err))
     }
 }
 
diff --git a/src/expr.rs b/src/expr.rs
index d3c528eb4..bc7dbeffd 100644
--- a/src/expr.rs
+++ b/src/expr.rs
@@ -15,12 +15,14 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use datafusion::logical_expr::expr::{AggregateFunctionParams, WindowFunctionParams};
 use datafusion::logical_expr::utils::exprlist_to_fields;
 use datafusion::logical_expr::{
     ExprFuncBuilder, ExprFunctionExt, LogicalPlan, WindowFunctionDefinition,
 };
 use pyo3::IntoPyObjectExt;
 use pyo3::{basic::CompareOp, prelude::*};
+use std::collections::HashMap;
 use std::convert::{From, Into};
 use std::sync::Arc;
 use window::PyWindowFrame;
@@ -35,9 +37,7 @@ use datafusion::logical_expr::{
 };
 
 use crate::common::data_type::{DataTypeMap, NullTreatment, PyScalarValue, RexType};
-use crate::errors::{
-    py_runtime_err, py_type_err, py_unsupported_variant_err, PyDataFusionError, PyDataFusionResult,
-};
+use crate::errors::{py_runtime_err, py_type_err, py_unsupported_variant_err, PyDataFusionResult};
 use crate::expr::aggregate_expr::PyAggregateFunction;
 use crate::expr::binary_expr::PyBinaryExpr;
 use crate::expr::column::PyColumn;
@@ -65,10 +65,21 @@ pub mod case;
 pub mod cast;
 pub mod column;
 pub mod conditional_expr;
+pub mod copy_to;
+pub mod create_catalog;
+pub mod create_catalog_schema;
+pub mod create_external_table;
+pub mod create_function;
+pub mod create_index;
 pub mod create_memory_table;
 pub mod create_view;
+pub mod describe_table;
 pub mod distinct;
+pub mod dml;
+pub mod drop_catalog_schema;
+pub mod drop_function;
 pub mod drop_table;
+pub mod drop_view;
 pub mod empty_relation;
 pub mod exists;
 pub mod explain;
@@ -84,18 +95,21 @@ pub mod literal;
 pub mod logical_node;
 pub mod placeholder;
 pub mod projection;
+pub mod recursive_query;
 pub mod repartition;
 pub mod scalar_subquery;
 pub mod scalar_variable;
 pub mod signature;
 pub mod sort;
 pub mod sort_expr;
+pub mod statement;
 pub mod subquery;
 pub mod subquery_alias;
 pub mod table_scan;
 pub mod union;
 pub mod unnest;
 pub mod unnest_expr;
+pub mod values;
 pub mod window;
 
 use sort_expr::{to_sort_expressions, PySortExpr};
@@ -172,6 +186,7 @@ impl PyExpr {
             Expr::ScalarSubquery(value) => {
                 Ok(scalar_subquery::PyScalarSubquery::from(value.clone()).into_bound_py_any(py)?)
             }
+            #[allow(deprecated)]
             Expr::Wildcard { qualifier, options } => Err(py_unsupported_variant_err(format!(
                 "Converting Expr::Wildcard to a Python object is not implemented : {:?} {:?}",
                 qualifier, options
@@ -273,8 +288,9 @@ impl PyExpr {
     }
 
     /// assign a name to the PyExpr
-    pub fn alias(&self, name: &str) -> PyExpr {
-        self.expr.clone().alias(name).into()
+    #[pyo3(signature = (name, metadata=None))]
+    pub fn alias(&self, name: &str, metadata: Option<HashMap<String, String>>) -> PyExpr {
+        self.expr.clone().alias_with_metadata(name, metadata).into()
     }
 
     /// Create a sort PyExpr from an existing PyExpr.
@@ -332,7 +348,6 @@ impl PyExpr {
             | Expr::AggregateFunction { .. }
             | Expr::WindowFunction { .. }
             | Expr::InList { .. }
-            | Expr::Wildcard { .. }
             | Expr::Exists { .. }
             | Expr::InSubquery { .. }
             | Expr::GroupingSet(..)
@@ -346,6 +361,10 @@ impl PyExpr {
             | Expr::Unnest(_)
             | Expr::IsNotUnknown(_) => RexType::Call,
             Expr::ScalarSubquery(..) => RexType::ScalarSubquery,
+            #[allow(deprecated)]
+            Expr::Wildcard { .. } => {
+                return Err(py_unsupported_variant_err("Expr::Wildcard is unsupported"))
+            }
         })
     }
 
@@ -394,11 +413,15 @@ impl PyExpr {
             | Expr::InSubquery(InSubquery { expr, .. }) => Ok(vec![PyExpr::from(*expr.clone())]),
 
             // Expr variants containing a collection of Expr(s) for operands
-            Expr::AggregateFunction(AggregateFunction { args, .. })
+            Expr::AggregateFunction(AggregateFunction {
+                params: AggregateFunctionParams { args, .. },
+                ..
+            })
             | Expr::ScalarFunction(ScalarFunction { args, .. })
-            | Expr::WindowFunction(WindowFunction { args, .. }) => {
-                Ok(args.iter().map(|arg| PyExpr::from(arg.clone())).collect())
-            }
+            | Expr::WindowFunction(WindowFunction {
+                params: WindowFunctionParams { args, .. },
+                ..
+            }) => Ok(args.iter().map(|arg| PyExpr::from(arg.clone())).collect()),
 
             // Expr(s) that require more specific processing
             Expr::Case(Case {
@@ -465,13 +488,17 @@ impl PyExpr {
             Expr::GroupingSet(..)
             | Expr::Unnest(_)
             | Expr::OuterReferenceColumn(_, _)
-            | Expr::Wildcard { .. }
             | Expr::ScalarSubquery(..)
             | Expr::Placeholder { .. }
             | Expr::Exists { .. } => Err(py_runtime_err(format!(
                 "Unimplemented Expr type: {}",
                 self.expr
             ))),
+
+            #[allow(deprecated)]
+            Expr::Wildcard { .. } => {
+                Err(py_unsupported_variant_err("Expr::Wildcard is unsupported"))
+            }
         }
     }
 
@@ -575,7 +602,7 @@ impl PyExpr {
             Expr::AggregateFunction(agg_fn) => {
                 let window_fn = Expr::WindowFunction(WindowFunction::new(
                     WindowFunctionDefinition::AggregateUDF(agg_fn.func.clone()),
-                    agg_fn.args.clone(),
+                    agg_fn.params.args.clone(),
                 ));
 
                 add_builder_fns_to_window(
@@ -593,11 +620,11 @@ impl PyExpr {
                 order_by,
                 null_treatment,
             ),
-            _ => Err(
-                PyDataFusionError::ExecutionError(datafusion::error::DataFusionError::Plan(
-                    format!("Using {} with `over` is not allowed. Must use an aggregate or window function.", self.expr.variant_name()),
-                ))
-            ),
+            _ => Err(datafusion::error::DataFusionError::Plan(format!(
+                "Using {} with `over` is not allowed. Must use an aggregate or window function.",
+                self.expr.variant_name()
+            ))
+            .into()),
         }
     }
 }
@@ -663,16 +690,8 @@ impl PyExpr {
 
     /// Create a [Field] representing an [Expr], given an input [LogicalPlan] to resolve against
     pub fn expr_to_field(expr: &Expr, input_plan: &LogicalPlan) -> PyDataFusionResult<Arc<Field>> {
-        match expr {
-            Expr::Wildcard { .. } => {
-                // Since * could be any of the valid column names just return the first one
-                Ok(Arc::new(input_plan.schema().field(0).clone()))
-            }
-            _ => {
-                let fields = exprlist_to_fields(&[expr.clone()], input_plan)?;
-                Ok(fields[0].1.clone())
-            }
-        }
+        let fields = exprlist_to_fields(&[expr.clone()], input_plan)?;
+        Ok(fields[0].1.clone())
     }
     fn _types(expr: &Expr) -> PyResult<DataTypeMap> {
         match expr {
@@ -709,9 +728,19 @@ impl PyExpr {
                 | Operator::BitwiseXor
                 | Operator::BitwiseAnd
                 | Operator::BitwiseOr => DataTypeMap::map_from_arrow_type(&DataType::Binary),
-                Operator::AtArrow | Operator::ArrowAt => {
-                    Err(py_type_err(format!("Unsupported expr: ${op}")))
-                }
+                Operator::AtArrow
+                | Operator::ArrowAt
+                | Operator::Arrow
+                | Operator::LongArrow
+                | Operator::HashArrow
+                | Operator::HashLongArrow
+                | Operator::AtAt
+                | Operator::IntegerDivide
+                | Operator::HashMinus
+                | Operator::AtQuestion
+                | Operator::Question
+                | Operator::QuestionAnd
+                | Operator::QuestionPipe => Err(py_type_err(format!("Unsupported expr: ${op}"))),
             },
             Expr::Cast(Cast { expr: _, data_type }) => DataTypeMap::map_from_arrow_type(data_type),
             Expr::Literal(scalar_value) => DataTypeMap::map_from_scalar_value(scalar_value),
@@ -785,5 +814,32 @@ pub(crate) fn init_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<window::PyWindowExpr>()?;
     m.add_class::<window::PyWindowFrame>()?;
     m.add_class::<window::PyWindowFrameBound>()?;
+    m.add_class::<copy_to::PyCopyTo>()?;
+    m.add_class::<copy_to::PyFileType>()?;
+    m.add_class::<create_catalog::PyCreateCatalog>()?;
+    m.add_class::<create_catalog_schema::PyCreateCatalogSchema>()?;
+    m.add_class::<create_external_table::PyCreateExternalTable>()?;
+    m.add_class::<create_function::PyCreateFunction>()?;
+    m.add_class::<create_function::PyOperateFunctionArg>()?;
+    m.add_class::<create_function::PyCreateFunctionBody>()?;
+    m.add_class::<create_index::PyCreateIndex>()?;
+    m.add_class::<describe_table::PyDescribeTable>()?;
+    m.add_class::<dml::PyDmlStatement>()?;
+    m.add_class::<drop_catalog_schema::PyDropCatalogSchema>()?;
+    m.add_class::<drop_function::PyDropFunction>()?;
+    m.add_class::<drop_view::PyDropView>()?;
+    m.add_class::<recursive_query::PyRecursiveQuery>()?;
+
+    m.add_class::<statement::PyTransactionStart>()?;
+    m.add_class::<statement::PyTransactionEnd>()?;
+    m.add_class::<statement::PySetVariable>()?;
+    m.add_class::<statement::PyPrepare>()?;
+    m.add_class::<statement::PyExecute>()?;
+    m.add_class::<statement::PyDeallocate>()?;
+    m.add_class::<values::PyValues>()?;
+    m.add_class::<statement::PyTransactionAccessMode>()?;
+    m.add_class::<statement::PyTransactionConclusion>()?;
+    m.add_class::<statement::PyTransactionIsolationLevel>()?;
+
     Ok(())
 }
diff --git a/src/expr/aggregate.rs b/src/expr/aggregate.rs
index 8fc9da5b0..a99d83d23 100644
--- a/src/expr/aggregate.rs
+++ b/src/expr/aggregate.rs
@@ -16,7 +16,7 @@
 // under the License.
 
 use datafusion::common::DataFusionError;
-use datafusion::logical_expr::expr::{AggregateFunction, Alias};
+use datafusion::logical_expr::expr::{AggregateFunction, AggregateFunctionParams, Alias};
 use datafusion::logical_expr::logical_plan::Aggregate;
 use datafusion::logical_expr::Expr;
 use pyo3::{prelude::*, IntoPyObjectExt};
@@ -126,9 +126,11 @@ impl PyAggregate {
         match expr {
             // TODO: This Alias logic seems to be returning some strange results that we should investigate
             Expr::Alias(Alias { expr, .. }) => self._aggregation_arguments(expr.as_ref()),
-            Expr::AggregateFunction(AggregateFunction { func: _, args, .. }) => {
-                Ok(args.iter().map(|e| PyExpr::from(e.clone())).collect())
-            }
+            Expr::AggregateFunction(AggregateFunction {
+                func: _,
+                params: AggregateFunctionParams { args, .. },
+                ..
+            }) => Ok(args.iter().map(|e| PyExpr::from(e.clone())).collect()),
             _ => Err(py_type_err(
                 "Encountered a non Aggregate type in aggregation_arguments",
             )),
diff --git a/src/expr/aggregate_expr.rs b/src/expr/aggregate_expr.rs
index 09471097f..c09f116e3 100644
--- a/src/expr/aggregate_expr.rs
+++ b/src/expr/aggregate_expr.rs
@@ -40,7 +40,13 @@ impl From<AggregateFunction> for PyAggregateFunction {
 
 impl Display for PyAggregateFunction {
     fn fmt(&self, f: &mut Formatter) -> std::fmt::Result {
-        let args: Vec<String> = self.aggr.args.iter().map(|expr| expr.to_string()).collect();
+        let args: Vec<String> = self
+            .aggr
+            .params
+            .args
+            .iter()
+            .map(|expr| expr.to_string())
+            .collect();
         write!(f, "{}({})", self.aggr.func.name(), args.join(", "))
     }
 }
@@ -54,12 +60,13 @@ impl PyAggregateFunction {
 
     /// is this a distinct aggregate such as `COUNT(DISTINCT expr)`
     fn is_distinct(&self) -> bool {
-        self.aggr.distinct
+        self.aggr.params.distinct
     }
 
     /// Get the arguments to the aggregate function
     fn args(&self) -> Vec<PyExpr> {
         self.aggr
+            .params
             .args
             .iter()
             .map(|expr| PyExpr::from(expr.clone()))
diff --git a/src/expr/copy_to.rs b/src/expr/copy_to.rs
new file mode 100644
index 000000000..ebfcb8ebc
--- /dev/null
+++ b/src/expr/copy_to.rs
@@ -0,0 +1,138 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    collections::HashMap,
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::{common::file_options::file_type::FileType, logical_expr::dml::CopyTo};
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::sql::logical::PyLogicalPlan;
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "CopyTo", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCopyTo {
+    copy: CopyTo,
+}
+
+impl From<PyCopyTo> for CopyTo {
+    fn from(copy: PyCopyTo) -> Self {
+        copy.copy
+    }
+}
+
+impl From<CopyTo> for PyCopyTo {
+    fn from(copy: CopyTo) -> PyCopyTo {
+        PyCopyTo { copy }
+    }
+}
+
+impl Display for PyCopyTo {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "CopyTo: {:?}", self.copy.output_url)
+    }
+}
+
+impl LogicalNode for PyCopyTo {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![PyLogicalPlan::from((*self.copy.input).clone())]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyCopyTo {
+    #[new]
+    pub fn new(
+        input: PyLogicalPlan,
+        output_url: String,
+        partition_by: Vec<String>,
+        file_type: PyFileType,
+        options: HashMap<String, String>,
+    ) -> Self {
+        PyCopyTo {
+            copy: CopyTo {
+                input: input.plan(),
+                output_url,
+                partition_by,
+                file_type: file_type.file_type,
+                options,
+            },
+        }
+    }
+
+    fn input(&self) -> PyLogicalPlan {
+        PyLogicalPlan::from((*self.copy.input).clone())
+    }
+
+    fn output_url(&self) -> String {
+        self.copy.output_url.clone()
+    }
+
+    fn partition_by(&self) -> Vec<String> {
+        self.copy.partition_by.clone()
+    }
+
+    fn file_type(&self) -> PyFileType {
+        PyFileType {
+            file_type: self.copy.file_type.clone(),
+        }
+    }
+
+    fn options(&self) -> HashMap<String, String> {
+        self.copy.options.clone()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CopyTo({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CopyTo".to_string())
+    }
+}
+
+#[pyclass(name = "FileType", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyFileType {
+    file_type: Arc<dyn FileType>,
+}
+
+impl Display for PyFileType {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "FileType: {}", self.file_type)
+    }
+}
+
+#[pymethods]
+impl PyFileType {
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("FileType({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("FileType".to_string())
+    }
+}
diff --git a/src/expr/create_catalog.rs b/src/expr/create_catalog.rs
new file mode 100644
index 000000000..f4ea0f517
--- /dev/null
+++ b/src/expr/create_catalog.rs
@@ -0,0 +1,100 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::CreateCatalog;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "CreateCatalog", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateCatalog {
+    create: CreateCatalog,
+}
+
+impl From<PyCreateCatalog> for CreateCatalog {
+    fn from(create: PyCreateCatalog) -> Self {
+        create.create
+    }
+}
+
+impl From<CreateCatalog> for PyCreateCatalog {
+    fn from(create: CreateCatalog) -> PyCreateCatalog {
+        PyCreateCatalog { create }
+    }
+}
+
+impl Display for PyCreateCatalog {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "CreateCatalog: {:?}", self.create.catalog_name)
+    }
+}
+
+#[pymethods]
+impl PyCreateCatalog {
+    #[new]
+    pub fn new(
+        catalog_name: String,
+        if_not_exists: bool,
+        schema: PyDFSchema,
+    ) -> PyResult<PyCreateCatalog> {
+        Ok(PyCreateCatalog {
+            create: CreateCatalog {
+                catalog_name,
+                if_not_exists,
+                schema: Arc::new(schema.into()),
+            },
+        })
+    }
+
+    pub fn catalog_name(&self) -> String {
+        self.create.catalog_name.clone()
+    }
+
+    pub fn if_not_exists(&self) -> bool {
+        self.create.if_not_exists
+    }
+
+    pub fn schema(&self) -> PyDFSchema {
+        (*self.create.schema).clone().into()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CreateCatalog({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CreateCatalog".to_string())
+    }
+}
+
+impl LogicalNode for PyCreateCatalog {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/create_catalog_schema.rs b/src/expr/create_catalog_schema.rs
new file mode 100644
index 000000000..85f447e1e
--- /dev/null
+++ b/src/expr/create_catalog_schema.rs
@@ -0,0 +1,100 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::CreateCatalogSchema;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "CreateCatalogSchema", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateCatalogSchema {
+    create: CreateCatalogSchema,
+}
+
+impl From<PyCreateCatalogSchema> for CreateCatalogSchema {
+    fn from(create: PyCreateCatalogSchema) -> Self {
+        create.create
+    }
+}
+
+impl From<CreateCatalogSchema> for PyCreateCatalogSchema {
+    fn from(create: CreateCatalogSchema) -> PyCreateCatalogSchema {
+        PyCreateCatalogSchema { create }
+    }
+}
+
+impl Display for PyCreateCatalogSchema {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "CreateCatalogSchema: {:?}", self.create.schema_name)
+    }
+}
+
+#[pymethods]
+impl PyCreateCatalogSchema {
+    #[new]
+    pub fn new(
+        schema_name: String,
+        if_not_exists: bool,
+        schema: PyDFSchema,
+    ) -> PyResult<PyCreateCatalogSchema> {
+        Ok(PyCreateCatalogSchema {
+            create: CreateCatalogSchema {
+                schema_name,
+                if_not_exists,
+                schema: Arc::new(schema.into()),
+            },
+        })
+    }
+
+    pub fn schema_name(&self) -> String {
+        self.create.schema_name.clone()
+    }
+
+    pub fn if_not_exists(&self) -> bool {
+        self.create.if_not_exists
+    }
+
+    pub fn schema(&self) -> PyDFSchema {
+        (*self.create.schema).clone().into()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CreateCatalogSchema({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CreateCatalogSchema".to_string())
+    }
+}
+
+impl LogicalNode for PyCreateCatalogSchema {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/create_external_table.rs b/src/expr/create_external_table.rs
new file mode 100644
index 000000000..01ce7d0ca
--- /dev/null
+++ b/src/expr/create_external_table.rs
@@ -0,0 +1,183 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use crate::{common::schema::PyConstraints, expr::PyExpr, sql::logical::PyLogicalPlan};
+use std::{
+    collections::HashMap,
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::CreateExternalTable;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::common::df_schema::PyDFSchema;
+
+use super::{logical_node::LogicalNode, sort_expr::PySortExpr};
+
+#[pyclass(name = "CreateExternalTable", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateExternalTable {
+    create: CreateExternalTable,
+}
+
+impl From<PyCreateExternalTable> for CreateExternalTable {
+    fn from(create: PyCreateExternalTable) -> Self {
+        create.create
+    }
+}
+
+impl From<CreateExternalTable> for PyCreateExternalTable {
+    fn from(create: CreateExternalTable) -> PyCreateExternalTable {
+        PyCreateExternalTable { create }
+    }
+}
+
+impl Display for PyCreateExternalTable {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(
+            f,
+            "CreateExternalTable: {:?}{}",
+            self.create.name, self.create.constraints
+        )
+    }
+}
+
+#[pymethods]
+impl PyCreateExternalTable {
+    #[allow(clippy::too_many_arguments)]
+    #[new]
+    #[pyo3(signature = (schema, name, location, file_type, table_partition_cols, if_not_exists, temporary, order_exprs, unbounded, options, constraints, column_defaults, definition=None))]
+    pub fn new(
+        schema: PyDFSchema,
+        name: String,
+        location: String,
+        file_type: String,
+        table_partition_cols: Vec<String>,
+        if_not_exists: bool,
+        temporary: bool,
+        order_exprs: Vec<Vec<PySortExpr>>,
+        unbounded: bool,
+        options: HashMap<String, String>,
+        constraints: PyConstraints,
+        column_defaults: HashMap<String, PyExpr>,
+        definition: Option<String>,
+    ) -> Self {
+        let create = CreateExternalTable {
+            schema: Arc::new(schema.into()),
+            name: name.into(),
+            location,
+            file_type,
+            table_partition_cols,
+            if_not_exists,
+            temporary,
+            definition,
+            order_exprs: order_exprs
+                .into_iter()
+                .map(|vec| vec.into_iter().map(|s| s.into()).collect::<Vec<_>>())
+                .collect::<Vec<_>>(),
+            unbounded,
+            options,
+            constraints: constraints.constraints,
+            column_defaults: column_defaults
+                .into_iter()
+                .map(|(k, v)| (k, v.into()))
+                .collect(),
+        };
+        PyCreateExternalTable { create }
+    }
+
+    pub fn schema(&self) -> PyDFSchema {
+        (*self.create.schema).clone().into()
+    }
+
+    pub fn name(&self) -> PyResult<String> {
+        Ok(self.create.name.to_string())
+    }
+
+    pub fn location(&self) -> String {
+        self.create.location.clone()
+    }
+
+    pub fn file_type(&self) -> String {
+        self.create.file_type.clone()
+    }
+
+    pub fn table_partition_cols(&self) -> Vec<String> {
+        self.create.table_partition_cols.clone()
+    }
+
+    pub fn if_not_exists(&self) -> bool {
+        self.create.if_not_exists
+    }
+
+    pub fn temporary(&self) -> bool {
+        self.create.temporary
+    }
+
+    pub fn definition(&self) -> Option<String> {
+        self.create.definition.clone()
+    }
+
+    pub fn order_exprs(&self) -> Vec<Vec<PySortExpr>> {
+        self.create
+            .order_exprs
+            .iter()
+            .map(|vec| vec.iter().map(|s| s.clone().into()).collect())
+            .collect()
+    }
+
+    pub fn unbounded(&self) -> bool {
+        self.create.unbounded
+    }
+
+    pub fn options(&self) -> HashMap<String, String> {
+        self.create.options.clone()
+    }
+
+    pub fn constraints(&self) -> PyConstraints {
+        PyConstraints {
+            constraints: self.create.constraints.clone(),
+        }
+    }
+
+    pub fn column_defaults(&self) -> HashMap<String, PyExpr> {
+        self.create
+            .column_defaults
+            .iter()
+            .map(|(k, v)| (k.clone(), v.clone().into()))
+            .collect()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CreateExternalTable({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CreateExternalTable".to_string())
+    }
+}
+
+impl LogicalNode for PyCreateExternalTable {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/create_function.rs b/src/expr/create_function.rs
new file mode 100644
index 000000000..6f3c3f0ff
--- /dev/null
+++ b/src/expr/create_function.rs
@@ -0,0 +1,182 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::{
+    CreateFunction, CreateFunctionBody, OperateFunctionArg, Volatility,
+};
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use super::logical_node::LogicalNode;
+use super::PyExpr;
+use crate::common::{data_type::PyDataType, df_schema::PyDFSchema};
+use crate::sql::logical::PyLogicalPlan;
+
+#[pyclass(name = "CreateFunction", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateFunction {
+    create: CreateFunction,
+}
+
+impl From<PyCreateFunction> for CreateFunction {
+    fn from(create: PyCreateFunction) -> Self {
+        create.create
+    }
+}
+
+impl From<CreateFunction> for PyCreateFunction {
+    fn from(create: CreateFunction) -> PyCreateFunction {
+        PyCreateFunction { create }
+    }
+}
+
+impl Display for PyCreateFunction {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "CreateFunction: name {:?}", self.create.name)
+    }
+}
+
+#[pyclass(name = "OperateFunctionArg", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyOperateFunctionArg {
+    arg: OperateFunctionArg,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(eq, eq_int, name = "Volatility", module = "datafusion.expr")]
+pub enum PyVolatility {
+    Immutable,
+    Stable,
+    Volatile,
+}
+
+#[pyclass(name = "CreateFunctionBody", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateFunctionBody {
+    body: CreateFunctionBody,
+}
+
+#[pymethods]
+impl PyCreateFunctionBody {
+    pub fn language(&self) -> Option<String> {
+        self.body
+            .language
+            .as_ref()
+            .map(|language| language.to_string())
+    }
+
+    pub fn behavior(&self) -> Option<PyVolatility> {
+        self.body.behavior.as_ref().map(|behavior| match behavior {
+            Volatility::Immutable => PyVolatility::Immutable,
+            Volatility::Stable => PyVolatility::Stable,
+            Volatility::Volatile => PyVolatility::Volatile,
+        })
+    }
+
+    pub fn function_body(&self) -> Option<PyExpr> {
+        self.body
+            .function_body
+            .as_ref()
+            .map(|function_body| function_body.clone().into())
+    }
+}
+
+#[pymethods]
+impl PyCreateFunction {
+    #[new]
+    #[pyo3(signature = (or_replace, temporary, name, params, schema, return_type=None, args=None))]
+    pub fn new(
+        or_replace: bool,
+        temporary: bool,
+        name: String,
+        params: PyCreateFunctionBody,
+        schema: PyDFSchema,
+        return_type: Option<PyDataType>,
+        args: Option<Vec<PyOperateFunctionArg>>,
+    ) -> Self {
+        PyCreateFunction {
+            create: CreateFunction {
+                or_replace,
+                temporary,
+                name,
+                args: args.map(|args| args.into_iter().map(|arg| arg.arg).collect()),
+                return_type: return_type.map(|return_type| return_type.data_type),
+                params: params.body,
+                schema: Arc::new(schema.into()),
+            },
+        }
+    }
+
+    pub fn or_replace(&self) -> bool {
+        self.create.or_replace
+    }
+
+    pub fn temporary(&self) -> bool {
+        self.create.temporary
+    }
+
+    pub fn name(&self) -> String {
+        self.create.name.clone()
+    }
+
+    pub fn params(&self) -> PyCreateFunctionBody {
+        PyCreateFunctionBody {
+            body: self.create.params.clone(),
+        }
+    }
+
+    pub fn schema(&self) -> PyDFSchema {
+        (*self.create.schema).clone().into()
+    }
+
+    pub fn return_type(&self) -> Option<PyDataType> {
+        self.create
+            .return_type
+            .as_ref()
+            .map(|return_type| return_type.clone().into())
+    }
+
+    pub fn args(&self) -> Option<Vec<PyOperateFunctionArg>> {
+        self.create.args.as_ref().map(|args| {
+            args.iter()
+                .map(|arg| PyOperateFunctionArg { arg: arg.clone() })
+                .collect()
+        })
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CreateFunction({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CreateFunction".to_string())
+    }
+}
+
+impl LogicalNode for PyCreateFunction {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/create_index.rs b/src/expr/create_index.rs
new file mode 100644
index 000000000..13dadbc3f
--- /dev/null
+++ b/src/expr/create_index.rs
@@ -0,0 +1,129 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::CreateIndex;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::{logical_node::LogicalNode, sort_expr::PySortExpr};
+
+#[pyclass(name = "CreateIndex", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyCreateIndex {
+    create: CreateIndex,
+}
+
+impl From<PyCreateIndex> for CreateIndex {
+    fn from(create: PyCreateIndex) -> Self {
+        create.create
+    }
+}
+
+impl From<CreateIndex> for PyCreateIndex {
+    fn from(create: CreateIndex) -> PyCreateIndex {
+        PyCreateIndex { create }
+    }
+}
+
+impl Display for PyCreateIndex {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "CreateIndex: {:?}", self.create.name)
+    }
+}
+
+#[pymethods]
+impl PyCreateIndex {
+    #[new]
+    #[pyo3(signature = (table, columns, unique, if_not_exists, schema, name=None, using=None))]
+    pub fn new(
+        table: String,
+        columns: Vec<PySortExpr>,
+        unique: bool,
+        if_not_exists: bool,
+        schema: PyDFSchema,
+        name: Option<String>,
+        using: Option<String>,
+    ) -> PyResult<Self> {
+        Ok(PyCreateIndex {
+            create: CreateIndex {
+                name,
+                table: table.into(),
+                using,
+                columns: columns.iter().map(|c| c.clone().into()).collect(),
+                unique,
+                if_not_exists,
+                schema: Arc::new(schema.into()),
+            },
+        })
+    }
+
+    pub fn name(&self) -> Option<String> {
+        self.create.name.clone()
+    }
+
+    pub fn table(&self) -> PyResult<String> {
+        Ok(self.create.table.to_string())
+    }
+
+    pub fn using(&self) -> Option<String> {
+        self.create.using.clone()
+    }
+
+    pub fn columns(&self) -> Vec<PySortExpr> {
+        self.create
+            .columns
+            .iter()
+            .map(|c| c.clone().into())
+            .collect()
+    }
+
+    pub fn unique(&self) -> bool {
+        self.create.unique
+    }
+
+    pub fn if_not_exists(&self) -> bool {
+        self.create.if_not_exists
+    }
+
+    pub fn schema(&self) -> PyDFSchema {
+        (*self.create.schema).clone().into()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("CreateIndex({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("CreateIndex".to_string())
+    }
+}
+
+impl LogicalNode for PyCreateIndex {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/describe_table.rs b/src/expr/describe_table.rs
new file mode 100644
index 000000000..5658a13f2
--- /dev/null
+++ b/src/expr/describe_table.rs
@@ -0,0 +1,92 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use arrow::{datatypes::Schema, pyarrow::PyArrowType};
+use datafusion::logical_expr::DescribeTable;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "DescribeTable", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDescribeTable {
+    describe: DescribeTable,
+}
+
+impl Display for PyDescribeTable {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "DescribeTable")
+    }
+}
+
+#[pymethods]
+impl PyDescribeTable {
+    #[new]
+    fn new(schema: PyArrowType<Schema>, output_schema: PyDFSchema) -> Self {
+        Self {
+            describe: DescribeTable {
+                schema: Arc::new(schema.0),
+                output_schema: Arc::new(output_schema.into()),
+            },
+        }
+    }
+
+    pub fn schema(&self) -> PyArrowType<Schema> {
+        (*self.describe.schema).clone().into()
+    }
+
+    pub fn output_schema(&self) -> PyDFSchema {
+        (*self.describe.output_schema).clone().into()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("DescribeTable({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("DescribeTable".to_string())
+    }
+}
+
+impl From<PyDescribeTable> for DescribeTable {
+    fn from(describe: PyDescribeTable) -> Self {
+        describe.describe
+    }
+}
+
+impl From<DescribeTable> for PyDescribeTable {
+    fn from(describe: DescribeTable) -> PyDescribeTable {
+        PyDescribeTable { describe }
+    }
+}
+
+impl LogicalNode for PyDescribeTable {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/dml.rs b/src/expr/dml.rs
new file mode 100644
index 000000000..251e336cc
--- /dev/null
+++ b/src/expr/dml.rs
@@ -0,0 +1,136 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use datafusion::logical_expr::dml::InsertOp;
+use datafusion::logical_expr::{DmlStatement, WriteOp};
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::common::schema::PyTableSource;
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "DmlStatement", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDmlStatement {
+    dml: DmlStatement,
+}
+
+impl From<PyDmlStatement> for DmlStatement {
+    fn from(dml: PyDmlStatement) -> Self {
+        dml.dml
+    }
+}
+
+impl From<DmlStatement> for PyDmlStatement {
+    fn from(dml: DmlStatement) -> PyDmlStatement {
+        PyDmlStatement { dml }
+    }
+}
+
+impl LogicalNode for PyDmlStatement {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![PyLogicalPlan::from((*self.dml.input).clone())]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyDmlStatement {
+    pub fn table_name(&self) -> PyResult<String> {
+        Ok(self.dml.table_name.to_string())
+    }
+
+    pub fn target(&self) -> PyResult<PyTableSource> {
+        Ok(PyTableSource {
+            table_source: self.dml.target.clone(),
+        })
+    }
+
+    pub fn op(&self) -> PyWriteOp {
+        self.dml.op.clone().into()
+    }
+
+    pub fn input(&self) -> PyLogicalPlan {
+        PyLogicalPlan {
+            plan: self.dml.input.clone(),
+        }
+    }
+
+    pub fn output_schema(&self) -> PyDFSchema {
+        (*self.dml.output_schema).clone().into()
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok("DmlStatement".to_string())
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("DmlStatement".to_string())
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(eq, eq_int, name = "WriteOp", module = "datafusion.expr")]
+pub enum PyWriteOp {
+    Append,
+    Overwrite,
+    Replace,
+
+    Update,
+    Delete,
+    Ctas,
+}
+
+impl From<WriteOp> for PyWriteOp {
+    fn from(write_op: WriteOp) -> Self {
+        match write_op {
+            WriteOp::Insert(InsertOp::Append) => PyWriteOp::Append,
+            WriteOp::Insert(InsertOp::Overwrite) => PyWriteOp::Overwrite,
+            WriteOp::Insert(InsertOp::Replace) => PyWriteOp::Replace,
+
+            WriteOp::Update => PyWriteOp::Update,
+            WriteOp::Delete => PyWriteOp::Delete,
+            WriteOp::Ctas => PyWriteOp::Ctas,
+        }
+    }
+}
+
+impl From<PyWriteOp> for WriteOp {
+    fn from(py: PyWriteOp) -> Self {
+        match py {
+            PyWriteOp::Append => WriteOp::Insert(InsertOp::Append),
+            PyWriteOp::Overwrite => WriteOp::Insert(InsertOp::Overwrite),
+            PyWriteOp::Replace => WriteOp::Insert(InsertOp::Replace),
+
+            PyWriteOp::Update => WriteOp::Update,
+            PyWriteOp::Delete => WriteOp::Delete,
+            PyWriteOp::Ctas => WriteOp::Ctas,
+        }
+    }
+}
+
+#[pymethods]
+impl PyWriteOp {
+    fn name(&self) -> String {
+        let write_op: WriteOp = self.clone().into();
+        write_op.name().to_string()
+    }
+}
diff --git a/src/expr/drop_catalog_schema.rs b/src/expr/drop_catalog_schema.rs
new file mode 100644
index 000000000..b7420a99c
--- /dev/null
+++ b/src/expr/drop_catalog_schema.rs
@@ -0,0 +1,116 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::{common::SchemaReference, logical_expr::DropCatalogSchema, sql::TableReference};
+use pyo3::{exceptions::PyValueError, prelude::*, IntoPyObjectExt};
+
+use crate::common::df_schema::PyDFSchema;
+
+use super::logical_node::LogicalNode;
+use crate::sql::logical::PyLogicalPlan;
+
+#[pyclass(name = "DropCatalogSchema", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDropCatalogSchema {
+    drop: DropCatalogSchema,
+}
+
+impl From<PyDropCatalogSchema> for DropCatalogSchema {
+    fn from(drop: PyDropCatalogSchema) -> Self {
+        drop.drop
+    }
+}
+
+impl From<DropCatalogSchema> for PyDropCatalogSchema {
+    fn from(drop: DropCatalogSchema) -> PyDropCatalogSchema {
+        PyDropCatalogSchema { drop }
+    }
+}
+
+impl Display for PyDropCatalogSchema {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "DropCatalogSchema")
+    }
+}
+
+fn parse_schema_reference(name: String) -> PyResult<SchemaReference> {
+    match name.into() {
+        TableReference::Bare { table } => Ok(SchemaReference::Bare { schema: table }),
+        TableReference::Partial { schema, table } => Ok(SchemaReference::Full {
+            schema: table,
+            catalog: schema,
+        }),
+        TableReference::Full {
+            catalog: _,
+            schema: _,
+            table: _,
+        } => Err(PyErr::new::<PyValueError, String>(
+            "Invalid schema specifier (has 3 parts)".to_string(),
+        )),
+    }
+}
+
+#[pymethods]
+impl PyDropCatalogSchema {
+    #[new]
+    fn new(name: String, schema: PyDFSchema, if_exists: bool, cascade: bool) -> PyResult<Self> {
+        let name = parse_schema_reference(name)?;
+        Ok(PyDropCatalogSchema {
+            drop: DropCatalogSchema {
+                name,
+                schema: Arc::new(schema.into()),
+                if_exists,
+                cascade,
+            },
+        })
+    }
+
+    fn name(&self) -> PyResult<String> {
+        Ok(self.drop.name.to_string())
+    }
+
+    fn schema(&self) -> PyDFSchema {
+        (*self.drop.schema).clone().into()
+    }
+
+    fn if_exists(&self) -> PyResult<bool> {
+        Ok(self.drop.if_exists)
+    }
+
+    fn cascade(&self) -> PyResult<bool> {
+        Ok(self.drop.cascade)
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("DropCatalogSchema({})", self))
+    }
+}
+
+impl LogicalNode for PyDropCatalogSchema {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/drop_function.rs b/src/expr/drop_function.rs
new file mode 100644
index 000000000..9fbd78fdc
--- /dev/null
+++ b/src/expr/drop_function.rs
@@ -0,0 +1,95 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::DropFunction;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use super::logical_node::LogicalNode;
+use crate::common::df_schema::PyDFSchema;
+use crate::sql::logical::PyLogicalPlan;
+
+#[pyclass(name = "DropFunction", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDropFunction {
+    drop: DropFunction,
+}
+
+impl From<PyDropFunction> for DropFunction {
+    fn from(drop: PyDropFunction) -> Self {
+        drop.drop
+    }
+}
+
+impl From<DropFunction> for PyDropFunction {
+    fn from(drop: DropFunction) -> PyDropFunction {
+        PyDropFunction { drop }
+    }
+}
+
+impl Display for PyDropFunction {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(f, "DropFunction")
+    }
+}
+
+#[pymethods]
+impl PyDropFunction {
+    #[new]
+    fn new(name: String, schema: PyDFSchema, if_exists: bool) -> PyResult<Self> {
+        Ok(PyDropFunction {
+            drop: DropFunction {
+                name,
+                schema: Arc::new(schema.into()),
+                if_exists,
+            },
+        })
+    }
+    fn name(&self) -> PyResult<String> {
+        Ok(self.drop.name.clone())
+    }
+
+    fn schema(&self) -> PyDFSchema {
+        (*self.drop.schema).clone().into()
+    }
+
+    fn if_exists(&self) -> PyResult<bool> {
+        Ok(self.drop.if_exists)
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("DropFunction({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("DropFunction".to_string())
+    }
+}
+
+impl LogicalNode for PyDropFunction {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/drop_view.rs b/src/expr/drop_view.rs
new file mode 100644
index 000000000..1d1ab1e59
--- /dev/null
+++ b/src/expr/drop_view.rs
@@ -0,0 +1,102 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::{
+    fmt::{self, Display, Formatter},
+    sync::Arc,
+};
+
+use datafusion::logical_expr::DropView;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::common::df_schema::PyDFSchema;
+
+use super::logical_node::LogicalNode;
+use crate::sql::logical::PyLogicalPlan;
+
+#[pyclass(name = "DropView", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDropView {
+    drop: DropView,
+}
+
+impl From<PyDropView> for DropView {
+    fn from(drop: PyDropView) -> Self {
+        drop.drop
+    }
+}
+
+impl From<DropView> for PyDropView {
+    fn from(drop: DropView) -> PyDropView {
+        PyDropView { drop }
+    }
+}
+
+impl Display for PyDropView {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(
+            f,
+            "DropView: {name:?} if not exist:={if_exists}",
+            name = self.drop.name,
+            if_exists = self.drop.if_exists
+        )
+    }
+}
+
+#[pymethods]
+impl PyDropView {
+    #[new]
+    fn new(name: String, schema: PyDFSchema, if_exists: bool) -> PyResult<Self> {
+        Ok(PyDropView {
+            drop: DropView {
+                name: name.into(),
+                schema: Arc::new(schema.into()),
+                if_exists,
+            },
+        })
+    }
+
+    fn name(&self) -> PyResult<String> {
+        Ok(self.drop.name.to_string())
+    }
+
+    fn schema(&self) -> PyDFSchema {
+        (*self.drop.schema).clone().into()
+    }
+
+    fn if_exists(&self) -> PyResult<bool> {
+        Ok(self.drop.if_exists)
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("DropView({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("DropView".to_string())
+    }
+}
+
+impl LogicalNode for PyDropView {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/recursive_query.rs b/src/expr/recursive_query.rs
new file mode 100644
index 000000000..65181f7d3
--- /dev/null
+++ b/src/expr/recursive_query.rs
@@ -0,0 +1,111 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::fmt::{self, Display, Formatter};
+
+use datafusion::logical_expr::RecursiveQuery;
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::sql::logical::PyLogicalPlan;
+
+use super::logical_node::LogicalNode;
+
+#[pyclass(name = "RecursiveQuery", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyRecursiveQuery {
+    query: RecursiveQuery,
+}
+
+impl From<PyRecursiveQuery> for RecursiveQuery {
+    fn from(query: PyRecursiveQuery) -> Self {
+        query.query
+    }
+}
+
+impl From<RecursiveQuery> for PyRecursiveQuery {
+    fn from(query: RecursiveQuery) -> PyRecursiveQuery {
+        PyRecursiveQuery { query }
+    }
+}
+
+impl Display for PyRecursiveQuery {
+    fn fmt(&self, f: &mut Formatter) -> fmt::Result {
+        write!(
+            f,
+            "RecursiveQuery {name:?} is_distinct:={is_distinct}",
+            name = self.query.name,
+            is_distinct = self.query.is_distinct
+        )
+    }
+}
+
+#[pymethods]
+impl PyRecursiveQuery {
+    #[new]
+    fn new(
+        name: String,
+        static_term: PyLogicalPlan,
+        recursive_term: PyLogicalPlan,
+        is_distinct: bool,
+    ) -> Self {
+        Self {
+            query: RecursiveQuery {
+                name,
+                static_term: static_term.plan(),
+                recursive_term: recursive_term.plan(),
+                is_distinct,
+            },
+        }
+    }
+
+    fn name(&self) -> PyResult<String> {
+        Ok(self.query.name.clone())
+    }
+
+    fn static_term(&self) -> PyLogicalPlan {
+        PyLogicalPlan::from((*self.query.static_term).clone())
+    }
+
+    fn recursive_term(&self) -> PyLogicalPlan {
+        PyLogicalPlan::from((*self.query.recursive_term).clone())
+    }
+
+    fn is_distinct(&self) -> PyResult<bool> {
+        Ok(self.query.is_distinct)
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("RecursiveQuery({})", self))
+    }
+
+    fn __name__(&self) -> PyResult<String> {
+        Ok("RecursiveQuery".to_string())
+    }
+}
+
+impl LogicalNode for PyRecursiveQuery {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![
+            PyLogicalPlan::from((*self.query.static_term).clone()),
+            PyLogicalPlan::from((*self.query.recursive_term).clone()),
+        ]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
diff --git a/src/expr/statement.rs b/src/expr/statement.rs
new file mode 100644
index 000000000..83774cda1
--- /dev/null
+++ b/src/expr/statement.rs
@@ -0,0 +1,454 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use datafusion::logical_expr::{
+    Deallocate, Execute, Prepare, SetVariable, TransactionAccessMode, TransactionConclusion,
+    TransactionEnd, TransactionIsolationLevel, TransactionStart,
+};
+use pyo3::{prelude::*, IntoPyObjectExt};
+
+use crate::{common::data_type::PyDataType, sql::logical::PyLogicalPlan};
+
+use super::{logical_node::LogicalNode, PyExpr};
+
+#[pyclass(name = "TransactionStart", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyTransactionStart {
+    transaction_start: TransactionStart,
+}
+
+impl From<TransactionStart> for PyTransactionStart {
+    fn from(transaction_start: TransactionStart) -> PyTransactionStart {
+        PyTransactionStart { transaction_start }
+    }
+}
+
+impl TryFrom<PyTransactionStart> for TransactionStart {
+    type Error = PyErr;
+
+    fn try_from(py: PyTransactionStart) -> Result<Self, Self::Error> {
+        Ok(py.transaction_start)
+    }
+}
+
+impl LogicalNode for PyTransactionStart {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(eq, eq_int, name = "TransactionAccessMode", module = "datafusion.expr")]
+pub enum PyTransactionAccessMode {
+    ReadOnly,
+    ReadWrite,
+}
+
+impl From<TransactionAccessMode> for PyTransactionAccessMode {
+    fn from(access_mode: TransactionAccessMode) -> PyTransactionAccessMode {
+        match access_mode {
+            TransactionAccessMode::ReadOnly => PyTransactionAccessMode::ReadOnly,
+            TransactionAccessMode::ReadWrite => PyTransactionAccessMode::ReadWrite,
+        }
+    }
+}
+
+impl TryFrom<PyTransactionAccessMode> for TransactionAccessMode {
+    type Error = PyErr;
+
+    fn try_from(py: PyTransactionAccessMode) -> Result<Self, Self::Error> {
+        match py {
+            PyTransactionAccessMode::ReadOnly => Ok(TransactionAccessMode::ReadOnly),
+            PyTransactionAccessMode::ReadWrite => Ok(TransactionAccessMode::ReadWrite),
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(
+    eq,
+    eq_int,
+    name = "TransactionIsolationLevel",
+    module = "datafusion.expr"
+)]
+pub enum PyTransactionIsolationLevel {
+    ReadUncommitted,
+    ReadCommitted,
+    RepeatableRead,
+    Serializable,
+    Snapshot,
+}
+
+impl From<TransactionIsolationLevel> for PyTransactionIsolationLevel {
+    fn from(isolation_level: TransactionIsolationLevel) -> PyTransactionIsolationLevel {
+        match isolation_level {
+            TransactionIsolationLevel::ReadUncommitted => {
+                PyTransactionIsolationLevel::ReadUncommitted
+            }
+            TransactionIsolationLevel::ReadCommitted => PyTransactionIsolationLevel::ReadCommitted,
+            TransactionIsolationLevel::RepeatableRead => {
+                PyTransactionIsolationLevel::RepeatableRead
+            }
+            TransactionIsolationLevel::Serializable => PyTransactionIsolationLevel::Serializable,
+            TransactionIsolationLevel::Snapshot => PyTransactionIsolationLevel::Snapshot,
+        }
+    }
+}
+
+impl TryFrom<PyTransactionIsolationLevel> for TransactionIsolationLevel {
+    type Error = PyErr;
+
+    fn try_from(value: PyTransactionIsolationLevel) -> Result<Self, Self::Error> {
+        match value {
+            PyTransactionIsolationLevel::ReadUncommitted => {
+                Ok(TransactionIsolationLevel::ReadUncommitted)
+            }
+            PyTransactionIsolationLevel::ReadCommitted => {
+                Ok(TransactionIsolationLevel::ReadCommitted)
+            }
+            PyTransactionIsolationLevel::RepeatableRead => {
+                Ok(TransactionIsolationLevel::RepeatableRead)
+            }
+            PyTransactionIsolationLevel::Serializable => {
+                Ok(TransactionIsolationLevel::Serializable)
+            }
+            PyTransactionIsolationLevel::Snapshot => Ok(TransactionIsolationLevel::Snapshot),
+        }
+    }
+}
+
+#[pymethods]
+impl PyTransactionStart {
+    #[new]
+    pub fn new(
+        access_mode: PyTransactionAccessMode,
+        isolation_level: PyTransactionIsolationLevel,
+    ) -> PyResult<Self> {
+        let access_mode = access_mode.try_into()?;
+        let isolation_level = isolation_level.try_into()?;
+        Ok(PyTransactionStart {
+            transaction_start: TransactionStart {
+                access_mode,
+                isolation_level,
+            },
+        })
+    }
+
+    pub fn access_mode(&self) -> PyResult<PyTransactionAccessMode> {
+        Ok(self.transaction_start.access_mode.clone().into())
+    }
+
+    pub fn isolation_level(&self) -> PyResult<PyTransactionIsolationLevel> {
+        Ok(self.transaction_start.isolation_level.clone().into())
+    }
+}
+
+#[pyclass(name = "TransactionEnd", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyTransactionEnd {
+    transaction_end: TransactionEnd,
+}
+
+impl From<TransactionEnd> for PyTransactionEnd {
+    fn from(transaction_end: TransactionEnd) -> PyTransactionEnd {
+        PyTransactionEnd { transaction_end }
+    }
+}
+
+impl TryFrom<PyTransactionEnd> for TransactionEnd {
+    type Error = PyErr;
+
+    fn try_from(py: PyTransactionEnd) -> Result<Self, Self::Error> {
+        Ok(py.transaction_end)
+    }
+}
+
+impl LogicalNode for PyTransactionEnd {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[pyclass(eq, eq_int, name = "TransactionConclusion", module = "datafusion.expr")]
+pub enum PyTransactionConclusion {
+    Commit,
+    Rollback,
+}
+
+impl From<TransactionConclusion> for PyTransactionConclusion {
+    fn from(value: TransactionConclusion) -> Self {
+        match value {
+            TransactionConclusion::Commit => PyTransactionConclusion::Commit,
+            TransactionConclusion::Rollback => PyTransactionConclusion::Rollback,
+        }
+    }
+}
+
+impl TryFrom<PyTransactionConclusion> for TransactionConclusion {
+    type Error = PyErr;
+
+    fn try_from(value: PyTransactionConclusion) -> Result<Self, Self::Error> {
+        match value {
+            PyTransactionConclusion::Commit => Ok(TransactionConclusion::Commit),
+            PyTransactionConclusion::Rollback => Ok(TransactionConclusion::Rollback),
+        }
+    }
+}
+#[pymethods]
+impl PyTransactionEnd {
+    #[new]
+    pub fn new(conclusion: PyTransactionConclusion, chain: bool) -> PyResult<Self> {
+        let conclusion = conclusion.try_into()?;
+        Ok(PyTransactionEnd {
+            transaction_end: TransactionEnd { conclusion, chain },
+        })
+    }
+
+    pub fn conclusion(&self) -> PyResult<PyTransactionConclusion> {
+        Ok(self.transaction_end.conclusion.clone().into())
+    }
+
+    pub fn chain(&self) -> bool {
+        self.transaction_end.chain
+    }
+}
+
+#[pyclass(name = "SetVariable", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PySetVariable {
+    set_variable: SetVariable,
+}
+
+impl From<SetVariable> for PySetVariable {
+    fn from(set_variable: SetVariable) -> PySetVariable {
+        PySetVariable { set_variable }
+    }
+}
+
+impl TryFrom<PySetVariable> for SetVariable {
+    type Error = PyErr;
+
+    fn try_from(py: PySetVariable) -> Result<Self, Self::Error> {
+        Ok(py.set_variable)
+    }
+}
+
+impl LogicalNode for PySetVariable {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PySetVariable {
+    #[new]
+    pub fn new(variable: String, value: String) -> Self {
+        PySetVariable {
+            set_variable: SetVariable { variable, value },
+        }
+    }
+
+    pub fn variable(&self) -> String {
+        self.set_variable.variable.clone()
+    }
+
+    pub fn value(&self) -> String {
+        self.set_variable.value.clone()
+    }
+}
+
+#[pyclass(name = "Prepare", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyPrepare {
+    prepare: Prepare,
+}
+
+impl From<Prepare> for PyPrepare {
+    fn from(prepare: Prepare) -> PyPrepare {
+        PyPrepare { prepare }
+    }
+}
+
+impl TryFrom<PyPrepare> for Prepare {
+    type Error = PyErr;
+
+    fn try_from(py: PyPrepare) -> Result<Self, Self::Error> {
+        Ok(py.prepare)
+    }
+}
+
+impl LogicalNode for PyPrepare {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![PyLogicalPlan::from((*self.prepare.input).clone())]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyPrepare {
+    #[new]
+    pub fn new(name: String, data_types: Vec<PyDataType>, input: PyLogicalPlan) -> Self {
+        let input = input.plan().clone();
+        let data_types = data_types
+            .into_iter()
+            .map(|data_type| data_type.into())
+            .collect();
+        PyPrepare {
+            prepare: Prepare {
+                name,
+                data_types,
+                input,
+            },
+        }
+    }
+
+    pub fn name(&self) -> String {
+        self.prepare.name.clone()
+    }
+
+    pub fn data_types(&self) -> Vec<PyDataType> {
+        self.prepare
+            .data_types
+            .clone()
+            .into_iter()
+            .map(|t| t.into())
+            .collect()
+    }
+
+    pub fn input(&self) -> PyLogicalPlan {
+        PyLogicalPlan {
+            plan: self.prepare.input.clone(),
+        }
+    }
+}
+
+#[pyclass(name = "Execute", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyExecute {
+    execute: Execute,
+}
+
+impl From<Execute> for PyExecute {
+    fn from(execute: Execute) -> PyExecute {
+        PyExecute { execute }
+    }
+}
+
+impl TryFrom<PyExecute> for Execute {
+    type Error = PyErr;
+
+    fn try_from(py: PyExecute) -> Result<Self, Self::Error> {
+        Ok(py.execute)
+    }
+}
+
+impl LogicalNode for PyExecute {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyExecute {
+    #[new]
+    pub fn new(name: String, parameters: Vec<PyExpr>) -> Self {
+        let parameters = parameters
+            .into_iter()
+            .map(|parameter| parameter.into())
+            .collect();
+        PyExecute {
+            execute: Execute { name, parameters },
+        }
+    }
+
+    pub fn name(&self) -> String {
+        self.execute.name.clone()
+    }
+
+    pub fn parameters(&self) -> Vec<PyExpr> {
+        self.execute
+            .parameters
+            .clone()
+            .into_iter()
+            .map(|t| t.into())
+            .collect()
+    }
+}
+
+#[pyclass(name = "Deallocate", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyDeallocate {
+    deallocate: Deallocate,
+}
+
+impl From<Deallocate> for PyDeallocate {
+    fn from(deallocate: Deallocate) -> PyDeallocate {
+        PyDeallocate { deallocate }
+    }
+}
+
+impl TryFrom<PyDeallocate> for Deallocate {
+    type Error = PyErr;
+
+    fn try_from(py: PyDeallocate) -> Result<Self, Self::Error> {
+        Ok(py.deallocate)
+    }
+}
+
+impl LogicalNode for PyDeallocate {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyDeallocate {
+    #[new]
+    pub fn new(name: String) -> Self {
+        PyDeallocate {
+            deallocate: Deallocate { name },
+        }
+    }
+
+    pub fn name(&self) -> String {
+        self.deallocate.name.clone()
+    }
+}
diff --git a/src/expr/values.rs b/src/expr/values.rs
new file mode 100644
index 000000000..fb2692230
--- /dev/null
+++ b/src/expr/values.rs
@@ -0,0 +1,86 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::sync::Arc;
+
+use datafusion::logical_expr::Values;
+use pyo3::{prelude::*, IntoPyObjectExt};
+use pyo3::{pyclass, PyErr, PyResult, Python};
+
+use crate::{common::df_schema::PyDFSchema, sql::logical::PyLogicalPlan};
+
+use super::{logical_node::LogicalNode, PyExpr};
+
+#[pyclass(name = "Values", module = "datafusion.expr", subclass)]
+#[derive(Clone)]
+pub struct PyValues {
+    values: Values,
+}
+
+impl From<Values> for PyValues {
+    fn from(values: Values) -> PyValues {
+        PyValues { values }
+    }
+}
+
+impl TryFrom<PyValues> for Values {
+    type Error = PyErr;
+
+    fn try_from(py: PyValues) -> Result<Self, Self::Error> {
+        Ok(py.values)
+    }
+}
+
+impl LogicalNode for PyValues {
+    fn inputs(&self) -> Vec<PyLogicalPlan> {
+        vec![]
+    }
+
+    fn to_variant<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        self.clone().into_bound_py_any(py)
+    }
+}
+
+#[pymethods]
+impl PyValues {
+    #[new]
+    pub fn new(schema: PyDFSchema, values: Vec<Vec<PyExpr>>) -> PyResult<Self> {
+        let values = values
+            .into_iter()
+            .map(|row| row.into_iter().map(|expr| expr.into()).collect())
+            .collect();
+        Ok(PyValues {
+            values: Values {
+                schema: Arc::new(schema.into()),
+                values,
+            },
+        })
+    }
+
+    pub fn schema(&self) -> PyResult<PyDFSchema> {
+        Ok((*self.values.schema).clone().into())
+    }
+
+    pub fn values(&self) -> Vec<Vec<PyExpr>> {
+        self.values
+            .values
+            .clone()
+            .into_iter()
+            .map(|row| row.into_iter().map(|expr| expr.into()).collect())
+            .collect()
+    }
+}
diff --git a/src/expr/window.rs b/src/expr/window.rs
index 13deaec25..c5467bf94 100644
--- a/src/expr/window.rs
+++ b/src/expr/window.rs
@@ -16,7 +16,7 @@
 // under the License.
 
 use datafusion::common::{DataFusionError, ScalarValue};
-use datafusion::logical_expr::expr::WindowFunction;
+use datafusion::logical_expr::expr::{WindowFunction, WindowFunctionParams};
 use datafusion::logical_expr::{Expr, Window, WindowFrame, WindowFrameBound, WindowFrameUnits};
 use pyo3::{prelude::*, IntoPyObjectExt};
 use std::fmt::{self, Display, Formatter};
@@ -118,7 +118,10 @@ impl PyWindowExpr {
     /// Returns order by columns in a window function expression
     pub fn get_sort_exprs(&self, expr: PyExpr) -> PyResult<Vec<PySortExpr>> {
         match expr.expr.unalias() {
-            Expr::WindowFunction(WindowFunction { order_by, .. }) => py_sort_expr_list(&order_by),
+            Expr::WindowFunction(WindowFunction {
+                params: WindowFunctionParams { order_by, .. },
+                ..
+            }) => py_sort_expr_list(&order_by),
             other => Err(not_window_function_err(other)),
         }
     }
@@ -126,9 +129,10 @@ impl PyWindowExpr {
     /// Return partition by columns in a window function expression
     pub fn get_partition_exprs(&self, expr: PyExpr) -> PyResult<Vec<PyExpr>> {
         match expr.expr.unalias() {
-            Expr::WindowFunction(WindowFunction { partition_by, .. }) => {
-                py_expr_list(&partition_by)
-            }
+            Expr::WindowFunction(WindowFunction {
+                params: WindowFunctionParams { partition_by, .. },
+                ..
+            }) => py_expr_list(&partition_by),
             other => Err(not_window_function_err(other)),
         }
     }
@@ -136,7 +140,10 @@ impl PyWindowExpr {
     /// Return input args for window function
     pub fn get_args(&self, expr: PyExpr) -> PyResult<Vec<PyExpr>> {
         match expr.expr.unalias() {
-            Expr::WindowFunction(WindowFunction { args, .. }) => py_expr_list(&args),
+            Expr::WindowFunction(WindowFunction {
+                params: WindowFunctionParams { args, .. },
+                ..
+            }) => py_expr_list(&args),
             other => Err(not_window_function_err(other)),
         }
     }
@@ -152,7 +159,10 @@ impl PyWindowExpr {
     /// Returns a Pywindow frame for a given window function expression
     pub fn get_frame(&self, expr: PyExpr) -> Option<PyWindowFrame> {
         match expr.expr.unalias() {
-            Expr::WindowFunction(WindowFunction { window_frame, .. }) => Some(window_frame.into()),
+            Expr::WindowFunction(WindowFunction {
+                params: WindowFunctionParams { window_frame, .. },
+                ..
+            }) => Some(window_frame.into()),
             _ => None,
         }
     }
diff --git a/src/functions.rs b/src/functions.rs
index 8fac239b4..caa79b8ad 100644
--- a/src/functions.rs
+++ b/src/functions.rs
@@ -15,8 +15,11 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use std::collections::HashMap;
+
 use datafusion::functions_aggregate::all_default_aggregate_functions;
 use datafusion::functions_window::all_default_window_functions;
+use datafusion::logical_expr::expr::WindowFunctionParams;
 use datafusion::logical_expr::ExprFunctionExt;
 use datafusion::logical_expr::WindowFrame;
 use pyo3::{prelude::*, wrap_pyfunction};
@@ -204,10 +207,13 @@ fn order_by(expr: PyExpr, asc: bool, nulls_first: bool) -> PyResult<PySortExpr>
 
 /// Creates a new Alias Expr
 #[pyfunction]
-fn alias(expr: PyExpr, name: &str) -> PyResult<PyExpr> {
+#[pyo3(signature = (expr, name, metadata=None))]
+fn alias(expr: PyExpr, name: &str, metadata: Option<HashMap<String, String>>) -> PyResult<PyExpr> {
     let relation: Option<TableReference> = None;
     Ok(PyExpr {
-        expr: datafusion::logical_expr::Expr::Alias(Alias::new(expr.expr, relation, name)),
+        expr: datafusion::logical_expr::Expr::Alias(
+            Alias::new(expr.expr, relation, name).with_metadata(metadata),
+        ),
     })
 }
 
@@ -215,10 +221,7 @@ fn alias(expr: PyExpr, name: &str) -> PyResult<PyExpr> {
 #[pyfunction]
 fn col(name: &str) -> PyResult<PyExpr> {
     Ok(PyExpr {
-        expr: datafusion::logical_expr::Expr::Column(Column {
-            relation: None,
-            name: name.to_string(),
-        }),
+        expr: datafusion::logical_expr::Expr::Column(Column::new_unqualified(name)),
     })
 }
 
@@ -333,19 +336,21 @@ fn window(
     Ok(PyExpr {
         expr: datafusion::logical_expr::Expr::WindowFunction(WindowFunction {
             fun,
-            args: args.into_iter().map(|x| x.expr).collect::<Vec<_>>(),
-            partition_by: partition_by
-                .unwrap_or_default()
-                .into_iter()
-                .map(|x| x.expr)
-                .collect::<Vec<_>>(),
-            order_by: order_by
-                .unwrap_or_default()
-                .into_iter()
-                .map(|x| x.into())
-                .collect::<Vec<_>>(),
-            window_frame,
-            null_treatment: None,
+            params: WindowFunctionParams {
+                args: args.into_iter().map(|x| x.expr).collect::<Vec<_>>(),
+                partition_by: partition_by
+                    .unwrap_or_default()
+                    .into_iter()
+                    .map(|x| x.expr)
+                    .collect::<Vec<_>>(),
+                order_by: order_by
+                    .unwrap_or_default()
+                    .into_iter()
+                    .map(|x| x.into())
+                    .collect::<Vec<_>>(),
+                window_frame,
+                null_treatment: None,
+            },
         }),
     })
 }
@@ -375,27 +380,6 @@ macro_rules! aggregate_function {
     };
 }
 
-macro_rules! aggregate_function_vec_args {
-    ($NAME: ident) => {
-        aggregate_function_vec_args!($NAME, expr);
-    };
-    ($NAME: ident, $($arg:ident)*) => {
-        #[pyfunction]
-        #[pyo3(signature = ($($arg),*, distinct=None, filter=None, order_by=None, null_treatment=None))]
-        fn $NAME(
-            $($arg: PyExpr),*,
-            distinct: Option<bool>,
-            filter: Option<PyExpr>,
-            order_by: Option<Vec<PySortExpr>>,
-            null_treatment: Option<NullTreatment>
-        ) -> PyDataFusionResult<PyExpr> {
-            let agg_fn = functions_aggregate::expr_fn::$NAME(vec![$($arg.into()),*]);
-
-            add_builder_fns_to_aggregate(agg_fn, distinct, filter, order_by, null_treatment)
-        }
-    };
-}
-
 /// Generates a [pyo3] wrapper for [datafusion::functions::expr_fn]
 ///
 /// These functions have explicit named arguments.
@@ -698,8 +682,22 @@ pub fn approx_percentile_cont_with_weight(
     add_builder_fns_to_aggregate(agg_fn, None, filter, None, None)
 }
 
-aggregate_function_vec_args!(last_value);
+// We handle first_value explicitly because the signature expects an order_by
+// https://github.com/apache/datafusion/issues/12376
+#[pyfunction]
+#[pyo3(signature = (expr, distinct=None, filter=None, order_by=None, null_treatment=None))]
+pub fn last_value(
+    expr: PyExpr,
+    distinct: Option<bool>,
+    filter: Option<PyExpr>,
+    order_by: Option<Vec<PySortExpr>>,
+    null_treatment: Option<NullTreatment>,
+) -> PyDataFusionResult<PyExpr> {
+    // If we initialize the UDAF with order_by directly, then it gets over-written by the builder
+    let agg_fn = functions_aggregate::expr_fn::last_value(expr.expr, None);
 
+    add_builder_fns_to_aggregate(agg_fn, distinct, filter, order_by, null_treatment)
+}
 // We handle first_value explicitly because the signature expects an order_by
 // https://github.com/apache/datafusion/issues/12376
 #[pyfunction]
diff --git a/src/lib.rs b/src/lib.rs
index ce93ff0c3..7dced1fbd 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -52,6 +52,7 @@ pub mod pyarrow_util;
 mod record_batch;
 pub mod sql;
 pub mod store;
+pub mod unparser;
 
 #[cfg(feature = "substrait")]
 pub mod substrait;
@@ -59,6 +60,7 @@ pub mod substrait;
 mod udaf;
 #[allow(clippy::borrow_deref_ref)]
 mod udf;
+pub mod udtf;
 mod udwf;
 pub mod utils;
 
@@ -87,6 +89,7 @@ fn _internal(py: Python, m: Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<udf::PyScalarUDF>()?;
     m.add_class::<udaf::PyAggregateUDF>()?;
     m.add_class::<udwf::PyWindowUDF>()?;
+    m.add_class::<udtf::PyTableFunction>()?;
     m.add_class::<config::PyConfig>()?;
     m.add_class::<sql::logical::PyLogicalPlan>()?;
     m.add_class::<physical_plan::PyExecutionPlan>()?;
@@ -103,6 +106,10 @@ fn _internal(py: Python, m: Bound<'_, PyModule>) -> PyResult<()> {
     expr::init_module(&expr)?;
     m.add_submodule(&expr)?;
 
+    let unparser = PyModule::new(py, "unparser")?;
+    unparser::init_module(&unparser)?;
+    m.add_submodule(&unparser)?;
+
     // Register the functions as a submodule
     let funcs = PyModule::new(py, "functions")?;
     functions::init_module(&funcs)?;
diff --git a/src/sql/logical.rs b/src/sql/logical.rs
index 96561c434..198d68bdc 100644
--- a/src/sql/logical.rs
+++ b/src/sql/logical.rs
@@ -17,10 +17,25 @@
 
 use std::sync::Arc;
 
+use crate::context::PySessionContext;
 use crate::errors::PyDataFusionResult;
 use crate::expr::aggregate::PyAggregate;
 use crate::expr::analyze::PyAnalyze;
+use crate::expr::copy_to::PyCopyTo;
+use crate::expr::create_catalog::PyCreateCatalog;
+use crate::expr::create_catalog_schema::PyCreateCatalogSchema;
+use crate::expr::create_external_table::PyCreateExternalTable;
+use crate::expr::create_function::PyCreateFunction;
+use crate::expr::create_index::PyCreateIndex;
+use crate::expr::create_memory_table::PyCreateMemoryTable;
+use crate::expr::create_view::PyCreateView;
+use crate::expr::describe_table::PyDescribeTable;
 use crate::expr::distinct::PyDistinct;
+use crate::expr::dml::PyDmlStatement;
+use crate::expr::drop_catalog_schema::PyDropCatalogSchema;
+use crate::expr::drop_function::PyDropFunction;
+use crate::expr::drop_table::PyDropTable;
+use crate::expr::drop_view::PyDropView;
 use crate::expr::empty_relation::PyEmptyRelation;
 use crate::expr::explain::PyExplain;
 use crate::expr::extension::PyExtension;
@@ -28,14 +43,20 @@ use crate::expr::filter::PyFilter;
 use crate::expr::join::PyJoin;
 use crate::expr::limit::PyLimit;
 use crate::expr::projection::PyProjection;
+use crate::expr::recursive_query::PyRecursiveQuery;
+use crate::expr::repartition::PyRepartition;
 use crate::expr::sort::PySort;
+use crate::expr::statement::{
+    PyDeallocate, PyExecute, PyPrepare, PySetVariable, PyTransactionEnd, PyTransactionStart,
+};
 use crate::expr::subquery::PySubquery;
 use crate::expr::subquery_alias::PySubqueryAlias;
 use crate::expr::table_scan::PyTableScan;
+use crate::expr::union::PyUnion;
 use crate::expr::unnest::PyUnnest;
+use crate::expr::values::PyValues;
 use crate::expr::window::PyWindowExpr;
-use crate::{context::PySessionContext, errors::py_unsupported_variant_err};
-use datafusion::logical_expr::LogicalPlan;
+use datafusion::logical_expr::{DdlStatement, LogicalPlan, Statement};
 use datafusion_proto::logical_plan::{AsLogicalPlan, DefaultLogicalExtensionCodec};
 use prost::Message;
 use pyo3::{exceptions::PyRuntimeError, prelude::*, types::PyBytes};
@@ -82,18 +103,54 @@ impl PyLogicalPlan {
             LogicalPlan::SubqueryAlias(plan) => PySubqueryAlias::from(plan.clone()).to_variant(py),
             LogicalPlan::Unnest(plan) => PyUnnest::from(plan.clone()).to_variant(py),
             LogicalPlan::Window(plan) => PyWindowExpr::from(plan.clone()).to_variant(py),
-            LogicalPlan::Repartition(_)
-            | LogicalPlan::Union(_)
-            | LogicalPlan::Statement(_)
-            | LogicalPlan::Values(_)
-            | LogicalPlan::Dml(_)
-            | LogicalPlan::Ddl(_)
-            | LogicalPlan::Copy(_)
-            | LogicalPlan::DescribeTable(_)
-            | LogicalPlan::RecursiveQuery(_) => Err(py_unsupported_variant_err(format!(
-                "Conversion of variant not implemented: {:?}",
-                self.plan
-            ))),
+            LogicalPlan::Repartition(plan) => PyRepartition::from(plan.clone()).to_variant(py),
+            LogicalPlan::Union(plan) => PyUnion::from(plan.clone()).to_variant(py),
+            LogicalPlan::Statement(plan) => match plan {
+                Statement::TransactionStart(plan) => {
+                    PyTransactionStart::from(plan.clone()).to_variant(py)
+                }
+                Statement::TransactionEnd(plan) => {
+                    PyTransactionEnd::from(plan.clone()).to_variant(py)
+                }
+                Statement::SetVariable(plan) => PySetVariable::from(plan.clone()).to_variant(py),
+                Statement::Prepare(plan) => PyPrepare::from(plan.clone()).to_variant(py),
+                Statement::Execute(plan) => PyExecute::from(plan.clone()).to_variant(py),
+                Statement::Deallocate(plan) => PyDeallocate::from(plan.clone()).to_variant(py),
+            },
+            LogicalPlan::Values(plan) => PyValues::from(plan.clone()).to_variant(py),
+            LogicalPlan::Dml(plan) => PyDmlStatement::from(plan.clone()).to_variant(py),
+            LogicalPlan::Ddl(plan) => match plan {
+                DdlStatement::CreateExternalTable(plan) => {
+                    PyCreateExternalTable::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::CreateMemoryTable(plan) => {
+                    PyCreateMemoryTable::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::CreateView(plan) => PyCreateView::from(plan.clone()).to_variant(py),
+                DdlStatement::CreateCatalogSchema(plan) => {
+                    PyCreateCatalogSchema::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::CreateCatalog(plan) => {
+                    PyCreateCatalog::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::CreateIndex(plan) => PyCreateIndex::from(plan.clone()).to_variant(py),
+                DdlStatement::DropTable(plan) => PyDropTable::from(plan.clone()).to_variant(py),
+                DdlStatement::DropView(plan) => PyDropView::from(plan.clone()).to_variant(py),
+                DdlStatement::DropCatalogSchema(plan) => {
+                    PyDropCatalogSchema::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::CreateFunction(plan) => {
+                    PyCreateFunction::from(plan.clone()).to_variant(py)
+                }
+                DdlStatement::DropFunction(plan) => {
+                    PyDropFunction::from(plan.clone()).to_variant(py)
+                }
+            },
+            LogicalPlan::Copy(plan) => PyCopyTo::from(plan.clone()).to_variant(py),
+            LogicalPlan::DescribeTable(plan) => PyDescribeTable::from(plan.clone()).to_variant(py),
+            LogicalPlan::RecursiveQuery(plan) => {
+                PyRecursiveQuery::from(plan.clone()).to_variant(py)
+            }
         }
     }
 
diff --git a/src/udtf.rs b/src/udtf.rs
new file mode 100644
index 000000000..db16d6c05
--- /dev/null
+++ b/src/udtf.rs
@@ -0,0 +1,127 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use pyo3::prelude::*;
+use std::sync::Arc;
+
+use crate::dataframe::PyTableProvider;
+use crate::errors::{py_datafusion_err, to_datafusion_err};
+use crate::expr::PyExpr;
+use crate::utils::validate_pycapsule;
+use datafusion::catalog::{TableFunctionImpl, TableProvider};
+use datafusion::error::Result as DataFusionResult;
+use datafusion::logical_expr::Expr;
+use datafusion_ffi::table_provider::{FFI_TableProvider, ForeignTableProvider};
+use datafusion_ffi::udtf::{FFI_TableFunction, ForeignTableFunction};
+use pyo3::exceptions::PyNotImplementedError;
+use pyo3::types::{PyCapsule, PyTuple};
+
+/// Represents a user defined table function
+#[pyclass(name = "TableFunction", module = "datafusion")]
+#[derive(Debug, Clone)]
+pub struct PyTableFunction {
+    pub(crate) name: String,
+    pub(crate) inner: PyTableFunctionInner,
+}
+
+// TODO: Implement pure python based user defined table functions
+#[derive(Debug, Clone)]
+pub(crate) enum PyTableFunctionInner {
+    PythonFunction(Arc<PyObject>),
+    FFIFunction(Arc<dyn TableFunctionImpl>),
+}
+
+#[pymethods]
+impl PyTableFunction {
+    #[new]
+    #[pyo3(signature=(name, func))]
+    pub fn new(name: &str, func: Bound<'_, PyAny>) -> PyResult<Self> {
+        let inner = if func.hasattr("__datafusion_table_function__")? {
+            let capsule = func.getattr("__datafusion_table_function__")?.call0()?;
+            let capsule = capsule.downcast::<PyCapsule>().map_err(py_datafusion_err)?;
+            validate_pycapsule(capsule, "datafusion_table_function")?;
+
+            let ffi_func = unsafe { capsule.reference::<FFI_TableFunction>() };
+            let foreign_func: ForeignTableFunction = ffi_func.to_owned().into();
+
+            PyTableFunctionInner::FFIFunction(Arc::new(foreign_func))
+        } else {
+            let py_obj = Arc::new(func.unbind());
+            PyTableFunctionInner::PythonFunction(py_obj)
+        };
+
+        Ok(Self {
+            name: name.to_string(),
+            inner,
+        })
+    }
+
+    #[pyo3(signature = (*args))]
+    pub fn __call__(&self, args: Vec<PyExpr>) -> PyResult<PyTableProvider> {
+        let args: Vec<Expr> = args.iter().map(|e| e.expr.clone()).collect();
+        let table_provider = self.call(&args).map_err(py_datafusion_err)?;
+
+        Ok(PyTableProvider::new(table_provider))
+    }
+
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!("TableUDF({})", self.name))
+    }
+}
+
+#[allow(clippy::result_large_err)]
+fn call_python_table_function(
+    func: &Arc<PyObject>,
+    args: &[Expr],
+) -> DataFusionResult<Arc<dyn TableProvider>> {
+    let args = args
+        .iter()
+        .map(|arg| PyExpr::from(arg.clone()))
+        .collect::<Vec<_>>();
+
+    // move |args: &[ArrayRef]| -> Result<ArrayRef, DataFusionError> {
+    Python::with_gil(|py| {
+        let py_args = PyTuple::new(py, args)?;
+        let provider_obj = func.call1(py, py_args)?;
+        let provider = provider_obj.bind(py);
+
+        if provider.hasattr("__datafusion_table_provider__")? {
+            let capsule = provider.getattr("__datafusion_table_provider__")?.call0()?;
+            let capsule = capsule.downcast::<PyCapsule>().map_err(py_datafusion_err)?;
+            validate_pycapsule(capsule, "datafusion_table_provider")?;
+
+            let provider = unsafe { capsule.reference::<FFI_TableProvider>() };
+            let provider: ForeignTableProvider = provider.into();
+
+            Ok(Arc::new(provider) as Arc<dyn TableProvider>)
+        } else {
+            Err(PyNotImplementedError::new_err(
+                "__datafusion_table_provider__ does not exist on Table Provider object.",
+            ))
+        }
+    })
+    .map_err(to_datafusion_err)
+}
+
+impl TableFunctionImpl for PyTableFunction {
+    fn call(&self, args: &[Expr]) -> DataFusionResult<Arc<dyn TableProvider>> {
+        match &self.inner {
+            PyTableFunctionInner::FFIFunction(func) => func.call(args),
+            PyTableFunctionInner::PythonFunction(obj) => call_python_table_function(obj, args),
+        }
+    }
+}
diff --git a/src/unparser/dialect.rs b/src/unparser/dialect.rs
new file mode 100644
index 000000000..caeef9949
--- /dev/null
+++ b/src/unparser/dialect.rs
@@ -0,0 +1,63 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use std::sync::Arc;
+
+use datafusion::sql::unparser::dialect::{
+    DefaultDialect, Dialect, DuckDBDialect, MySqlDialect, PostgreSqlDialect, SqliteDialect,
+};
+use pyo3::prelude::*;
+
+#[pyclass(name = "Dialect", module = "datafusion.unparser", subclass)]
+#[derive(Clone)]
+pub struct PyDialect {
+    pub dialect: Arc<dyn Dialect>,
+}
+
+#[pymethods]
+impl PyDialect {
+    #[staticmethod]
+    pub fn default() -> Self {
+        Self {
+            dialect: Arc::new(DefaultDialect {}),
+        }
+    }
+    #[staticmethod]
+    pub fn postgres() -> Self {
+        Self {
+            dialect: Arc::new(PostgreSqlDialect {}),
+        }
+    }
+    #[staticmethod]
+    pub fn mysql() -> Self {
+        Self {
+            dialect: Arc::new(MySqlDialect {}),
+        }
+    }
+    #[staticmethod]
+    pub fn sqlite() -> Self {
+        Self {
+            dialect: Arc::new(SqliteDialect {}),
+        }
+    }
+    #[staticmethod]
+    pub fn duckdb() -> Self {
+        Self {
+            dialect: Arc::new(DuckDBDialect::new()),
+        }
+    }
+}
diff --git a/src/unparser/mod.rs b/src/unparser/mod.rs
new file mode 100644
index 000000000..b4b0fed10
--- /dev/null
+++ b/src/unparser/mod.rs
@@ -0,0 +1,66 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+mod dialect;
+
+use std::sync::Arc;
+
+use datafusion::sql::unparser::{dialect::Dialect, Unparser};
+use dialect::PyDialect;
+use pyo3::{exceptions::PyValueError, prelude::*};
+
+use crate::sql::logical::PyLogicalPlan;
+
+#[pyclass(name = "Unparser", module = "datafusion.unparser", subclass)]
+#[derive(Clone)]
+pub struct PyUnparser {
+    dialect: Arc<dyn Dialect>,
+    pretty: bool,
+}
+
+#[pymethods]
+impl PyUnparser {
+    #[new]
+    pub fn new(dialect: PyDialect) -> Self {
+        Self {
+            dialect: dialect.dialect.clone(),
+            pretty: false,
+        }
+    }
+
+    pub fn plan_to_sql(&self, plan: &PyLogicalPlan) -> PyResult<String> {
+        let mut unparser = Unparser::new(self.dialect.as_ref());
+        unparser = unparser.with_pretty(self.pretty);
+        let sql = unparser
+            .plan_to_sql(&plan.plan())
+            .map_err(|e| PyValueError::new_err(e.to_string()))?;
+        Ok(sql.to_string())
+    }
+
+    pub fn with_pretty(&self, pretty: bool) -> Self {
+        Self {
+            dialect: self.dialect.clone(),
+            pretty,
+        }
+    }
+}
+
+pub(crate) fn init_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_class::<PyUnparser>()?;
+    m.add_class::<PyDialect>()?;
+    Ok(())
+}
diff --git a/src/utils.rs b/src/utils.rs
index 999aad755..0a24ab254 100644
--- a/src/utils.rs
+++ b/src/utils.rs
@@ -15,8 +15,10 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use crate::common::data_type::PyScalarValue;
 use crate::errors::{PyDataFusionError, PyDataFusionResult};
 use crate::TokioRuntime;
+use datafusion::common::ScalarValue;
 use datafusion::execution::context::SessionContext;
 use datafusion::logical_expr::Volatility;
 use pyo3::exceptions::PyValueError;
@@ -42,7 +44,7 @@ pub(crate) fn get_tokio_runtime() -> &'static TokioRuntime {
 #[inline]
 pub(crate) fn get_global_ctx() -> &'static SessionContext {
     static CTX: OnceLock<SessionContext> = OnceLock::new();
-    CTX.get_or_init(|| SessionContext::new())
+    CTX.get_or_init(SessionContext::new)
 }
 
 /// Utility to collect rust futures with GIL released
@@ -87,3 +89,19 @@ pub(crate) fn validate_pycapsule(capsule: &Bound<PyCapsule>, name: &str) -> PyRe
 
     Ok(())
 }
+
+pub(crate) fn py_obj_to_scalar_value(py: Python, obj: PyObject) -> PyResult<ScalarValue> {
+    // convert Python object to PyScalarValue to ScalarValue
+
+    let pa = py.import("pyarrow")?;
+
+    // Convert Python object to PyArrow scalar
+    let scalar = pa.call_method1("scalar", (obj,))?;
+
+    // Convert PyArrow scalar to PyScalarValue
+    let py_scalar = PyScalarValue::extract_bound(scalar.as_ref())
+        .map_err(|e| PyValueError::new_err(format!("Failed to extract PyScalarValue: {}", e)))?;
+
+    // Convert PyScalarValue to ScalarValue
+    Ok(py_scalar.into())
+}