8000 feat: add undirected edge motif pattern by goungoun · Pull Request #712 · graphframes/graphframes · GitHub
[go: up one dir, main page]
Skip to content

feat: add undirected edge motif pattern #712

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SemyonSinchenko merged 1 commit into from
Oct 9, 2025
Merged

feat: add undirected edge motif pattern #712

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 18 additions & 3 deletions core/src/main/scala/org/graphframes/GraphFrame.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -373,9 +373,11 @@ class GraphFrame private (
* @group motif
*/
def find(pattern: String): DataFrame = {
val VarLengthPattern = """\((\w+)\)-\[(\w*)\*(\d*)\.\.(\d*)\]->\((\w+)\)""".r
val VarLengthPattern = """\((\w+)\)-\[(\w*)\*(\d*)\.\.(\d*)\]-(>?)\((\w+)\)""".r
val UndirectedPattern = """\((\w+)\)-\[(\w*)\]-\((\w+)\)""".r

pattern match {
case VarLengthPattern(src, name, min, max, dst) =>
case VarLengthPattern(src, name, min, max, direction, dst) =>
if (min.isEmpty || max.isEmpty) {
8000 throw new InvalidParseException(
s"Unbounded length patten ${pattern} is not supported! " +
Expand All @@ -384,9 +386,22 @@ class GraphFrame private (
val strToSeq: Seq[String] = (min.toInt to max.toInt).reverse.map { hop =>
s"($src)-[$name*$hop]->($dst)"
}
strToSeq
val strToSeqReverse: Seq[String] = if (direction.isEmpty) {
(min.toInt to max.toInt).reverse.map(hop => s"($dst)-[$name*$hop]->($src)")
} else {
Seq.empty[String]
}

(strToSeq ++ strToSeqReverse)
.map(findAugmentedPatterns)
.reduce((a, b) => a.unionByName(b, allowMissingColumns = true))

case UndirectedPattern(src, name, dst) =>
val out: DataFrame = findAugmentedPatterns(s"($src)-[$name]->($dst)")
val in: DataFrame = findAugmentedPatterns(s"($dst)-[$name]->($src)")

out.unionByName(in)

case _ =>
findAugmentedPatterns(pattern)
}
Expand Down
45 changes: 45 additions & 0 deletions core/src/test/scala/org/graphframes/PatternMatchSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -658,6 +658,51 @@ class PatternMatchSuite extends SparkFunSuite with GraphFrameTestSparkContext {
assert(varEdge.except(unionEdge).isEmpty && unionEdge.except(varEdge).isEmpty)
}

test("undirected edge") {
val res = g
.find("(u)-[]-(v)")
.where("u.id == 0")
.select("u.id", "v.id")
.collect()
.toSet

val expected = Set(Row(0L, 1L), Row(0L, 2L))

compareResultToExpected(res, expected)
}

test("undirected with edge name") {
val res = g
.find("(u)-[e]-(v)")
.where("u.id == 0")
.select("e.src", "e.dst", "e.relationship")
.collect()
.toSet

val expected = Set(Row(0L, 1L, "friend"), Row(1L, 0L, "follow"), Row(2L, 0L, "unknown"))

compareResultToExpected(res, expected)
}

test("undirected var-length pattern") {
val res = g
.find("(u)-[e*1..3]-(v)")
.where("u.id == 2")

val df1 = g
.find("(u)-[e*1..3]->(v)")
.where("u.id == 2")

val df2 = g
.find("(v)-[e*1..3]->(u)")
.where("u.id == 2")

val expected = df1.unionByName(df2, allowMissingColumns = true)

assert(res.schema === expected.schema)
assert(res.except(expected).isEmpty && expected.except(res).isEmpty)
}

test("stateful predicates via UDFs") {
val chain4 = g
.find("(a)-[ab]->(b); (b)-[bc]->(c); (c)-[cd]->(d)")
Expand Down
0