feat: modify code generation to reduce bundle size

1. Add `bin/get_size.py` so that `python bin/get_size.py plotly build` reports the number of files and total size in bytes of the `plotly` directory (where generated code is put) and the `build` directory that is populated by `python setup.py build`. 1. Modify `codegen/__init__.py` and `./setup.py` so that `python setup.py --reformat=false` disables reformatting. 1. Assign an empty string to the `data_docs` field of generated validators. (This has a major impact because those docs are duplicated many times.) 1. Alias name of base validator during import in `codegen/validators.py`. 1. Remove the long list of CSS colors from help strings for color properties. 1. Replace `super(Parent, self)` with `super()` in generated code. 1. Drop use of sys.version_info and TYPE_CHECKING. Removed the check for Python < 3.7 using `sys.version_info` and as a backup checking `typing.TYPE_CHECKING`; this saves a little space and also cleans up the code. 1. Remove mention of Chart Studio and explicit enumeration of system font names from plotly.js / plot-schema.json so that this text isn't copied dozens of times into the plotly.py bundle. 1. Introduce `_init_provided()` for `BaseFigure` and `BasePlotlyType` that calls a helper function `_initialize_provided()` to replace repetitions of: ``` _v = arg.pop("something", None) _v = something if something is not None else _v if _v is not None: self["something"] = _v ``` Original size of plotly/**/*.py: 42283582 bytes Current size of plotly/**/*.py: 31931739 bytes Change: -25%
plotly · gvwilson · Feb 4, 2025 · Feb 5, 2025 · Feb 11, 2025 · Feb 11, 2025
commit 3cb93037ff81940f6e9fc0284729e18d06b863fe
diff --git a/_plotly_utils/basevalidators.py b/_plotly_utils/basevalidators.py
@@ -1328,25 +1328,14 @@ def numbers_allowed(self):
         return self.colorscale_path is not None
 
     def description(self):
-
-        named_clrs_str = "\n".join(
-            textwrap.wrap(
-                ", ".join(self.named_colors),
-                width=79 - 16,
-                initial_indent=" " * 12,
-                subsequent_indent=" " * 12,
-            )
-        )
-
         valid_color_description = """\
     The '{plotly_name}' property is a color and may be specified as:
       - A hex string (e.g. '#ff0000')
       - An rgb/rgba string (e.g. 'rgb(255,0,0)')
       - An hsl/hsla string (e.g. 'hsl(0,100%,50%)')
       - An hsv/hsva string (e.g. 'hsv(0,100%,100%)')
-      - A named CSS color:
-{clrs}""".format(
-            plotly_name=self.plotly_name, clrs=named_clrs_str
+      - A named CSS color""".format(
+            plotly_name=self.plotly_name
         )
 
         if self.colorscale_path:
@@ -2483,15 +2472,11 @@ def description(self):
     that may be specified as:
       - An instance of :class:`{module_str}.{class_str}`
       - A dict of string/value properties that will be passed
-        to the {class_str} constructor
-
-        Supported dict properties:
-            {constructor_params_str}"""
+        to the {class_str} constructor"""
         ).format(
             plotly_name=self.plotly_name,
             class_str=self.data_class_str,
             module_str=self.module_str,
-            constructor_params_str=self.data_docs,
         )
 
         return desc
@@ -2560,15 +2545,11 @@ def description(self):
     {class_str} that may be specified as:
       - A list or tuple of instances of {module_str}.{class_str}
       - A list or tuple of dicts of string/value properties that
-        will be passed to the {class_str} constructor
-
-        Supported dict properties:
-            {constructor_params_str}"""
+        will be passed to the {class_str} constructor"""
         ).format(
             plotly_name=self.plotly_name,
             class_str=self.data_class_str,
             module_str=self.module_str,
-            constructor_params_str=self.data_docs,
         )
 
         return desc

diff --git a/bin/get_size.py b/bin/get_size.py
@@ -0,0 +1,32 @@
+"""Calculate total size and total number of files of package."""
+
+from pathlib import Path
+import sys
+
+
+def main():
+    """Main driver."""
+    assert 2 <= len(sys.argv) <= 3, "Usage: get_size.py src_dir [build_dir]"
+
+    src_files, src_bytes = get_size(sys.argv[1])
+    print(f"src,files,{src_files}")
+    print(f"src,bytes,{src_bytes}")
+
+    if len(sys.argv) == 3:
+        build_files, build_bytes = get_size(sys.argv[2])
+        print(f"build,files,{build_files}")
+        print(f"build,bytes,{build_bytes}")
+
+
+def get_size(root_dir):
+    """Count files and size in bytes."""
+    num_files, num_bytes = 0, 0
+    for f in Path(root_dir).glob("**/*.*"):
+        if "__pycache__" not in str(f):
+            num_files += 1
+            num_bytes += f.stat().st_size
+    return num_files, num_bytes
+
+
+if __name__ == "__main__":
+    main()
diff --git a/codegen/__init__.py b/codegen/__init__.py
@@ -85,7 +85,7 @@ def preprocess_schema(plotly_schema):
         items["colorscale"] = items.pop("concentrationscales")
 
 
-def perform_codegen():
+def perform_codegen(reformat=True):
     # Set root codegen output directory
     # ---------------------------------
     # (relative to project root)
@@ -267,36 +267,24 @@ def perform_codegen():
         root_datatype_imports.append(f"._deprecations.{dep_clas}")
 
     optional_figure_widget_import = f"""
-if sys.version_info < (3, 7) or TYPE_CHECKING:
-    try:
-        import ipywidgets as _ipywidgets
-        from packaging.version import Version as _Version
-        if _Version(_ipywidgets.__version__) >= _Version("7.0.0"):
-            from ..graph_objs._figurewidget import FigureWidget
-        else:
-            raise ImportError()
-    except Exception:
-        from ..missing_anywidget import FigureWidget
-else:
-    __all__.append("FigureWidget")
-    orig_getattr = __getattr__
-    def __getattr__(import_name):
-        if import_name == "FigureWidget":
-            try:
-                import ipywidgets
-                from packaging.version import Version
-
-                if Version(ipywidgets.__version__) >= Version("7.0.0"):
-                    from ..graph_objs._figurewidget import FigureWidget
-
-                    return FigureWidget
-                else:
-                    raise ImportError()
-            except Exception:
-                from ..missing_anywidget import FigureWidget
+__all__.append("FigureWidget")
+orig_getattr = __getattr__
+def __getattr__(import_name):
+    if import_name == "FigureWidget":
+        try:
+            import ipywidgets
+            from packaging.version import Version
+
+            if Version(ipywidgets.__version__) >= Version("7.0.0"):
+                from ..graph_objs._figurewidget import FigureWidget
                 return FigureWidget
+            else:
+                raise ImportError()
+        except Exception:
+            from ..missing_anywidget import FigureWidget
+            return FigureWidget
 
-        return orig_getattr(import_name)
+    return orig_getattr(import_name)
 """
     # ### __all__ ###
     for path_parts, class_names in alls.items():
@@ -337,9 +325,12 @@ def __getattr__(import_name):
         f.write(graph_objects_init_source)
 
     # ### Run black code formatter on output directories ###
-    subprocess.call(["black", "--target-version=py36", validators_pkgdir])
-    subprocess.call(["black", "--target-version=py36", graph_objs_pkgdir])
-    subprocess.call(["black", "--target-version=py36", graph_objects_path])
+    if reformat:
+        subprocess.call(["black", "--target-version=py36", validators_pkgdir])
+        subprocess.call(["black", "--target-version=py36", graph_objs_pkgdir])
+        subprocess.call(["black", "--target-version=py36", graph_objects_path])
+    else:
+        print("skipping reformatting")
 
 
 if __name__ == "__main__":

diff --git a/codegen/compatibility.py b/codegen/compatibility.py
@@ -89,7 +89,7 @@ def __init__(self, *args, **kwargs):
         {depr_msg}
         \"\"\"
         warnings.warn(\"\"\"{depr_msg}\"\"\", DeprecationWarning)
-        super({class_name}, self).__init__(*args, **kwargs)\n\n\n"""
+        super().__init__(*args, **kwargs)\n\n\n"""
         )
 
     # Return source string

diff --git a/codegen/datatypes.py b/codegen/datatypes.py
@@ -127,7 +127,7 @@ class {datatype_class}(_{node.name_base_datatype}):\n"""
 
     import re
     _subplotid_prop_re = re.compile(
-        '^(' + '|'.join(_subplotid_prop_names) + r')(\d+)$')
+        '^(' + '|'.join(_subplotid_prop_names) + r')(\\d+)$')
 """
         )
 
@@ -323,8 +323,7 @@ def __init__(self"""
 
     buffer.write(
         f"""
-        super({datatype_class}, self).__init__('{node.name_property}')
-
+        super().__init__('{node.name_property}')
         if '_parent' in kwargs:
             self._parent = kwargs['_parent']
             return
@@ -373,10 +372,7 @@ def __init__(self"""
         name_prop = subtype_node.name_property
         buffer.write(
             f"""
-        _v = arg.pop('{name_prop}', None)
-        _v = {name_prop} if {name_prop} is not None else _v
-        if _v is not None:
-            self['{name_prop}'] = _v"""
+        self._init_provided('{name_prop}', arg, {name_prop})"""
         )
 
     # ### Literals ###

diff --git a/codegen/figure.py b/codegen/figure.py
@@ -108,9 +108,7 @@ def __init__(self, data=None, layout=None,
             if a property in the specification of data, layout, or frames
             is invalid AND skip_invalid is False
         \"\"\"
-        super({fig_classname} ,self).__init__(data, layout,
-                                              frames, skip_invalid,
-                                              **kwargs)
+        super().__init__(data, layout, frames, skip_invalid, **kwargs)
     """
     )
 
@@ -121,7 +119,7 @@ def {wrapped_name}(self, {full_params}) -> "{fig_classname}":
         '''
         {getattr(BaseFigure, wrapped_name).__doc__}
         '''
-        return super({fig_classname}, self).{wrapped_name}({param_list})
+        return super().{wrapped_name}({param_list})
     """
         )