feat: modifying 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.  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.  Assign an empty string to the `data_docs` field of generated validators.

1.  Introduce a method `_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: 50365842 bytes
Current size of plotly/**/*.py:  38256842 bytes
Change: -26%

Author: gvwilson

Diff for: packages/python/plotly/_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 for: packages/python/plotly/bin/get_size.py

@@ -0,0 +1,29 @@
+"""Calculate total size and total number of files of package."""
+
+from pathlib import Path
+import sys
+
+
+def main():
+    """Main driver."""
+    assert len(sys.argv) == 3, "Usage: get_size.py src_dir build_dir"
+    src_files, src_bytes = get_size(sys.argv[1])
+    build_files, build_bytes = get_size(sys.argv[2])
+    print(f"src,files,{src_files}")
+    print(f"src,bytes,{src_bytes}")
+    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 for: packages/python/plotly/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)
@@ -337,9 +337,12 @@ 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 for: packages/python/plotly/codegen/datatypes.py

@@ -373,10 +373,7 @@ 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 for: packages/python/plotly/codegen/utils.py

@@ -456,9 +456,7 @@ def get_validator_params(self):
 
         if self.is_compound:
             params["data_class_str"] = repr(self.name_datatype_class)
-            params["data_docs"] = (
-                '"""' + self.get_constructor_params_docstring() + '\n"""'
-            )
+            params["data_docs"] = '"""\n"""'
         else:
             assert self.is_simple
 

Diff for: packages/python/plotly/codegen/validators.py

@@ -24,15 +24,15 @@ def build_validator_py(node: PlotlyNode):
     # ---------------
     assert node.is_datatype
 
-    # Initialize source code buffer
-    # -----------------------------
+    # Initialize
     buffer = StringIO()
+    import_alias = "_bv"
 
     # Imports
     # -------
     # ### Import package of the validator's superclass ###
     import_str = ".".join(node.name_base_validator.split(".")[:-1])
-    buffer.write(f"import {import_str }\n")
+    buffer.write(f"import {import_str} as {import_alias}\n")
 
     # Build Validator
     # ---------------
@@ -41,11 +41,11 @@ def build_validator_py(node: PlotlyNode):
 
     # ### Write class definition ###
     class_name = node.name_validator_class
-    superclass_name = node.name_base_validator
+    superclass_name = node.name_base_validator.split(".")[-1]
     buffer.write(
         f"""
 
-class {class_name}({superclass_name}):
+class {class_name}({import_alias}.{superclass_name}):
     def __init__(self, plotly_name={params['plotly_name']},
                        parent_name={params['parent_name']},
                        **kwargs):"""

Diff for: packages/python/plotly/plotly/basedatatypes.py

@@ -385,6 +385,18 @@ def _generator(i):
         yield x
 
 
+def _initialize_provided(obj, name, arg, provided):
+    """
+    Initialize a property of this object using the provided value
+    or a value popped from the arguments dictionary. If neither
+    is available, do not set the property.
+    """
+    val = arg.pop(name, None)
+    val = provided if provided is not None else val
+    if val is not None:
+        obj[name] = val
+
+
 class BaseFigure(object):
     """
     Base class for all figure types (both widget and non-widget)
@@ -834,6 +846,14 @@ def _ipython_display_(self):
         else:
             print(repr(self))
 
+    def _init_provided(self, name, arg, provided):
+        """
+        Initialize a property of this object using the provided value
+        or a value popped from the arguments dictionary. If neither
+        is available, do not set the property.
+        """
+        _initialize_provided(self, name, arg, provided)
+
     def update(self, dict1=None, overwrite=False, **kwargs):
         """
         Update the properties of the figure with a dict and/or with
@@ -4329,6 +4349,14 @@ def _get_validator(self, prop):
 
         return ValidatorCache.get_validator(self._path_str, prop)
 
+    def _init_provided(self, name, arg, provided):
+        """
+        Initialize a property of this object using the provided value
+        or a value popped from the arguments dictionary. If neither
+        is available, do not set the property.
+        """
+        _initialize_provided(self, name, arg, provided)
+
     @property
     def _validators(self):
         """

Diff for: packages/python/plotly/plotly/graph_objects/__init__.py

@@ -1,6 +1,5 @@
 import sys
 from typing import TYPE_CHECKING
-
 if sys.version_info < (3, 7) or TYPE_CHECKING:
     from ..graph_objs import Waterfall
     from ..graph_objs import Volume
@@ -131,148 +130,17 @@
     from ..graph_objs import layout
 else:
     from _plotly_utils.importers import relative_import
-
     __all__, __getattr__, __dir__ = relative_import(
         __name__,
-        [
-            "..graph_objs.waterfall",
-            "..graph_objs.volume",
-            "..graph_objs.violin",
-            "..graph_objs.treemap",
-            "..graph_objs.table",
-            "..graph_objs.surface",
-            "..graph_objs.sunburst",
-            "..graph_objs.streamtube",
-            "..graph_objs.splom",
-            "..graph_objs.scatterternary",
-            "..graph_objs.scattersmith",
-            "..graph_objs.scatterpolargl",
-            "..graph_objs.scatterpolar",
-            "..graph_objs.scattermapbox",
-            "..graph_objs.scattermap",
-            "..graph_objs.scattergl",
-            "..graph_objs.scattergeo",
-            "..graph_objs.scattercarpet",
-            "..graph_objs.scatter3d",
-            "..graph_objs.scatter",
-            "..graph_objs.sankey",
-            "..graph_objs.pie",
-            "..graph_objs.parcoords",
-            "..graph_objs.parcats",
-            "..graph_objs.ohlc",
-            "..graph_objs.mesh3d",
-            "..graph_objs.isosurface",
-            "..graph_objs.indicator",
-            "..graph_objs.image",
-            "..graph_objs.icicle",
-            "..graph_objs.histogram2dcontour",
-            "..graph_objs.histogram2d",
-            "..graph_objs.histogram",
-            "..graph_objs.heatmap",
-            "..graph_objs.funnelarea",
-            "..graph_objs.funnel",
-            "..graph_objs.densitymapbox",
-            "..graph_objs.densitymap",
-            "..graph_objs.contourcarpet",
-            "..graph_objs.contour",
-            "..graph_objs.cone",
-            "..graph_objs.choroplethmapbox",
-            "..graph_objs.choroplethmap",
-            "..graph_objs.choropleth",
-            "..graph_objs.carpet",
-            "..graph_objs.candlestick",
-            "..graph_objs.box",
-            "..graph_objs.barpolar",
-            "..graph_objs.bar",
-            "..graph_objs.layout",
-        ],
-        [
-            "..graph_objs.Waterfall",
-            "..graph_objs.Volume",
-            "..graph_objs.Violin",
-            "..graph_objs.Treemap",
-            "..graph_objs.Table",
-            "..graph_objs.Surface",
-            "..graph_objs.Sunburst",
-            "..graph_objs.Streamtube",
-            "..graph_objs.Splom",
-            "..graph_objs.Scatterternary",
-            "..graph_objs.Scattersmith",
-            "..graph_objs.Scatterpolargl",
-            "..graph_objs.Scatterpolar",
-            "..graph_objs.Scattermapbox",
-            "..graph_objs.Scattermap",
-            "..graph_objs.Scattergl",
-            "..graph_objs.Scattergeo",
-            "..graph_objs.Scattercarpet",
-            "..graph_objs.Scatter3d",
-            "..graph_objs.Scatter",
-            "..graph_objs.Sankey",
-            "..graph_objs.Pie",
-            "..graph_objs.Parcoords",
-            "..graph_objs.Parcats",
-            "..graph_objs.Ohlc",
-            "..graph_objs.Mesh3d",
-            "..graph_objs.Isosurface",
-            "..graph_objs.Indicator",
-            "..graph_objs.Image",
-            "..graph_objs.Icicle",
-            "..graph_objs.Histogram2dContour",
-            "..graph_objs.Histogram2d",
-            "..graph_objs.Histogram",
-            "..graph_objs.Heatmap",
-            "..graph_objs.Funnelarea",
-            "..graph_objs.Funnel",
-            "..graph_objs.Densitymapbox",
-            "..graph_objs.Densitymap",
-            "..graph_objs.Contourcarpet",
-            "..graph_objs.Contour",
-            "..graph_objs.Cone",
-            "..graph_objs.Choroplethmapbox",
-            "..graph_objs.Choroplethmap",
-            "..graph_objs.Choropleth",
-            "..graph_objs.Carpet",
-            "..graph_objs.Candlestick",
-            "..graph_objs.Box",
-            "..graph_objs.Barpolar",
-            "..graph_objs.Bar",
-            "..graph_objs.Layout",
-            "..graph_objs.Frame",
-            "..graph_objs.Figure",
-            "..graph_objs.Data",
-            "..graph_objs.Annotations",
-            "..graph_objs.Frames",
-            "..graph_objs.AngularAxis",
-            "..graph_objs.Annotation",
-            "..graph_objs.ColorBar",
-            "..graph_objs.Contours",
-            "..graph_objs.ErrorX",
-            "..graph_objs.ErrorY",
-            "..graph_objs.ErrorZ",
-            "..graph_objs.Font",
-            "..graph_objs.Legend",
-            "..graph_objs.Line",
-            "..graph_objs.Margin",
-            "..graph_objs.Marker",
-            "..graph_objs.RadialAxis",
-            "..graph_objs.Scene",
-            "..graph_objs.Stream",
-            "..graph_objs.XAxis",
-            "..graph_objs.YAxis",
-            "..graph_objs.ZAxis",
-            "..graph_objs.XBins",
-            "..graph_objs.YBins",
-            "..graph_objs.Trace",
-            "..graph_objs.Histogram2dcontour",
-        ],
+        ['..graph_objs.waterfall', '..graph_objs.volume', '..graph_objs.violin', '..graph_objs.treemap', '..graph_objs.table', '..graph_objs.surface', '..graph_objs.sunburst', '..graph_objs.streamtube', '..graph_objs.splom', '..graph_objs.scatterternary', '..graph_objs.scattersmith', '..graph_objs.scatterpolargl', '..graph_objs.scatterpolar', '..graph_objs.scattermapbox', '..graph_objs.scattermap', '..graph_objs.scattergl', '..graph_objs.scattergeo', '..graph_objs.scattercarpet', '..graph_objs.scatter3d', '..graph_objs.scatter', '..graph_objs.sankey', '..graph_objs.pie', '..graph_objs.parcoords', '..graph_objs.parcats', '..graph_objs.ohlc', '..graph_objs.mesh3d', '..graph_objs.isosurface', '..graph_objs.indicator', '..graph_objs.image', '..graph_objs.icicle', '..graph_objs.histogram2dcontour', '..graph_objs.histogram2d', '..graph_objs.histogram', '..graph_objs.heatmap', '..graph_objs.funnelarea', '..graph_objs.funnel', '..graph_objs.densitymapbox', '..graph_objs.densitymap', '..graph_objs.contourcarpet', '..graph_objs.contour', '..graph_objs.cone', '..graph_objs.choroplethmapbox', '..graph_objs.choroplethmap', '..graph_objs.choropleth', '..graph_objs.carpet', '..graph_objs.candlestick', '..graph_objs.box', '..graph_objs.barpolar', '..graph_objs.bar', '..graph_objs.layout'],
+        ['..graph_objs.Waterfall', '..graph_objs.Volume', '..graph_objs.Violin', '..graph_objs.Treemap', '..graph_objs.Table', '..graph_objs.Surface', '..graph_objs.Sunburst', '..graph_objs.Streamtube', '..graph_objs.Splom', '..graph_objs.Scatterternary', '..graph_objs.Scattersmith', '..graph_objs.Scatterpolargl', '..graph_objs.Scatterpolar', '..graph_objs.Scattermapbox', '..graph_objs.Scattermap', '..graph_objs.Scattergl', '..graph_objs.Scattergeo', '..graph_objs.Scattercarpet', '..graph_objs.Scatter3d', '..graph_objs.Scatter', '..graph_objs.Sankey', '..graph_objs.Pie', '..graph_objs.Parcoords', '..graph_objs.Parcats', '..graph_objs.Ohlc', '..graph_objs.Mesh3d', '..graph_objs.Isosurface', '..graph_objs.Indicator', '..graph_objs.Image', '..graph_objs.Icicle', '..graph_objs.Histogram2dContour', '..graph_objs.Histogram2d', '..graph_objs.Histogram', '..graph_objs.Heatmap', '..graph_objs.Funnelarea', '..graph_objs.Funnel', '..graph_objs.Densitymapbox', '..graph_objs.Densitymap', '..graph_objs.Contourcarpet', '..graph_objs.Contour', '..graph_objs.Cone', '..graph_objs.Choroplethmapbox', '..graph_objs.Choroplethmap', '..graph_objs.Choropleth', '..graph_objs.Carpet', '..graph_objs.Candlestick', '..graph_objs.Box', '..graph_objs.Barpolar', '..graph_objs.Bar', '..graph_objs.Layout', '..graph_objs.Frame', '..graph_objs.Figure', '..graph_objs.Data', '..graph_objs.Annotations', '..graph_objs.Frames', '..graph_objs.AngularAxis', '..graph_objs.Annotation', '..graph_objs.ColorBar', '..graph_objs.Contours', '..graph_objs.ErrorX', '..graph_objs.ErrorY', '..graph_objs.ErrorZ', '..graph_objs.Font', '..graph_objs.Legend', '..graph_objs.Line', '..graph_objs.Margin', '..graph_objs.Marker', '..graph_objs.RadialAxis', '..graph_objs.Scene', '..graph_objs.Stream', '..graph_objs.XAxis', '..graph_objs.YAxis', '..graph_objs.ZAxis', '..graph_objs.XBins', '..graph_objs.YBins', '..graph_objs.Trace', '..graph_objs.Histogram2dcontour']
     )
 
 
 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:
@@ -282,7 +150,6 @@
 else:
     __all__.append("FigureWidget")
     orig_getattr = __getattr__
-
     def __getattr__(import_name):
         if import_name == "FigureWidget":
             try:
@@ -297,7 +164,7 @@ def __getattr__(import_name):
                     raise ImportError()
             except Exception:
                 from ..missing_anywidget import FigureWidget
-
                 return FigureWidget
 
         return orig_getattr(import_name)
+