Ci lint (#338)

* setup pre-commit

* add error codes

* precommit run

* fix build

Author: andrewfulton9

.github/workflows/ci-lint.yml

@@ -0,0 +1,21 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+     branches: [master]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4.1.7
+      with:
+        # Ensure the full history is fetched
+        # This is required to run pre-commit on a specific set of commits
+        # TODO: Remove this when all the pre-commit issues are fixed
+        fetch-depth: 0
+    - uses: actions/setup-python@v5.1.1
+      with:
+        python-version: 3.13
+    - uses: pre-commit/action@v3.0.1

.github/workflows/ci-test.yml

@@ -36,4 +36,4 @@ jobs:
     - name: Run unit tests
       shell: bash
       run: |
-        pytest 
+        pytest

.github/workflows/wheels.yml

@@ -20,11 +20,11 @@ jobs:
         python-version: '3.10'
 
     - name: Install python dependencies
-      run: pip install build twine
+      run: pip install --upgrade pip build twine
 
     - name: Build sdist and wheel
       run: |
-        python -m build -o wheelhouse
+        python -m build --sdist --wheel -o wheelhouse
 
     - name: List and check sdist
       run: |

.pre-commit-config.yaml

@@ -0,0 +1,39 @@
+# pre-commit is a tool to perform a predefined set of tasks manually and/or
+# automatically before git commits are made.
+#
+# Config reference: https://pre-commit.com/#pre-commit-configyaml---top-level
+#
+# Common tasks
+#
+# - Register git hooks: pre-commit install --install-hooks
+# - Run on all files:   pre-commit run --all-files
+#
+# These pre-commit hooks are run as CI.
+#
+# NOTE: if it can be avoided, add configs/args in pyproject.toml or below instead of creating a new `.config.file`.
+# https://pre-commit.ci/#configuration
+ci:
+  autoupdate_schedule: monthly
+  autofix_commit_msg: |
+    [pre-commit.ci] Apply automatic pre-commit fixes
+
+repos:
+  # general
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: end-of-file-fixer
+        exclude: '\.svg$'
+      - id: trailing-whitespace
+        exclude: '\.svg$'
+      - id: check-json
+      - id: check-yaml
+        args: [--allow-multiple-documents, --unsafe]
+      - id: check-toml
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format

RELEASE.md

@@ -67,7 +67,7 @@
 *   Enable passing `tf.saved_model.SaveOptions` to model saving functionality.
 *   Census and sentiment examples updated to only use Keras instead of
     estimator.
-*   Depends on `apache-beam[gcp]>=2.53.0,<3` for Python 3.11 and on 
+*   Depends on `apache-beam[gcp]>=2.53.0,<3` for Python 3.11 and on
     `apache-beam[gcp]>=2.47.0,<3` for 3.9 and 3.10.
 *   Depends on `protobuf>=4.25.2,<5` for Python 3.11 and on `protobuf>3.20.3,<5`
     for 3.9 and 3.10.
@@ -1535,4 +1535,3 @@ the generated vocab_filename on a downstream component.
 * Update tensorflow_transform to use `tf.saved_model` APIs.
 * Add default values on example proto coder.
 * Various performance and stability improvements.
-

docs/build_tft_beam_docs.py

@@ -25,51 +25,53 @@
 ```
 
 """
-from absl import app
-from absl import flags
 
-from tensorflow_docs.api_generator import doc_controls
-from tensorflow_docs.api_generator import generate_lib
-from tensorflow_docs.api_generator import public_api
-import tensorflow_transform.beam as tft_beam
+from absl import app, flags
+from tensorflow_docs.api_generator import doc_controls, generate_lib, public_api
 
+import tensorflow_transform.beam as tft_beam
 
-flags.DEFINE_string('output_dir', '/tmp/tft_beam_api/',
-                    'The path to output the files to')
+flags.DEFINE_string(
+    "output_dir", "/tmp/tft_beam_api/", "The path to output the files to"
+)
 
 flags.DEFINE_string(
-    'code_url_prefix',
-    'https://github.com/tensorflow/transform/tree/master/tensorflow_transform',
-    'The url prefix for links to code.')
+    "code_url_prefix",
+    "https://github.com/tensorflow/transform/tree/master/tensorflow_transform",
+    "The url prefix for links to code.",
+)
 
-flags.DEFINE_bool('search_hints', True,
-                  'Include metadata search hints in the generated files')
+flags.DEFINE_bool(
+    "search_hints", True, "Include metadata search hints in the generated files"
+)
 
-flags.DEFINE_string('site_path', 'tfx/transform/api_docs/python',
-                    'Path prefix in the _toc.yaml')
+flags.DEFINE_string(
+    "site_path", "tfx/transform/api_docs/python", "Path prefix in the _toc.yaml"
+)
 
 FLAGS = flags.FLAGS
 
 
 def main(args):
-  if args[1:]:
-    raise ValueError('Unrecognized Command line args', args[1:])
+    if args[1:]:
+        raise ValueError("Unrecognized Command line args", args[1:])
 
-  doc_controls.do_not_generate_docs(tft_beam.analyzer_impls)
+    doc_controls.do_not_generate_docs(tft_beam.analyzer_impls)
 
-  doc_generator = generate_lib.DocGenerator(
-      root_title='TFT-Beam',
-      py_modules=[('tft_beam', tft_beam)],
-      code_url_prefix=FLAGS.code_url_prefix + '/beam',
-      search_hints=FLAGS.search_hints,
-      site_path=FLAGS.site_path,
-      callbacks=[
-          public_api.explicit_package_contents_filter,
-          public_api.local_definitions_filter
-      ])
+    doc_generator = generate_lib.DocGenerator(
+        root_title="TFT-Beam",
+        py_modules=[("tft_beam", tft_beam)],
+        code_url_prefix=FLAGS.code_url_prefix + "/beam",
+        search_hints=FLAGS.search_hints,
+        site_path=FLAGS.site_path,
+        callbacks=[
+            public_api.explicit_package_contents_filter,
+            public_api.local_definitions_filter,
+        ],
+    )
 
-  doc_generator.build(FLAGS.output_dir)
+    doc_generator.build(FLAGS.output_dir)
 
 
-if __name__ == '__main__':
-  app.run(main)
+if __name__ == "__main__":
+    app.run(main)

docs/build_tft_docs.py

@@ -25,45 +25,46 @@
 ```
 
 """
-from absl import app
-from absl import flags
 
-from tensorflow_docs.api_generator import generate_lib
-from tensorflow_docs.api_generator import public_api
-import tensorflow_transform as transform
+from absl import app, flags
+from tensorflow_docs.api_generator import generate_lib, public_api
 
+import tensorflow_transform as transform
 
-flags.DEFINE_string('output_dir', '/tmp/tft_api/',
-                    'The path to output the files to')
+flags.DEFINE_string("output_dir", "/tmp/tft_api/", "The path to output the files to")
 
 flags.DEFINE_string(
-    'code_url_prefix',
-    'https://github.com/tensorflow/transform/tree/master/tensorflow_transform',
-    'The url prefix for links to code.')
+    "code_url_prefix",
+    "https://github.com/tensorflow/transform/tree/master/tensorflow_transform",
+    "The url prefix for links to code.",
+)
 
-flags.DEFINE_bool('search_hints', True,
-                  'Include metadata search hints in the generated files')
+flags.DEFINE_bool(
+    "search_hints", True, "Include metadata search hints in the generated files"
+)
 
-flags.DEFINE_string('site_path', 'tfx/transform/api_docs/python',
-                    'Path prefix in the _toc.yaml')
+flags.DEFINE_string(
+    "site_path", "tfx/transform/api_docs/python", "Path prefix in the _toc.yaml"
+)
 
 FLAGS = flags.FLAGS
 
 
 def main(args):
-  if args[1:]:
-    raise ValueError('Unrecognized Command line args', args[1:])
+    if args[1:]:
+        raise ValueError("Unrecognized Command line args", args[1:])
 
-  doc_generator = generate_lib.DocGenerator(
-      root_title='TF-Transform',
-      py_modules=[('tft', transform)],
-      code_url_prefix=FLAGS.code_url_prefix,
-      search_hints=FLAGS.search_hints,
-      site_path=FLAGS.site_path,
-      callbacks=[public_api.explicit_package_contents_filter])
+    doc_generator = generate_lib.DocGenerator(
+        root_title="TF-Transform",
+        py_modules=[("tft", transform)],
+        code_url_prefix=FLAGS.code_url_prefix,
+        search_hints=FLAGS.search_hints,
+        site_path=FLAGS.site_path,
+        callbacks=[public_api.explicit_package_contents_filter],
+    )
 
-  doc_generator.build(FLAGS.output_dir)
+    doc_generator.build(FLAGS.output_dir)
 
 
-if __name__ == '__main__':
-  app.run(main)
+if __name__ == "__main__":
+    app.run(main)

docs/index.md

@@ -11,7 +11,7 @@ The [`tft`](api_docs/python/tft)
 module documentation is the only module that is relevant to TFX users.
 The [`tft_beam`](api_docs/python/tft-beam)
 module is relevant only when using Transform as a standalone library.
-Typically, a TFX user constructs a `preprocessing_fn`, and the rest of the 
+Typically, a TFX user constructs a `preprocessing_fn`, and the rest of the
 Transform library calls are made by the Transform component.
 
 You can also use the Apache Beam `MLTransform`

docs/javascripts/mathjax.js

@@ -11,7 +11,7 @@ window.MathJax = {
   }
 };
 
-document$.subscribe(() => { 
+document$.subscribe(() => {
   MathJax.startup.output.clearCache()
   MathJax.typesetClear()
   MathJax.texReset()