Merge pull request #1994 from SamuelMarks:auto_check_and_precommit_and_bash_code_style_sh

PiperOrigin-RevId: 813846084

Author: Google-ML-Automation

.editorconfig

@@ -0,0 +1,11 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+
+[*.py]
+charset = utf-8
+indent_style = space
+indent_size = 2
+max_line_length = 125

.github/workflows/CPUTests.yml

@@ -34,20 +34,9 @@ jobs:
     - name: Typecheck the code with pytype
       run: |
         pytype --jobs auto --disable 'import-error,late-directive,wrong-arg-types,module-attr,unsupported-operands' src/MaxText/ || true
-    - name: Analysing the code with pylint in Maxtext/
+    - name: pylint
       run: |
-         pylint --verbose --msg-template='[{abspath}] {msg_id}:{line:3d},{column}: {obj}: {msg}' --disable C0114,R0401,R0917,W0201,W0613 src/MaxText/ || true
-    - name: Analysing the code with pylint in pedagogical_examples/
+         pylint --disable=R0401,R0917,W0201,W0613 --ignore-patterns='.pytype,.*pyi$' benchmarks end_to_end src tests
+    - name: pyink
       run: |
-         pylint pedagogical_examples/ && \
-         echo 'PyLint check on pedagogical_examples/ is successful' || { echo \
-         'PyLint check has failed. Please run bash code_style.sh to fix issues'; exit 20; }
-    - name: Analysing the code with pyink in Maxtext/
-      run: |
-        pyink src/MaxText --check --diff --color --pyink-indentation=2 --line-length=125 || true
-    - name: Analysing the code with pyink in pedagogical_examples/
-      run: |
-        pyink pedagogical_examples --check --diff --color --pyink-indentation=2 --line-length=125
-
-
-
+        pyink --pyink-indentation=2 --line-length=122 --check .

.pre-commit-config.yaml

@@ -1,7 +1,54 @@
+---
+files: ^(.*\.(py|md|sh|yaml|yml|in|cfg|txt|rst|toml|precommit-toml|wordlist))$
+exclude: ^(\.[^/]*(cache|assets|uv|venv)/.*)$
 repos:
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.4
+    rev: v2.4.1
     hooks:
-    - id: codespell
-      name: Running codespell for typos
-      entry: codespell -w --skip="*.txt,pylintrc,.*,src/MaxText/assets/*" .
+      - id: codespell
+        args:
+          - '-w'
+          - '--skip="*.txt,pylintrc,.*,src/MaxText/assets/*"'
+          - '-L ND,nd,sems,TE,ROUGE,rouge,astroid'
+          - '.'
+        additional_dependencies:
+          - tomli
+
+  #   - repo: https://github.com/abravalheri/validate-pyproject
+  #     rev: v0.24.1
+  #     hooks:
+  #       - id: validate-pyproject
+  #         name: Validate pyproject.toml
+  #         language: python
+  #         files: '^pyproject\.toml$'
+  #         entry: python
+
+  - repo: https://github.com/pylint-dev/pylint
+    rev: v3.3.8
+    hooks:
+      - id: pylint
+        args:
+          - '--disable=R0401,R0917,W0201,W0613'
+          - "--ignore-patterns='.pytype,.*pyi$'"
+          - 'benchmarks'
+          - 'end_to_end'
+          - 'src'
+          - 'tests'
+
+  #  - repo: https://github.com/google/pytype
+  #    rev: 2024.10.11
+  #    hooks:
+  #      - id: pytype
+  #        args:
+  #          - '--jobs=auto'
+  #          - '--keep-going'
+  #          - 'src/MaxText/'
+
+  - repo: https://github.com/google/pyink
+    rev: 24.10.1
+    hooks:
+      - id: pyink
+        args:
+          - '--pyink-indentation=2'
+          - '--line-length=122'
+          - '--check'

.pre-commit-hooks.yaml

@@ -0,0 +1,40 @@
+- id: codespell
+  name: codespell
+  description: Checks for common misspellings in text files.
+  entry: codespell
+  language: python
+  exclude: '^\.[^/]*(cache|assets|uv|venv)/.*'
+  types: [ text ]
+
+- id: pyink
+  name: pyink
+  description: Run pyink Python code formatter.
+  entry: pyink
+  language: python
+  types:
+    - python
+    - text
+
+# - id: pytype
+#   name: Pytype
+#   description: A static type analyzer for Python code.
+#   entry: pytype
+#   language: system
+#   types: [ python ]
+
+- id: pylint
+  name: pylint
+  description: Checks for errors, enforces a coding standard, looks for code smells.
+  entry: pylint
+  language: system
+  types: [ python ]
+
+# - id: validate-pyproject
+#   name: check toml
+#   description: checks pyproject.toml file
+#   types:
+#     - python
+#     - text
+#     - toml
+#   files: '^pyproject\.toml$'
+#   entry: validate-pyproject

benchmarks/__init__.py

@@ -11,3 +11,5 @@
 # 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.
+
+"""Init file for the benchmarks directory."""

benchmarks/api_server/README.md

@@ -291,7 +291,7 @@ python -m eval.eval \
     --output_path logs
 ```
 
-An example benchmark outpus will be like:
+An example benchmark outputs will be like:
 
 <img src="./images/mmlu_example.png" alt="MMLU Example" width="894"/>
 
@@ -314,4 +314,4 @@ python -m eval.eval \
 ```
 The valid arguments for `--gen_kwargs` are `temperature`, `top_p`, `top_k`, `stop`, `seed`, `max_tokens` and `max_gen_toks`. The `max_gen_toks` argument is used by some tasks in evaluation harness to control the maximum number of tokens to generate. We suggest pass `max_tokens` and `max_gen_toks` with the same value at the same time.
 
-The evaluation results will be saved to the directory specified by the `--output_path` argument (in the examples above, a directory named `logs`).
+The evaluation results will be saved to the directory specified by the `--output_path` argument (in the examples above, a directory named `logs`).