CI check comments of cheanged Python files

.github/workflows/tests.yml

@@ -95,6 +95,38 @@ jobs:
           version: ">=0.11.x"
           args: "check"
 
+      - name: Check comments of changed Python files
+        if: ${{ !cancelled() && !failure() }}
+        run: |
+          if [[ ${{ github.event_name }} == 'pull_request_target' ]]; then
+            CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }}...${{ github.event.pull_request.head.sha }} \
+              | grep -E '\.(py)$' || true)
+
+            if [ -n "$CHANGED_FILES" ]; then
+              echo "Check comments of changed Python files with check_comment_ascii.py"
+
+              readarray -t files <<< "$CHANGED_FILES"
+              HAS_ERROR=0
+
+              for file in "${files[@]}"; do
+                if [ -f "$file" ]; then
+                  if python3 check_comment_ascii.py $file"; then
+                    echo "✅ $file"
+                  else
+                    echo "❌ $file"
+                    HAS_ERROR=1
+                  fi
+                fi
+              done
+
+              if [ $HAS_ERROR -ne 0 ]; then
+                exit 1
+              fi
+            else
+              echo "No Python files changed"
+            fi
+          fi
+
       - name: Build ragflow:nightly
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-${HOME}}

check_comment_ascii.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+import sys
+import tokenize
+import ast
+import pathlib
+import re
+
+ASCII = re.compile(r"^[ -~]*\Z")  # Only printable ASCII
+
+
+def check(src: str, name: str) -> int:
+    """
+    I'm a docstring
+    """
+    ok = 1
+    # A common comment begins with `#`
+    with tokenize.open(src) as fp:
+        for tk in tokenize.generate_tokens(fp.readline):
+            if tk.type == tokenize.COMMENT and not ASCII.fullmatch(tk.string):
+                print(f"{name}:{tk.start[0]}: non-ASCII comment: {tk.string}")
+                ok = 0
+    # A docstring begins and ends with `'''`
+    for node in ast.walk(ast.parse(pathlib.Path(src).read_text(), filename=name)):
+        if isinstance(node, (ast.FunctionDef, ast.ClassDef, ast.Module)):
+            if (doc := ast.get_docstring(node)) and not ASCII.fullmatch(doc):
+                print(f"{name}:{node.lineno}: non-ASCII docstring: {doc}")
+                ok = 0
+    return ok
+
+
+if __name__ == "__main__":
+    status = 0
+    for file in sys.argv[1:]:
+        if not check(file, file):
+            status = 1
+    sys.exit(status)