refactor: Refactor changed_files option

Author: kvankova

pyproject.toml

@@ -8,7 +8,7 @@ license = "MIT"
 packages = [{include = "src"}]
 
 [tool.poetry.scripts]
-code-embedder = "src.main:run"
+code-embedder = "src.main:app"
 
 [tool.poetry.dependencies]
 python = "^3.11"

src/code_embedding.py

@@ -9,16 +9,18 @@ class CodeEmbedder:
     def __init__(
         self,
         readme_paths: list[str],
+        changed_files: list[str] | None,
         script_metadata_extractor: ScriptMetadataExtractorInterface,
         script_content_reader: ScriptContentReaderInterface,
     ) -> None:
         self._readme_paths = readme_paths
+        self._changed_files = changed_files
         self._script_metadata_extractor = script_metadata_extractor
         self._script_content_reader = script_content_reader
 
     def __call__(self) -> None:
         for readme_path in self._readme_paths:
-            self._process_readme(readme_path)
+            self._process_readme(readme_path=readme_path)
 
     def _process_readme(self, readme_path: str) -> None:
         readme_content = self._read_readme(readme_path)
@@ -27,9 +29,16 @@ def _process_readme(self, readme_path: str) -> None:
             return
 
         scripts = self._extract_scripts(readme_content=readme_content, readme_path=readme_path)
+
         if not scripts:
             return
 
+        if self._changed_files:
+            # Reduce scripts to only the ones that have changed only when there were no changes
+            # to the readme file
+            if readme_path not in self._changed_files:
+                scripts = [script for script in scripts if script.path in self._changed_files]
+
         script_contents = self._script_content_reader.read(scripts=scripts)
 
         self._update_readme(

src/main.py

@@ -10,13 +10,13 @@
 
 app = typer.Typer()
 
-# Setup logging for the script running as pre-commit hook
 logger.remove()
 logger.add(sys.stderr, level="ERROR")
 
 
 @app.command(help="Embed code from scripts to markdown files.")
 def run(
+    all_files: bool = typer.Option(False, help="Process all files in the repository."),
     changed_files: list[str] = typer.Argument(None, help="List of changed files to process."),
 ):
     readme_paths = glob.glob("**/*.md", recursive=True)
@@ -27,8 +27,11 @@ def run(
 
     script_metadata_extractor = ScriptMetadataExtractor()
     script_content_reader = ScriptContentReader()
+    files = changed_files if not all_files else None  # None for all files
+
     code_embedder = CodeEmbedder(
         readme_paths=readme_paths,
+        changed_files=files,
         script_metadata_extractor=script_metadata_extractor,
         script_content_reader=script_content_reader,
     )
@@ -38,7 +41,4 @@ def run(
 
 
 if __name__ == "__main__":
-    # Update logging for the script running as github action
-    logger.remove()
-    logger.add(sys.stderr, level="INFO")
     typer.run(run)

tests/test_code_embedding.py

@@ -48,6 +48,7 @@ def test_code_embedder(
 
     code_embedder = CodeEmbedder(
         readme_paths=[str(temp_readme_path)],
+        changed_files=None,
         script_metadata_extractor=ScriptMetadataExtractor(),
         script_content_reader=ScriptContentReader(),
     )
@@ -66,6 +67,7 @@ def test_code_embedder(
 def test_code_embedder_unknown_path() -> None:
     code_embedder = CodeEmbedder(
         readme_paths=["tests/data/readme4.md"],
+        changed_files=None,
         script_metadata_extractor=ScriptMetadataExtractor(),
         script_content_reader=ScriptContentReader(),
     )