⚒️ Tweak translate script and CI (#13939)

diff --git a/.github/workflows/translate.yml b/.github/workflows/translate.yml
index edbff6fe54e4dcef21007b40c8fb43cbaaa74766..fc6b4d73075e75dc686bd62984a4fba9cf58e434 100644 (file)
--- a/.github/workflows/translate.yml
+++ b/.github/workflows/translate.yml
@@ -17,7 +17,7 @@ on:
           - add-missing
           - update-and-add
           - remove-all-removable
-      lang:
+      language:
         description: Language to translate to as a letter code (e.g. "es" for Spanish)
         type: string
         required: false
@@ -73,5 +73,5 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.FASTAPI_TRANSLATIONS }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          LANG: ${{ github.event.inputs.lang }}
+          LANGUAGE: ${{ github.event.inputs.language }}
           EN_PATH: ${{ github.event.inputs.en_path }}

diff --git a/scripts/translate.py b/scripts/translate.py
index 5fdbe7220366389157a16c66ee330c51a56626e4..e184496856b806b564dffffb572849bfd1b20ec0 100644 (file)
--- a/scripts/translate.py
+++ b/scripts/translate.py
@@ -94,12 +94,12 @@ def generate_en_path(*, lang: str, path: Path) -> Path:
 @app.command()
 def translate_page(
     *,
-    lang: Annotated[str, typer.Option(envvar="LANG")],
+    language: Annotated[str, typer.Option(envvar="LANGUAGE")],
     en_path: Annotated[Path, typer.Option(envvar="EN_PATH")],
 ) -> None:
     langs = get_langs()
-    language = langs[lang]
-    lang_path = Path(f"docs/{lang}")
+    language_name = langs[language]
+    lang_path = Path(f"docs/{language}")
     lang_path.mkdir(exist_ok=True)
     lang_prompt_path = lang_path / "llm-prompt.md"
     assert lang_prompt_path.exists(), f"Prompt file not found: {lang_prompt_path}"
@@ -109,14 +109,14 @@ def translate_page(
     assert str(en_path).startswith(str(en_docs_path)), (
         f"Path must be inside {en_docs_path}"
     )
-    out_path = generate_lang_path(lang=lang, path=en_path)
+    out_path = generate_lang_path(lang=language, path=en_path)
     out_path.parent.mkdir(parents=True, exist_ok=True)
     original_content = en_path.read_text()
     old_translation: str | None = None
     if out_path.exists():
         print(f"Found existing translation: {out_path}")
         old_translation = out_path.read_text()
-    print(f"Translating {en_path} to {lang} ({language})")
+    print(f"Translating {en_path} to {language} ({language_name})")
     agent = Agent("openai:gpt-4o")
 
     prompt_segments = [
@@ -135,7 +135,7 @@ def translate_page(
         )
     prompt_segments.extend(
         [
-            f"Translate to {language} ({lang}).",
+            f"Translate to {language} ({language_name}).",
             "Original content:",
             f"%%%\n{original_content}%%%",
         ]
@@ -180,7 +180,7 @@ def iter_en_paths_to_translate() -> Iterable[Path]:
 
 
 @app.command()
-def translate_lang(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
+def translate_lang(language: Annotated[str, typer.Option(envvar="LANGUAGE")]) -> None:
     paths_to_process = list(iter_en_paths_to_translate())
     print("Original paths:")
     for p in paths_to_process:
@@ -189,7 +189,7 @@ def translate_lang(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
     missing_paths: list[Path] = []
     skipped_paths: list[Path] = []
     for p in paths_to_process:
-        lang_path = generate_lang_path(lang=lang, path=p)
+        lang_path = generate_lang_path(lang=language, path=p)
         if lang_path.exists():
             skipped_paths.append(p)
             continue
@@ -204,16 +204,16 @@ def translate_lang(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
     print(f"Total paths to process: {len(missing_paths)}")
     for p in missing_paths:
         print(f"Translating: {p}")
-        translate_page(lang="es", en_path=p)
+        translate_page(language="es", en_path=p)
         print(f"Done translating: {p}")
 
 
 @app.command()
-def list_removable(lang: str) -> list[Path]:
+def list_removable(language: str) -> list[Path]:
     removable_paths: list[Path] = []
-    lang_paths = Path(f"docs/{lang}").rglob("*.md")
+    lang_paths = Path(f"docs/{language}").rglob("*.md")
     for path in lang_paths:
-        en_path = generate_en_path(lang=lang, path=path)
+        en_path = generate_en_path(lang=language, path=path)
         if not en_path.exists():
             removable_paths.append(path)
     print(removable_paths)
@@ -234,8 +234,8 @@ def list_all_removable() -> list[Path]:
 
 
 @app.command()
-def remove_removable(lang: str) -> None:
-    removable_paths = list_removable(lang)
+def remove_removable(language: str) -> None:
+    removable_paths = list_removable(language)
     for path in removable_paths:
         path.unlink()
         print(f"Removed: {path}")
@@ -252,11 +252,11 @@ def remove_all_removable() -> None:
 
 
 @app.command()
-def list_missing(lang: str) -> list[Path]:
+def list_missing(language: str) -> list[Path]:
     missing_paths: list[Path] = []
     en_lang_paths = list(iter_en_paths_to_translate())
     for path in en_lang_paths:
-        lang_path = generate_lang_path(lang=lang, path=path)
+        lang_path = generate_lang_path(lang=language, path=path)
         if not lang_path.exists():
             missing_paths.append(path)
     print(missing_paths)
@@ -264,14 +264,14 @@ def list_missing(lang: str) -> list[Path]:
 
 
 @app.command()
-def list_outdated(lang: str) -> list[Path]:
+def list_outdated(language: str) -> list[Path]:
     dir_path = Path(__file__).absolute().parent.parent
     repo = git.Repo(dir_path)
 
     outdated_paths: list[Path] = []
     en_lang_paths = list(iter_en_paths_to_translate())
     for path in en_lang_paths:
-        lang_path = generate_lang_path(lang=lang, path=path)
+        lang_path = generate_lang_path(lang=language, path=path)
         if not lang_path.exists():
             continue
         en_commit_datetime = list(repo.iter_commits(paths=path, max_count=1))[
@@ -287,38 +287,38 @@ def list_outdated(lang: str) -> list[Path]:
 
 
 @app.command()
-def update_outdated(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
-    outdated_paths = list_outdated(lang)
+def update_outdated(language: Annotated[str, typer.Option(envvar="LANGUAGE")]) -> None:
+    outdated_paths = list_outdated(language)
     for path in outdated_paths:
-        print(f"Updating lang: {lang} path: {path}")
-        translate_page(lang=lang, en_path=path)
+        print(f"Updating lang: {language} path: {path}")
+        translate_page(language=language, en_path=path)
         print(f"Done updating: {path}")
     print("Done updating all outdated paths")
 
 
 @app.command()
-def add_missing(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
-    missing_paths = list_missing(lang)
+def add_missing(language: Annotated[str, typer.Option(envvar="LANGUAGE")]) -> None:
+    missing_paths = list_missing(language)
     for path in missing_paths:
-        print(f"Adding lang: {lang} path: {path}")
-        translate_page(lang=lang, en_path=path)
+        print(f"Adding lang: {language} path: {path}")
+        translate_page(language=language, en_path=path)
         print(f"Done adding: {path}")
     print("Done adding all missing paths")
 
 
 @app.command()
-def update_and_add(lang: Annotated[str, typer.Option(envvar="LANG")]) -> None:
-    print(f"Updating outdated translations for {lang}")
-    update_outdated(lang=lang)
-    print(f"Adding missing translations for {lang}")
-    add_missing(lang=lang)
-    print(f"Done updating and adding for {lang}")
+def update_and_add(language: Annotated[str, typer.Option(envvar="LANGUAGE")]) -> None:
+    print(f"Updating outdated translations for {language}")
+    update_outdated(language=language)
+    print(f"Adding missing translations for {language}")
+    add_missing(language=language)
+    print(f"Done updating and adding for {language}")
 
 
 @app.command()
 def make_pr(
     *,
-    lang: Annotated[str, typer.Option(envvar="LANG")],
+    language: Annotated[str | None, typer.Option(envvar="LANGUAGE")] = None,
     github_token: Annotated[str, typer.Option(envvar="GITHUB_TOKEN")],
     github_repository: Annotated[str, typer.Option(envvar="GITHUB_REPOSITORY")],
 ) -> None:
@@ -331,14 +331,19 @@ def make_pr(
     subprocess.run(
         ["git", "config", "user.email", "github-actions@github.com"], check=True
     )
-    branch_name = f"translate-{lang}-{secrets.token_hex(4)}"
+    branch_name = "translate"
+    if language:
+        branch_name += f"-{language}"
+    branch_name += f"-{secrets.token_hex(4)}"
     print(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-b", branch_name], check=True)
     print("Adding updated files")
-    lang_path = Path(f"docs/{lang}")
-    subprocess.run(["git", "add", str(lang_path)], check=True)
+    git_path = Path("docs")
+    subprocess.run(["git", "add", str(git_path)], check=True)
     print("Committing updated file")
-    message = f"🌐 Update translations - {lang}"
+    message = "🌐 Update translations"
+    if language:
+        message += f" for {language}"
     subprocess.run(["git", "commit", "-m", message], check=True)
     print("Pushing branch")
     subprocess.run(["git", "push", "origin", branch_name], check=True)