scripts/wrong-filename.sh: convert to Python-script

scripts/README.md

@@ -13,13 +13,13 @@ This section contains a summary of the scripts available in this directory. For
 - [build.sh](build.sh) script builds the ZIP archives of the `pages` directory.
 - [build-index.sh](build-index.sh) script builds the index of available pages.
 - [check-pr.sh](check-pr.sh) script checks the page's syntax and performs various checks on the PR.
+- [check-page-title.py](check-page-title.py) is a Python script to check the consistency between the filenames and the page title.
 - [deploy.sh](deploy.sh) script deploys the ZIP and PDF archives to the static website repository.
 - [send-to-bot.py](send-to-bot.py) is a Python script that sends the build or test output to tldr-bot.
 - [set-alias-page.py](set-alias-page.py) is a Python script to generate or update alias pages.
 - [set-more-info-link.py](set-more-info-link.py) is a Python script to generate or update more information links across pages.
 - [set-page-title.py](set-page-title.py) is a Python script to update the title across pages.
 - [test.sh](test.sh) script runs some basic tests on every PR/commit to ensure the pages are valid and the code is formatted correctly.
-- [wrong-filename.sh](wrong-filename.sh) script checks the consistency between the filenames and the page title.
 - [update-command.py](update-command.py) is a Python script to update the common contents of a command example across all languages.
 
 ## Compatibility
@@ -31,8 +31,8 @@ The table below shows the compatibility of user-executable scripts with differen
 | [render.py](pdf/render.py) | ✅ | ✅ | ✅ |
 | [build-pdf.sh](pdf/build-pdf.sh) | ✅ | ✅ | ❌ (WSL ✅)|
 | [build.sh](build.sh) | ✅ | ✅ | ❌ (WSL ✅)|
+| [check-page-title.py](check-page-title.py) | ✅ | ✅ | ✅ |
 | [set-alias-pages.py](set-alias-pages.py) | ✅ | ✅ | ✅ |
 | [set-more-info-link.py](set-more-info-link.py) | ✅ | ✅ | ✅ |
 | [set-page-title.py](set-page-title.py) | ✅ | ✅ | ✅ |
-| [wrong-filename.sh](wrong-filename.sh) | ✅ | ❌ | ❌ (WSL ✅)|
 | [update-command.py](update-command.py) | ✅ | ✅ | ✅ |

scripts/_common.py

@@ -134,7 +134,59 @@ def test_get_pages_dir():
     shutil.rmtree(root, True)
 
 
-def get_target_paths(page: Path, pages_dirs: Path) -> list[Path]:
+def get_page_title(path: Path) -> str:
+    """
+    Determine whether the given path has a title.
+
+    Parameters:
+    path (Path): Path to a page
+
+    Returns:
+    str: "" If the path doesn't exit or does not have a title,
+         otherwise return the page title.
+    """
+
+    if not path.exists():
+        return ""
+    with path.open(encoding="utf-8") as f:
+        first_line = f.readline().strip()
+
+    return first_line.split("#", 1)[-1].strip()
+
+
+def test_get_page_title():
+    # Test valid title
+    root = Path("test_root")
+
+    shutil.rmtree(root, True)
+
+    root.mkdir(exist_ok=True)
+
+    valid_path = root / "test.md"
+    valid_path.write_text("# Git Clone\nSome content", encoding="utf-8")
+    assert get_page_title(valid_path) == "Git Clone"
+
+    # Test title with multiple hashes
+    hash_path = root / "multiple_hash.md"
+    hash_path.write_text("# Git ### Clone\nSome content", encoding="utf-8")
+    assert get_page_title(hash_path) == "Git ### Clone"
+
+    # Test empty title
+    empty_path = root / "empty.md"
+    empty_path.write_text("#\nSome content", encoding="utf-8")
+    assert get_page_title(empty_path) == ""
+
+    # Test non-existent file
+    nonexistent_path = root / "nonexistent.md"
+    assert get_page_title(nonexistent_path) == ""
+
+    # Test title with leading/trailing spaces
+    spaces_path = root / "spaces.md"
+    spaces_path.write_text("#    Git Clone    \nSome content", encoding="utf-8")
+    assert get_page_title(spaces_path) == "Git Clone"
+
+
+def get_target_paths(page: Path, pages_dirs: Path, language: str = "") -> list[Path]:
     """
     Get all paths in all languages that match the page.
 
@@ -152,6 +204,14 @@ def get_target_paths(page: Path, pages_dirs: Path) -> list[Path]:
     arg_platform, arg_page = page.split("/")
 
     for pages_dir in pages_dirs:
+        if "." in pages_dir.name:
+            _, locale = pages_dir.name.split(".")
+        else:
+            locale = "en"
+
+        if language != "" and language != locale:
+            continue
+
         page_path = pages_dir / arg_platform / arg_page
 
         if not page_path.exists():
@@ -173,18 +233,20 @@ def test_get_target_paths():
     shutil.os.makedirs(root / "pages" / "common")
     shutil.os.makedirs(root / "pages.fr" / "common")
 
-    file_path = root / "pages" / "common" / "tldr.md"
-    with open(file_path, "w"):
-        pass
-
-    file_path = root / "pages.fr" / "common" / "tldr.md"
-    with open(file_path, "w"):
-        pass
+    (root / "pages" / "common" / "tldr.md").touch()
+    (root / "pages.fr" / "common" / "tldr.md").touch()
 
     target_paths = get_target_paths("common/tldr", get_pages_dir(root))
-    for path in target_paths:
-        rel_path = "/".join(path.parts[-3:])
-        print(rel_path)
+    assert len(target_paths) == 2
+    assert all(p.name == "tldr.md" for p in target_paths)
+
+    fr_paths = get_target_paths("common/tldr", get_pages_dir(root), "fr")
+    assert len(fr_paths) == 1
+    assert str(fr_paths[0]).endswith("pages.fr/common/tldr.md")
+
+    en_paths = get_target_paths("common/tldr", get_pages_dir(root), "en")
+    assert len(en_paths) == 1
+    assert str(en_paths[0]).endswith("pages/common/tldr.md")
 
     shutil.rmtree(root, True)
 

scripts/check-page-title.py

@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: MIT
+
+"""
+A Python script to check if all page titles match with their filename.
+
+Usage:
+    python3 scripts/check-page-title.py [-p PAGE] [-l LANGUAGE]
+
+Options:
+    -p, --page PAGE
+        Specify the page in the format "platform/command". This option allows checking the title for a specific page.
+    -l, --language LANGUAGE
+        Specify the language, a POSIX Locale Name in the form of "ll" or "ll_CC" (e.g. "fr" or "pt_BR").
+
+Examples:
+    1. Check the page title for a specific page:
+       python3 scripts/check-page-title.py -p common/tar
+       python3 scripts/check-page-title.py --page common/tar
+
+    2. Check the page titles for Brazilian Portuguese pages only:
+       python3 scripts/check-page-title.py -l pt_BR
+       python3 scripts/check-page-title.py --language pt_BR
+"""
+
+from pathlib import Path
+import re
+import argparse
+from _common import (
+    IGNORE_FILES,
+    Colors,
+    get_tldr_root,
+    get_pages_dir,
+    get_target_paths,
+    get_page_title,
+    create_colored_line,
+)
+
+IGNORE_LIST = [
+    "exclamation mark",
+    "caret",
+    "dollar sign",
+    "tilde",
+    "percent sign",
+    "curly brace",
+    "history expansion",
+    "acme.sh   dns",
+    "pacman  d",
+    "pacman   database",
+    "pacman   deptest",
+    "pacman  f",
+    "pacman   files",
+    "pacman  q",
+    "pacman   query",
+    "pacman  r",
+    "pacman   remove",
+    "pacman  s",
+    "pacman   sync",
+    "pacman  t",
+    "pacman  u",
+    "pacman   upgrade",
+    "qm move disk",
+    "rename",
+    "umount",
+]
+
+
+def normalize_command_name(name: str) -> str:
+    name = name.lower()
+    name = re.sub(r"nix3", "nix", name)
+    name = re.sub(r"\.fish|\.js|\.1", "", name)
+    name = name.replace("-", " ")
+    return name.strip()
+
+
+def check_page_title(path: Path) -> str:
+    """
+    Check if the title of a page matches the filename.
+    """
+    command_name_file = normalize_command_name(path.stem)
+    command_name_page = normalize_command_name(get_page_title(path))
+
+    if command_name_file != command_name_page and command_name_page not in IGNORE_LIST:
+        return f"title should be {command_name_file} instead of {command_name_page}"
+
+    return ""
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Check if all page titles match with their filename."
+    )
+    parser.add_argument(
+        "-p",
+        "--page",
+        type=str,
+        default="",
+        help='page name in the format "platform/alias_command.md"',
+    )
+    parser.add_argument(
+        "-l",
+        "--language",
+        type=str,
+        default="",
+        help='language in the format "ll" or "ll_CC" (e.g. "fr" or "pt_BR")',
+    )
+
+    args = parser.parse_args()
+
+    root = get_tldr_root()
+    pages_dirs = get_pages_dir(root)
+
+    # Use '--page' option
+    if args.page != "":
+        target_paths = get_target_paths(args.page, pages_dirs, args.language)
+
+        for path in target_paths:
+            rel_path = "/".join(path.parts[-3:])
+            status = check_page_title(path)
+            if status != "":
+                print(create_colored_line(Colors.RED, f"{rel_path}: {status}"))
+        return
+
+    # Use '--language' option
+    if not args.language:
+        # Get all language folders (pages.*)
+        language_dirs = [d for d in root.iterdir() if d.name.startswith("pages.")]
+        locales = [d.name.split(".")[1] for d in language_dirs]
+    else:
+        locales = [args.language]
+
+    for locale in locales:
+        en_path = root / "pages"
+        platforms = [i.name for i in en_path.iterdir() if i.name not in IGNORE_FILES]
+
+        for platform in platforms:
+            platform_path = en_path / platform
+            commands = [
+                f"{platform}/{page.name}"
+                for page in platform_path.iterdir()
+                if page.name not in IGNORE_FILES
+            ]
+
+            for command in commands:
+                path = root / (f"pages.{locale}") / command
+                if path.exists():
+                    status = check_page_title(path)
+                    if status:
+                        rel_path = "/".join(path.parts[-3:])
+                        print(create_colored_line(Colors.RED, f"{rel_path} {status}"))
+
+
+if __name__ == "__main__":
+    main()

scripts/set-page-title.py

@@ -54,6 +54,7 @@
     get_tldr_root,
     get_pages_dir,
     get_target_paths,
+    get_page_title,
     get_locale,
     get_status,
     stage,
@@ -108,26 +109,6 @@ def set_page_title(
     return status
 
 
-def get_page_title(path: Path) -> str:
-    """
-    Determine whether the given path has a title.
-
-    Parameters:
-    path (Path): Path to a page
-
-    Returns:
-    str: "" If the path doesn't exit or does not have a title,
-         otherwise return the page title.
-    """
-
-    if not path.exists():
-        return ""
-    with path.open(encoding="utf-8") as f:
-        first_line = f.readline().strip()
-
-    return first_line.split("#", 1)[-1].strip()
-
-
 def sync(
     root: Path,
     pages_dirs: list[Path],