blumeops/mise-tasks/doc-links

133 lines
4.2 KiB
Text
Raw Normal View History

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.12"
# dependencies = ["pyyaml>=6.0", "rich>=13.0.0"]
# ///
#MISE description="Validate all wiki-links point to existing doc titles"
"""Validate that all wiki-links in documentation point to existing titles.
This script scans all markdown files in the docs/ directory (excluding
changelog.d/ and zk/), extracts wiki-links, and verifies each link target
exists as a frontmatter title in the documentation.
Wiki-link formats supported:
- [[Title]] - links to a doc with frontmatter title "Title"
- [[Title|Display Text]] - links to "Title", displays "Display Text"
Usage: mise run doc-links
"""
import re
import sys
from collections import defaultdict
from pathlib import Path
import yaml
from rich.console import Console
from rich.markup import escape
from rich.table import Table
DOCS_DIR = Path(__file__).parent.parent / "docs"
# Regex to match wiki-links: [[Target]] or [[Target|Display]]
WIKILINK_PATTERN = re.compile(r"\[\[([^\]|]+)(?:\|[^\]]+)?\]\]")
# Regex to match inline code (backticks)
INLINE_CODE_PATTERN = re.compile(r"`[^`]+`")
def extract_frontmatter(file_path: Path) -> dict | None:
"""Extract YAML frontmatter from a markdown file."""
content = file_path.read_text()
if not content.startswith("---"):
return None
end_idx = content.find("---", 3)
if end_idx == -1:
return None
frontmatter_text = content[3:end_idx].strip()
try:
return yaml.safe_load(frontmatter_text) or {}
except yaml.YAMLError:
return None
def extract_wikilinks(file_path: Path) -> list[tuple[str, int]]:
"""Extract all wiki-link targets from a markdown file with line numbers.
Ignores wiki-links inside inline code (backticks) as these are examples.
"""
content = file_path.read_text()
links = []
for line_num, line in enumerate(content.splitlines(), start=1):
# Remove inline code before searching for wiki-links
line_without_code = INLINE_CODE_PATTERN.sub("", line)
for match in WIKILINK_PATTERN.finditer(line_without_code):
target = match.group(1).strip()
links.append((target, line_num))
return links
def main() -> int:
console = Console()
# Collect all valid titles from frontmatter
valid_titles: set[str] = set()
# Scan all markdown files for titles (excluding zk/ and changelog.d/)
for md_file in DOCS_DIR.rglob("*.md"):
if "changelog.d" in md_file.parts or "zk" in md_file.parts:
continue
frontmatter = extract_frontmatter(md_file)
if frontmatter and frontmatter.get("title"):
valid_titles.add(frontmatter["title"])
# Collect all broken links
# Key: (file_path, line_num), Value: target
broken_links: list[tuple[str, int, str]] = []
# Scan all markdown files for wiki-links (excluding zk/ and changelog.d/)
for md_file in sorted(DOCS_DIR.rglob("*.md")):
if "changelog.d" in md_file.parts or "zk" in md_file.parts:
continue
rel_path = str(md_file.relative_to(DOCS_DIR))
links = extract_wikilinks(md_file)
for target, line_num in links:
if target not in valid_titles:
broken_links.append((rel_path, line_num, target))
# Print results
console.print("[bold]Wiki-Link Validation[/bold]")
console.print()
console.print(f"Found {len(valid_titles)} valid titles in documentation.")
console.print()
if broken_links:
console.print("[bold red]Broken Wiki-Links Found[/bold red]")
table = Table(show_header=True, header_style="bold")
table.add_column("File")
table.add_column("Line", justify="right")
table.add_column("Target")
for file_path, line_num, target in broken_links:
table.add_row(file_path, str(line_num), escape(f"[[{target}]]"))
console.print(table)
console.print()
console.print(f"[bold red]{len(broken_links)} broken link(s) found.[/bold red]")
console.print()
console.print("Each wiki-link target must match a frontmatter title in docs/.")
return 1
console.print("[bold green]All wiki-links are valid![/bold green]")
return 0
if __name__ == "__main__":
sys.exit(main())