blumeops/mise-tasks/doc-links
Erich Blume 9630655cc9 Switch to filename-based wiki-links (Quartz resolves by filename)
- Convert all wiki-links from title-based to filename-based
- Update doc-links to validate against filenames
- Add doc-filenames task for duplicate filename detection
- Consolidate doc hooks into single local block in pre-commit config

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 16:29:31 -08:00

110 lines
3.5 KiB
Text
Executable file

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.12"
# dependencies = ["rich>=13.0.0"]
# ///
#MISE description="Validate all wiki-links point to existing doc filenames"
"""Validate that all wiki-links in documentation point to existing filenames.
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 filename in the documentation.
Wiki-link formats supported:
- [[filename]] - links to filename.md
- [[filename | Display Text]] - links to filename.md, displays "Display Text"
Usage: mise run doc-links
"""
import re
import sys
from pathlib import Path
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"\[\[([^\]|]+)(?:\s*\|\s*[^\]]+)?\]\]")
# Regex to match inline code (backticks)
INLINE_CODE_PATTERN = re.compile(r"`[^`]+`")
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 filenames
valid_filenames: set[str] = set()
# Scan all markdown files for filenames (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
valid_filenames.add(md_file.stem)
# Collect all broken links
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_filenames:
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_filenames)} valid filenames 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 filename in docs/.")
return 1
console.print("[bold green]All wiki-links are valid![/bold green]")
return 0
if __name__ == "__main__":
sys.exit(main())