openclew 0.2.1 → 0.4.0

package/hooks/generate-index.py

@@ -1,226 +0,0 @@
-#!/usr/bin/env python3
-"""
-openclew index generator.
-
-Scans doc/_*.md (refdocs) and doc/log/*.md (logs),
-parses metadata line + L1 blocks, and generates doc/_INDEX.md.
-
-Usage:
-    python generate-index.py              # from project root
-    python generate-index.py /path/to/doc # custom doc directory
-
-Idempotent: running twice produces the same output.
-Zero dependencies: Python 3.8+ standard library only.
-"""
-
-import os
-import re
-import sys
-from datetime import datetime
-from pathlib import Path
-
-
-def find_doc_dir():
-    """Find the doc/ directory."""
-    if len(sys.argv) > 1:
-        doc_dir = Path(sys.argv[1])
-    else:
-        doc_dir = Path("doc")
-
-    if not doc_dir.is_dir():
-        print(f"No '{doc_dir}' directory found. Nothing to index.")
-        sys.exit(0)
-
-    return doc_dir
-
-
-def parse_metadata_line(content):
-    """Extract metadata from the first line (before L1_START).
-
-    Format: openclew@VERSION · key: value · key: value · ...
-    """
-    meta = {}
-    first_line = content.split("\n", 1)[0].strip()
-    if not first_line.startswith("openclew@"):
-        return meta
-
-    parts = first_line.split(" · ")
-    for part in parts:
-        part = part.strip()
-        if part.startswith("openclew@"):
-            meta["version"] = part.split("@", 1)[1]
-            continue
-        if ":" in part:
-            key, _, value = part.partition(":")
-            meta[key.strip().lower()] = value.strip()
-
-    return meta
-
-
-def parse_l1(content):
-    """Extract L1 fields (subject, doc_brief) from L1_START/L1_END block."""
-    meta = {}
-    match = re.search(
-        r"<!--\s*L1_START\s*-->(.+?)<!--\s*L1_END\s*-->",
-        content,
-        re.DOTALL,
-    )
-    if not match:
-        return meta
-
-    block = match.group(1)
-
-    # Extract **subject:** value
-    subject_match = re.search(r"\*\*subject:\*\*\s*(.+)", block)
-    if subject_match:
-        meta["subject"] = subject_match.group(1).strip()
-
-    # Extract **doc_brief:** value
-    brief_match = re.search(r"\*\*doc_brief:\*\*\s*(.+)", block)
-    if brief_match:
-        meta["doc_brief"] = brief_match.group(1).strip()
-
-    return meta
-
-
-def parse_l1_legacy(content):
-    """Fallback parser for old format (key: value lines inside L1 block)."""
-    meta = {}
-    match = re.search(
-        r"<!--\s*L1_START\s*-->(.+?)<!--\s*L1_END\s*-->",
-        content,
-        re.DOTALL,
-    )
-    if not match:
-        return meta
-
-    block = match.group(1)
-    for line in block.splitlines():
-        line = line.strip()
-        if line.startswith("#") or not line:
-            continue
-        if ":" in line:
-            key, _, value = line.partition(":")
-            meta[key.strip().lower()] = value.strip()
-
-    return meta
-
-
-def parse_file(filepath):
-    """Parse a file and return combined metadata + L1 fields."""
-    try:
-        content = filepath.read_text(encoding="utf-8")
-    except (OSError, UnicodeDecodeError):
-        return None
-
-    # Try new format first
-    meta_line = parse_metadata_line(content)
-    l1 = parse_l1(content)
-
-    if l1.get("subject"):
-        # New format
-        meta_line.update(l1)
-        return meta_line
-
-    # Fallback to legacy format
-    legacy = parse_l1_legacy(content)
-    if legacy:
-        meta_line.update(legacy)
-        return meta_line
-
-    return None
-
-
-def collect_docs(doc_dir):
-    """Collect refdocs and logs with their metadata."""
-    refdocs = []
-    logs = []
-
-    # Refdocs: doc/_*.md
-    for f in sorted(doc_dir.glob("_*.md")):
-        if f.name == "_INDEX.md":
-            continue
-        meta = parse_file(f)
-        if meta:
-            refdocs.append((f, meta))
-
-    # Log docs: doc/log/*.md
-    log_dir = doc_dir / "log"
-    if log_dir.is_dir():
-        for f in sorted(log_dir.glob("*.md"), reverse=True):
-            meta = parse_file(f)
-            if meta:
-                logs.append((f, meta))
-
-    return refdocs, logs
-
-
-def generate_index(doc_dir, refdocs, logs):
-    """Generate _INDEX.md content."""
-    now = datetime.now().strftime("%Y-%m-%d %H:%M")
-    lines = [
-        f"# Project Knowledge Index",
-        f"",
-        f"> Auto-generated by [openclew](https://github.com/openclew/openclew) on {now}.",
-        f"> Do not edit manually — rebuilt from L1 metadata on every commit.",
-        f"",
-    ]
-
-    # Refdocs section
-    lines.append("## Refdocs")
-    lines.append("")
-    if refdocs:
-        lines.append("| Document | Subject | Status | Category |")
-        lines.append("|----------|---------|--------|----------|")
-        for f, meta in refdocs:
-            name = f.name
-            subject = meta.get("subject", "—")
-            status = meta.get("status", "—")
-            category = meta.get("category", "—")
-            rel_path = f.relative_to(doc_dir.parent)
-            lines.append(f"| [{name}]({rel_path}) | {subject} | {status} | {category} |")
-    else:
-        lines.append("_No refdocs yet. Create one with `templates/refdoc.md`._")
-    lines.append("")
-
-    # Logs section (last 20)
-    lines.append("## Recent logs")
-    lines.append("")
-    display_logs = logs[:20]
-    if display_logs:
-        lines.append("| Date | Subject | Status | Category |")
-        lines.append("|------|---------|--------|----------|")
-        for f, meta in display_logs:
-            date = meta.get("date", f.stem[:10])
-            subject = meta.get("subject", "—")
-            status = meta.get("status", "—")
-            category = meta.get("category", "—")
-            rel_path = f.relative_to(doc_dir.parent)
-            lines.append(f"| {date} | [{subject}]({rel_path}) | {status} | {category} |")
-        if len(logs) > 20:
-            lines.append(f"")
-            lines.append(f"_{len(logs) - 20} older logs not shown._")
-    else:
-        lines.append("_No logs yet. Create one with `templates/log.md`._")
-    lines.append("")
-
-    # Stats
-    lines.append("---")
-    lines.append(f"**{len(refdocs)}** refdocs, **{len(logs)}** logs.")
-    lines.append("")
-
-    return "\n".join(lines)
-
-
-def main():
-    doc_dir = find_doc_dir()
-    refdocs, logs = collect_docs(doc_dir)
-    index_content = generate_index(doc_dir, refdocs, logs)
-
-    index_path = doc_dir / "_INDEX.md"
-    index_path.write_text(index_content, encoding="utf-8")
-    print(f"Generated {index_path} ({len(refdocs)} refdocs, {len(logs)} logs)")
-
-
-if __name__ == "__main__":
-    main()