unification: INDEX → CANON v1 (| # | Group | EN title | Author(s) | Status | File |), 219 rows, 0 status mismatches; sec02 legacy triage table dropped (dup of main table + cards)

tools/migrate_indexes.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""Migrate section INDEX.md to CANON v1: | # | Group | EN title | Author(s) | Status | File |
+Usage: python3 tools/migrate_indexes.py <section> [--dry-run]"""
+import re, sys, os, glob
+
+NAMES = {'01-fundamentals': 'Fundamentals', '02-dreams': 'Dreams',
+         '03-myths-fairy-tales': 'Myths & Fairy Tales', '04-pictures': 'Pictures'}
+COLMAP = {'block': 'group', 'subsection': 'group', 'group': 'group',
+          'en title': 'title', 'title': 'title', 'item': 'title', 'book': 'title',
+          'author(s)': 'author', 'author(s) ': 'author', 'authors': 'author', 'author': 'author',
+          'status': 'status', 'file': 'file'}
+
+def main():
+    sec = sys.argv[1]
+    dry = '--dry-run' in sys.argv
+    p = f'sections/{sec}/INDEX.md'
+    c = open(p).read()
+    lines = c.split('\n')
+    # find table
+    ti = next(i for i, l in enumerate(lines) if l.startswith('| #') or l.startswith('|#'))
+    header = [x.strip() for x in lines[ti].strip().strip('|').split('|')]
+    colidx = {}
+    for i, h in enumerate(header):
+        key = COLMAP.get(h.lower())
+        if key:
+            colidx[key] = i
+    rows, ti_end = [], ti
+    for i in range(ti+1, len(lines)):
+        if not lines[i].startswith('|'):
+            ti_end = i
+            break
+        cells = [x.strip() for x in lines[i].strip().strip('|').split('|')]
+        if len(cells) >= 2 and not (set(cells[0]) <= set('- ') or cells[0] == '#'):
+            rows.append(cells)
+    else:
+        ti_end = len(lines)
+    intro = '\n'.join(lines[1:ti]).strip()
+    tail = '\n'.join(lines[ti_end:]).strip()
+    out_rows = []
+    for cells in rows:
+        num = cells[0]
+        group = cells[colidx.get('group', 1)] if 'group' in colidx else ''
+        group = group or '—'
+        title = cells[colidx.get('title')]
+        author = cells[colidx.get('author')] if 'author' in colidx else ''
+        status = cells[colidx.get('status')] if 'status' in colidx else ''
+        filecol = cells[colidx.get('file')] if 'file' in colidx else ''
+        m = re.match(r'\[(.+?)\]\((.+?)\)', title)
+        if m:
+            title, filecol = m.group(1), m.group(2)
+        if not filecol:
+            cand = glob.glob(f'sections/{sec}/{num}-*.md')
+            filecol = os.path.basename(cand[0]) if cand else ''
+        elif not filecol.startswith(num + '-'):
+            cand = glob.glob(f'sections/{sec}/{num}-{filecol}')
+            filecol = os.path.basename(cand[0]) if cand else f'{num}-{filecol}'
+        mark = status[:1]
+        if mark not in '✅🔶❌⬜🔎':
+            mm = re.search(r'[✅🔶❌⬜🔎]', status)
+            mark = mm.group(0) if mm else '?'
+        out_rows.append(f'| {num} | {group} | {title} | {author} | {mark} | {filecol} |')
+    new = f'# Section {sec[:2]} — {NAMES[sec]}: INDEX\n\n{intro}\n\n'
+    new += '| # | Group | EN title | Author(s) | Status | File |\n|---|-------|----------|-----------|--------|------|\n'
+    new += '\n'.join(out_rows) + '\n'
+    if tail:
+        # keep trailing sections (## ...) only
+        tlines = tail.split('\n')
+        i0 = next((i for i, l in enumerate(tlines) if l.startswith('## ')), None)
+        if i0 is not None:
+            new += '\n' + '\n'.join(tlines[i0:]).strip() + '\n'
+    if dry:
+        print(new)
+    else:
+        open(p, 'w').write(new)
+        # verify against cards
+        bad = []
+        for r in out_rows:
+            num = r.split('|')[1].strip()
+            mark = r.split('|')[5].strip()
+            card = glob.glob(f'sections/{sec}/{num}-*.md')
+            if not card:
+                bad.append(f'{num}: no card'); continue
+            cm = re.search(r'\*\*Status:\*\* (.)', open(card[0]).read())
+            if cm and cm.group(1) != mark:
+                bad.append(f'{num}: index {mark} != card {cm.group(1)}')
+        print(f'wrote {p} ({len(out_rows)} rows); mismatches: {bad if bad else 0}')
+
+if __name__ == '__main__':
+    main()