| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960 |
- """Audit metadata consistency across all knowledge documents."""
- import os
- docs_dir = r'E:\workspace\dan\num\knowledge\research'
- results = []
- for f in sorted(os.listdir(docs_dir)):
- if not f.endswith('.md'):
- continue
- path = os.path.join(docs_dir, f)
- content = open(path, 'r', encoding='utf-8').read()
- lines = content.split('\n')
-
- # Check frontmatter
- has_frontmatter = content.startswith('---')
- if not has_frontmatter:
- results.append((f, 'NO_FRONTMATTER'))
- continue
-
- # Parse frontmatter
- in_frontmatter = False
- tags = []
- title = ''
- confidence = ''
- has_tags = False
- for line in lines[:40]:
- if line.strip() == '---':
- in_frontmatter = not in_frontmatter
- continue
- if in_frontmatter:
- if line.startswith('title:'):
- title = line.replace('title:', '').strip().strip('"').strip("'")
- elif line.startswith('confidence:'):
- confidence = line.split(':')[1].strip()
- elif line.startswith('tags:'):
- has_tags = True
- elif line.strip().startswith('- ') and in_frontmatter:
- tags.append(line.strip().lstrip('- ').strip())
-
- file_size = os.path.getsize(path)
- line_count = len(lines)
-
- # Determine which layer (A/B/C/D/E/other) the doc belongs to
- layer = 'OTHER'
- if f.startswith('A') or '命盘24位置' in f:
- layer = 'A'
- elif f.startswith('B') or '八星' in f or '联合密码' in f or '三角命盘组合' in f:
- layer = 'B'
- elif f.startswith('C') or '维度手册' in f or '五区三组' in f or '数字0与5' in f:
- layer = 'C'
- elif f.startswith('D') or '递进' in f or '组合能量' in f:
- layer = 'D'
- elif f.startswith('E') or '天赋数' in f:
- layer = 'E'
-
- print(f'{layer} | {f:40s} | tags={len(tags):2d} | conf={confidence:8s} | {line_count:4d}行 | {file_size:6d}B')
-
- if not has_tags:
- print(f' >>> WARNING: No tags found in {f}')
- if not confidence:
- print(f' >>> WARNING: No confidence in {f}')
|