import os, sys, re, json

sys.stdout.reconfigure(encoding='utf-8')

base_dir = 'resources/knowledge/original/원가계산/건설공사_표준품셈'
target_dirs = ['02_토목부문', '05_유지관리부문', '04_기계설비부문']

candidates = []
for td in target_dirs:
    dirpath = os.path.join(base_dir, td)
    for root, dirs, files in os.walk(dirpath):
        for f in files:
            if td == '04_기계설비부문' and '제13장' not in f:
                continue
            if f.endswith('.md') and not f.startswith('_') and '개정사항' not in f:
                fpath = os.path.join(root, f)
                with open(fpath, 'r', encoding='utf-8') as fp:
                    lines = fp.readlines()
                for idx, line in enumerate(lines):
                    line_s = line.strip()
                    if not line_s.startswith('|') and len(line_s) > 25:
                        has_kw = (('구 분' in line_s or '구분' in line_s or '직 종' in line_s or '직종' in line_s) and 
                                  ('단위' in line_s or '단 위' in line_s or '수량' in line_s or '수 량' in line_s or '인력품' in line_s))
                        if has_kw:
                            candidates.append({
                                'file': f,
                                'line': idx + 1,
                                'text': line_s
                            })

print(f"Total candidates: {len(candidates)}")
for c in candidates:
    print(f"[{c['file']}] L{c['line']}: {c['text'][:110]}")