import os, sys, re

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

target_files = [
    # 02_토목부문
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제1장_도로포장공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제2장_하천공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제3장_터널공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제4장_궤도공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제5장_강구조공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제6장_관부설및접합공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제7장_항만공사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제8장_지반조사.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제9장_측량.md',
    # 05_유지관리부문
    'resources/knowledge/original/원가계산/건설공사_표준품셈/05_유지관리부문/제1장_공통.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/05_유지관리부문/제2장_토목.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/05_유지관리부문/제3장_건축.md',
    'resources/knowledge/original/원가계산/건설공사_표준품셈/05_유지관리부문/제4장_기계설비.md',
    # 04_기계설비부문 제13장
    'resources/knowledge/original/원가계산/건설공사_표준품셈/04_기계설비부문/제13장_플랜트설비공사.md',
]

# Suspect sentence continuation words in Col 0
CONTINUATION_PATTERNS = [
    r'^구\s*간$', r'^설\s*치$', r'^후\s*설치$', r'^조립\s*설치$', r'^취급함', r'^정돈함',
    r'^[가-힣\w\s]+(하고|하며|하여|혹은|및|등|까지|위해|위하여|취부함|포함|제외|운반|조양함)\b',
    r'^→', r'^[A-Za-z0-9#]+\s*$', r'^분기기$', r'^교\s*환$', r'^매\s*립\s*식$', r'^\( 직 결 형 \)$'
]

print("=== Scanning All Target Files for Broken Groupings / Split Col 0 Sentences ===")

results = []

for fpath in target_files:
    fname = os.path.basename(fpath)
    with open(fpath, 'r', encoding='utf-8') as f:
        lines = f.readlines()
        
    for idx, line in enumerate(lines):
        if not line.startswith('|'):
            continue
        cells = [c.strip() for c in line.split('|')[1:-1]]
        if not cells or all(re.match(r'^:?-+:?$', c) for c in cells if c):
            continue
            
        c0 = cells[0]
        # check if c0 matches any continuation patterns
        for pat in CONTINUATION_PATTERNS:
            if re.search(pat, c0):
                # Also check surrounding lines to confirm it's part of a split
                prev_line = lines[idx-1].strip() if idx > 0 else ""
                next_line = lines[idx+1].strip() if idx + 1 < len(lines) else ""
                results.append({
                    'file': fname,
                    'line': idx + 1,
                    'c0': c0,
                    'full_line': line.strip()[:100],
                    'matched_pat': pat
                })
                break

print(f"Total Suspect Split Col 0 Cells Found: {len(results)}")
by_file = {}
for r in results:
    by_file.setdefault(r['file'], []).append(r)

for f, items in sorted(by_file.items()):
    print(f"\n[{f}] ({len(items)}건)")
    for it in items:
        print(f"  L{it['line']:<5} | Col0: '{it['c0']}' | {it['full_line']}")