49 lines
1.9 KiB
Python
49 lines
1.9 KiB
Python
import sys, os, re, json
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
|
|
base_dir = "resources/knowledge/original/원가계산/건설공사_표준품셈"
|
|
merged_file = os.path.join(base_dir, "2026년_건설공사_표준품셈.md")
|
|
|
|
with open(merged_file, 'r', encoding='utf-8') as f:
|
|
merged_text = f.read()
|
|
|
|
# Check key restored tables in merged_text:
|
|
# 1. 제8장 손료표 11곳: 0230, 3601, 5220, 6532, 6801, 7101, 7120, 7830, 7995, 9020, 9060
|
|
loss_codes = ['0230', '3601', '5220', '6532', '6801', '7101', '7120', '7830', '7995', '9020', '9060']
|
|
|
|
print("=== Checking 11 손료표 in 합본 ===")
|
|
for code in loss_codes:
|
|
# search for e.g. "({code})" followed by table
|
|
pattern = re.compile(rf'\({code}\)[^\n]*\n+(\|[^\n]+\|\n)+', re.DOTALL)
|
|
m = pattern.search(merged_text)
|
|
if m:
|
|
# count rows in table
|
|
rows = [l for l in m.group(0).split('\n') if l.strip().startswith('|') and not re.match(r'^\|(?:\s*:?-+:?\s*\|)+$', l.strip())]
|
|
print(f" - ({code}): Restored as table with {len(rows)} rows in 합본")
|
|
else:
|
|
# check if it exists as text
|
|
m2 = re.search(rf'\({code}\)', merged_text)
|
|
if m2:
|
|
print(f" ❌ ({code}): Exists as TEXT only (NOT TABLE) in 합본!")
|
|
else:
|
|
print(f" ❌ ({code}): Missing in 합본!")
|
|
|
|
# 2. Check 1-2-2 in merged_text
|
|
print("\n=== Checking 1-2-2 in 합본 ===")
|
|
if "돌 쌓 기 및 돌 붙 임" in merged_text:
|
|
# check if it is collapsed or separate rows
|
|
p_122 = re.compile(r'\|\s*돌\s*쌓\s*기\s*및\s*돌\s*붙\s*임\s*사\s*석')
|
|
if p_122.search(merged_text):
|
|
print(" ❌ 1-2-2 is COLLAPSED in 합본!")
|
|
else:
|
|
print(" ✅ 1-2-2 is properly expanded in 합본")
|
|
else:
|
|
print(" ❓ 1-2-2 not matched")
|
|
|
|
# 3. Check 6-1-1 in merged_text
|
|
print("\n=== Checking 6-1-1 in 합본 ===")
|
|
if "6-1-1 레디믹스트콘크리트 타설" in merged_text:
|
|
print(" ✅ 6-1-1 exists in 합본")
|
|
else:
|
|
print(" ❌ 6-1-1 is MISSING in 합본!")
|