25 lines
946 B
Python
25 lines
946 B
Python
import json, sys
|
|
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
|
|
ch13_path = "resources/knowledge/original/원가계산/건설공사_표준품셈/04_기계설비부문/제13장_플랜트설비공사.md"
|
|
with open(ch13_path, 'r', encoding='utf-8') as f:
|
|
lines = f.readlines()
|
|
|
|
remaining = []
|
|
for idx, line in enumerate(lines):
|
|
line_str = line.strip()
|
|
if not (line_str.startswith('|') and line_str.endswith('|')):
|
|
continue
|
|
cells = [c.strip() for c in line_str.split('|')[1:-1]]
|
|
# Check if first cell has multiple numbers or multiple specs
|
|
for c_idx, c in enumerate(cells):
|
|
toks = c.split()
|
|
if len(toks) >= 6 and any(t[0].isdigit() for t in toks if t):
|
|
remaining.append((idx + 1, c_idx, len(toks), c[:80]))
|
|
break
|
|
|
|
print(f"Total multi-token rows in 제13장: {len(remaining)}")
|
|
for l_num, c_idx, cnt, snip in remaining[:20]:
|
|
print(f"L{l_num} col{c_idx} (tokens: {cnt}): {snip}")
|