59 lines
1.9 KiB
Python
59 lines
1.9 KiB
Python
import os, sys, re
|
|
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
|
|
fpath = 'resources/knowledge/original/원가계산/건설공사_표준품셈/02_토목부문/제9장_측량.md'
|
|
with open(fpath, 'r', encoding='utf-8') as f:
|
|
lines = f.readlines()
|
|
|
|
tables = []
|
|
cur_t = []
|
|
cur_start = 0
|
|
cur_title = ""
|
|
|
|
for idx, l in enumerate(lines):
|
|
line_str = l.strip()
|
|
if not line_str.startswith('|'):
|
|
if line_str and not line_str.startswith('>'):
|
|
cur_title = line_str
|
|
if cur_t:
|
|
tables.append((cur_start, cur_title, cur_t))
|
|
cur_t = []
|
|
else:
|
|
if not cur_t:
|
|
cur_start = idx + 1
|
|
cur_t.append((idx + 1, line_str))
|
|
if cur_t:
|
|
tables.append((cur_start, cur_title, cur_t))
|
|
|
|
print(f"Total tables in Survey: {len(tables)}")
|
|
|
|
# Check for multi-level hierarchical headers (Col 0 and Col 1)
|
|
hierarchical_tables = []
|
|
for t_start, t_title, t_rows in tables:
|
|
data_rows = []
|
|
for lno, r_str in t_rows:
|
|
cells = [c.strip() for c in r_str.split('|')[1:-1]]
|
|
if all(re.match(r'^:?-+:?$', c) for c in cells if c):
|
|
continue
|
|
data_rows.append((lno, r_str, cells))
|
|
if len(data_rows) < 3:
|
|
continue
|
|
|
|
# Check if Col 0 has blanks or ditto marks with changing Col 1
|
|
has_blank_col0 = False
|
|
col0_vals = []
|
|
for lno, r_str, cells in data_rows[1:]:
|
|
c0 = cells[0] if len(cells) > 0 else ""
|
|
if c0 == "" or c0 == "〃":
|
|
has_blank_col0 = True
|
|
elif c0:
|
|
col0_vals.append(c0)
|
|
|
|
if has_blank_col0 and len(set(col0_vals)) >= 2:
|
|
hierarchical_tables.append((t_start, t_title, len(data_rows), set(col0_vals)))
|
|
|
|
print(f"Hierarchical / Grouped tables in Survey: {len(hierarchical_tables)}")
|
|
for start, title, rcnt, groups in hierarchical_tables[:20]:
|
|
print(f"L{start}: {title[:40]} | Rows: {rcnt} | Groups: {list(groups)[:4]}")
|