import pymupdf # fitz
import sys
import re
from pathlib import Path

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

pdf_path = Path("resources/knowledge/original/행정규칙/임도 품셈 적용기준 (현 산림사업 표준품셈)/첨부/(산림청고시 제2025-82호) 산림사업 표준품셈.pdf")
doc = pymupdf.open(pdf_path)
print(f"Total pages in PDF: {len(doc)}")

# Let's search for keywords around F0046, F0068, F0076, F0077
# F0046: 2-1-1 휘발유·오일 관련 기계? (line 1353 in MD)
# F0068: 2-2-5 천공기 (line 1661 in MD)
# F0076: 3-2 작업로 선정 (line 1742 in MD)
# F0077: 3-3 작업로 설치 (line 1754 in MD)

# First inspect in MD around lines 1350~1360, 1655~1670, 1735~1765
md_path = Path("resources/knowledge/original/행정규칙/임도 품셈 적용기준 (현 산림사업 표준품셈)/첨부/(산림청고시 제2025-82호) 산림사업 표준품셈.md")
with open(md_path, "r", encoding="utf-8") as f:
    md_lines = f.readlines()

def show_md_lines(start, end):
    print(f"--- MD lines {start}~{end} ---")
    for i in range(start-1, min(end, len(md_lines))):
        print(f"{i+1:5d}: {md_lines[i].rstrip()}")

print("=== MD Context for F0046 ===")
show_md_lines(1345, 1370)

print("\n=== MD Context for F0068 ===")
show_md_lines(1650, 1675)

print("\n=== MD Context for F0076 & F0077 ===")
show_md_lines(1735, 1765)