import pymupdf
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"Loaded PDF with {len(doc)} pages.")

# Search pages for keywords
# 1. 천공기 휘발유 (F0046)
# 2. 2-2-5. 천공기 손료 (F0068)
# 3. 3-2. 작업로 선정 (F0076)
# 4. 3-3. 작업로 설치 (F0077)

keywords = [
    ("F0046", "천공기 (휘발유)"),
    ("F0068", "2-2-5. 천공기"),
    ("F0076", "3-2. 작업로 선정"),
    ("F0077", "3-3. 작업로 설치")
]

for label, kw in keywords:
    print(f"\n==================== Searching for {label}: '{kw}' ====================")
    found = False
    for page_num in range(len(doc)):
        page = doc[page_num]
        text = page.get_text()
        if kw in text:
            found = True
            print(f"Found on PDF Page {page_num + 1} (0-indexed: {page_num}):")
            # Print surrounding text
            lines = text.splitlines()
            for idx, l in enumerate(lines):
                if kw in l:
                    start_l = max(0, idx - 8)
                    end_l = min(len(lines), idx + 20)
                    for k in range(start_l, end_l):
                        print(f"  [{k:3d}] {lines[k]}")
                    break
    if not found:
        print(f"NOT FOUND for {kw}")