#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
rebuild_doc65.py — Rebuild doc-65-hs1-834228961-62-hq-83894-section-4
Processes all 179 pages, writes chunks/, images/, _index.json, document.md
"""

import os
import sys
import json
import base64
import datetime
import time
from pathlib import Path

DOC_ID = "doc-65-hs1-834228961-62-hq-83894-section-4"
DOC_TITLE = "65 HS1-834228961 62-HQ-83894 Section 4 — FBI Flying Discs Investigation"
RAW_DIR = Path(f"/Users/guto/ufo/raw/{DOC_ID}")
PNG_DIR = Path(f"/Users/guto/ufo/processing/png/{DOC_ID}")
OCR_DIR = Path(f"/Users/guto/ufo/processing/ocr/{DOC_ID}")

CHUNKS_DIR = RAW_DIR / "chunks"
IMAGES_DIR = RAW_DIR / "images"
TABLES_DIR = RAW_DIR / "tables"

# Ensure dirs exist
CHUNKS_DIR.mkdir(parents=True, exist_ok=True)
IMAGES_DIR.mkdir(parents=True, exist_ok=True)
TABLES_DIR.mkdir(parents=True, exist_ok=True)

# Build ordered page map: page_number (1-based) -> (png_filename, ocr_filename)
def build_page_map():
    pngs = sorted([f for f in os.listdir(PNG_DIR) if f.endswith('.png')])
    ocrs = sorted([f for f in os.listdir(OCR_DIR) if f.endswith('.txt')])
    page_map = {}
    for i, (png, ocr) in enumerate(zip(pngs, ocrs), 1):
        page_map[i] = {
            'png': str(PNG_DIR / png),
            'ocr': str(OCR_DIR / ocr),
            'png_filename': png,
            'ocr_filename': ocr
        }
    return page_map

def read_ocr(path):
    try:
        with open(path, 'r', encoding='utf-8') as f:
            return f.read().strip()
    except:
        return ""

def encode_image_b64(path):
    with open(path, 'rb') as f:
        return base64.standard_b64encode(f.read()).decode('utf-8')

def now_iso():
    return datetime.datetime.utcnow().strftime('%Y-%m-%dT%H:%M:%SZ')

if __name__ == "__main__":
    page_map = build_page_map()
    print(f"Total pages: {len(page_map)}")
    for p, info in list(page_map.items())[:5]:
        print(f"  Page {p:03d}: png={info['png_filename']}, ocr={info['ocr_filename']}")
    print("Script loaded OK")