#!/usr/bin/env python3
import sys, os, hashlib, json
from ebooklib import epub
from bs4 import BeautifulSoup
import requests

MEILI_URL = os.getenv("MEILI_URL","http://localhost:7700")
MEILI_KEY = os.getenv("MEILI_KEY","change_me")

def post(doc):
    r = requests.post(f"{MEILI_URL}/indexes/library/documents",
                      headers={"Authorization": f"Bearer {MEILI_KEY}", "Content-Type":"application/json"},
                      data=json.dumps(doc))
    r.raise_for_status()

for path in sys.argv[1:]:
    book = epub.read_epub(path)
    title = book.get_metadata('DC', 'title')[0][0] if book.get_metadata('DC','title') else os.path.basename(path)
    author = "; ".join([a[0] for a in book.get_metadata('DC','creator')]) if book.get_metadata('DC','creator') else ""
    n=0
    for item in book.get_items_of_type(9):
        soup = BeautifulSoup(item.get_body_content(), "lxml")
        text = soup.get_text(separator=" ", strip=True)
        if not text.strip(): continue
        n+=1
        doc = {
          "id": hashlib.sha1((path+item.get_name()).encode()).hexdigest(),
          "type": "epub",
          "title": f"{title} - {item.get_name()}",
          "source": f"file://{os.path.abspath(path)}",
          "date": "",
          "text": text,
          "meta": {"book_title": title, "book_author": author, "chapter": item.get_name()}
        }
        post(doc)
    print(f"Indexed {title} ({n} sections)")