#!/usr/bin/env python3
"""
download_lecturas.py — Descarga lecturas bíblicas litúrgicas (texto católico oficial)
desde evangelizo.org en es/en/fr/it/pt, para una fecha litúrgica dada.

Fuente: feed.evangelizo.org/v2/reader.php (lecturas del día, leccionario católico).
Códigos de idioma evangelizo: SP=es, AM=en, FR=fr, IT=it, PT=pt.

Uso:  python3 download_lecturas.py 2026-06-21 [--books Jeremías,Romanos]
Salida: JSON a stdout con {libro: {lang: {title, html}}}.
"""
import sys, re, html, json, urllib.request

LANGS = {"SP": "es", "AM": "en", "FR": "fr", "IT": "it", "PT": "pt"}
# nombre del libro por idioma (para casar el bloque correcto)
BOOK_ALIASES = {
    "Jeremías": ["Jeremías", "Jeremiah", "Jérémie", "Geremia", "Jeremias"],
    "Romanos":  ["Romanos", "Romans", "Romains", "Romani"],
    "Mateo":    ["Mateo", "Matthew", "Matthieu", "Matteo", "Mateus"],
    "Marcos":   ["Marcos", "Mark", "Marc", "Marco", "Marcos"],
    "Lucas":    ["Lucas", "Luke", "Luc", "Luca", "Lucas"],
    "Juan":     ["Juan", "John", "Jean", "Giovanni", "João"],
}

REF_RE = re.compile(r"(\d{1,3}\s*,[\d.\-\s]+)\.?$")


def fetch(date, lang_code):
    url = f"https://feed.evangelizo.org/v2/reader.php?date={date}&lang={lang_code}&type=all"
    req = urllib.request.Request(url, headers={"User-Agent": "fea-lecturas/1.0"})
    with urllib.request.urlopen(req, timeout=30) as r:
        raw = r.read().decode("utf-8", "replace")
    raw = re.sub(r"<br\s*/?>", "\n", raw)
    raw = re.sub(r"<[^>]+>", "", raw)
    txt = html.unescape(raw)
    return [l.strip() for l in txt.split("\n") if l.strip()]


def is_header(line):
    return len(line) < 110 and bool(REF_RE.search(line))


def parse_blocks(lines):
    """Devuelve [(header, [parrafos])] saltando la 1ª línea (título del día)."""
    blocks = []
    cur_h, cur_t = None, []
    for ln in lines[1:]:
        if is_header(ln):
            if cur_h:
                blocks.append((cur_h, cur_t))
            cur_h, cur_t = ln, []
        else:
            if cur_h:
                cur_t.append(ln)
    if cur_h:
        blocks.append((cur_h, cur_t))
    return blocks


def short_title(header):
    """'Carta de San Pablo a los Romanos 5,12-15.' -> 'ROMANOS 5,12-15'."""
    m = re.search(r"([A-Za-zÀ-ÿ]+)\s+(\d{1,3}\s*,[\d.\-\s]+)\.?$", header)
    if not m:
        return header.rstrip(".")
    return m.group(1).upper() + " " + re.sub(r"\s+", "", m.group(2)).rstrip(".")


def main():
    date = sys.argv[1]
    books = ["Jeremías", "Romanos"]
    if "--books" in sys.argv:
        books = sys.argv[sys.argv.index("--books") + 1].split(",")

    result = {b: {} for b in books}
    for code, wl in LANGS.items():
        blocks = parse_blocks(fetch(date, code))
        for b in books:
            aliases = BOOK_ALIASES.get(b, [b])
            for header, paras in blocks:
                if any(a.lower() in header.lower() for a in aliases):
                    htmlc = "".join(f"<p>{p}</p>\n" for p in paras)
                    result[b][wl] = {"title": short_title(header), "html": htmlc, "header": header}
                    break
    json.dump(result, sys.stdout, ensure_ascii=False, indent=2)


if __name__ == "__main__":
    main()