feadulta/scripts/phase_a_enrique_preview.py

#!/usr/bin/env python3
"""Fase A local: borrador de Enrique + copia draft de la carta para revisión.

Por defecto no escribe WordPress. --apply-local sólo modifica el WordPress Docker local.
Nunca publica ni toca producción.
"""
import argparse
import base64
import hashlib
import html
import json
import os
import re
import subprocess
import sys
import zipfile
from pathlib import Path
from xml.etree import ElementTree as ET

ROOT = Path(__file__).resolve().parent.parent
DEFAULT_DOC = Path("/home/rafa/.hermes/cache/documents/doc_7909db597c74_7r_Enrique_Mart_nez_Lozano_tesoro_esta_ya_en_nosotros.docx")
CARTA_PROD_ID = 54914
AUTHOR_ID = 384  # Enrique Martínez Lozano, verificado localmente.
CATEGORIES = [1650, 71]  # Artículos + Feadulta
SLUG = "el-tesoro-esta-ya-en-nosotros"


def docx_text(path: Path) -> list[str]:
    ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}
    with zipfile.ZipFile(path) as zf:
        root = ET.fromstring(zf.read("word/document.xml"))
    out = []
    for p in root.findall(".//w:p", ns):
        text = "".join(t.text or "" for t in p.findall(".//w:t", ns)).strip()
        if text:
            out.append(text)
    return out


def parse_source(path: Path) -> dict:
    lines = docx_text(path)
    def after(label: str) -> str:
        return lines[lines.index(label) + 1]
    title = after("Título:")
    author = after("Autor:")
    assert title == "EL TESORO ESTÁ YA EN NOSOTROS", title
    assert author == "ENRIQUE MARTÍNEZ LOZANO", author
    body_start = lines.index("Cuerpo:") + 1
    body = lines[body_start:]
    # Última firma del boletín no es contenido del post: el autor va en WP.
    if body[-1].startswith("ENRIQUE MARTÍNEZ LOZANO"):
        body = body[:-1]
    date_line, bible, *paragraphs = body
    intro = lines[lines.index("Entradilla:") + 1]
    content = "\n".join(
        [f"<p><strong>{html.escape(date_line)}</strong></p>",
         f"<p><strong>{html.escape(bible)}</strong></p>"]
        + [f"<p>{html.escape(p)}</p>" for p in paragraphs]
    )
    return {"title": title.lower().capitalize(), "author": author.title(), "intro": intro,
            "content": content, "source_sha256": hashlib.sha256(path.read_bytes()).hexdigest()}


def prod_card() -> dict:
    sys.path.insert(0, str(ROOT / "scripts"))
    import sync_translations_to_prod as sync
    return json.loads(sync.prod_helper("read_full", str(CARTA_PROD_ID)))


def carta_candidate(card: dict, anchor: str) -> str:
    marker = '<p>&nbsp;</p>\n<p><span style="color: #ff0000;"><strong>Para unas eucaristías más participativas y actuales</strong></span></p>'
    assert card["content"].count(marker) == 1, "Marcador de sección no único/no encontrado"
    return card["content"].replace(marker, anchor + "\n" + marker, 1)


def run_wp(payload: dict, apply: bool) -> dict:
    encoded = base64.b64encode(json.dumps(payload, ensure_ascii=False).encode()).decode()
    php = r'''
$p=json_decode(base64_decode(getenv('FEA_PAYLOAD')), true);
$apply=getenv('FEA_APPLY') === '1';
$existing=get_page_by_path($p['slug'], OBJECT, 'post');
$author=get_user_by('id',(int)$p['author_id']);
$cats=array_map('intval',$p['categories']);
$cat_ok=count(array_filter($cats, fn($id)=>term_exists($id,'category')))===count($cats);
$preview=get_posts(['post_type'=>'post','post_status'=>'any','meta_key'=>'fea_phase_a_source_hash','meta_value'=>$p['source_sha256'],'numberposts'=>1]);
$out=['dry_run'=>!$apply,'existing_slug'=>$existing?['id'=>$existing->ID,'status'=>$existing->post_status]:null,
      'author'=>$author?['id'=>$author->ID,'name'=>$author->display_name]:null,'categories_ok'=>$cat_ok,
      'preview_existing'=>$preview?['id'=>$preview[0]->ID,'status'=>$preview[0]->post_status]:null,
      'candidate_anchor'=>$p['anchor']];
if (!$author || !$cat_ok) { $out['error']='Autor o categorías no válidos'; echo wp_json_encode($out,JSON_UNESCAPED_UNICODE); exit(3); }
if ($existing || $preview) { $out['error']='Ya existe un borrador/slug para esta Fase A; no se duplica'; echo wp_json_encode($out,JSON_UNESCAPED_UNICODE); exit(4); }
if (!$apply) { echo wp_json_encode($out,JSON_UNESCAPED_UNICODE); exit; }
$article_id=wp_insert_post(['post_type'=>'post','post_status'=>'draft','post_author'=>(int)$p['author_id'],
  'post_title'=>$p['article_title'],'post_name'=>$p['slug'],'post_excerpt'=>$p['intro'],
  'post_content'=>$p['article_content'],'post_category'=>$cats],true);
if (is_wp_error($article_id)) { $out['error']=$article_id->get_error_message(); echo wp_json_encode($out,JSON_UNESCAPED_UNICODE); exit(5); }
if (function_exists('pll_set_post_language')) pll_set_post_language($article_id,'es');
update_post_meta($article_id,'fea_phase_a_source_hash',$p['source_sha256']);
update_post_meta($article_id,'fea_phase_a_source_doc','7r_Enrique Martínez Lozano_tesoro_esta_ya_en_nosotros.docx');
update_post_meta($article_id,'fea_phase_a_status','preview-only');
$preview_id=wp_insert_post(['post_type'=>'post','post_status'=>'draft','post_author'=>(int)$p['card_author_id'],
  'post_title'=>'PREVIEW — Hacia el corazón (+ Enrique Martínez Lozano)','post_excerpt'=>'Copia local de validación; no publicar.',
  'post_content'=>$p['candidate_card_content']],true);
if (is_wp_error($preview_id)) { wp_delete_post($article_id,true); $out['error']=$preview_id->get_error_message(); echo wp_json_encode($out,JSON_UNESCAPED_UNICODE); exit(6); }
if (function_exists('pll_set_post_language')) pll_set_post_language($preview_id,'es');
update_post_meta($preview_id,'fea_phase_a_source_hash',$p['source_sha256']);
update_post_meta($preview_id,'fea_phase_a_source_prod_id',(int)$p['carta_prod_id']);
update_post_meta($preview_id,'fea_phase_a_preview_article_id',$article_id);
update_post_meta($preview_id,'fea_phase_a_status','preview-only');
$out['article']=['id'=>$article_id,'status'=>'draft','slug'=>get_post_field('post_name',$article_id),'author'=>get_the_author_meta('display_name',(int)$p['author_id'])];
$out['preview_card']=['id'=>$preview_id,'status'=>'draft','source_prod_id'=>(int)$p['carta_prod_id']];
echo wp_json_encode($out,JSON_UNESCAPED_UNICODE);
'''
    cmd = [
        "docker", "exec", "-i", "-e", f"FEA_PAYLOAD={encoded}",
        "-e", f"FEA_APPLY={'1' if apply else '0'}", "wordpress-web",
        "wp", "--allow-root", "eval", php,
    ]
    result = subprocess.run(cmd, text=True, capture_output=True, check=False)
    if result.returncode:
        raise RuntimeError(f"WP local rc={result.returncode}: {result.stderr}\n{result.stdout}")
    return json.loads(result.stdout)


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--doc", type=Path, default=DEFAULT_DOC)
    ap.add_argument("--apply-local", action="store_true")
    ap.add_argument("--output", type=Path, required=True)
    args = ap.parse_args()
    source = parse_source(args.doc)
    card = prod_card()  # lectura server-side únicamente.
    article_url = "http://localhost:8080/" + SLUG + "/"
    anchor = (f'<p><strong><a href="{article_url}">Enrique Martínez Lozano: '
              f'{html.escape(source["title"])}.</a></strong> {html.escape(source["intro"])}</p>')
    payload = {
        "source_sha256": source["source_sha256"], "article_title": source["title"],
        "article_content": source["content"], "intro": source["intro"], "slug": SLUG,
        "author_id": AUTHOR_ID, "categories": CATEGORIES, "anchor": anchor,
        "candidate_card_content": carta_candidate(card, anchor), "card_author_id": card["author"],
        "carta_prod_id": CARTA_PROD_ID,
    }
    result = run_wp(payload, args.apply_local)
    report = {"source": source, "prod_card": {"id": card["id"], "title": card["title"], "status": card["status"]},
              "result": result, "mode": "apply-local" if args.apply_local else "dry-run"}
    args.output.parent.mkdir(parents=True, exist_ok=True)
    args.output.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
    print(json.dumps(report, ensure_ascii=False, indent=2))

if __name__ == "__main__":
    main()