#!/usr/bin/env python3
"""Cruza el inventario historico de Internet Archive contra el mirror.

Responde a la pregunta de aceptacion que de verdad importa: **de las URLs legacy que el mundo
exterior tiene enlazadas, cuantas resuelven en el mirror**. Sustituto parcial de la fuente F2 (GA4),
que sigue bloqueada porque requiere que Rafa abra el OAuth a mano.
"""
import os, json
from collections import Counter
from urllib.parse import urlsplit, unquote

BASE = "/home/rafa/joomla-migration/mirror-antiguo"
RUN = open(os.path.join(BASE, "CURRENT_RUN")).read().strip()
DIR = os.path.join(BASE, "runs", RUN)
SITE = os.path.join(DIR, "site", "antiguo.feadulta.com")

def existe(path):
    p = unquote(path).lstrip("/")
    for c in (p, p.split("?", 1)[0], os.path.join(p, "index.html")):
        if c and os.path.isfile(os.path.join(SITE, c)):
            return True
    return False

paths, cats = set(), Counter()
for fn in ("wayback-antiguo.txt", "wayback-feadulta.txt"):
    for line in open(os.path.join(BASE, "inventory", fn), errors="replace"):
        u = line.strip()
        if not u:
            continue
        p = urlsplit(u).path
        q = urlsplit(u).query
        if q:                      # las URLs con query no forman parte del mirror estatico
            cats["con_query (fuera de alcance)"] += 1
            continue
        if not p or p == "/":
            cats["raiz"] += 1
            continue
        paths.add(p)

ok, missing = 0, []
for p in sorted(paths):
    if existe(p):
        ok += 1
    else:
        missing.append(p)

print("URLs distintas de Wayback sin query:", len(paths))
print("presentes en el mirror:", ok, "(%.1f%%)" % (ok * 100.0 / max(len(paths), 1)))
print("ausentes:", len(missing))
for k, v in cats.most_common():
    print("  %s: %s" % (k, v))

# clasificar las ausentes para ver si importan
tipo = Counter()
for p in missing:
    seg = p.strip("/").split("/")[0] if p.strip("/") else "(raiz)"
    tipo[seg] += 1
print("\n--- ausentes por primer segmento ---")
for k, v in tipo.most_common(20):
    print("%7d  %s" % (v, k))

with open(os.path.join(DIR, "wayback-missing.txt"), "w") as f:
    for p in missing:
        f.write(p + "\n")
json.dump({"wayback_paths": len(paths), "presentes": ok, "ausentes": len(missing),
           "pct": round(ok * 100.0 / max(len(paths), 1), 2)},
          open(os.path.join(DIR, "wayback-report.json"), "w"), indent=2)
print("\n--- muestra de ausentes ---")
for p in missing[:20]:
    print("  ", p)