#!/usr/bin/env python3
"""Cobertura real: cada URL del inventario debe tener su fichero en raw/.

Contempla las tres formas en que wget nombra el fichero:
  /es/x.html                -> x.html
  /es/                      -> index.html
  /es/x?.html  (alias con '?' literal)  -> "x?.html"  o  "x"
"""
import os, json
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)
RAW = os.path.join(DIR, "raw", "antiguo.feadulta.com")

def candidates(url):
    rest = url.split("antiguo.feadulta.com", 1)[1]
    rest = unquote(rest)
    yield rest.lstrip("/")                      # nombre literal, con '?' incluido
    p = urlsplit(rest).path.lstrip("/")
    yield p                                     # truncado en el '?'
    if rest.endswith("/") or p.endswith("/") or p == "":
        yield (p + "index.html")

ok, missing = 0, []
urls = [l.strip() for l in open(os.path.join(BASE, "inventory", "urls-input.txt")) if l.strip()]
for u in urls:
    if any(os.path.isfile(os.path.join(RAW, c)) for c in candidates(u) if c):
        ok += 1
    else:
        missing.append(u)

print("inventario:", len(urls))
print("con fichero en raw/:", ok)
print("sin fichero:", len(missing))
print("cobertura: %.2f%%" % (ok * 100.0 / len(urls)))
with open(os.path.join(DIR, "coverage-missing.txt"), "w") as f:
    for u in missing:
        f.write(u + "\n")
for u in missing[:25]:
    print("  ", u)

total = sum(len(fs) for _r, _d, fs in os.walk(os.path.join(DIR, "raw")))
json.dump({"inventario": len(urls), "capturadas": ok, "sin_fichero": len(missing),
           "cobertura_pct": round(ok * 100.0 / len(urls), 2), "ficheros_totales_raw": total},
          open(os.path.join(DIR, "coverage-report.json"), "w"), indent=2)