#!/usr/bin/env python3
"""Antes de tocar nada: que hay realmente dentro de los bloques sociales del mirror."""
import os, re
from collections import Counter

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

OPEN = re.compile(r'<div\b[^>]*class="[^"]*itemSocialSharing[^"]*"[^>]*>', re.I)
DIV = re.compile(r'<div\b[^>]*>|</div>', re.I)
CLASS = re.compile(r'<div\b[^>]*class="([^"]+)"', re.I)
SCRIPTSRC = re.compile(r'<script[^>]+src="([^"]+)"', re.I)

def bloque(html, m):
    """Devuelve (inicio, fin) del div equilibrado que empieza en m."""
    depth, pos = 0, m.start()
    for d in DIV.finditer(html, m.start()):
        if d.group(0).lower().startswith("</"):
            depth -= 1
            if depth == 0:
                return m.start(), d.end()
        else:
            depth += 1
    return None

clases, scripts, sin_bloque, con_bloque = Counter(), Counter(), 0, 0
n = 0
for root, _d, files in os.walk(SITE):
    for fn in files:
        if not fn.split("?", 1)[0].lower().endswith((".html", ".htm")):
            continue
        p = os.path.join(root, fn)
        try:
            html = open(p, encoding="utf-8", errors="replace").read()
        except OSError:
            continue
        if "itemSocialSharing" not in html:
            continue
        n += 1
        if n > 400:
            break
        for m in OPEN.finditer(html):
            r = bloque(html, m)
            if not r:
                sin_bloque += 1
                continue
            con_bloque += 1
            frag = html[r[0]:r[1]]
            for c in CLASS.findall(frag):
                clases[c.strip()] += 1
            for s in SCRIPTSRC.findall(frag):
                scripts[s.split("?")[0]] += 1
    if n > 400:
        break

print("paginas inspeccionadas con itemSocialSharing:", n)
print("bloques equilibrados:", con_bloque, " sin cerrar:", sin_bloque)
print("\n--- clases de div dentro del bloque ---")
for k, v in clases.most_common(15):
    print("%7d  %s" % (v, k))
print("\n--- scripts dentro del bloque ---")
for k, v in scripts.most_common(15):
    print("%7d  %s" % (v, k))