"""Drop <img> tags in article bodies whose image is gone for good.

Two kinds of gone, same symptom:

**Local.** The same situation as assetcheck.py, one level down: the recovered
bodies kept their original /library/ references, and 22 of 200 point at files no
archive holds (checked against Wayback; the CDX API returns no captures).

**Remote.** Older posts hotlink images from other people's servers, and some of
those servers no longer exist: visualberlin.org, mutanten.org, web.mac.com,
kino.web.de, lh4.google.it, l.yimg.com. Name them in LOSTIMAGES_DEAD_HOSTS and
their images are treated exactly like a lost local file. The host is matched
rather than the URL fetched, because a build must not depend on the network and
a dead host is a fact about the world, not about this document.

Left alone either kind renders as a broken-image box, which on a phone reads as
an unexplained 40px hole between paragraphs. On a gemtext capsule it is worse:
an image becomes a visible link line, so the page advertises a dead host.

The reference is still worth keeping in the Markdown source, so this strips it
only from the generated output and leaves a comment naming the file, which keeps
the output self-documenting for anyone who later finds the originals.
"""
import os
import re

from pelican import signals

IMG = re.compile(r'<img[^>]*\bsrc="([^"]+)"[^>]*>')
REMOTE = re.compile(r'^https?://([^/]+)/', re.IGNORECASE)
ANCHOR = re.compile(r'<a[^>]*\bhref="(/library/[^"]+)"[^>]*>(.*?)</a>', re.S)


def _strip(content):
    body = getattr(content, "_content", None)
    if not body or "<img" not in body:
        return
    base = content.settings.get("PATH", "content")
    dead = {h.lower().lstrip(".") for h in
            content.settings.get("LOSTIMAGES_DEAD_HOSTS", [])}
    lost = []

    def is_lost(src):
        """True when this src can never resolve again."""
        remote = REMOTE.match(src)
        if remote:
            host = remote.group(1).lower().split(":")[0]
            # match the host and any subdomain of it, so naming
            # visualberlin.org also covers www.visualberlin.org
            return any(host == d or host.endswith("." + d) for d in dead)
        if not src.startswith("/"):
            return False
        return not os.path.exists(os.path.join(base, src.lstrip("/")))

    def name_of(src):
        return os.path.basename(src.split("?")[0].rstrip("/")) or src

    def anchor(m):
        rel = m.group(1).lstrip("/")
        if os.path.exists(os.path.join(base, rel)):
            return m.group(0)
        return m.group(2)

    def sub(m):
        src = m.group(1)
        if not is_lost(src):
            return m.group(0)
        lost.append(name_of(src))
        return "<!-- lost image: %s -->" % name_of(src)

    body = IMG.sub(sub, body)
    # a thumbnail that linked to the full-size file leaves the <a> behind, and
    # its href 404s just as the <img> did
    body = ANCHOR.sub(anchor, body)
    if not lost:
        return
    # a paragraph that held nothing but the lost image would still occupy space
    body = re.sub(r"<p>\s*((?:<!-- lost image: [^>]*-->\s*)+)</p>", r"\1", body)
    content._content = body
    content.lost_images = lost


def register():
    signals.content_object_init.connect(_strip)