"""Drop <img> tags in article bodies whose file did not survive the recovery.

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 for them).

Left alone they render as a broken-image box, which on a phone reads as an
unexplained 40px hole between paragraphs. The reference is still worth keeping
in the Markdown source, so this strips it only from the generated HTML and
leaves a comment naming the file, which keeps the output self-documenting for
anyone who later finds the originals on the offline drive.
"""
import os
import re

from pelican import signals

IMG = re.compile(r'<img[^>]*\bsrc="(/[^"]+)"[^>]*>')
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")
    lost = []

    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):
        rel = m.group(1).lstrip("/")
        if os.path.exists(os.path.join(base, rel)):
            return m.group(0)
        lost.append(os.path.basename(rel))
        return "<!-- lost image: %s -->" % os.path.basename(rel)

    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)