From ff293d73ac0b22622bc50c7fae95f828b2492126 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 10 Dec 2011 09:36:08 +0530
Subject: [PATCH] HTML Input: Ignore unparseable URLs instead of crashing on
 them. Fixes #902372 (HTML convert crashes with " Invalid IPv6 URL" error)

---
 src/calibre/ebooks/html/input.py              | 6 +++++-
 src/calibre/ebooks/mobi/writer2/serializer.py | 6 +++++-
 src/calibre/ebooks/oeb/transforms/split.py    | 6 +++++-
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/src/calibre/ebooks/html/input.py b/src/calibre/ebooks/html/input.py
index e958b9dd27..ccbc987533 100644
--- a/src/calibre/ebooks/html/input.py
+++ b/src/calibre/ebooks/html/input.py
@@ -148,7 +148,11 @@ class HTMLFile(object):
                 url = match.group(i)
                 if url:
                     break
-            link = self.resolve(url)
+            try:
+                link = self.resolve(url)
+            except ValueError:
+                # Unparseable URL, ignore
+                continue
             if link not in self.links:
                 self.links.append(link)
 
diff --git a/src/calibre/ebooks/mobi/writer2/serializer.py b/src/calibre/ebooks/mobi/writer2/serializer.py
index 041a9922cb..5bf6b10d23 100644
--- a/src/calibre/ebooks/mobi/writer2/serializer.py
+++ b/src/calibre/ebooks/mobi/writer2/serializer.py
@@ -178,7 +178,11 @@ class Serializer(object):
         at the end.
         '''
         hrefs = self.oeb.manifest.hrefs
-        path, frag = urldefrag(urlnormalize(href))
+        try:
+            path, frag = urldefrag(urlnormalize(href))
+        except ValueError:
+            # Unparseable URL
+            return False
         if path and base:
             path = base.abshref(path)
         if path and path not in hrefs:
diff --git a/src/calibre/ebooks/oeb/transforms/split.py b/src/calibre/ebooks/oeb/transforms/split.py
index 24af1aa4f7..96e4b08079 100644
--- a/src/calibre/ebooks/oeb/transforms/split.py
+++ b/src/calibre/ebooks/oeb/transforms/split.py
@@ -154,7 +154,11 @@ class Split(object):
 
     def rewrite_links(self, url):
         href, frag = urldefrag(url)
-        href = self.current_item.abshref(href)
+        try:
+            href = self.current_item.abshref(href)
+        except ValueError:
+            # Unparseable URL
+            return url
         if href in self.map:
             anchor_map = self.map[href]
             nhref = anchor_map[frag if frag else None]