From 40cb9772038e2bf889beb975eee14abeda542a55 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 16 Dec 2009 15:32:21 -0700
Subject: [PATCH] Fix #4230 (Can't view/convert certain Mobipocket files)

---
 src/calibre/ebooks/mobi/input.py  | 12 +++++++++---
 src/calibre/ebooks/mobi/reader.py | 10 ++++++----
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/src/calibre/ebooks/mobi/input.py b/src/calibre/ebooks/mobi/input.py
index bc9409b852..487e70c04f 100644
--- a/src/calibre/ebooks/mobi/input.py
+++ b/src/calibre/ebooks/mobi/input.py
@@ -16,10 +16,16 @@ class MOBIInput(InputFormatPlugin):
                 accelerators):
         from calibre.ebooks.mobi.reader import MobiReader
         from lxml import html
-        mr = MobiReader(stream, log, options.input_encoding,
-                        options.debug_pipeline)
         parse_cache = {}
-        mr.extract_content('.', parse_cache)
+        try:
+            mr = MobiReader(stream, log, options.input_encoding,
+                        options.debug_pipeline)
+            mr.extract_content('.', parse_cache)
+        except:
+            mr = MobiReader(stream, log, options.input_encoding,
+                        options.debug_pipeline, try_extra_data_fix=True)
+            mr.extract_content('.', parse_cache)
+
         raw = parse_cache.pop('calibre_raw_mobi_markup', False)
         if raw:
             if isinstance(raw, unicode):
diff --git a/src/calibre/ebooks/mobi/reader.py b/src/calibre/ebooks/mobi/reader.py
index 20d31d48b4..973418204f 100644
--- a/src/calibre/ebooks/mobi/reader.py
+++ b/src/calibre/ebooks/mobi/reader.py
@@ -108,7 +108,7 @@ class EXTHHeader(object):
 
 class BookHeader(object):
 
-    def __init__(self, raw, ident, user_encoding, log):
+    def __init__(self, raw, ident, user_encoding, log, try_extra_data_fix=False):
         self.log = log
         self.compression_type = raw[:2]
         self.records, self.records_size = struct.unpack('>HH', raw[8:12])
@@ -141,7 +141,8 @@ class BookHeader(object):
                 self.codec = 'cp1252' if user_encoding is None else user_encoding
                 log.warn('Unknown codepage %d. Assuming %s' % (self.codepage,
                     self.codec))
-            if ident == 'TEXTREAD' or self.length < 0xE4 or 0xE8 < self.length:
+            if ident == 'TEXTREAD' or self.length < 0xE4 or 0xE8 < self.length \
+                or (try_extra_data_fix and self.length == 0xE4):
                 self.extra_flags = 0
             else:
                 self.extra_flags, = struct.unpack('>H', raw[0xF2:0xF4])
@@ -229,7 +230,8 @@ class MobiReader(object):
     PAGE_BREAK_PAT = re.compile(r'(<[/]{0,1}mbp:pagebreak\s*[/]{0,1}>)+', re.IGNORECASE)
     IMAGE_ATTRS = ('lowrecindex', 'recindex', 'hirecindex')
 
-    def __init__(self, filename_or_stream, log, user_encoding=None, debug=None):
+    def __init__(self, filename_or_stream, log, user_encoding=None, debug=None,
+            try_extra_data_fix=False):
         self.log = log
         self.debug = debug
         self.embedded_mi = None
@@ -284,7 +286,7 @@ class MobiReader(object):
 
 
         self.book_header = BookHeader(self.sections[0][0], self.ident,
-            user_encoding, self.log)
+            user_encoding, self.log, try_extra_data_fix=try_extra_data_fix)
         self.name = self.name.decode(self.book_header.codec, 'replace')
 
     def extract_content(self, output_dir, parse_cache):