KF8 Input: Do not fail if the input file contains corrupted font records. Fixes #953260 (error converting kindle ebooks)

src/calibre/ebooks/conversion/plugins/mobi_input.py

@@ -52,7 +52,7 @@ class MOBIInput(InputFormatPlugin):
                 mr.extract_content(u'.', parse_cache)
 
         if mr.kf8_type is not None:
-            log('Found KF8 MOBI')
+            log('Found KF8 MOBI of type %s'%mr.kf8_type)
             from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
             return os.path.abspath(Mobi8Reader(mr, log)())
 

src/calibre/ebooks/metadata/opf2.py

@@ -1148,7 +1148,8 @@ class OPFCreator(Metadata):
         self.manifest = Manifest.from_paths(entries)
         self.manifest.set_basedir(self.base_path)
 
-    def create_manifest_from_files_in(self, files_and_dirs):
+    def create_manifest_from_files_in(self, files_and_dirs,
+            exclude=lambda x:False):
         entries = []
 
         def dodir(dir):
@@ -1156,7 +1157,7 @@ class OPFCreator(Metadata):
                 root, files = spec[0], spec[-1]
                 for name in files:
                     path = os.path.join(root, name)
-                    if os.path.isfile(path):
+                    if os.path.isfile(path) and not exclude(path):
                         entries.append((path, None))
 
         for i in files_and_dirs:

src/calibre/ebooks/mobi/reader/mobi8.py

@@ -347,8 +347,18 @@ class Mobi8Reader(object):
                 # bytes 12 - 15:  ?? offset to start of compressed data ?? (typically 0x00000018 = 24)
                 # bytes 16 - 23:  ?? typically all 0x00 ??  Are these compression flags from zlib?
                 # The compressed data begins with 2 bytes of header and has 4 bytes of checksum at the end
-                data = data[26:-4]
-                uncompressed_data = zlib.decompress(data, -15)
+                try:
+                    fields = struct.unpack_from(b'>LLLL', data, 4)
+                except:
+                    fields = None
+                #self.log.debug('Font record fields: %s'%(fields,))
+                cdata = data[26:-4]
+                try:
+                    uncompressed_data = zlib.decompress(cdata, -15)
+                except:
+                    self.log.warn('Failed to uncompress embedded font %d: '
+                            'Fields: %s' % (fname_idx, fields,))
+                    uncompressed_data = data[4:]
                 hdr = uncompressed_data[0:4]
                 ext = 'dat'
                 if hdr == b'\0\1\0\0' or hdr == b'true' or hdr == b'ttcf':
@@ -379,7 +389,11 @@ class Mobi8Reader(object):
 
         opf = OPFCreator(os.getcwdu(), mi)
         opf.guide = guide
-        opf.create_manifest_from_files_in([os.getcwdu()])
+
+        def exclude(path):
+            return os.path.basename(path) == 'debug-raw.html'
+
+        opf.create_manifest_from_files_in([os.getcwdu()], exclude=exclude)
         opf.create_spine(spine)
         opf.set_toc(toc)