rename mobi7 components to toc.ncx, book.html, content.opf to prevent…

… bugs in opf generation

add in mobiml2xhtml.py for future use in converting old mobi7 ml to something closer to xhtml
Authors: KevinH

lib/kindleunpack.py

@@ -108,7 +108,7 @@
 #  0.73   faster mobi split, numerous bug fixes in mobi_k8proc, mobi_header, mobi_opf, mobi_k8resc, etc
 #  0.74   added refines metadata, fixed language code in ncx and title in nav, added support for opf: from refines
 #  0.75   much improved dictioanry support including support for multiple inflection sections, minor mobi_opf fixes
-
+#  0.76   rename mobi7 pieces to book.html, toc.ncx, and content.opf to prevent bug in opf
 
 DUMP = False
 """ Set to True to dump all possible information. """
@@ -589,7 +589,8 @@ def processMobi7(mh, metadata, sect, files, imgnames):
 
     # write the proper mobi html
     fileinfo=[]
-    fname = files.getInputFileBasename() + '.html'
+    # fname = files.getInputFileBasename() + '.html'
+    fname = 'book.html'
     fileinfo.append([None,'', fname])
     outhtml = os.path.join(files.mobi7dir, fname)
     open(pathof(outhtml), 'wb').write(srctext)
@@ -898,7 +899,7 @@ def main():
     global DUMP
     global WRITE_RAW_DATA
     global SPLIT_COMBO_MOBIS
-    print "KindleUnpack v0.75"
+    print "KindleUnpack v0.76"
     print "   Based on initial mobipocket version Copyright © 2009 Charles M. Hannum <[email protected]>"
     print "   Extensive Extensions and Improvements Copyright © 2009-2014 "
     print "       by:  P. Durrant, K. Hendricks, S. Siebert, fandrieu, DiapDealer, nickredding, tkeo."

lib/mobi_header.py

@@ -818,8 +818,11 @@ def addValue(name, value):
                         addValue(name, str(value))
                     elif size == 12:
                         value, = struct.unpack('>L',content)
-                        # handle special case of missing CoverOffset
-                        if id != 201 or value != 0xffffffff:
+                        # handle special case of missing CoverOffset or missing ThumbOffset
+                        if id == 201 or id == 202:
+                            if value != 0xffffffff:
+                                addValue(name, str(value))
+                        else:
                             addValue(name, str(value))
                     else:
                         print "Warning: Bad key, size, value combination detected in EXTH ", id, size, content.encode('hex')

lib/mobi_ncx.py

@@ -171,8 +171,9 @@ def writeNCX(self, metadata):
         htmlname = os.path.basename(self.files.outbase)
         htmlname += '.html'
         xml = self.buildNCX(htmlname, metadata['Title'][0], metadata['UniqueID'][0], metadata.get('Language')[0])
-        #write the ncx file
-        ncxname = os.path.join(self.files.mobi7dir, self.files.getInputFileBasename() + '.ncx')
+        # write the ncx file
+        # ncxname = os.path.join(self.files.mobi7dir, self.files.getInputFileBasename() + '.ncx')
+        ncxname = os.path.join(self.files.mobi7dir, 'toc.ncx')
         open(pathof(ncxname), 'wb').write(xml)
 
 

lib/mobi_opf.py

@@ -336,18 +336,19 @@ def buildOPFManifest(self, ncxname, navname=None):
                 '.gif'  : 'image/gif',
                 '.svg'  : 'image/svg+xml',
                 '.xhtml': 'application/xhtml+xml',
-                '.html' : 'text/x-oeb1-document', # for mobi7
-                '.pdf'  : 'application/pdf', # for azw4(print replica textbook)
+                '.html' : 'text/html',                   # for mobi7
+                '.pdf'  : 'application/pdf',             # for azw4(print replica textbook)
                 '.ttf'  : 'application/x-font-ttf',
                 '.otf'  : 'application/x-font-opentype', # replaced?
-                #'.otf' : 'application/vnd.ms-opentype', # [OpenType] OpenType fonts
-                #'.woff' : 'application/font-woff', # [WOFF] WOFF fonts
-                #'.smil' : 'application/smil+xml', # [MediaOverlays301] EPUB Media Overlay documents
-                #'.pls' : 'application/pls+xml', # [PLS] Text-to-Speech (TTS) Pronunciation lexicons
+                '.css'  : 'text/css',
+                #'.html' : 'text/x-oeb1-document',        # for mobi7
+                #'.otf'  : 'application/vnd.ms-opentype', # [OpenType] OpenType fonts
+                #'.woff' : 'application/font-woff',       # [WOFF] WOFF fonts
+                #'.smil' : 'application/smil+xml',        # [MediaOverlays301] EPUB Media Overlay documents
+                #'.pls'  : 'application/pls+xml',         # [PLS] Text-to-Speech (TTS) Pronunciation lexicons
                 #'.mp3'  : 'audio/mpeg',
-                #'.mp4'  : 'audio/mp4',
-                #'.js'   : 'text/javascript', # not supported in K8
-                '.css'  : 'text/css'
+                #'.mp4'  : 'video/mp4',
+                #'.js'   : 'text/javascript',             # not supported in K8
                 }
         spinerefs = []
 
@@ -467,7 +468,8 @@ def buildMobi7OPF(self):
         opf_metadata = self.buildOPFMetadata(metadata_tag)
         data += opf_metadata
         if self.has_ncx:
-            ncxname = self.files.getInputFileBasename() + '.ncx'
+            # ncxname = self.files.getInputFileBasename() + '.ncx'
+            ncxname = 'toc.ncx'
         else:
             ncxname = None
         [opf_manifest, spinerefs] = self.buildOPFManifest(ncxname)
@@ -527,7 +529,8 @@ def writeOPF(self, has_obfuscated_fonts=False):
             return self.BookId
         else:
             data = self.buildMobi7OPF()
-            outopf = os.path.join(self.files.mobi7dir, self.files.getInputFileBasename() + '.opf')
+            # outopf = os.path.join(self.files.mobi7dir, self.files.getInputFileBasename() + '.opf')
+            outopf = os.path.join(self.files.mobi7dir, 'content.opf')
             open(pathof(outopf), 'wb').write(data)
             return 0