def record0(self): ''' We generate the EXTH header and record0 dynamically, to allow other code to customize various values after build_records() has been called''' opts = self.opts self.exth = build_exth(self.metadata, prefer_author_sort=opts.prefer_author_sort, is_periodical=opts.mobi_periodical, share_not_sync=opts.share_not_sync, cover_offset=self.cover_offset, thumbnail_offset=self.thumbnail_offset, num_of_resources=self.num_of_resources, kf8_unknown_count=self.kuc, be_kindlegen2=True, start_offset=self.start_offset, mobi_doctype=self.book_type) kwargs = {field:getattr(self, field) for field in HEADER_FIELDS} return MOBIHeader()(**kwargs)
def generate_joint_record0(self): # {{{ from calibre.ebooks.mobi.writer8.mobi import (MOBIHeader, HEADER_FIELDS) from calibre.ebooks.mobi.writer8.exth import build_exth # Insert resource records first_image_record = None old = len(self.records) if self.resources: used_images = self.serializer.used_images | self.kf8.used_images first_image_record = len(self.records) self.resources.serialize(self.records, used_images) resource_record_count = len(self.records) - old last_content_record = len(self.records) - 1 # FCIS/FLIS (Seems to serve no purpose) flis_number = len(self.records) self.records.append(FLIS) fcis_number = len(self.records) self.records.append(fcis(self.text_length)) # Insert KF8 records self.records.append(b'BOUNDARY') kf8_header_index = len(self.records) self.kf8.start_offset = (self.serializer.start_offset, self.kf8.start_offset) self.records.append(self.kf8.record0) self.records.extend(self.kf8.records[1:]) first_image_record = (first_image_record if first_image_record else len(self.records)) header_fields = {k:getattr(self.kf8, k) for k in HEADER_FIELDS} # Now change the header fields that need to be different in the MOBI 6 # header header_fields['first_resource_record'] = first_image_record ef = 0b100001010000 # Kinglegen uses this if self.resources.has_fonts: ef |= 0b1000000000000 header_fields['exth_flags'] = ef header_fields['fdst_record'] = pack(b'>HH', 1, last_content_record) header_fields['fdst_count'] = 1 # Why not 0? Kindlegen uses 1 header_fields['flis_record'] = flis_number header_fields['fcis_record'] = fcis_number header_fields['text_length'] = self.text_length extra_data_flags = 0b1 # Has multibyte overlap bytes if self.primary_index_record_idx is not None: extra_data_flags |= 0b10 header_fields['extra_data_flags'] = extra_data_flags for k, v in iteritems({'last_text_record':'last_text_record_idx', 'first_non_text_record':'first_non_text_record_idx', 'ncx_index':'primary_index_record_idx', }): header_fields[k] = getattr(self, v) if header_fields['ncx_index'] is None: header_fields['ncx_index'] = NULL_INDEX for x in ('skel', 'chunk', 'guide'): header_fields[x+'_index'] = NULL_INDEX # Create the MOBI 6 EXTH opts = self.opts kuc = 0 if resource_record_count > 0 else None header_fields['exth'] = build_exth(self.oeb.metadata, prefer_author_sort=opts.prefer_author_sort, is_periodical=opts.mobi_periodical, share_not_sync=opts.share_not_sync, cover_offset=self.cover_offset, thumbnail_offset=self.thumbnail_offset, num_of_resources=resource_record_count, kf8_unknown_count=kuc, be_kindlegen2=True, kf8_header_index=kf8_header_index, start_offset=self.serializer.start_offset, mobi_doctype=2) self.records[0] = MOBIHeader(file_version=6)(**header_fields)
def generate_record0(self): # MOBI header {{{ metadata = self.oeb.metadata bt = 0x002 if self.primary_index_record_idx is not None: if False and self.indexer.is_flat_periodical: # Disabled as setting this to 0x102 causes the Kindle to not # auto archive the issues bt = 0x102 elif self.indexer.is_periodical: # If you change this, remember to change the cdetype in the EXTH # header as well bt = 0x103 if self.indexer.is_flat_periodical else 0x101 from calibre.ebooks.mobi.writer8.exth import build_exth exth = build_exth(metadata, prefer_author_sort=self.opts.prefer_author_sort, is_periodical=self.is_periodical, share_not_sync=self.opts.share_not_sync, cover_offset=self.cover_offset, thumbnail_offset=self.thumbnail_offset, start_offset=self.serializer.start_offset, mobi_doctype=bt ) first_image_record = None if self.resources: used_images = self.serializer.used_images first_image_record = len(self.records) self.resources.serialize(self.records, used_images) last_content_record = len(self.records) - 1 # FCIS/FLIS (Seems to serve no purpose) flis_number = len(self.records) self.records.append(FLIS) fcis_number = len(self.records) self.records.append(fcis(self.text_length)) # EOF record self.records.append(b'\xE9\x8E\x0D\x0A') record0 = io.BytesIO() # The MOBI Header record0.write(pack(b'>HHIHHHH', self.compression, # compression type # compression type 0, # Unused self.text_length, # Text length self.last_text_record_idx, # Number of text records or last tr idx RECORD_SIZE, # Text record size 0, # Unused 0 # Unused )) # 0 - 15 (0x0 - 0xf) uid = random.randint(0, 0xffffffff) title = normalize(unicode_type(metadata.title[0])).encode('utf-8') # 0x0 - 0x3 record0.write(b'MOBI') # 0x4 - 0x7 : Length of header # 0x8 - 0x11 : MOBI type # type meaning # 0x002 MOBI book (chapter - chapter navigation) # 0x101 News - Hierarchical navigation with sections and articles # 0x102 News feed - Flat navigation # 0x103 News magazine - same as 0x101 # 0xC - 0xF : Text encoding (65001 is utf-8) # 0x10 - 0x13 : UID # 0x14 - 0x17 : Generator version record0.write(pack(b'>IIIII', 0xe8, bt, 65001, uid, 6)) # 0x18 - 0x1f : Unknown record0.write(b'\xff' * 8) # 0x20 - 0x23 : Secondary index record sir = 0xffffffff if (self.primary_index_record_idx is not None and self.indexer.secondary_record_offset is not None): sir = (self.primary_index_record_idx + self.indexer.secondary_record_offset) record0.write(pack(b'>I', sir)) # 0x24 - 0x3f : Unknown record0.write(b'\xff' * 28) # 0x40 - 0x43 : Offset of first non-text record record0.write(pack(b'>I', self.first_non_text_record_idx)) # 0x44 - 0x4b : title offset, title length record0.write(pack(b'>II', 0xe8 + 16 + len(exth), len(title))) # 0x4c - 0x4f : Language specifier record0.write(iana2mobi( unicode_type(metadata.language[0]))) # 0x50 - 0x57 : Input language and Output language record0.write(b'\0' * 8) # 0x58 - 0x5b : Format version # 0x5c - 0x5f : First image record number record0.write(pack(b'>II', 6, first_image_record if first_image_record else len(self.records))) # 0x60 - 0x63 : First HUFF/CDIC record number # 0x64 - 0x67 : Number of HUFF/CDIC records # 0x68 - 0x6b : First DATP record number # 0x6c - 0x6f : Number of DATP records record0.write(b'\0' * 16) # 0x70 - 0x73 : EXTH flags # Bit 6 (0b1000000) being set indicates the presence of an EXTH header # Bit 12 being set indicates the presence of embedded fonts # The purpose of the other bits is unknown exth_flags = 0b1010000 if self.is_periodical: exth_flags |= 0b1000 if self.resources.has_fonts: exth_flags |= 0b1000000000000 record0.write(pack(b'>I', exth_flags)) # 0x74 - 0x93 : Unknown record0.write(b'\0' * 32) # 0x94 - 0x97 : DRM offset # 0x98 - 0x9b : DRM count # 0x9c - 0x9f : DRM size # 0xa0 - 0xa3 : DRM flags record0.write(pack(b'>IIII', 0xffffffff, 0xffffffff, 0, 0)) # 0xa4 - 0xaf : Unknown record0.write(b'\0'*12) # 0xb0 - 0xb1 : First content record number # 0xb2 - 0xb3 : last content record number # (Includes Image, DATP, HUFF, DRM) record0.write(pack(b'>HH', 1, last_content_record)) # 0xb4 - 0xb7 : Unknown record0.write(b'\0\0\0\x01') # 0xb8 - 0xbb : FCIS record number record0.write(pack(b'>I', fcis_number)) # 0xbc - 0xbf : Unknown (FCIS record count?) record0.write(pack(b'>I', 1)) # 0xc0 - 0xc3 : FLIS record number record0.write(pack(b'>I', flis_number)) # 0xc4 - 0xc7 : Unknown (FLIS record count?) record0.write(pack(b'>I', 1)) # 0xc8 - 0xcf : Unknown record0.write(b'\0'*8) # 0xd0 - 0xdf : Unknown record0.write(pack(b'>IIII', 0xffffffff, 0, 0xffffffff, 0xffffffff)) # 0xe0 - 0xe3 : Extra record data # Extra record data flags: # - 0b1 : <extra multibyte bytes><size> # - 0b10 : <TBS indexing description of this HTML record><size> # - 0b100: <uncrossable breaks><size> # Setting bit 2 (0x2) disables <guide><reference type="start"> functionality extra_data_flags = 0b1 # Has multibyte overlap bytes if self.primary_index_record_idx is not None: extra_data_flags |= 0b10 if WRITE_UNCROSSABLE_BREAKS: extra_data_flags |= 0b100 record0.write(pack(b'>I', extra_data_flags)) # 0xe4 - 0xe7 : Primary index record record0.write(pack(b'>I', 0xffffffff if self.primary_index_record_idx is None else self.primary_index_record_idx)) record0.write(exth) record0.write(title) record0 = record0.getvalue() # Add some buffer so that Amazon can add encryption information if this # MOBI is submitted for publication record0 += (b'\0' * (1024*8)) self.records[0] = align_block(record0)
def generate_joint_record0(self): # {{{ from calibre.ebooks.mobi.writer8.mobi import (MOBIHeader, HEADER_FIELDS) from calibre.ebooks.mobi.writer8.exth import build_exth # Insert resource records first_image_record = None old = len(self.records) if self.resources: used_images = self.serializer.used_images | self.kf8.used_images first_image_record = len(self.records) self.resources.serialize(self.records, used_images) resource_record_count = len(self.records) - old last_content_record = len(self.records) - 1 # FCIS/FLIS (Seems to serve no purpose) flis_number = len(self.records) self.records.append(FLIS) fcis_number = len(self.records) self.records.append(fcis(self.text_length)) # Insert KF8 records self.records.append(b'BOUNDARY') kf8_header_index = len(self.records) self.kf8.start_offset = (self.serializer.start_offset, self.kf8.start_offset) self.records.append(self.kf8.record0) self.records.extend(self.kf8.records[1:]) first_image_record = (first_image_record if first_image_record else len(self.records)) header_fields = {k:getattr(self.kf8, k) for k in HEADER_FIELDS} # Now change the header fields that need to be different in the MOBI 6 # header header_fields['first_resource_record'] = first_image_record ef = 0b100001010000 # Kinglegen uses this if self.resources.has_fonts: ef |= 0b1000000000000 header_fields['exth_flags'] = ef header_fields['fdst_record'] = pack(b'>HH', 1, last_content_record) header_fields['fdst_count'] = 1 # Why not 0? Kindlegen uses 1 header_fields['flis_record'] = flis_number header_fields['fcis_record'] = fcis_number header_fields['text_length'] = self.text_length extra_data_flags = 0b1 # Has multibyte overlap bytes if self.primary_index_record_idx is not None: extra_data_flags |= 0b10 header_fields['extra_data_flags'] = extra_data_flags for k, v in {'last_text_record':'last_text_record_idx', 'first_non_text_record':'first_non_text_record_idx', 'ncx_index':'primary_index_record_idx', }.iteritems(): header_fields[k] = getattr(self, v) if header_fields['ncx_index'] is None: header_fields['ncx_index'] = NULL_INDEX for x in ('skel', 'chunk', 'guide'): header_fields[x+'_index'] = NULL_INDEX # Create the MOBI 6 EXTH opts = self.opts kuc = 0 if resource_record_count > 0 else None header_fields['exth'] = build_exth(self.oeb.metadata, prefer_author_sort=opts.prefer_author_sort, is_periodical=opts.mobi_periodical, share_not_sync=opts.share_not_sync, cover_offset=self.cover_offset, thumbnail_offset=self.thumbnail_offset, num_of_resources=resource_record_count, kf8_unknown_count=kuc, be_kindlegen2=True, kf8_header_index=kf8_header_index, start_offset=self.serializer.start_offset, mobi_doctype=2) self.records[0] = MOBIHeader(file_version=6)(**header_fields)
def generate_record0(self): # MOBI header {{{ metadata = self.oeb.metadata bt = 0x002 if self.primary_index_record_idx is not None: if False and self.indexer.is_flat_periodical: # Disabled as setting this to 0x102 causes the Kindle to not # auto archive the issues bt = 0x102 elif self.indexer.is_periodical: # If you change this, remember to change the cdetype in the EXTH # header as well bt = 0x103 if self.indexer.is_flat_periodical else 0x101 from calibre.ebooks.mobi.writer8.exth import build_exth exth = build_exth(metadata, prefer_author_sort=self.opts.prefer_author_sort, is_periodical=self.is_periodical, share_not_sync=self.opts.share_not_sync, cover_offset=self.cover_offset, thumbnail_offset=self.thumbnail_offset, start_offset=self.serializer.start_offset, mobi_doctype=bt ) first_image_record = None if self.resources: used_images = self.serializer.used_images first_image_record = len(self.records) self.resources.serialize(self.records, used_images) last_content_record = len(self.records) - 1 # FCIS/FLIS (Seems to serve no purpose) flis_number = len(self.records) self.records.append(FLIS) fcis_number = len(self.records) self.records.append(fcis(self.text_length)) # EOF record self.records.append(b'\xE9\x8E\x0D\x0A') record0 = StringIO() # The MOBI Header record0.write(pack(b'>HHIHHHH', self.compression, # compression type # compression type 0, # Unused self.text_length, # Text length self.last_text_record_idx, # Number of text records or last tr idx RECORD_SIZE, # Text record size 0, # Unused 0 # Unused )) # 0 - 15 (0x0 - 0xf) uid = random.randint(0, 0xffffffff) title = normalize(unicode(metadata.title[0])).encode('utf-8') # 0x0 - 0x3 record0.write(b'MOBI') # 0x4 - 0x7 : Length of header # 0x8 - 0x11 : MOBI type # type meaning # 0x002 MOBI book (chapter - chapter navigation) # 0x101 News - Hierarchical navigation with sections and articles # 0x102 News feed - Flat navigation # 0x103 News magazine - same as 0x101 # 0xC - 0xF : Text encoding (65001 is utf-8) # 0x10 - 0x13 : UID # 0x14 - 0x17 : Generator version record0.write(pack(b'>IIIII', 0xe8, bt, 65001, uid, 6)) # 0x18 - 0x1f : Unknown record0.write(b'\xff' * 8) # 0x20 - 0x23 : Secondary index record sir = 0xffffffff if (self.primary_index_record_idx is not None and self.indexer.secondary_record_offset is not None): sir = (self.primary_index_record_idx + self.indexer.secondary_record_offset) record0.write(pack(b'>I', sir)) # 0x24 - 0x3f : Unknown record0.write(b'\xff' * 28) # 0x40 - 0x43 : Offset of first non-text record record0.write(pack(b'>I', self.first_non_text_record_idx)) # 0x44 - 0x4b : title offset, title length record0.write(pack(b'>II', 0xe8 + 16 + len(exth), len(title))) # 0x4c - 0x4f : Language specifier record0.write(iana2mobi( str(metadata.language[0]))) # 0x50 - 0x57 : Input language and Output language record0.write(b'\0' * 8) # 0x58 - 0x5b : Format version # 0x5c - 0x5f : First image record number record0.write(pack(b'>II', 6, first_image_record if first_image_record else len(self.records))) # 0x60 - 0x63 : First HUFF/CDIC record number # 0x64 - 0x67 : Number of HUFF/CDIC records # 0x68 - 0x6b : First DATP record number # 0x6c - 0x6f : Number of DATP records record0.write(b'\0' * 16) # 0x70 - 0x73 : EXTH flags # Bit 6 (0b1000000) being set indicates the presence of an EXTH header # Bit 12 being set indicates the presence of embedded fonts # The purpose of the other bits is unknown exth_flags = 0b1010000 if self.is_periodical: exth_flags |= 0b1000 if self.resources.has_fonts: exth_flags |= 0b1000000000000 record0.write(pack(b'>I', exth_flags)) # 0x74 - 0x93 : Unknown record0.write(b'\0' * 32) # 0x94 - 0x97 : DRM offset # 0x98 - 0x9b : DRM count # 0x9c - 0x9f : DRM size # 0xa0 - 0xa3 : DRM flags record0.write(pack(b'>IIII', 0xffffffff, 0xffffffff, 0, 0)) # 0xa4 - 0xaf : Unknown record0.write(b'\0'*12) # 0xb0 - 0xb1 : First content record number # 0xb2 - 0xb3 : last content record number # (Includes Image, DATP, HUFF, DRM) record0.write(pack(b'>HH', 1, last_content_record)) # 0xb4 - 0xb7 : Unknown record0.write(b'\0\0\0\x01') # 0xb8 - 0xbb : FCIS record number record0.write(pack(b'>I', fcis_number)) # 0xbc - 0xbf : Unknown (FCIS record count?) record0.write(pack(b'>I', 1)) # 0xc0 - 0xc3 : FLIS record number record0.write(pack(b'>I', flis_number)) # 0xc4 - 0xc7 : Unknown (FLIS record count?) record0.write(pack(b'>I', 1)) # 0xc8 - 0xcf : Unknown record0.write(b'\0'*8) # 0xd0 - 0xdf : Unknown record0.write(pack(b'>IIII', 0xffffffff, 0, 0xffffffff, 0xffffffff)) # 0xe0 - 0xe3 : Extra record data # Extra record data flags: # - 0b1 : <extra multibyte bytes><size> # - 0b10 : <TBS indexing description of this HTML record><size> # - 0b100: <uncrossable breaks><size> # Setting bit 2 (0x2) disables <guide><reference type="start"> functionality extra_data_flags = 0b1 # Has multibyte overlap bytes if self.primary_index_record_idx is not None: extra_data_flags |= 0b10 if WRITE_UNCROSSABLE_BREAKS: extra_data_flags |= 0b100 record0.write(pack(b'>I', extra_data_flags)) # 0xe4 - 0xe7 : Primary index record record0.write(pack(b'>I', 0xffffffff if self.primary_index_record_idx is None else self.primary_index_record_idx)) record0.write(exth) record0.write(title) record0 = record0.getvalue() # Add some buffer so that Amazon can add encryption information if this # MOBI is submitted for publication record0 += (b'\0' * (1024*8)) self.records[0] = align_block(record0)