def write_content(self, oeb_book, out_stream, metadata=None):
title = self.opts.title if self.opts.title else oeb_book.metadata.title[0].value if oeb_book.metadata.title != [] else _('Unknown')
txt_records, txt_length = self._generate_text(oeb_book)
crc32 = 0
section_lengths = []
compressor = zlib.compressobj(9)
self.log.info('Compressing data...')
for i in range(0, len(txt_records)):
self.log.debug('\tCompressing record %i' % i)
txt_records[i] = compressor.compress(txt_records[i])
txt_records[i] = txt_records[i] + compressor.flush(zlib.Z_FULL_FLUSH)
section_lengths.append(len(txt_records[i]))
crc32 = zlib.crc32(txt_records[i], crc32) & 0xffffffff
header_record = self._header_record(txt_length, len(txt_records), crc32)
section_lengths.insert(0, len(header_record))
out_stream.seek(0)
hb = PdbHeaderBuilder('zTXTGPlm', title)
hb.build_header(section_lengths, out_stream)
for record in [header_record]+txt_records:
out_stream.write(record)
def write_content(self, oeb_book, out_stream, metadata=None):
pmlmlizer = PMLMLizer(self.log)
pml = unicode_type(pmlmlizer.extract_content(oeb_book,
self.opts)).encode(
'cp1252', 'replace')
text, text_sizes = self._text(pml)
chapter_index = self._index_item(
br'(?s)\\C(?P<val>[0-4])="(?P<text>.+?)"', pml)
chapter_index += self._index_item(
br'(?s)\\X(?P<val>[0-4])(?P<text>.+?)\\X[0-4]', pml)
chapter_index += self._index_item(br'(?s)\\x(?P<text>.+?)\\x', pml)
link_index = self._index_item(br'(?s)\\Q="(?P<text>.+?)"', pml)
images = self._images(oeb_book.manifest, pmlmlizer.image_hrefs)
metadata = [self._metadata(metadata)]
hr = [
self._header_record(len(text), len(chapter_index), len(link_index),
len(images))
]
'''
Record order as generated by Dropbook.
1. eReader Header
2. Compressed text
3. Small font page index
4. Large font page index
5. Chapter index
6. Links index
7. Images
8. (Extrapolation: there should be one more record type here though yet uncovered what it might be).
9. Metadata
10. Sidebar records
11. Footnote records
12. Text block size record
13. "MeTaInFo\x00" word record
'''
sections = hr + text + chapter_index + link_index + images + metadata + [
text_sizes
] + [b'MeTaInFo\x00']
lengths = [
len(i) if i not in images else len(i[0]) + len(i[1])
for i in sections
]
pdbHeaderBuilder = PdbHeaderBuilder(IDENTITY,
metadata[0].partition('\x00')[0])
pdbHeaderBuilder.build_header(lengths, out_stream)
for item in sections:
if item in images:
out_stream.write(item[0])
out_stream.write(item[1])
else:
out_stream.write(item)
def set_metadata(stream, mi):
pheader = PdbHeaderReader(stream)
# Only Dropbook produced 132 byte record0 files are supported
if pheader.section_data(0) != 132:
return
sections = [
pheader.section_data(x) for x in range(0, pheader.section_count())
]
hr = HeaderRecord(sections[0])
if hr.compression not in (2, 10):
return
# Create a metadata record for the file if one does not already exist
if not hr.has_metadata:
sections += [b'', b'MeTaInFo\x00']
last_data = len(sections) - 1
for i in range(0, 132, 2):
val, = struct.unpack('>H', sections[0][i:i + 2])
if val >= hr.last_data_offset:
sections[0][i:i + 2] = struct.pack('>H', last_data)
sections[0][24:26] = struct.pack('>H', 1) # Set has metadata
sections[0][44:46] = struct.pack('>H', last_data -
1) # Set location of metadata
sections[0][52:54] = struct.pack(
'>H', last_data) # Ensure last data offset is updated
# Merge the metadata into the file
file_mi = get_metadata(stream, False)
file_mi.smart_update(mi)
sections[hr.metadata_offset] = (
'%s\x00%s\x00%s\x00%s\x00%s\x00' %
(file_mi.title, authors_to_string(file_mi.authors), '',
file_mi.publisher, file_mi.isbn)).encode('cp1252', 'replace')
# Rebuild the PDB wrapper because the offsets have changed due to the
# new metadata.
pheader_builder = PdbHeaderBuilder(pheader.ident, pheader.title)
stream.seek(0)
stream.truncate(0)
pheader_builder.build_header([len(x) for x in sections], stream)
# Write the data back to the file
for item in sections:
stream.write(item)
def set_metadata(stream, mi):
pheader = PdbHeaderReader(stream)
# Only Dropbook produced 132 byte record0 files are supported
if pheader.section_data(0) != 132:
return
sections = [pheader.section_data(x) for x in range(0, pheader.section_count())]
hr = HeaderRecord(sections[0])
if hr.compression not in (2, 10):
return
# Create a metadata record for the file if one does not alreay exist
if not hr.has_metadata:
sections += ['', 'MeTaInFo\x00']
last_data = len(sections) - 1
for i in range(0, 132, 2):
val, = struct.unpack('>H', sections[0][i:i + 2])
if val >= hr.last_data_offset:
sections[0][i:i + 2] = struct.pack('>H', last_data)
sections[0][24:26] = struct.pack('>H', 1) # Set has metadata
sections[0][44:46] = struct.pack('>H', last_data - 1) # Set location of metadata
sections[0][52:54] = struct.pack('>H', last_data) # Ensure last data offset is updated
# Merge the metadata into the file
file_mi = get_metadata(stream, False)
file_mi.smart_update(mi)
sections[hr.metadata_offset] = '%s\x00%s\x00%s\x00%s\x00%s\x00' % \
(file_mi.title, authors_to_string(file_mi.authors), '', file_mi.publisher, file_mi.isbn)
# Rebuild the PDB wrapper because the offsets have changed due to the
# new metadata.
pheader_builder = PdbHeaderBuilder(pheader.ident, pheader.title)
stream.seek(0)
stream.truncate(0)
pheader_builder.build_header([len(x) for x in sections], stream)
# Write the data back to the file
for item in sections:
stream.write(item)
def write_content(self, oeb_book, out_stream, metadata=None):
pmlmlizer = PMLMLizer(self.log)
pml = unicode(pmlmlizer.extract_content(oeb_book, self.opts)).encode('cp1252', 'replace')
text, text_sizes = self._text(pml)
chapter_index = self._index_item(r'(?s)\\C(?P<val>[0-4])="(?P<text>.+?)"', pml)
chapter_index += self._index_item(r'(?s)\\X(?P<val>[0-4])(?P<text>.+?)\\X[0-4]', pml)
chapter_index += self._index_item(r'(?s)\\x(?P<text>.+?)\\x', pml)
link_index = self._index_item(r'(?s)\\Q="(?P<text>.+?)"', pml)
images = self._images(oeb_book.manifest, pmlmlizer.image_hrefs)
metadata = [self._metadata(metadata)]
hr = [self._header_record(len(text), len(chapter_index), len(link_index), len(images))]
'''
Record order as generated by Dropbook.
1. eReader Header
2. Compressed text
3. Small font page index
4. Large font page index
5. Chapter index
6. Links index
7. Images
8. (Extrapolation: there should be one more record type here though yet uncovered what it might be).
9. Metadata
10. Sidebar records
11. Footnote records
12. Text block size record
13. "MeTaInFo\x00" word record
'''
sections = hr+text+chapter_index+link_index+images+metadata+[text_sizes]+['MeTaInFo\x00']
lengths = [len(i) if i not in images else len(i[0]) + len(i[1]) for i in sections]
pdbHeaderBuilder = PdbHeaderBuilder(IDENTITY, metadata[0].partition('\x00')[0])
pdbHeaderBuilder.build_header(lengths, out_stream)
for item in sections:
if item in images:
out_stream.write(item[0])
out_stream.write(item[1])
else:
out_stream.write(item)
def write_content(self, oeb_book, out_stream, metadata=None):
from calibre.ebooks.compression.palmdoc import compress_doc
title = self.opts.title if self.opts.title else oeb_book.metadata.title[0].value if oeb_book.metadata.title != [] else _('Unknown')
txt_records, txt_length = self._generate_text(oeb_book)
header_record = self._header_record(txt_length, len(txt_records))
section_lengths = [len(header_record)]
self.log.info('Compessing data...')
for i in range(0, len(txt_records)):
self.log.debug('\tCompressing record %i' % i)
txt_records[i] = compress_doc(txt_records[i])
section_lengths.append(len(txt_records[i]))
out_stream.seek(0)
hb = PdbHeaderBuilder('TEXtREAd', title)
hb.build_header(section_lengths, out_stream)
for record in [header_record] + txt_records:
out_stream.write(record)
def write_content(self, oeb_book, out_stream, metadata=None):
from calibre.ebooks.compression.palmdoc import compress_doc
title = self.opts.title if self.opts.title else oeb_book.metadata.title[0].value if oeb_book.metadata.title != [] else _('Unknown')
txt_records, txt_length = self._generate_text(oeb_book)
header_record = self._header_record(txt_length, len(txt_records))
section_lengths = [len(header_record)]
self.log.info('Compessing data...')
for i in range(0, len(txt_records)):
self.log.debug('\tCompressing record %i' % i)
txt_records[i] = compress_doc(txt_records[i])
section_lengths.append(len(txt_records[i]))
out_stream.seek(0)
hb = PdbHeaderBuilder('TEXtREAd', title)
hb.build_header(section_lengths, out_stream)
for record in [header_record] + txt_records:
out_stream.write(record)
