Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

ztxt reader: check version and flags (only newer ztxt format is supported). log info and debug for ztxt and palmdoc input/output.

Browse Source
This commit is contained in:
John Schember 2009-05-03 19:07:21 -04:00
parent 5b8974dbb1
commit d77f83f9a6
4 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/pdb/palmdoc/reader.py
View File

@ -53,9 +53,12 @@ class Reader(FormatReader):
def extract_content(self, output_dir):
txt = ''
self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %i' % i)
txt += self.decompress_text(i)
self.log.info('Converting text to OEB...')
html = txt_to_markdown(txt)
with open(os.path.join(output_dir, 'index.html'), 'wb') as index:
index.write(html.encode('utf-8'))

2
src/calibre/ebooks/pdb/palmdoc/writer.py
View File

@ -30,7 +30,9 @@ class Writer(FormatWriter):
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].encode('utf-8'))
section_lengths.append(len(txt_records[i]))

16
src/calibre/ebooks/pdb/ztxt/reader.py
View File

@ -14,6 +14,8 @@ from calibre.ebooks.pdb.formatreader import FormatReader
from calibre.ebooks.pdb.ztxt import zTXTError
from calibre.ebooks.txt.processor import txt_to_markdown, opf_writer
SUPPORTED_VERSION = (1, 40)
class HeaderRecord(object):
'''
The first record in the file is always the header record. It holds
@ -27,6 +29,7 @@ class HeaderRecord(object):
self.num_records, = struct.unpack('>H', raw[2:4])
self.size, = struct.unpack('>L', raw[4:8])
self.record_size, = struct.unpack('>H', raw[8:10])
self.flags, = struct.unpack('>B', raw[18:19])
class Reader(FormatReader):
@ -42,6 +45,16 @@ class Reader(FormatReader):
self.header_record = HeaderRecord(self.section_data(0))
vmajor = (self.header_record.version & 0x0000FF00) >> 8
vminor = self.header_record.version & 0x000000FF
if vmajor < 1 or (vmajor == 1 and vminor < 40):
raise zTXTError('Unsupported ztxt version (%i.%i). Only versions newer than %i.%i are supported.' % (vmajor, vminor, SUPPORTED_VERSION[0], SUPPORTED_VERSION[1]))
if (self.header_record.flags & 0x01) == 0:
raise zTXTError('Only compression method 1 (random access) is supported')
self.log.debug('Foud ztxt version: %i.%i' % (vmajor, vminor))
# Initalize the decompressor
self.uncompressor = zlib.decompressobj()
self.uncompressor.decompress(self.section_data(1))
@ -57,9 +70,12 @@ class Reader(FormatReader):
def extract_content(self, output_dir):
txt = ''
self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %i' % i)
txt += self.decompress_text(i)
self.log.info('Converting text to OEB...')
html = txt_to_markdown(txt)
with open(os.path.join(output_dir, 'index.html'), 'wb') as index:
index.write(html.encode('utf-8'))

2
src/calibre/ebooks/pdb/ztxt/writer.py
View File

@ -30,7 +30,9 @@ class Writer(FormatWriter):
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].encode('utf-8'))
txt_records[i] = txt_records[i] + compressor.flush(zlib.Z_FULL_FLUSH)
section_lengths.append(len(txt_records[i]))