Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update inspector with new known values and makebook files. Better error message.

Browse Source
This commit is contained in:
John Schember 2009-05-25 07:34:42 -04:00
parent 3432735e48
commit 6b9ea1d0ae
2 changed files with 76 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
src/calibre/ebooks/pdb/ereader/inspector.py
View File

@ -7,10 +7,27 @@ __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import struct, sys import struct
import sys
from calibre.ebooks.pdb.ereader import EreaderError
from calibre.ebooks.pdb.header import PdbHeaderReader from calibre.ebooks.pdb.header import PdbHeaderReader
from calibre.ebooks.pdb.ereader.reader import HeaderRecord
def ereader_header_info(header):
h0 = header.section_data(0)
print 'Header Size: %s' % len(h0)
if len(h0) == 132:
print 'Header Type: Dropbook compatible'
print ''
ereader_header_info132(h0)
elif len(h0) == 202:
print 'Header Type: Makebook compatible'
print ''
ereader_header_info202(h0)
else:
raise EreaderError('Size mismatch. eReader header record size %i KB is not supported.' % len(h0))
def pdb_header_info(header): def pdb_header_info(header):
print 'PDB Header Info:' print 'PDB Header Info:'
@ -20,70 +37,101 @@ def pdb_header_info(header):
print 'Title: %s' % header.title print 'Title: %s' % header.title
print '' print ''
def ereader_header_info(header): def ereader_header_info132(h0):
h0 = header.section_data(0)
print 'Ereader Record 0 (Header) Info:' print 'Ereader Record 0 (Header) Info:'
print '' print ''
print '0-2 Version: %i' % struct.unpack('>H', h0[0:2])[0] print '0-2 Version: %i' % struct.unpack('>H', h0[0:2])[0]
print '2-4: %i' % struct.unpack('>H', h0[2:4])[0] print '2-4: %i' % struct.unpack('>H', h0[2:4])[0]
print '4-6: %i' % struct.unpack('>H', h0[4:6])[0] print '4-6: %i' % struct.unpack('>H', h0[4:6])[0]
print '6-8: %i' % struct.unpack('>H', h0[6:8])[0] print '6-8 Codepage: %i' % struct.unpack('>H', h0[6:8])[0]
print '8-10: %i' % struct.unpack('>H', h0[8:10])[0] print '8-10: %i' % struct.unpack('>H', h0[8:10])[0]
print '10-12: %i' % struct.unpack('>H', h0[10:12])[0] print '10-12: %i' % struct.unpack('>H', h0[10:12])[0]
print '12-14 Non-Text: %i' % struct.unpack('>H', h0[12:14])[0] print '12-14 Non-Text offset: %i' % struct.unpack('>H', h0[12:14])[0]
print '14-16: %i' % struct.unpack('>H', h0[14:16])[0] print '14-16: %i' % struct.unpack('>H', h0[14:16])[0]
print '16-18: %i' % struct.unpack('>H', h0[16:18])[0] print '16-18: %i' % struct.unpack('>H', h0[16:18])[0]
print '18-20: %i' % struct.unpack('>H', h0[18:20])[0] print '18-20: %i' % struct.unpack('>H', h0[18:20])[0]
print '20-22: %i' % struct.unpack('>H', h0[20:22])[0] print '20-22 Image Count: %i' % struct.unpack('>H', h0[20:22])[0]
print '22-24: %i' % struct.unpack('>H', h0[22:24])[0] print '22-24: %i' % struct.unpack('>H', h0[22:24])[0]
print '24-26: %i' % struct.unpack('>H', h0[24:26])[0] print '24-26 Has Metadata?: %i' % struct.unpack('>H', h0[24:26])[0]
print '26-28: %i' % struct.unpack('>H', h0[26:28])[0] print '26-28: %i' % struct.unpack('>H', h0[26:28])[0]
print '28-30 footnote_rec: %i' % struct.unpack('>H', h0[28:30])[0] print '28-30 Footnote Count: %i' % struct.unpack('>H', h0[28:30])[0]
print '30-32 sidebar_rec: %i' % struct.unpack('>H', h0[30:32])[0] print '30-32 Sidebar Count: %i' % struct.unpack('>H', h0[30:32])[0]
print '32-34 bookmark_offset: %i' % struct.unpack('>H', h0[32:34])[0] print '32-34 Bookmark Offset: %i' % struct.unpack('>H', h0[32:34])[0]
print '34-36: %i' % struct.unpack('>H', h0[34:36])[0] print '34-36 MAGIC: %i' % struct.unpack('>H', h0[34:36])[0]
print '36-38: %i' % struct.unpack('>H', h0[36:38])[0] print '36-38: %i' % struct.unpack('>H', h0[36:38])[0]
print '38-40: %i' % struct.unpack('>H', h0[38:40])[0] print '38-40: %i' % struct.unpack('>H', h0[38:40])[0]
print '40-42 image_data_offset: %i' % struct.unpack('>H', h0[40:42])[0] print '40-42 Image Data Offset: %i' % struct.unpack('>H', h0[40:42])[0]
print '42-44: %i' % struct.unpack('>H', h0[42:44])[0] print '42-44: %i' % struct.unpack('>H', h0[42:44])[0]
print '44-46 metadata_offset: %i' % struct.unpack('>H', h0[44:46])[0] print '44-46 Metadata Offset: %i' % struct.unpack('>H', h0[44:46])[0]
print '46-48: %i' % struct.unpack('>H', h0[46:48])[0] print '46-48: %i' % struct.unpack('>H', h0[46:48])[0]
print '48-50 footnote_offset: %i' % struct.unpack('>H', h0[48:50])[0] print '48-50 Footnote Offset: %i' % struct.unpack('>H', h0[48:50])[0]
print '50-52 sidebar_offset: %i' % struct.unpack('>H', h0[50:52])[0] print '50-52 Sidebar Offset: %i' % struct.unpack('>H', h0[50:52])[0]
print '52-54 last_data_offset: %i' % struct.unpack('>H', h0[52:54])[0] print '52-54 Last Data Offset: %i' % struct.unpack('>H', h0[52:54])[0]
for i in range(54, 131, 2): for i in range(54, 131, 2):
print '%i-%i: %i' % (i, i+2, struct.unpack('>H', h0[i:i+2])[0]) print '%i-%i: %i' % (i, i+2, struct.unpack('>H', h0[i:i+2])[0])
print ''
def ereader_header_info202(h0):
print 'Ereader Record 0 (Header) Info:'
print ''
print '0-2 Version: %i' % struct.unpack('>H', h0[0:2])[0]
print '2-4 Garbage: %i' % struct.unpack('>H', h0[2:4])[0]
print '4-6 Garbage: %i' % struct.unpack('>H', h0[4:6])[0]
print '6-8 Garbage: %i' % struct.unpack('>H', h0[6:8])[0]
print '8-10 Non-Text Offset: %i' % struct.unpack('>H', h0[8:10])[0]
print '10-12: %i' % struct.unpack('>H', h0[10:12])[0]
print '12-14: %i' % struct.unpack('>H', h0[12:14])[0]
print '14-16 Garbage: %i' % struct.unpack('>H', h0[14:16])[0]
print '16-18 Garbage: %i' % struct.unpack('>H', h0[16:18])[0]
print '18-20 Garbage: %i' % struct.unpack('>H', h0[18:20])[0]
print '20-22 Garbage: %i' % struct.unpack('>H', h0[20:22])[0]
print '22-24 Garbage: %i' % struct.unpack('>H', h0[22:24])[0]
print '24-26: %i' % struct.unpack('>H', h0[24:26])[0]
print '26-28: %i' % struct.unpack('>H', h0[26:28])[0]
for i in range(28, 98, 2):
print '%i-%i Garbage: %i' % (i, i+2, struct.unpack('>H', h0[i:i+2])[0])
print '98-100: %i' % struct.unpack('>H', h0[98:100])[0]
for i in range(100, 110, 2):
print '%i-%i Garbage: %i' % (i, i+2, struct.unpack('>H', h0[i:i+2])[0])
print '110-112: %i' % struct.unpack('>H', h0[110:112])[0]
print '112-114: %i' % struct.unpack('>H', h0[112:114])[0]
print '114-116 Garbage: %i' % struct.unpack('>H', h0[114:116])[0]
for i in range(116, 202, 2):
print '%i-%i: %i' % (i, i+2, struct.unpack('>H', h0[i:i+2])[0])
print ''
print '* Garbage: Random values.'
print '' print ''
def section_lengths(header): def section_lengths(header):
print 'Section Sizes' print 'Section Sizes'
print '' print ''
for i in range(0, header.section_count()): for i in range(0, header.section_count()):
size = len(header.section_data(i)) size = len(header.section_data(i))
if size > 65505: if size > 65505:
message = '<--- Over!' message = '<--- Over!'
else: else:
message = '' message = ''
print 'Section %i: %i %s' % (i, size, message) print 'Section %i: %i %s' % (i, size, message)
def main(args=sys.argv): def main(args=sys.argv):
if len(args) < 2: if len(args) < 2:
print 'Error: requires input file.' print 'Error: requires input file.'
return 1 return 1
f = open(sys.argv[1], 'rb') f = open(sys.argv[1], 'rb')
pheader = PdbHeaderReader(f) pheader = PdbHeaderReader(f)
pdb_header_info(pheader) pdb_header_info(pheader)
ereader_header_info(pheader) ereader_header_info(pheader)
section_lengths(pheader) section_lengths(pheader)
return 0 return 0
if __name__ == '__main__': if __name__ == '__main__':

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

@ -8,6 +8,7 @@ __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
from calibre.ebooks.pdb.ereader import EreaderError
from calibre.ebooks.pdb.formatreader import FormatReader from calibre.ebooks.pdb.formatreader import FormatReader
from calibre.ebooks.pdb.ereader.reader132 import Reader132 from calibre.ebooks.pdb.ereader.reader132 import Reader132
from calibre.ebooks.pdb.ereader.reader202 import Reader202 from calibre.ebooks.pdb.ereader.reader202 import Reader202
@ -22,7 +23,7 @@ class Reader(FormatReader):
elif record0_size == 202: elif record0_size == 202:
self.reader = Reader202(header, stream, log, encoding) self.reader = Reader202(header, stream, log, encoding)
else: else:
raise ValueError('Unknown eReader Header') raise EreaderError('Size mismatch. eReader header record size %s KB is not supported.' % record0_size)
def extract_content(self, output_dir): def extract_content(self, output_dir):
return self.reader.extract_content(output_dir) return self.reader.extract_content(output_dir)