Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

py3: more unicode porting

Browse Source
This commit is contained in:
Kovid Goyal 2019-06-13 11:11:52 +05:30
parent 3a688453ab
commit 4d9c050e03
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
3 changed files with 30 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/calibre/ebooks/pdb/ereader/__init__.py
View File

@ -1,18 +1,18 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import os import os
from polyglot.builtins import range
class EreaderError(Exception): class EreaderError(Exception):
pass pass
def image_name(name, taken_names=[]): def image_name(name, taken_names=()):
name = os.path.basename(name) name = os.path.basename(name)
if len(name) > 32: if len(name) > 32:
@ -21,10 +21,10 @@ def image_name(name, taken_names=[]):
namee = name[10+cut:] namee = name[10+cut:]
name = '%s%s.png' % (names, namee) name = '%s%s.png' % (names, namee)
i = 0
base_name, ext = os.path.splitext(name)
while name in taken_names: while name in taken_names:
for i in range(999999999999999999999999999): i += 1
name = '%s%s.png' % (name[:-len('%s' % i)], i) name = '%s%s%s' % (base_name, i, ext)
name = name.ljust(32, '\x00')[:32] return name.ljust(32, '\x00')[:32]
return name

2
src/calibre/ebooks/pdb/ereader/inspector.py
View File

@ -2,7 +2,7 @@
''' '''
Inspect the header of ereader files. This is primarily used for debugging. Inspect the header of ereader files. This is primarily used for debugging.
''' '''
from __future__ import print_function from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

42
src/calibre/ebooks/pdb/ereader/writer.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
''' '''
Write content to ereader pdb file. Write content to ereader pdb file.
@ -22,7 +23,7 @@ except ImportError:
from calibre.ebooks.pdb.formatwriter import FormatWriter from calibre.ebooks.pdb.formatwriter import FormatWriter
from calibre.ebooks.pdb.header import PdbHeaderBuilder from calibre.ebooks.pdb.header import PdbHeaderBuilder
from calibre.ebooks.pml.pmlml import PMLMLizer from calibre.ebooks.pml.pmlml import PMLMLizer
from polyglot.builtins import unicode_type from polyglot.builtins import unicode_type, as_bytes
IDENTITY = 'PNRdPPrs' IDENTITY = 'PNRdPPrs'
@ -42,10 +43,10 @@ class Writer(FormatWriter):
pml = unicode_type(pmlmlizer.extract_content(oeb_book, self.opts)).encode('cp1252', 'replace') pml = unicode_type(pmlmlizer.extract_content(oeb_book, self.opts)).encode('cp1252', 'replace')
text, text_sizes = self._text(pml) 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(br'(?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(br'(?s)\\X(?P<val>[0-4])(?P<text>.+?)\\X[0-4]', pml)
chapter_index += self._index_item(r'(?s)\\x(?P<text>.+?)\\x', pml) chapter_index += self._index_item(br'(?s)\\x(?P<text>.+?)\\x', pml)
link_index = self._index_item(r'(?s)\\Q="(?P<text>.+?)"', pml) link_index = self._index_item(br'(?s)\\Q="(?P<text>.+?)"', pml)
images = self._images(oeb_book.manifest, pmlmlizer.image_hrefs) images = self._images(oeb_book.manifest, pmlmlizer.image_hrefs)
metadata = [self._metadata(metadata)] metadata = [self._metadata(metadata)]
hr = [self._header_record(len(text), len(chapter_index), len(link_index), len(images))] hr = [self._header_record(len(text), len(chapter_index), len(link_index), len(images))]
@ -66,7 +67,7 @@ class Writer(FormatWriter):
12. Text block size record 12. Text block size record
13. "MeTaInFo\x00" word record 13. "MeTaInFo\x00" word record
''' '''
sections = hr+text+chapter_index+link_index+images+metadata+[text_sizes]+['MeTaInFo\x00'] 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] lengths = [len(i) if i not in images else len(i[0]) + len(i[1]) for i in sections]
@ -82,13 +83,13 @@ class Writer(FormatWriter):
def _text(self, pml): def _text(self, pml):
pml_pages = [] pml_pages = []
text_sizes = '' text_sizes = b''
index = 0 index = 0
while index < len(pml): while index < len(pml):
''' '''
Split on the space character closest to MAX_RECORD_SIZE when possible. Split on the space character closest to MAX_RECORD_SIZE when possible.
''' '''
split = pml.rfind(' ', index, MAX_RECORD_SIZE) split = pml.rfind(b' ', index, MAX_RECORD_SIZE)
if split == -1: if split == -1:
len_end = len(pml[index:]) len_end = len(pml[index:])
if len_end > MAX_RECORD_SIZE: if len_end > MAX_RECORD_SIZE:
@ -106,19 +107,19 @@ class Writer(FormatWriter):
def _index_item(self, regex, pml): def _index_item(self, regex, pml):
index = [] index = []
for mo in re.finditer(regex, pml): for mo in re.finditer(regex, pml):
item = '' item = b''
if 'text' in mo.groupdict().keys(): if 'text' in mo.groupdict().keys():
item += struct.pack('>L', mo.start()) item += struct.pack('>L', mo.start())
text = mo.group('text') text = mo.group('text')
# Strip all PML tags from text # Strip all PML tags from text
text = re.sub(r'\\U[0-9a-z]{4}', '', text) text = re.sub(br'\\U[0-9a-z]{4}', '', text)
text = re.sub(r'\\a\d{3}', '', text) text = re.sub(br'\\a\d{3}', '', text)
text = re.sub(r'\\.', '', text) text = re.sub(br'\\.', '', text)
# Add appropriate spacing to denote the various levels of headings # Add appropriate spacing to denote the various levels of headings
if 'val' in mo.groupdict().keys(): if 'val' in mo.groupdict().keys():
text = '%s%s' % (' ' * 4 * int(mo.group('val')), text) text = b'%s%s' % (b' ' * 4 * int(mo.group('val')), text)
item += text item += text
item += '\x00' item += b'\x00'
if item: if item:
index.append(item) index.append(item)
return index return index
@ -146,12 +147,13 @@ class Writer(FormatWriter):
data = io.BytesIO() data = io.BytesIO()
im.save(data, 'PNG') im.save(data, 'PNG')
data = data.getvalue() data = data.getvalue()
href = as_bytes(image_hrefs[item.href])
header = 'PNG ' header = b'PNG '
header += image_hrefs[item.href].ljust(32, '\x00')[:32] header += href.ljust(32, b'\x00')[:32]
header = header.ljust(58, '\x00') header = header.ljust(58, b'\x00')
header += struct.pack('>HH', im.size[0], im.size[1]) header += struct.pack('>HH', im.size[0], im.size[1])
header = header.ljust(62, '\x00') header = header.ljust(62, b'\x00')
if len(data) + len(header) < 65505: if len(data) + len(header) < 65505:
images.append((header, data)) images.append((header, data))
@ -188,7 +190,7 @@ class Writer(FormatWriter):
if len(metadata.publisher) >= 1: if len(metadata.publisher) >= 1:
publisher = metadata.publisher[0].value publisher = metadata.publisher[0].value
return '%s\x00%s\x00%s\x00%s\x00%s\x00' % (title, author, copyright, publisher, isbn) return as_bytes('%s\x00%s\x00%s\x00%s\x00%s\x00' % (title, author, copyright, publisher, isbn))
def _header_record(self, text_count, chapter_count, link_count, image_count): def _header_record(self, text_count, chapter_count, link_count, image_count):
''' '''
@ -215,7 +217,7 @@ class Writer(FormatWriter):
if link_count == 0: if link_count == 0:
link_offset = last_data_offset link_offset = last_data_offset
record = '' record = b''
record += struct.pack('>H', compression) # [0:2] # Compression. Specifies compression and drm. 2 = palmdoc, 10 = zlib. 260 and 272 = DRM record += struct.pack('>H', compression) # [0:2] # Compression. Specifies compression and drm. 2 = palmdoc, 10 = zlib. 260 and 272 = DRM
record += struct.pack('>H', 0) # [2:4] # Unknown. record += struct.pack('>H', 0) # [2:4] # Unknown.