gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-01-06 11:14:12 +01:00
Code Issues Projects Releases Wiki Activity

Convert calibre modules to ebook_converter.

Browse Source 
Here is the first batch of modules, which are needed for converting
several formats to LRF. Some of the logic has been change, more cleanups
will follow.
This commit is contained in:
gryf
2020-04-11 19:33:43 +02:00
parent 69d2e536c5
commit 0f9792df36
252 changed files with 1925 additions and 2344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ebook_converter/utils/cleantext.py
View File

@@ -4,17 +4,9 @@
from __future__ import absolute_import, division, print_function, unicode_literals
import re
from polyglot.builtins import codepoint_to_chr, map, range, filter
from polyglot.html_entities import name2codepoint
from calibre.constants import plugins, preferred_encoding
_ncxc = plugins['speedup'][0].clean_xml_chars
def native_clean_xml_chars(x):
if isinstance(x, bytes):
x = x.decode(preferred_encoding)
return _ncxc(x)
from ebook_converter.polyglot.builtins import codepoint_to_chr, map, range, filter
from ebook_converter.polyglot.html_entities import name2codepoint
from ebook_converter.constants import plugins, preferred_encoding
def ascii_pat(for_binary=False):
@@ -59,7 +51,7 @@ def py_clean_xml_chars(unicode_string):
return ''.join(filter(allowed, unicode_string))
clean_xml_chars = native_clean_xml_chars or py_clean_xml_chars
clean_xml_chars = py_clean_xml_chars
def test_clean_xml_chars():