gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-02-23 18:45:55 +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

14
ebook_converter/ebooks/oeb/parse_utils.py
View File

@@ -10,11 +10,11 @@ import re
from lxml import etree, html
from calibre import xml_replace_entities, force_unicode
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.constants import filesystem_encoding
from calibre.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes, map
from ebook_converter import xml_replace_entities, force_unicode
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.constants import filesystem_encoding
from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes, map
RECOVER_PARSER = etree.XMLParser(recover=True, no_network=True, resolve_entities=False)
XHTML_NS = 'http://www.w3.org/1999/xhtml'
@@ -94,7 +94,7 @@ def node_depth(node):
def html5_parse(data, max_nesting_depth=100):
from html5_parser import parse
from calibre.utils.cleantext import clean_xml_chars
from ebook_converter.utils.cleantext import clean_xml_chars
data = parse(clean_xml_chars(data), maybe_xhtml=True, keep_doctype=False, sanitize_names=True)
# Check that the asinine HTML 5 algorithm did not result in a tree with
# insane nesting depths
@@ -160,7 +160,7 @@ def check_for_html5(prefix, root):
def parse_html(data, log=None, decoder=None, preprocessor=None,
filename='<string>', non_html_file_tags=frozenset()):
if log is None:
from calibre.utils.logging import default_log
from ebook_converter.utils.logging import default_log
log = default_log
filename = force_unicode(filename, enc=filesystem_encoding)