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

Accept transport_encoding in html5lib.parse

Browse Source
This commit is contained in:
Kovid Goyal 2017-03-09 21:33:33 +05:30
parent 4da5526228
commit 0f7b73d7c4
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/html5lib/html5parser.py
View File

@ -19,6 +19,7 @@ from .constants import (
try: try:
unicode unicode
def with_metaclass(meta, *bases): def with_metaclass(meta, *bases):
"""Create a base class with a metaclass.""" """Create a base class with a metaclass."""
return meta(b"NewBase", bases, {}) return meta(b"NewBase", bases, {})
@ -29,11 +30,11 @@ except NameError:
def parse(doc, treebuilder="etree", encoding=None, def parse(doc, treebuilder="etree", encoding=None,
namespaceHTMLElements=True): namespaceHTMLElements=True, transport_encoding=None):
"""Parse a string or file-like object into a tree""" """Parse a string or file-like object into a tree"""
tb = treebuilders.getTreeBuilder(treebuilder) tb = treebuilders.getTreeBuilder(treebuilder)
p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
return p.parse(doc, encoding=encoding) return p.parse(doc, encoding=transport_encoding or encoding)
def parseFragment(doc, container="div", treebuilder="etree", encoding=None, def parseFragment(doc, container="div", treebuilder="etree", encoding=None,
@ -368,6 +369,7 @@ class HTMLParser(object):
ans['position'] = (self.tokenizer.stream.position(), True) ans['position'] = (self.tokenizer.stream.position(), True)
return ans return ans
def getPhases(debug): def getPhases(debug):
def log(function): def log(function):
"""Logger that records which phase processes each token""" """Logger that records which phase processes each token"""
@ -2668,11 +2670,13 @@ def getPhases(debug):
# XXX after after frameset # XXX after after frameset
} }
def adjust_attributes(token, replacements): def adjust_attributes(token, replacements):
if token['data'].viewkeys() & replacements.viewkeys(): if token['data'].viewkeys() & replacements.viewkeys():
token['data'] = OrderedDict( token['data'] = OrderedDict(
(replacements.get(k, k), v) for k, v in token['data'].iteritems()) (replacements.get(k, k), v) for k, v in token['data'].iteritems())
class ParseError(Exception): class ParseError(Exception):
"""Error in parsed document""" """Error in parsed document"""