mirror of
https://github.com/morpheus65535/bazarr.git
synced 2024-11-12 02:22:56 +08:00
130 lines
5.3 KiB
Python
130 lines
5.3 KiB
Python
from __future__ import absolute_import, division, unicode_literals
|
|
|
|
from six import PY2, text_type, unichr
|
|
|
|
import io
|
|
|
|
from . import support # noqa
|
|
|
|
from html5lib.constants import namespaces, tokenTypes
|
|
from html5lib import parse, parseFragment, HTMLParser
|
|
|
|
|
|
# tests that aren't autogenerated from text files
|
|
def test_assertDoctypeCloneable():
|
|
doc = parse('<!DOCTYPE HTML>', treebuilder="dom")
|
|
assert doc.cloneNode(True) is not None
|
|
|
|
|
|
def test_line_counter():
|
|
# http://groups.google.com/group/html5lib-discuss/browse_frm/thread/f4f00e4a2f26d5c0
|
|
assert parse("<pre>\nx\n>\n</pre>") is not None
|
|
|
|
|
|
def test_namespace_html_elements_0_dom():
|
|
doc = parse("<html></html>",
|
|
treebuilder="dom",
|
|
namespaceHTMLElements=True)
|
|
assert doc.childNodes[0].namespaceURI == namespaces["html"]
|
|
|
|
|
|
def test_namespace_html_elements_1_dom():
|
|
doc = parse("<html></html>",
|
|
treebuilder="dom",
|
|
namespaceHTMLElements=False)
|
|
assert doc.childNodes[0].namespaceURI is None
|
|
|
|
|
|
def test_namespace_html_elements_0_etree():
|
|
doc = parse("<html></html>",
|
|
treebuilder="etree",
|
|
namespaceHTMLElements=True)
|
|
assert doc.tag == "{%s}html" % (namespaces["html"],)
|
|
|
|
|
|
def test_namespace_html_elements_1_etree():
|
|
doc = parse("<html></html>",
|
|
treebuilder="etree",
|
|
namespaceHTMLElements=False)
|
|
assert doc.tag == "html"
|
|
|
|
|
|
def test_unicode_file():
|
|
assert parse(io.StringIO("a")) is not None
|
|
|
|
|
|
def test_maintain_attribute_order():
|
|
# This is here because we impl it in parser and not tokenizer
|
|
p = HTMLParser()
|
|
# generate loads to maximize the chance a hash-based mutation will occur
|
|
attrs = [(unichr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
|
|
token = {'name': 'html',
|
|
'selfClosing': False,
|
|
'selfClosingAcknowledged': False,
|
|
'type': tokenTypes["StartTag"],
|
|
'data': attrs}
|
|
out = p.normalizeToken(token)
|
|
attr_order = list(out["data"].keys())
|
|
assert attr_order == [x for x, i in attrs]
|
|
|
|
|
|
def test_duplicate_attribute():
|
|
# This is here because we impl it in parser and not tokenizer
|
|
doc = parse('<p class=a class=b>')
|
|
el = doc[1][0]
|
|
assert el.get("class") == "a"
|
|
|
|
|
|
def test_maintain_duplicate_attribute_order():
|
|
# This is here because we impl it in parser and not tokenizer
|
|
p = HTMLParser()
|
|
attrs = [(unichr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
|
|
token = {'name': 'html',
|
|
'selfClosing': False,
|
|
'selfClosingAcknowledged': False,
|
|
'type': tokenTypes["StartTag"],
|
|
'data': attrs + [('a', len(attrs))]}
|
|
out = p.normalizeToken(token)
|
|
attr_order = list(out["data"].keys())
|
|
assert attr_order == [x for x, i in attrs]
|
|
|
|
|
|
def test_debug_log():
|
|
parser = HTMLParser(debug=True)
|
|
parser.parse("<!doctype html><title>a</title><p>b<script>c</script>d</p>e")
|
|
|
|
expected = [('dataState', 'InitialPhase', 'InitialPhase', 'processDoctype', {'type': 'Doctype'}),
|
|
('dataState', 'BeforeHtmlPhase', 'BeforeHtmlPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
|
|
('dataState', 'BeforeHeadPhase', 'BeforeHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
|
|
('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
|
|
('rcdataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
|
|
('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'title', 'type': 'EndTag'}),
|
|
('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
|
|
('dataState', 'AfterHeadPhase', 'AfterHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
|
|
('dataState', 'InBodyPhase', 'InHeadPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
|
|
('scriptDataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
|
|
('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'script', 'type': 'EndTag'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processEndTag', {'name': 'p', 'type': 'EndTag'}),
|
|
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'})]
|
|
|
|
if PY2:
|
|
for i, log in enumerate(expected):
|
|
log = [x.encode("ascii") if isinstance(x, text_type) else x for x in log]
|
|
expected[i] = tuple(log)
|
|
|
|
assert parser.log == expected
|
|
|
|
|
|
def test_no_duplicate_clone():
|
|
frag = parseFragment("<b><em><foo><foob><fooc><aside></b></em>")
|
|
assert len(frag) == 2
|
|
|
|
|
|
def test_self_closing_col():
|
|
parser = HTMLParser()
|
|
parser.parseFragment('<table><colgroup><col /></colgroup></table>')
|
|
assert not parser.errors
|