88 lines
2.8 KiB
Python
88 lines
2.8 KiB
Python
"""Tests to ensure that the lxml tree builder generates good trees."""
|
|
|
|
import re
|
|
import warnings
|
|
|
|
try:
|
|
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
|
|
LXML_PRESENT = True
|
|
import lxml.etree
|
|
LXML_VERSION = lxml.etree.LXML_VERSION
|
|
except ImportError, e:
|
|
LXML_PRESENT = False
|
|
LXML_VERSION = (0,)
|
|
|
|
from bs4 import (
|
|
BeautifulSoup,
|
|
BeautifulStoneSoup,
|
|
)
|
|
from bs4.element import Comment, Doctype, SoupStrainer
|
|
from bs4.testing import skipIf
|
|
from bs4.tests import test_htmlparser
|
|
from bs4.testing import (
|
|
HTMLTreeBuilderSmokeTest,
|
|
XMLTreeBuilderSmokeTest,
|
|
SoupTest,
|
|
skipIf,
|
|
)
|
|
|
|
@skipIf(
|
|
not LXML_PRESENT,
|
|
"lxml seems not to be present, not testing its tree builder.")
|
|
class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
|
|
"""See ``HTMLTreeBuilderSmokeTest``."""
|
|
|
|
@property
|
|
def default_builder(self):
|
|
return LXMLTreeBuilder()
|
|
|
|
def test_out_of_range_entity(self):
|
|
self.assertSoupEquals(
|
|
"<p>foo�bar</p>", "<p>foobar</p>")
|
|
self.assertSoupEquals(
|
|
"<p>foo�bar</p>", "<p>foobar</p>")
|
|
self.assertSoupEquals(
|
|
"<p>foo�bar</p>", "<p>foobar</p>")
|
|
|
|
# In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
|
|
# test if an old version of lxml is installed.
|
|
|
|
@skipIf(
|
|
not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
|
|
"Skipping doctype test for old version of lxml to avoid segfault.")
|
|
def test_empty_doctype(self):
|
|
soup = self.soup("<!DOCTYPE>")
|
|
doctype = soup.contents[0]
|
|
self.assertEqual("", doctype.strip())
|
|
|
|
def test_beautifulstonesoup_is_xml_parser(self):
|
|
# Make sure that the deprecated BSS class uses an xml builder
|
|
# if one is installed.
|
|
with warnings.catch_warnings(record=False) as w:
|
|
soup = BeautifulStoneSoup("<b />")
|
|
self.assertEqual(u"<b/>", unicode(soup.b))
|
|
|
|
def test_real_xhtml_document(self):
|
|
"""lxml strips the XML definition from an XHTML doc, which is fine."""
|
|
markup = b"""<?xml version="1.0" encoding="utf-8"?>
|
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
<head><title>Hello.</title></head>
|
|
<body>Goodbye.</body>
|
|
</html>"""
|
|
soup = self.soup(markup)
|
|
self.assertEqual(
|
|
soup.encode("utf-8").replace(b"\n", b''),
|
|
markup.replace(b'\n', b'').replace(
|
|
b'<?xml version="1.0" encoding="utf-8"?>', b''))
|
|
|
|
|
|
@skipIf(
|
|
not LXML_PRESENT,
|
|
"lxml seems not to be present, not testing its XML tree builder.")
|
|
class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
|
|
"""See ``HTMLTreeBuilderSmokeTest``."""
|
|
|
|
@property
|
|
def default_builder(self):
|
|
return LXMLTreeBuilderForXML()
|