Include html5lib for BeautifulSoup

BeautifulSoup needs lxml or html5, have included html5lib. Also latest BeautifulSoup 4.1.3
2026-05-02 17:59:28 +01:00 · 2012-09-06 10:47:07 +12:00
parent 7aac60cecd
commit b8c5782765
136 changed files with 87265 additions and 2428 deletions
--- a/html5lib/tests/test_parser2.py
+++ b/html5lib/tests/test_parser2.py
@@ -0,0 +1,39 @@
+import support
+from html5lib import html5parser
+from html5lib.constants import namespaces
+from html5lib.treebuilders import dom
+
+import unittest
+
+# tests that aren't autogenerated from text files
+class MoreParserTests(unittest.TestCase):
+
+  def test_assertDoctypeCloneable(self):
+    parser = html5parser.HTMLParser(tree=dom.TreeBuilder)
+    doc = parser.parse('<!DOCTYPE HTML>')
+    self.assert_(doc.cloneNode(True))
+
+  def test_line_counter(self):
+    # http://groups.google.com/group/html5lib-discuss/browse_frm/thread/f4f00e4a2f26d5c0
+    parser = html5parser.HTMLParser(tree=dom.TreeBuilder)
+    parser.parse("<pre>\nx\n&gt;\n</pre>")
+
+  def test_namespace_html_elements_0(self): 
+    parser = html5parser.HTMLParser(namespaceHTMLElements=True)
+    doc = parser.parse("<html></html>")
+    self.assert_(doc.childNodes[0].namespace == namespaces["html"])
+
+  def test_namespace_html_elements_1(self): 
+    parser = html5parser.HTMLParser(namespaceHTMLElements=False)
+    doc = parser.parse("<html></html>")
+    self.assert_(doc.childNodes[0].namespace == None)
+
+def buildTestSuite():
+  return unittest.defaultTestLoader.loadTestsFromName(__name__)
+
+def main():
+    buildTestSuite()
+    unittest.main()
+
+if __name__ == '__main__':
+    main()