diff options
Diffstat (limited to 'bs4/tests')
| -rw-r--r-- | bs4/tests/test_html5lib.py | 6 | ||||
| -rw-r--r-- | bs4/tests/test_lxml.py | 12 | ||||
| -rw-r--r-- | bs4/tests/test_soup.py | 38 | ||||
| -rw-r--r-- | bs4/tests/test_tree.py | 21 |
4 files changed, 67 insertions, 10 deletions
diff --git a/bs4/tests/test_html5lib.py b/bs4/tests/test_html5lib.py index f1edddf..0828cfd 100644 --- a/bs4/tests/test_html5lib.py +++ b/bs4/tests/test_html5lib.py @@ -7,7 +7,7 @@ except ImportError, e: HTML5LIB_PRESENT = False from bs4.element import SoupStrainer from bs4.testing import ( - HTMLTreeBuilderSmokeTest, + HTML5TreeBuilderSmokeTest, SoupTest, skipIf, ) @@ -15,8 +15,8 @@ from bs4.testing import ( @skipIf( not HTML5LIB_PRESENT, "html5lib seems not to be present, not testing its tree builder.") -class HTML5LibBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): - """See ``HTMLTreeBuilderSmokeTest``.""" +class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest): + """See ``HTML5TreeBuilderSmokeTest``.""" @property def default_builder(self): diff --git a/bs4/tests/test_lxml.py b/bs4/tests/test_lxml.py index 92b7389..27ec570 100644 --- a/bs4/tests/test_lxml.py +++ b/bs4/tests/test_lxml.py @@ -14,6 +14,7 @@ from bs4.testing import skipIf from bs4.tests import test_htmlparser from bs4.testing import ( HTMLTreeBuilderSmokeTest, + XMLTreeBuilderSmokeTest, SoupTest, skipIf, ) @@ -35,3 +36,14 @@ class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): "<p>foo�bar</p>", "<p>foobar</p>") self.assertSoupEquals( "<p>foo�bar</p>", "<p>foobar</p>") + +@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() + diff --git a/bs4/tests/test_soup.py b/bs4/tests/test_soup.py index 2b7c003..33ab0fa 100644 --- a/bs4/tests/test_soup.py +++ b/bs4/tests/test_soup.py @@ -3,7 +3,10 @@ import unittest from bs4 import BeautifulSoup -from bs4.element import SoupStrainer +from bs4.element import ( + SoupStrainer, + NamespacedAttribute, + ) from bs4.dammit import EntitySubstitution, UnicodeDammit from bs4.testing import SoupTest import warnings @@ -16,7 +19,7 @@ class TestDeprecatedConstructorArguments(SoupTest): msg = str(w[0].message) self.assertTrue("parseOnlyThese" in msg) self.assertTrue("parse_only" in msg) - self.assertEquals(b"<b></b>", soup.encode()) + self.assertEqual(b"<b></b>", soup.encode()) def test_fromEncoding_renamed_to_from_encoding(self): with warnings.catch_warnings(record=True) as w: @@ -25,7 +28,7 @@ class TestDeprecatedConstructorArguments(SoupTest): msg = str(w[0].message) self.assertTrue("fromEncoding" in msg) self.assertTrue("from_encoding" in msg) - self.assertEquals("utf8", soup.original_encoding) + self.assertEqual("utf8", soup.original_encoding) def test_unrecognized_keyword_argument(self): self.assertRaises( @@ -206,7 +209,7 @@ class TestUnicodeDammit(unittest.TestCase): b"<html><meta charset=euc-jp /></html>", b"<html><meta charset=euc-jp/></html>"): dammit = UnicodeDammit(data, is_html=True) - self.assertEquals( + self.assertEqual( "euc-jp", dammit.original_encoding) def test_last_ditch_entity_replacement(self): @@ -233,3 +236,30 @@ class TestUnicodeDammit(unittest.TestCase): msg = w[0].message self.assertTrue(isinstance(msg, UnicodeWarning)) self.assertTrue("Some characters could not be decoded" in str(msg)) + + +class TestNamedspacedAttribute(SoupTest): + + def test_name_may_be_none(self): + a = NamespacedAttribute("xmlns", None) + self.assertEqual(a, "xmlns") + + def test_attribute_is_equivalent_to_colon_separated_string(self): + a = NamespacedAttribute("a", "b") + self.assertEqual("a:b", a) + + def test_attributes_are_equivalent_if_prefix_and_name_identical(self): + a = NamespacedAttribute("a", "b", "c") + b = NamespacedAttribute("a", "b", "c") + self.assertEqual(a, b) + + # The actual namespace is not considered. + c = NamespacedAttribute("a", "b", None) + self.assertEqual(a, c) + + # But name and prefix are important. + d = NamespacedAttribute("a", "z", "c") + self.assertNotEqual(a, d) + + e = NamespacedAttribute("z", "b", "c") + self.assertNotEqual(a, e) diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index 6aa02cb..c75b561 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -18,7 +18,13 @@ from bs4.builder import ( builder_registry, HTMLParserTreeBuilder, ) -from bs4.element import CData, NavigableString, SoupStrainer, Tag +from bs4.element import ( + CData, + Doctype, + NavigableString, + SoupStrainer, + Tag, +) from bs4.testing import ( SoupTest, skipIf, @@ -97,8 +103,8 @@ class TestFindAllBasicNamespaces(TreeTest): def test_find_by_namespaced_name(self): soup = self.soup('<mathml:msqrt>4</mathml:msqrt><a svg:fill="red">') - self.assertEquals("4", soup.find("mathml:msqrt").string) - self.assertEquals("a", soup.find(attrs= { "svg:fill" : "red" }).name) + self.assertEqual("4", soup.find("mathml:msqrt").string) + self.assertEqual("a", soup.find(attrs= { "svg:fill" : "red" }).name) class TestFindAllByName(TreeTest): @@ -1277,3 +1283,12 @@ class TestNavigableStringSubclasses(SoupTest): self.assertEqual(str(soup), "<![CDATA[foo]]>") self.assertEqual(soup.find(text="foo"), "foo") self.assertEqual(soup.contents[0], "foo") + + def test_doctype_ends_in_newline(self): + # Unlike other NavigableString subclasses, a DOCTYPE always ends + # in a newline. + doctype = Doctype("foo") + soup = self.soup("") + soup.insert(1, doctype) + self.assertEqual(soup.encode(), b"<!DOCTYPE foo>\n") + |