summaryrefslogtreecommitdiff
path: root/src/beautifulsoup/tests
diff options
context:
space:
mode:
Diffstat (limited to 'src/beautifulsoup/tests')
-rw-r--r--src/beautifulsoup/tests/helpers.py154
-rw-r--r--src/beautifulsoup/tests/test_html5lib.py12
-rw-r--r--src/beautifulsoup/tests/test_lxml.py14
-rw-r--r--src/beautifulsoup/tests/test_soup.py27
-rw-r--r--src/beautifulsoup/tests/test_strainer.py2
-rw-r--r--src/beautifulsoup/tests/test_tree.py2
6 files changed, 47 insertions, 164 deletions
diff --git a/src/beautifulsoup/tests/helpers.py b/src/beautifulsoup/tests/helpers.py
deleted file mode 100644
index 20d087e..0000000
--- a/src/beautifulsoup/tests/helpers.py
+++ /dev/null
@@ -1,154 +0,0 @@
-"""Helper classes for tests."""
-
-import unittest
-from beautifulsoup import BeautifulSoup
-from beautifulsoup.element import Comment, SoupStrainer
-from beautifulsoup.builder.lxml_builder import LXMLTreeBuilder
-
-class SoupTest(unittest.TestCase):
-
- def setUp(self):
- # LXMLTreeBuilder won't handle bad markup, but that's fine,
- # since all the parsing tests take place in parser-specific
- # test suites that override default_builder.
- self.default_builder = LXMLTreeBuilder()
-
- def soup(self, markup, **kwargs):
- """Build a Beautiful Soup object from markup."""
- return BeautifulSoup(markup, builder=self.default_builder, **kwargs)
-
- def document_for(self, markup):
- """Turn an HTML fragment into a document.
-
- The details depend on the builder.
- """
- return self.default_builder.test_fragment_to_document(markup)
-
- def assertSoupEquals(self, to_parse, compare_parsed_to=None):
- builder = self.default_builder
- obj = BeautifulSoup(to_parse, builder=builder)
- if compare_parsed_to is None:
- compare_parsed_to = to_parse
-
- self.assertEquals(obj.decode(), self.document_for(compare_parsed_to))
-
-
-
-class BuilderSmokeTest(SoupTest):
- """A generic smoke test for tree builders.
-
- Subclasses of this test ensure that all of Beautiful Soup's tree
- builders generate more or less the same trees. It's okay for trees
- to differ, especially when given invalid markup--just override the
- appropriate test method to demonstrate how one tree builder
- differs from others.
- """
-
- def test_bare_string(self):
- # A bare string is turned into some kind of HTML document or
- # fragment recognizable as the original string.
- self.assertSoupEquals("A bare string")
-
- def test_mixed_case_tags(self):
- # Mixed-case tags are folded to lowercase.
- self.assertSoupEquals(
- "<a><B><Cd><EFG></efg></CD></b></A>",
- "<a><b><cd><efg></efg></cd></b></a>")
-
- def test_self_closing(self):
- # HTML's self-closing tags are recognized as such.
- self.assertSoupEquals(
- "<p>A <meta> tag</p>", "<p>A <meta /> tag</p>")
-
- self.assertSoupEquals(
- "<p>Foo<br/>bar</p>", "<p>Foo<br />bar</p>")
-
- def test_comment(self):
- # Comments are represented as Comment objects.
- markup = "<p>foo<!--foobar-->baz</p>"
- self.assertSoupEquals(markup)
-
- soup = self.soup(markup)
- comment = soup.find(text="foobar")
- self.assertEquals(comment.__class__, Comment)
-
- def test_nested_inline_elements(self):
- # Inline tags can be nested indefinitely.
- b_tag = "<b>Inside a B tag</b>"
- self.assertSoupEquals(b_tag)
-
- nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
- self.assertSoupEquals(nested_b_tag)
-
- double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
- self.assertSoupEquals(nested_b_tag)
-
- def test_nested_block_level_elements(self):
- soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
- blockquote = soup.blockquote
- self.assertEqual(blockquote.p.b.string, 'Foo')
- self.assertEqual(blockquote.b.string, 'Foo')
-
- def test_collapsed_whitespace(self):
- """In most tags, whitespace is collapsed."""
- self.assertSoupEquals("<p> </p>", "<p> </p>")
-
- def test_preserved_whitespace_in_pre_and_textarea(self):
- """In <pre> and <textarea> tags, whitespace is preserved."""
- self.assertSoupEquals("<pre> </pre>")
- self.assertSoupEquals("<textarea> woo </textarea>")
-
- def test_single_quote_attribute_values_become_double_quotes(self):
- self.assertSoupEquals("<foo attr='bar'></foo>",
- '<foo attr="bar"></foo>')
-
- def test_attribute_values_with_nested_quotes_are_left_alone(self):
- text = """<foo attr='bar "brawls" happen'>a</foo>"""
- self.assertSoupEquals(text)
-
- def test_attribute_values_with_double_nested_quotes_get_quoted(self):
- text = """<foo attr='bar "brawls" happen'>a</foo>"""
- soup = self.soup(text)
- soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
- self.assertSoupEquals(
- soup.foo.decode(),
- """<foo attr='Brawls happen at "Bob&squot;s Bar"'>a</foo>""")
-
- def test_ampersand_in_attribute_value_gets_quoted(self):
- self.assertSoupEquals('<this is="really messed up & stuff"></this>',
- '<this is="really messed up &amp; stuff"></this>')
-
-
-class BuilderInvalidMarkupSmokeTest(SoupTest):
- """Tests of invalid markup.
-
- These are very likely to give different results for different tree
- builders. It's not required that a tree builder handle invalid
- markup at all.
- """
-
- def test_unclosed_block_level_elements(self):
- # Unclosed block-level elements should be closed.
- self.assertSoupEquals(
- '<blockquote><p><b>Foo</blockquote><p>Bar',
- '<blockquote><p><b>Foo</b></p></blockquote><p>Bar</p>')
-
- def test_fake_self_closing_tag(self):
- # If a self-closing tag presents as a normal tag, the 'open'
- # tag is treated as an instance of the self-closing tag and
- # the 'close' tag is ignored.
- self.assertSoupEquals(
- "<item><link>http://foo.com/</link></item>",
- "<item><link />http://foo.com/</item>")
-
- def test_boolean_attribute_with_no_value_gets_empty_value(self):
- soup = self.soup("<table><td nowrap>foo</td></table>")
- self.assertEquals(soup.table.td['nowrap'], '')
-
- def test_incorrectly_nested_tables(self):
- self.assertSoupEquals(
- '<table><tr><table><tr id="nested">',
- '<table><tr><table><tr id="nested"></tr></table></tr></table>')
-
-
-
diff --git a/src/beautifulsoup/tests/test_html5lib.py b/src/beautifulsoup/tests/test_html5lib.py
index 4ffd968..7164dac 100644
--- a/src/beautifulsoup/tests/test_html5lib.py
+++ b/src/beautifulsoup/tests/test_html5lib.py
@@ -1,5 +1,8 @@
-from helpers import BuilderInvalidMarkupSmokeTest, BuilderSmokeTest
from beautifulsoup.builder.html5lib_builder import HTML5TreeBuilder
+from beautifulsoup.testing import (
+ BuilderInvalidMarkupSmokeTest,
+ BuilderSmokeTest,
+)
class TestHTML5Builder(BuilderSmokeTest):
@@ -30,4 +33,11 @@ class TestHTML5BuilderInvalidMarkup(BuilderInvalidMarkupSmokeTest):
'<table><tbody><tr id="nested"></tr></tbody></table>'))
+ def test_foo(self):
+ isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
+ soup = self.soup(isolatin)
+ utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode())
+ utf8 = utf8.replace("\xe9", "\xc3\xa9")
+
+ print soup
diff --git a/src/beautifulsoup/tests/test_lxml.py b/src/beautifulsoup/tests/test_lxml.py
index cd22b6f..b53ee42 100644
--- a/src/beautifulsoup/tests/test_lxml.py
+++ b/src/beautifulsoup/tests/test_lxml.py
@@ -1,6 +1,9 @@
"""Tests to ensure that the lxml tree builder generates good trees."""
-from helpers import BuilderInvalidMarkupSmokeTest, BuilderSmokeTest
+from beautifulsoup.testing import (
+ BuilderInvalidMarkupSmokeTest,
+ BuilderSmokeTest,
+)
class TestLXMLBuilder(BuilderSmokeTest):
"""See `BuilderSmokeTest`."""
@@ -10,6 +13,15 @@ class TestLXMLBuilder(BuilderSmokeTest):
self.assertSoupEquals(
"A bare string", "<p>A bare string</p>")
+ def test_foo(self):
+ isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
+ soup = self.soup(isolatin)
+
+ utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode())
+ utf8 = utf8.replace("\xe9", "\xc3\xa9")
+
+ print soup
+
class TestLXMLBuilderInvalidMarkup(BuilderInvalidMarkupSmokeTest):
"""See `BuilderInvalidMarkupSmokeTest`."""
diff --git a/src/beautifulsoup/tests/test_soup.py b/src/beautifulsoup/tests/test_soup.py
index d95cba6..ec0394d 100644
--- a/src/beautifulsoup/tests/test_soup.py
+++ b/src/beautifulsoup/tests/test_soup.py
@@ -2,9 +2,9 @@
"""Tests of Beautiful Soup as a whole."""
import unittest
-from helpers import SoupTest
from beautifulsoup.element import SoupStrainer
from beautifulsoup.dammit import UnicodeDammit
+from beautifulsoup.testing import SoupTest
class TestEncodingConversion(SoupTest):
@@ -48,6 +48,15 @@ class TestEncodingConversion(SoupTest):
soup_from_unicode = self.soup(self.unicode_data)
self.assertEquals(soup_from_unicode.encode('utf-8'), self.utf8_data)
+ def test_hebrew(self):
+ # A real-world test to make sure we can convert ISO-8859-9 (a
+ # Hebrew encoding) to UTF-8.
+ iso_8859_8= '<HTML><HEAD><TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE></HEAD><BODY><H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\xed\xe5\xec\xf9</BODY></HTML>'
+ utf8 = '<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9</body></html>'
+ soup = self.soup(iso_8859_8, fromEncoding="iso-8859-8")
+ self.assertEquals(soup.originalEncoding, 'iso-8859-8')
+ self.assertEquals(soup.encode('utf-8'), utf8)
+
class TestSelectiveParsing(SoupTest):
@@ -58,14 +67,20 @@ class TestSelectiveParsing(SoupTest):
self.assertEquals(soup.encode(), "<b>Yes</b><b>Yes <c>Yes</c></b>")
-
class TestUnicodeDammit(unittest.TestCase):
"""Standalone tests of Unicode, Dammit."""
- def test_smart_quote_replacement(self):
- markup = "<foo>\x92</foo>"
+ def test_smart_quotes_to_xml_entities(self):
+ markup = "<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
- self.assertEquals(dammit.unicode, "<foo>&#x2019;</foo>")
+ self.assertEquals(
+ dammit.unicode, "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>")
+
+ def test_smart_quotes_to_html_entities(self):
+ markup = "<foo>\x91\x92\x93\x94</foo>"
+ dammit = UnicodeDammit(markup, smartQuotesTo="html")
+ self.assertEquals(
+ dammit.unicode, "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>")
def test_detect_utf8(self):
utf8 = "\xc3\xa9"
@@ -87,7 +102,7 @@ class TestUnicodeDammit(unittest.TestCase):
def test_ignore_inappropriate_codecs(self):
utf8_data = u"Räksmörgås".encode("utf-8")
- dammit = UnicodeDammit(utf8_data, ["iso-8859-1"])
+ dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
self.assertEquals(dammit.originalEncoding, 'utf-8')
def test_ignore_invalid_codecs(self):
diff --git a/src/beautifulsoup/tests/test_strainer.py b/src/beautifulsoup/tests/test_strainer.py
index 9a91463..f078935 100644
--- a/src/beautifulsoup/tests/test_strainer.py
+++ b/src/beautifulsoup/tests/test_strainer.py
@@ -1,7 +1,7 @@
import unittest
-from helpers import SoupTest
from beautifulsoup import BeautifulSoup
from beautifulsoup.element import SoupStrainer
+from beautifulsoup.testing import SoupTest
class TestSoupStrainer(unittest.TestCase):
diff --git a/src/beautifulsoup/tests/test_tree.py b/src/beautifulsoup/tests/test_tree.py
index 42430d3..344a462 100644
--- a/src/beautifulsoup/tests/test_tree.py
+++ b/src/beautifulsoup/tests/test_tree.py
@@ -12,7 +12,7 @@ methods tested here.
import re
from beautifulsoup import BeautifulSoup
from beautifulsoup.element import SoupStrainer, Tag
-from helpers import SoupTest
+from beautifulsoup.testing import SoupTest
class TreeTest(SoupTest):
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-02 21:33:52 +0000