diff options
Diffstat (limited to 'bs4/tests')
| -rw-r--r-- | bs4/tests/test_htmlparser.py | 15 | ||||
| -rw-r--r-- | bs4/tests/test_tree.py | 36 |
2 files changed, 47 insertions, 4 deletions
diff --git a/bs4/tests/test_htmlparser.py b/bs4/tests/test_htmlparser.py index d5cf025..0381c7d 100644 --- a/bs4/tests/test_htmlparser.py +++ b/bs4/tests/test_htmlparser.py @@ -5,6 +5,7 @@ from pdb import set_trace import pickle from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest from bs4.builder import HTMLParserTreeBuilder +from bs4.builder._htmlparser import BeautifulSoupHTMLParser class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): @@ -32,3 +33,17 @@ class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): def test_redundant_empty_element_closing_tags(self): self.assertSoupEquals('<br></br><br></br><br></br>', "<br/><br/><br/>") self.assertSoupEquals('</br></br></br>', "") + + def test_empty_element(self): + # This verifies that any buffered data present when the parser + # finishes working is handled. + self.assertSoupEquals("foo &# bar", "foo &# bar") + + +class TestHTMLParserSubclass(SoupTest): + def test_error(self): + """Verify that our HTMLParser subclass implements error() in a way + that doesn't cause a crash. + """ + parser = BeautifulSoupHTMLParser() + parser.error("don't crash") diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index c0e7c40..e8903e3 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -605,7 +605,7 @@ class SiblingTest(TreeTest): </html>''' # All that whitespace looks good but makes the tests more # difficult. Get rid of it. - markup = re.compile("\n\s*").sub("", markup) + markup = re.compile(r"\n\s*").sub("", markup) self.tree = self.soup(markup) @@ -821,6 +821,26 @@ class TestTreeModification(SoupTest): soup = self.soup(text) self.assertRaises(ValueError, soup.a.insert, 0, soup.a) + def test_insert_beautifulsoup_object_inserts_children(self): + """Inserting one BeautifulSoup object into another actually inserts all + of its children -- you'll never combine BeautifulSoup objects. + """ + soup = self.soup("<p>And now, a word:</p><p>And we're back.</p>") + + text = "<p>p2</p><p>p3</p>" + to_insert = self.soup(text) + soup.insert(1, to_insert) + + for i in soup.descendants: + assert not isinstance(i, BeautifulSoup) + + p1, p2, p3, p4 = list(soup.children) + self.assertEquals("And now, a word:", p1.string) + self.assertEquals("p2", p2.string) + self.assertEquals("p3", p3.string) + self.assertEquals("And we're back.", p4.string) + + def test_replace_with_maintains_next_element_throughout(self): soup = self.soup('<p><a>one</a><b>three</b></p>') a = soup.a @@ -1419,13 +1439,21 @@ class TestSubstitutions(SoupTest): u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) def test_formatter_html(self): - markup = u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = u"<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter="html") self.assertEqual( decoded, - self.document_for("<b><<Sacré bleu!>></b>")) + self.document_for("<br/><b><<Sacré bleu!>></b>")) + def test_formatter_html5(self): + markup = u"<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + soup = self.soup(markup) + decoded = soup.decode(formatter="html5") + self.assertEqual( + decoded, + self.document_for("<br><b><<Sacré bleu!>></b>")) + def test_formatter_minimal(self): markup = u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) @@ -1498,7 +1526,7 @@ class TestSubstitutions(SoupTest): u'<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n</div>', soup.div.prettify()) - def test_prettify_accepts_formatter(self): + def test_prettify_accepts_formatter_function(self): soup = BeautifulSoup("<html><body>foo</body></html>", 'html.parser') pretty = soup.prettify(formatter = lambda x: x.upper()) self.assertTrue("FOO" in pretty) |