From 7bbefa1fcc9a6006953eb0a79049ece9f05985de Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Fri, 28 Jan 2011 11:39:36 -0500 Subject: Moved everything into the top-level directory and got rid of buildout. --- src/beautifulsoup/AUTHORS | 34 -- src/beautifulsoup/CHANGELOG | 122 ------ src/beautifulsoup/README.txt | 26 -- src/beautifulsoup/TODO | 42 -- src/beautifulsoup/__init__.py | 375 ------------------ src/beautifulsoup/dammit.py | 292 -------------- src/beautifulsoup/element.py | 851 ----------------------------------------- src/beautifulsoup/python3.diff | 208 ---------- src/beautifulsoup/testing.py | 154 -------- src/beautifulsoup/util.py | 29 -- 10 files changed, 2133 deletions(-) delete mode 100644 src/beautifulsoup/AUTHORS delete mode 100644 src/beautifulsoup/CHANGELOG delete mode 100644 src/beautifulsoup/README.txt delete mode 100644 src/beautifulsoup/TODO delete mode 100644 src/beautifulsoup/__init__.py delete mode 100644 src/beautifulsoup/dammit.py delete mode 100644 src/beautifulsoup/element.py delete mode 100644 src/beautifulsoup/python3.diff delete mode 100644 src/beautifulsoup/testing.py delete mode 100644 src/beautifulsoup/util.py (limited to 'src') diff --git a/src/beautifulsoup/AUTHORS b/src/beautifulsoup/AUTHORS deleted file mode 100644 index d353253..0000000 --- a/src/beautifulsoup/AUTHORS +++ /dev/null @@ -1,34 +0,0 @@ -Behold, mortal, the origins of Beautiful Soup... -================================================ - -Leonard Richardson is the primary programmer. - -Sam Ruby helps with a lot of edge cases. - -Mark Pilgrim provided the encoding detection code that forms the base -of UnicodeDammit. - -Jonathan Ellis was awarded the prestigous Beau Potage D'Or for his -work in solving the nestable tags conundrum. - -The following people have contributed patches to Beautiful Soup: - - Istvan Albert, Andrew Lin, Anthony Baxter, Andrew Boyko, Tony Chang, - Zephyr Fang, Fuzzy, Roman Gaufman, Yoni Gilad, Richie Hindle, Peteris - Krumins, Kent Johnson, Ben Last, Robert Leftwich, Staffan Malmgren, - Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon", Ed - Oskiewicz, Greg Phillips, Giles Radford, Arthur Rudolph, Marko - Samastur, Jouni Seppänen, Alexander Schmolck, Andy Theyers, Glyn - Webster, Paul Wright, Danny Yoo - -The following people made suggestions or found bugs or found ways to -break Beautiful Soup: - - Hanno Böck, Matteo Bertini, Chris Curvey, Simon Cusack, Matt Ernst, - Michael Foord, Tom Harris, Bill de hOra, Donald Howes, Matt - Patterson, Scott Roberts, Steve Strassmann, Mike Williams, warchild - at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison, Joren Mc, - Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed Summers, - Dennis Sutch, Chris Smith, Aaron Sweep^W Swartz, Stuart Turner, Greg - Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de Sousa Rocha, - Yichun Wei, Per Vognsen diff --git a/src/beautifulsoup/CHANGELOG b/src/beautifulsoup/CHANGELOG deleted file mode 100644 index 4e97e1b..0000000 --- a/src/beautifulsoup/CHANGELOG +++ /dev/null @@ -1,122 +0,0 @@ -= 3.1.0 = - -A hybrid version that supports 2.4 and can be automatically converted -to run under Python 3.0. There are three backwards-incompatible -changes you should be aware of, but no new features or deliberate -behavior changes. - -1. str() may no longer do what you want. This is because the meaning -of str() inverts between Python 2 and 3; in Python 2 it gives you a -byte string, in Python 3 it gives you a Unicode string. - -The effect of this is that you can't pass an encoding to .__str__ -anymore. Use encode() to get a string and decode() to get Unicode, and -you'll be ready (well, readier) for Python 3. - -2. Beautiful Soup is now based on HTMLParser rather than SGMLParser, -which is gone in Python 3. There's some bad HTML that SGMLParser -handled but HTMLParser doesn't, usually to do with attribute values -that aren't closed or have brackets inside them: - - baz - ', '"> - -A later version of Beautiful Soup will allow you to plug in different -parsers to make tradeoffs between speed and the ability to handle bad -HTML. - -3. In Python 3 (but not Python 2),HTMLParser converts entities within -attributes to the corresponding Unicode characters. In Python 2 it's -possible to parse this string and leave the é intact. - - - -In Python 3, the é is always converted to \xe9 during -parsing. - - -= 3.0.7a = - -Added an import that makes BS work in Python 2.3. - - -= 3.0.7 = - -Fixed a UnicodeDecodeError when unpickling documents that contain -non-ASCII characters. - -Fixed a TypeError that occured in some circumstances when a tag -contained no text. - -Jump through hoops to avoid the use of chardet, which can be extremely -slow in some circumstances. UTF-8 documents should never trigger the -use of chardet. - -Whitespace is preserved inside 
 and ")
-
-    def test_single_quote_attribute_values_become_double_quotes(self):
-        self.assertSoupEquals("",
-                              '')
-
-    def test_attribute_values_with_nested_quotes_are_left_alone(self):
-        text = """a"""
-        self.assertSoupEquals(text)
-
-    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
-        text = """a"""
-        soup = self.soup(text)
-        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
-        self.assertSoupEquals(
-            soup.foo.decode(),
-            """a""")
-
-    def test_ampersand_in_attribute_value_gets_quoted(self):
-        self.assertSoupEquals('',
-                              '')
-
-
-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(
-            '
Foo
Bar',
-            '
Foo
Bar
')
-
-    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(
-            "http://foo.com/",
-            "http://foo.com/")
-
-    def test_boolean_attribute_with_no_value_gets_empty_value(self):
-        soup = self.soup("
foo
")
-        self.assertEquals(soup.table.td['nowrap'], '')
-
-    def test_incorrectly_nested_tables(self):
-        self.assertSoupEquals(
-            '
',
-            '
')
-
-
-
diff --git a/src/beautifulsoup/util.py b/src/beautifulsoup/util.py
deleted file mode 100644
index 693a7e2..0000000
--- a/src/beautifulsoup/util.py
+++ /dev/null
@@ -1,29 +0,0 @@
-# Helper functions and mixin classes for Beautiful Soup
-
-import types
-try:
-    set
-except NameError:
-    from sets import Set as set
-
-def isList(l):
-    """Convenience method that works with all 2.x versions of Python
-    to determine whether or not something is listlike."""
-    return ((hasattr(l, '__iter__') and not isString(l))
-            or (type(l) in (types.ListType, types.TupleType)))
-
-def isString(s):
-    """Convenience method that works with all 2.x versions of Python
-    to determine whether or not something is stringlike."""
-    try:
-        return isinstance(s, unicode) or isinstance(s, basestring)
-    except NameError:
-        return isinstance(s, str)
-
-def buildSet(args=None):
-    """Turns a list or a string into a set."""
-    if isinstance(args, str):
-        return set([args])
-    if args is None:
-        return set()
-    return set(args)
-- 
cgit v1.2.3