path: root/src/beautifulsoup/python3.diff

=== modified file 'src/beautifulsoup/builder.py'
--- src/beautifulsoup/builder.py	2009-04-10 15:22:53 +0000
+++ src/beautifulsoup/builder.py	2009-04-10 17:12:49 +0000
@@ -6,7 +6,7 @@
 from element import name2codepoint
 from element import (
     CData, Comment, Declaration, Entities, ProcessingInstruction)
-from HTMLParser import HTMLParser, HTMLParseError
+from html.parser import HTMLParser, HTMLParseError
 
 __all__ = ['TreeBuilder',
            'HTMLParserXMLTreeBuilder',

=== modified file 'src/beautifulsoup/element.py'
--- src/beautifulsoup/element.py	2009-04-10 15:22:53 +0000
+++ src/beautifulsoup/element.py	2009-04-10 17:12:49 +0000
@@ -1,7 +1,7 @@
 import re
 import types
 try:
-    from htmlentitydefs import name2codepoint
+    from html.entities import name2codepoint
 except ImportError:
     name2codepoint = {}
 
@@ -254,7 +254,7 @@
         g = generator()
         while True:
             try:
-                i = g.next()
+                i = g.__next__()
             except StopIteration:
                 break
             if i:

=== modified file 'src/beautifulsoup/tests/test_soup.py'
--- src/beautifulsoup/tests/test_soup.py	2009-04-10 15:45:04 +0000
+++ src/beautifulsoup/tests/test_soup.py	2009-04-10 17:15:31 +0000
@@ -635,9 +635,9 @@
         self.assertSoupEquals('<b>hello&nbsp;there</b>')
 
     def testEntitiesInAttributeValues(self):
-        self.assertSoupEquals('<x t="x&#241;">', '<x t="x\xc3\xb1"></x>',
+        self.assertSoupEquals('<x t="x&#241;">', b'<x t="x\xc3\xb1"></x>',
                               encoding='utf-8')
-        self.assertSoupEquals('<x t="x&#xf1;">', '<x t="x\xc3\xb1"></x>',
+        self.assertSoupEquals('<x t="x&#xf1;">', b'<x t="x\xc3\xb1"></x>',
                               encoding='utf-8')
 
         builder = HTMLParserTreeBuilder(convertEntities=Entities.HTML_ENTITIES)
@@ -681,11 +681,11 @@
     smart quote fixes."""
 
     def testUnicodeDammitStandalone(self):
-        markup = "<foo>\x92</foo>"
+        markup = b"<foo>\x92</foo>"
         dammit = UnicodeDammit(markup)
         self.assertEquals(dammit.unicode, "<foo>&#x2019;</foo>")
 
-        hebrew = "\xed\xe5\xec\xf9"
+        hebrew = b"\xed\xe5\xec\xf9"
         dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
         self.assertEquals(dammit.unicode, u'\u05dd\u05d5\u05dc\u05e9')
         self.assertEquals(dammit.originalEncoding, 'iso-8859-8')
@@ -697,7 +697,7 @@
 
         unicodeData = u"<foo>\u00FC</foo>"
         utf8 = unicodeData.encode("utf-8")
-        self.assertEquals(utf8, '<foo>\xc3\xbc</foo>')
+        self.assertEquals(utf8, b'<foo>\xc3\xbc</foo>')
 
         unicodeSoup = BeautifulStoneSoup(unicodeData)
         self.assertEquals(unicodeData, unicodeSoup.decode())
@@ -724,8 +724,8 @@
         self.assertEqual(soup.find(text=u'Räksmörgås'),u'Räksmörgås')
 
     def testRewrittenXMLHeader(self):
-        euc_jp = '<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n'
-        utf8 = "<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n"
+        euc_jp = b'<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n'
+        utf8 = b"<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n"
         soup = BeautifulStoneSoup(euc_jp)
         if soup.originalEncoding != "euc-jp":
             raise Exception("Test failed when parsing euc-jp document. "
@@ -736,12 +736,12 @@
         self.assertEquals(soup.originalEncoding, "euc-jp")
         self.assertEquals(soup.renderContents('utf-8'), utf8)
 
-        old_text = "<?xml encoding='windows-1252'><foo>\x92</foo>"
+        old_text = b"<?xml encoding='windows-1252'><foo>\x92</foo>"
         new_text = "<?xml version='1.0' encoding='utf-8'?><foo>&rsquo;</foo>"
         self.assertSoupEquals(old_text, new_text)
 
     def testRewrittenMetaTag(self):
-        no_shift_jis_html = '''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>'''
+        no_shift_jis_html = b'''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>'''
         soup = BeautifulSoup(no_shift_jis_html)
 
         # Beautiful Soup used to try to rewrite the meta tag even if the
@@ -751,16 +751,16 @@
         soup = BeautifulSoup(no_shift_jis_html, parseOnlyThese=strainer)
         self.assertEquals(soup.contents[0].name, 'pre')
 
-        meta_tag = ('<meta content="text/html; charset=x-sjis" '
-                    'http-equiv="Content-type" />')
+        meta_tag = (b'<meta content="text/html; charset=x-sjis" '
+                    b'http-equiv="Content-type" />')
         shift_jis_html = (
-            '<html><head>\n%s\n'
-            '<meta http-equiv="Content-language" content="ja" />'
-            '</head><body><pre>\n'
-            '\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
-            '\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
-            '\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n'
-            '</pre></body></html>') % meta_tag
+            b'<html><head>\n' + meta_tag + b'\n'
+            b'<meta http-equiv="Content-language" content="ja" />'
+            b'</head><body><pre>\n'
+            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
+            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
+            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n'
+            b'</pre></body></html>')
         soup = BeautifulSoup(shift_jis_html)
         if soup.originalEncoding != "shift-jis":
             raise Exception("Test failed when parsing shift-jis document "
@@ -773,60 +773,60 @@
         content_type_tag = soup.meta['content']
         self.assertEquals(content_type_tag[content_type_tag.find('charset='):],
                           'charset=%SOUP-ENCODING%')
-        content_type = str(soup.meta)
+        content_type = soup.meta.decode()
         index = content_type.find('charset=')
         self.assertEqual(content_type[index:index+len('charset=utf8')+1],
                          'charset=utf-8')
         content_type = soup.meta.encode('shift-jis')
-        index = content_type.find('charset=')
+        index = content_type.find(b'charset=')
         self.assertEqual(content_type[index:index+len('charset=shift-jis')],
                          'charset=shift-jis'.encode())
 
         self.assertEquals(soup.encode('utf-8'), (
-                '<html><head>\n'
-                '<meta content="text/html; charset=utf-8" '
-                'http-equiv="Content-type" />\n'
-                '<meta http-equiv="Content-language" content="ja" />'
-                '</head><body><pre>\n'
-                '\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3'
-                '\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3'
-                '\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6'
-                '\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3'
-                '\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n'
-                '</pre></body></html>'))
+                b'<html><head>\n'
+                b'<meta content="text/html; charset=utf-8" '
+                b'http-equiv="Content-type" />\n'
+                b'<meta http-equiv="Content-language" content="ja" />'
+                b'</head><body><pre>\n'
+                b'\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3'
+                b'\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3'
+                b'\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6'
+                b'\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3'
+                b'\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n'
+                b'</pre></body></html>'))
         self.assertEquals(soup.encode("shift-jis"),
                           shift_jis_html.replace('x-sjis'.encode(),
                                                  'shift-jis'.encode()))
 
-        isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
+        isolatin = b"""<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
         soup = BeautifulSoup(isolatin)
 
         utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode())
-        utf8 = utf8.replace("\xe9", "\xc3\xa9")
+        utf8 = utf8.replace(b"\xe9", b"\xc3\xa9")
         self.assertSoupEquals(soup.encode("utf-8"), utf8, encoding='utf-8')
 
     def testHebrew(self):
-        iso_8859_8= '<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n'
-        utf8 = '<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n'
+        iso_8859_8= b'<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n'
+        utf8 = b'<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n'
         soup = BeautifulStoneSoup(iso_8859_8, fromEncoding="iso-8859-8")
         self.assertEquals(soup.encode('utf-8'), utf8)
 
     def testSmartQuotesNotSoSmartAnymore(self):
-        self.assertSoupEquals("\x91Foo\x92 <!--blah-->",
+        self.assertSoupEquals(b"\x91Foo\x92 <!--blah-->",
                               '&lsquo;Foo&rsquo; <!--blah-->')
 
     def testDontConvertSmartQuotesWhenAlsoConvertingEntities(self):
-        smartQuotes = "Il a dit, \x8BSacr&eacute; bl&#101;u!\x9b"
+        smartQuotes = b"Il a dit, \x8BSacr&eacute; bl&#101;u!\x9b"
         soup = BeautifulSoup(smartQuotes)
         self.assertEquals(soup.decode(),
                           'Il a dit, &lsaquo;Sacr&eacute; bl&#101;u!&rsaquo;')
         builder = HTMLParserTreeBuilder(convertEntities="html")
         soup = BeautifulSoup(smartQuotes, builder)
         self.assertEquals(soup.encode('utf-8'),
-                          'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba')
+                          b'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba')
 
     def testDontSeeSmartQuotesWhereThereAreNone(self):
-        utf_8 = "\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
+        utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
         self.assertSoupEquals(utf_8, encoding='utf-8')