Remove a lot of old 2.3/2.4 support code

Author: gsnedders

html5lib/constants.py

@@ -2,13 +2,6 @@
 import string, gettext
 _ = gettext.gettext
 
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import Set as set
-    from sets import ImmutableSet as frozenset
-
 EOF = None
 
 E = {

html5lib/filters/whitespace.py

@@ -1,10 +1,4 @@
 from __future__ import absolute_import
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import ImmutableSet as frozenset
-
 import re
 
 from . import _base

html5lib/html5parser.py

@@ -1,37 +1,4 @@
 from __future__ import absolute_import
-from itertools import izip
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import Set as set
-    from sets import ImmutableSet as frozenset
-
-try:
-    any
-except:
-    # Implement 'any' for python 2.4 and previous
-    def any(iterable):
-        for element in iterable:
-            if element:
-                return True
-        return False
-    any.func_annotations = {}
-        
-try:
-    u"abc".startswith((u"a", u"b"))
-    def startswithany(unicode, prefixes):
-        return unicode.startswith(prefixes)
-    startswithany.func_annotations = {}
-except:
-    # Python 2.4 doesn't accept a tuple as argument to string startswith
-    def startswithany(unicode, prefixes):
-        for prefix in prefixes:
-            if unicode.startswith(prefix):
-                return True
-        return False
-    startswithany.func_annotations = {}
-
 import sys
 import types
 
@@ -50,6 +17,7 @@ def startswithany(unicode, prefixes):
 from .constants import cdataElements, rcdataElements, voidElements
 from .constants import tokenTypes, ReparseException, namespaces, spaceCharacters
 from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements
+from itertools import izip
 
 def parse(doc, treebuilder=u"simpletree", encoding=None,
           namespaceHTMLElements=True):
@@ -581,7 +549,7 @@ def processDoctype(self, token):
                 publicId = publicId.translate(asciiUpper2Lower)
 
             if (not correct or token[u"name"] != u"html"
-                or startswithany(publicId,
+                or publicId.startswith(
                 (u"+//silmaril//dtd html pro v0r11 19970101//",
                  u"-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
                  u"-//as//dtd html 3.0 aswedit + extensions//",
@@ -641,16 +609,16 @@ def processDoctype(self, token):
                     (u"-//w3o//dtd w3 html strict 3.0//en//",
                      u"-/w3c/dtd html 4.0 transitional/en",
                      u"html")
-                or startswithany(publicId,
+                or publicId.startswith(
                     (u"-//w3c//dtd html 4.01 frameset//",
                      u"-//w3c//dtd html 4.01 transitional//")) and 
                     systemId == None
                 or systemId and systemId.lower() == u"http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
                 self.parser.compatMode = u"quirks"
-            elif (startswithany(publicId,
+            elif (publicId.startswith(
                     (u"-//w3c//dtd xhtml 1.0 frameset//",
                      u"-//w3c//dtd xhtml 1.0 transitional//"))
-                  or startswithany(publicId,
+                  or publicId.startswith(
                       (u"-//w3c//dtd html 4.01 frameset//",
                        u"-//w3c//dtd html 4.01 transitional//")) and 
                       systemId != None):

html5lib/inputstream.py

@@ -133,6 +133,7 @@ def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True):
     if isUnicode:
         if encoding is not None:
             raise TypeError(u"Cannot explicitly set an encoding with a unicode string")
+
         return HTMLUnicodeInputStream(source)
     else:
         return HTMLBinaryInputStream(source, encoding, parseMeta, chardet)

html5lib/serializer/htmlserializer.py

@@ -1,18 +1,12 @@
 from __future__ import absolute_import
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import ImmutableSet as frozenset
+import gettext
+_ = gettext.gettext
 
 try:
     pass # no-op statement to avoid 3to2 introducing parse error
 except ImportError:
     pass
 
-import gettext
-_ = gettext.gettext
-
 from html5lib.constants import voidElements, booleanAttributes, spaceCharacters
 from html5lib.constants import rcdataElements, entities, xmlEntities
 from html5lib import utils

html5lib/tokenizer.py

@@ -1,14 +1,5 @@
 from __future__ import absolute_import
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import Set as set
-    from sets import ImmutableSet as frozenset
-try:
-    from collections import deque
-except ImportError:
-    from .utils import deque
+from collections import deque
 
 from .constants import spaceCharacters
 from .constants import entitiesWindows1252, entities

html5lib/treebuilders/_base.py

@@ -1,11 +1,5 @@
 from __future__ import absolute_import
 from html5lib.constants import scopingElements, tableInsertModeElements, namespaces
-try:
-    frozenset
-except NameError:
-    # Import from the sets module for python 2.3
-    from sets import Set as set
-    from sets import ImmutableSet as frozenset
 
 # The scope markers are inserted when entering object elements,
 # marquees, table cells, and table captions, and are used to prevent formatting

html5lib/utils.py

@@ -1,11 +1,4 @@
 from __future__ import absolute_import
-try:
-    frozenset
-except NameError:
-    #Import from the sets module for python 2.3
-    from sets import Set as set
-    from sets import ImmutableSet as frozenset
-
 from types import ModuleType
 
 
@@ -41,145 +34,6 @@ def __getitem__(self, key):
         return dict.get(self, key, self.default)
     __getitem__.func_annotations = {}
 
-#Pure python implementation of deque taken from the ASPN Python Cookbook
-#Original code by Raymond Hettinger
-
-class deque(object):
-
-    def __init__(self, iterable=(), maxsize=-1):
-        if not hasattr(self, u'data'):
-            self.left = self.right = 0
-            self.data = {}
-        self.maxsize = maxsize
-        self.extend(iterable)
-    __init__.func_annotations = {}
-
-    def append(self, x):
-        self.data[self.right] = x
-        self.right += 1
-        if self.maxsize != -1 and len(self) > self.maxsize:
-            self.popleft()
-    append.func_annotations = {}
-        
-    def appendleft(self, x):
-        self.left -= 1        
-        self.data[self.left] = x
-        if self.maxsize != -1 and len(self) > self.maxsize:
-            self.pop()      
-    appendleft.func_annotations = {}
-        
-    def pop(self):
-        if self.left == self.right:
-            raise IndexError(u'cannot pop from empty deque')
-        self.right -= 1
-        elem = self.data[self.right]
-        del self.data[self.right]         
-        return elem
-    pop.func_annotations = {}
-    
-    def popleft(self):
-        if self.left == self.right:
-            raise IndexError(u'cannot pop from empty deque')
-        elem = self.data[self.left]
-        del self.data[self.left]
-        self.left += 1
-        return elem
-    popleft.func_annotations = {}
-
-    def clear(self):
-        self.data.clear()
-        self.left = self.right = 0
-    clear.func_annotations = {}
-
-    def extend(self, iterable):
-        for elem in iterable:
-            self.append(elem)
-    extend.func_annotations = {}
-
-    def extendleft(self, iterable):
-        for elem in iterable:
-            self.appendleft(elem)
-    extendleft.func_annotations = {}
-
-    def rotate(self, n=1):
-        if self:
-            n %= len(self)
-            for i in xrange(n):
-                self.appendleft(self.pop())
-    rotate.func_annotations = {}
-
-    def __getitem__(self, i):
-        if i < 0:
-            i += len(self)
-        try:
-            return self.data[i + self.left]
-        except KeyError:
-            raise IndexError
-    __getitem__.func_annotations = {}
-
-    def __setitem__(self, i, value):
-        if i < 0:
-            i += len(self)        
-        try:
-            self.data[i + self.left] = value
-        except KeyError:
-            raise IndexError
-    __setitem__.func_annotations = {}
-
-    def __delitem__(self, i):
-        size = len(self)
-        if not (-size <= i < size):
-            raise IndexError
-        data = self.data
-        if i < 0:
-            i += size
-        for j in xrange(self.left+i, self.right-1):
-            data[j] = data[j+1]
-        self.pop()
-    __delitem__.func_annotations = {}
-    
-    def __len__(self):
-        return self.right - self.left
-    __len__.func_annotations = {}
-
-    def __cmp__(self, other):
-        if type(self) != type(other):
-            return cmp(type(self), type(other))
-        return cmp(list(self), list(other))
-    __cmp__.func_annotations = {}
-            
-    def __repr__(self, _track=[]):
-        if id(self) in _track:
-            return u'...'
-        _track.append(id(self))
-        r = u'deque(%r)' % (list(self),)
-        _track.remove(id(self))
-        return r
-    __repr__.func_annotations = {}
-    
-    def __getstate__(self):
-        return (tuple(self),)
-    __getstate__.func_annotations = {}
-    
-    def __setstate__(self, s):
-        self.__init__(s[0])
-    __setstate__.func_annotations = {}
-        
-    def __hash__(self):
-        raise TypeError
-    __hash__.func_annotations = {}
-    
-    def __copy__(self):
-        return self.__class__(self)
-    __copy__.func_annotations = {}
-    
-    def __deepcopy__(self, memo={}):
-        from copy import deepcopy
-        result = self.__class__()
-        memo[id(self)] = result
-        result.__init__(deepcopy(tuple(self), memo))
-        return result
-    __deepcopy__.func_annotations = {}
 
 #Some utility functions to dal with weirdness around UCS2 vs UCS4
 #python builds