Remove py3k deprecation warnings from these Unicode tools.

Tools/unicode/gencodec.py

@@ -40,8 +40,7 @@ mapRE = re.compile('((?:0x[0-9a-fA-F]+\+?)+)'
                    '\s*'
                    '(#.+)?')
 
-def parsecodes(codes,
-               len=len, filter=filter,range=range):
+def parsecodes(codes, len=len, range=range):
 
     """ Converts code combinations to either a single code integer
         or a tuple of integers.
@@ -62,7 +61,7 @@ def parsecodes(codes,
             l[i] = int(l[i],16)
         except ValueError:
             l[i] = None
-    l = filter(lambda x: x is not None, l)
+    l = [x for x in l if x is not None]
     if len(l) == 1:
         return l[0]
     else:
@@ -138,7 +137,7 @@ def python_mapdef_code(varname, map, comments=1, precisions=(2, 4)):
 
     l = []
     append = l.append
-    if map.has_key("IDENTITY"):
+    if "IDENTITY" in map:
         append("%s = codecs.make_identity_dict(range(%d))" %
                (varname, map["IDENTITY"]))
         append("%s.update({" % varname)
@@ -150,8 +149,7 @@ def python_mapdef_code(varname, map, comments=1, precisions=(2, 4)):
         splits = 0
         identity = 0
 
-    mappings = map.items()
-    mappings.sort()
+    mappings = sorted(map.items())
     i = 0
     key_precision, value_precision = precisions
     for mapkey, mapvalue in mappings:
@@ -199,11 +197,10 @@ def python_tabledef_code(varname, map, comments=1, key_precision=2):
     append('%s = (' % varname)
 
     # Analyze map and create table dict
-    mappings = map.items()
-    mappings.sort()
+    mappings = sorted(map.items())
     table = {}
     maxkey = 0
-    if map.has_key('IDENTITY'):
+    if 'IDENTITY' in map:
         for key in range(256):
             table[key] = (key, '')
         maxkey = 255
@@ -421,6 +418,6 @@ if __name__ == '__main__':
 
     import sys
     if 1:
-        apply(convertdir,tuple(sys.argv[1:]))
+        convertdir(*sys.argv[1:])
     else:
-        apply(rewritepythondir,tuple(sys.argv[1:]))
+        rewritepythondir(*sys.argv[1:])

Tools/unicode/makeunicodedata.py

@@ -156,8 +156,7 @@ def makeunicodedata(unicode, trace):
                 prefix = i
                 assert prefix < 256
                 # content
-                decomp = [prefix + (len(decomp)<<8)] +\
-                         map(lambda s: int(s, 16), decomp)
+                decomp = [prefix + (len(decomp)<<8)] + [int(s, 16) for s in decomp]
                 # Collect NFC pairs
                 if not prefix and len(decomp) == 3 and \
                    char not in unicode.exclusions and \
@@ -459,8 +458,7 @@ def makeunicodetype(unicode, trace):
     Array("index2", index2).dump(fp, trace)
 
     # Generate code for _PyUnicode_ToNumeric()
-    numeric_items = numeric.items()
-    numeric_items.sort()
+    numeric_items = sorted(numeric.items())
     print >>fp, '/* Returns the numeric value as double for Unicode characters'
     print >>fp, ' * having this property, -1.0 otherwise.'
     print >>fp, ' */'
@@ -506,8 +504,7 @@ def makeunicodetype(unicode, trace):
 
     haswide = False
     hasnonewide = False
-    spaces.sort()
-    for codepoint in spaces:
+    for codepoint in sorted(spaces):
         if codepoint < 0x10000:
             hasnonewide = True
         if codepoint >= 0x10000 and not haswide:
@@ -535,8 +532,7 @@ def makeunicodetype(unicode, trace):
     print >>fp, '    switch (ch) {'
     haswide = False
     hasnonewide = False
-    linebreaks.sort()
-    for codepoint in linebreaks:
+    for codepoint in sorted(linebreaks):
         if codepoint < 0x10000:
             hasnonewide = True
         if codepoint >= 0x10000 and not haswide:
@@ -601,12 +597,10 @@ def makeunicodename(unicode, trace):
     wordlist = words.items()
 
     # sort on falling frequency, then by name
-    def cmpwords((aword, alist),(bword, blist)):
-        r = -cmp(len(alist),len(blist))
-        if r:
-            return r
-        return cmp(aword, bword)
-    wordlist.sort(cmpwords)
+    def word_key(a):
+        aword, alist = a
+        return -len(alist), aword
+    wordlist.sort(key=word_key)
 
     # figure out how many phrasebook escapes we need
     escapes = 0
@@ -630,7 +624,7 @@ def makeunicodename(unicode, trace):
     # length (to maximize overlap)
 
     wordlist, wordtail = wordlist[:short], wordlist[short:]
-    wordtail.sort(lambda a, b: len(b[0])-len(a[0]))
+    wordtail.sort(key=lambda a: a[0], reverse=True)
     wordlist.extend(wordtail)
 
     # generate lexicon from words

Tools/unicode/mkstringprep.py

@@ -1,7 +1,7 @@
 import re, unicodedata, sys
 
 if sys.maxunicode == 65535:
-    raise RuntimeError, "need UCS-4 Python"
+    raise RuntimeError("need UCS-4 Python")
 
 def gen_category(cats):
     for i in range(0, 0x110000):
@@ -63,14 +63,14 @@ for l in data:
     if m:
         if m.group(1) == "Start":
             if curname:
-                raise "Double Start",(curname, l)
+                raise RuntimeError("Double Start", (curname, l))
             curname = m.group(2)
             table = {}
             tables.append((curname, table))
             continue
         else:
             if not curname:
-                raise "End without start", l
+                raise RuntimeError("End without start", l)
             curname = None
             continue
     if not curname:
@@ -87,7 +87,7 @@ for l in data:
             try:
                 start, end = fields
             except ValueError:
-                raise "Unpacking problem", l
+                raise RuntimeError("Unpacking problem", l)
         else:
             start = end = fields[0]
         start = int(start, 16)
@@ -146,8 +146,7 @@ def in_table_a1(code):
 name, table = tables[0]
 del tables[0]
 assert name == "B.1"
-table = table.keys()
-table.sort()
+table = sorted(table.keys())
 print """
 b1_set = """ + compact_set(table) + """
 def in_table_b1(code):
@@ -177,8 +176,7 @@ for k,v in table_b2.items():
     if map(ord, unichr(k).lower()) != v:
         b3_exceptions[k] = u"".join(map(unichr,v))
 
-b3 = b3_exceptions.items()
-b3.sort()
+b3 = sorted(b3_exceptions.items())
 
 print """
 b3_exceptions = {"""
@@ -353,8 +351,7 @@ name, table = tables[0]
 del tables[0]
 assert name == "C.6"
 
-table = table.keys()
-table.sort()
+table = sorted(table.keys())
 
 print """
 c6_set = """ + compact_set(table) + """
@@ -367,8 +364,7 @@ name, table = tables[0]
 del tables[0]
 assert name == "C.7"
 
-table = table.keys()
-table.sort()
+table = sorted(table.keys())
 
 print """
 c7_set = """ + compact_set(table) + """
@@ -381,8 +377,7 @@ name, table = tables[0]
 del tables[0]
 assert name == "C.8"
 
-table = table.keys()
-table.sort()
+table = sorted(table.keys())
 
 print """
 c8_set = """ + compact_set(table) + """
@@ -395,8 +390,7 @@ name, table = tables[0]
 del tables[0]
 assert name == "C.9"
 
-table = table.keys()
-table.sort()
+table = sorted(table.keys())
 
 print """
 c9_set = """ + compact_set(table) + """