string.maketrans() now produces translation tables for bytes.translate() -- wrong module?

birkenfeld · birkenfeld · commit 7f13e6b3e254 · 2007-08-31T10:37:15.000Z
Fix all remaining instances that did bad things with the new str.translate().
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
@@ -1549,19 +1549,18 @@ further useful methods also found on strings.
       b'example'
 
 
-.. method:: bytes.translate(table[, deletechars])
+.. method:: bytes.translate(table[, delete])
 
    Return a copy of the bytes object where all bytes occurring in the optional
-   argument *deletechars* are removed, and the remaining bytes have been mapped
+   argument *delete* are removed, and the remaining bytes have been mapped
    through the given translation table, which must be a bytes object of length
    256.
 
    You can use the :func:`maketrans` helper function in the :mod:`string` module to
    create a translation table.
 
    .. XXX a None table doesn't seem to be supported
-      For string objects, set the *table* argument to
-      ``None`` for translations that only delete characters::
+      Set the *table* argument to ``None`` for translations that only delete characters::
 
          >>> 'read this short text'.translate(None, 'aeiou')
          'rd ths shrt txt'
diff --git a/Doc/library/string.rst b/Doc/library/string.rst
@@ -128,10 +128,11 @@ formatting behaviors using the same implementation as the built-in
    .. method:: get_field(field_name, args, kwargs, used_args)
 
       Given *field_name* as returned by :meth:`parse` (see above), convert it to
-      an object to be formatted.  The default version takes strings of the form
-      defined in :pep:`3101`, such as "0[name]" or "label.title".  It records
-      which args have been used in *used_args*. *args* and *kwargs* are as
-      passed in to :meth:`vformat`.
+      an object to be formatted.  Returns a tuple (obj, used_key).  The default
+      version takes strings of the form defined in :pep:`3101`, such as
+      "0[name]" or "label.title".  *args* and *kwargs* are as passed in to
+      :meth:`vformat`.  The return value *used_key* has the same meaning as the
+      *key* parameter to :meth:`get_value`.
 
    .. method:: get_value(key, args, kwargs)
    
@@ -554,15 +555,8 @@ They are not available as string methods.
    leading and trailing whitespace.
 
 
-.. XXX is obsolete with unicode.translate
-.. function:: maketrans(from, to)
+.. function:: maketrans(frm, to)
 
-   Return a translation table suitable for passing to :func:`translate`, that will
-   map each character in *from* into the character at the same position in *to*;
-   *from* and *to* must have the same length.
-
-   .. warning::
-
-      Don't use strings derived from :const:`lowercase` and :const:`uppercase` as
-      arguments; in some locales, these don't have the same length.  For case
-      conversions, always use :func:`lower` and :func:`upper`.
+   Return a translation table suitable for passing to :meth:`bytes.translate`,
+   that will map each character in *from* into the character at the same
+   position in *to*; *from* and *to* must have the same length.
diff --git a/Lib/distutils/command/install.py b/Lib/distutils/command/install.py
@@ -348,11 +348,10 @@ def dump_dirs(self, msg):
                 if opt_name[-1] == "=":
                     opt_name = opt_name[0:-1]
                 if self.negative_opt.has_key(opt_name):
-                    opt_name = self.negative_opt[opt_name].translate(
-                                                               longopt_xlate)
+                    opt_name = longopt_xlate(self.negative_opt[opt_name])
                     val = not getattr(self, opt_name)
                 else:
-                    opt_name = opt_name.translate(longopt_xlate)
+                    opt_name = longopt_xlate(opt_name)
                     val = getattr(self, opt_name)
                 print("  %s: %s" % (opt_name, val))
 
diff --git a/Lib/distutils/fancy_getopt.py b/Lib/distutils/fancy_getopt.py
@@ -26,7 +26,7 @@
 
 # This is used to translate long options to legitimate Python identifiers
 # (for use as attributes of some object).
-longopt_xlate = string.maketrans('-', '_')
+longopt_xlate = lambda s: s.replace('-', '_')
 
 class FancyGetopt:
     """Wrapper around the standard 'getopt()' module that provides some
@@ -107,7 +107,7 @@ def get_attr_name(self, long_option):
         """Translate long option name 'long_option' to the form it
         has as an attribute of some object: ie., translate hyphens
         to underscores."""
-        return long_option.translate(longopt_xlate)
+        return longopt_xlate(long_option)
 
     def _check_alias_dict(self, aliases, what):
         assert isinstance(aliases, dict)
@@ -372,7 +372,7 @@ def fancy_getopt(options, negative_opt, object, args):
     return parser.getopt(args, object)
 
 
-WS_TRANS = string.maketrans(string.whitespace, ' ' * len(string.whitespace))
+WS_TRANS = {ord(_wschar) : ' ' for _wschar in string.whitespace}
 
 def wrap_text(text, width):
     """wrap_text(text : string, width : int) -> [string]
@@ -432,7 +432,7 @@ def translate_longopt(opt):
     """Convert a long option name to a valid Python identifier by
     changing "-" to "_".
     """
-    return opt.translate(longopt_xlate)
+    return longopt_xlate(opt)
 
 
 class OptionDummy:
diff --git a/Lib/string.py b/Lib/string.py
@@ -25,10 +25,6 @@
 punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
 printable = digits + ascii_letters + punctuation + whitespace
 
-# Case conversion helpers
-# Use str to convert Unicode literal in case of -U
-_idmap = str('').join(chr(c) for c in range(256))
-
 # Functions which aren't available as string methods.
 
 # Capitalize the words in a string, e.g. " aBc  dEf " -> "Abc Def".
@@ -44,26 +40,23 @@ def capwords(s, sep=None):
     return (sep or ' ').join([x.capitalize() for x in s.split(sep)])
 
 
-# Construct a translation string
-_idmapL = None
-def maketrans(fromstr, tostr):
-    """maketrans(frm, to) -> string
-
-    Return a translation table (a string of 256 bytes long)
-    suitable for use in string.translate.  The strings frm and to
-    must be of the same length.
+# Construct a translation map for bytes.translate
+def maketrans(frm, to):
+    """maketrans(frm, to) -> bytes
 
+    Return a translation table (a bytes object of length 256)
+    suitable for use in bytes.translate where each byte in frm is
+    mapped to the byte at the same position in to.
+    The strings frm and to must be of the same length.
     """
-    if len(fromstr) != len(tostr):
+    if len(frm) != len(to):
         raise ValueError("maketrans arguments must have same length")
-    global _idmapL
-    if not _idmapL:
-        _idmapL = list(_idmap)
-    L = _idmapL[:]
-    for i, c in enumerate(fromstr):
-        L[ord(c)] = tostr[i]
-    return ''.join(L)
-
+    if not (isinstance(frm, bytes) and isinstance(to, bytes)):
+        raise TypeError("maketrans arguments must be bytes objects")
+    L = bytes(range(256))
+    for i, c in enumerate(frm):
+        L[c] = to[i]
+    return L
 
 
 ####################################################################
diff --git a/Lib/test/test_bigmem.py b/Lib/test/test_bigmem.py
@@ -3,7 +3,6 @@
 
 import unittest
 import operator
-import string
 import sys
 
 # Bigmem testing houserules:
@@ -376,7 +375,7 @@ def test_title(self, size):
 
     @bigmemtest(minsize=_2G, memuse=2)
     def test_translate(self, size):
-        trans = string.maketrans('.aZ', '-!$')
+        trans = {ord('.'):'-', ord('a'):'!', ord('Z'):'$'}
         SUBSTR = 'aZz.z.Aaz.'
         sublen = len(SUBSTR)
         repeats = size // sublen + 2
diff --git a/Lib/test/test_string.py b/Lib/test/test_string.py
@@ -103,10 +103,11 @@ def check_unused_args(self, used_args, args, kwargs):
 
 
     def test_maketrans(self):
-        transtable = '\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`xyzdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
+        transtable = b'\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`xyzdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
 
-        self.assertEqual(string.maketrans('abc', 'xyz'), transtable)
-        self.assertRaises(ValueError, string.maketrans, 'abc', 'xyzq')
+        self.assertEqual(string.maketrans(b'abc', b'xyz'), transtable)
+        self.assertRaises(ValueError, string.maketrans, b'abc', b'xyzq')
+        self.assertRaises(TypeError, string.maketrans, 'abc', 'def')
 
 def test_main():
     test_support.run_unittest(ModuleTest)
diff --git a/Lib/textwrap.py b/Lib/textwrap.py
@@ -59,8 +59,6 @@ class TextWrapper:
         Drop leading and trailing whitespace from lines.
     """
 
-    whitespace_trans = string.maketrans(_whitespace, ' ' * len(_whitespace))
-
     unicode_whitespace_trans = {}
     uspace = ord(' ')
     for x in _whitespace:
@@ -116,10 +114,7 @@ def _munge_whitespace(self, text):
         if self.expand_tabs:
             text = text.expandtabs()
         if self.replace_whitespace:
-            if isinstance(text, str8):
-                text = text.translate(self.whitespace_trans)
-            elif isinstance(text, str):
-                text = text.translate(self.unicode_whitespace_trans)
+            text = text.translate(self.unicode_whitespace_trans)
         return text
 
 
diff --git a/Lib/urllib.py b/Lib/urllib.py
@@ -1420,7 +1420,6 @@ def reporthook(blocknum, blocksize, totalsize):
 
 # Test program
 def test(args=[]):
-    import string
     if not args:
         args = [
             '/etc/passwd',
@@ -1443,9 +1442,7 @@ def test(args=[]):
             fp = open(fn, 'rb')
             data = fp.read()
             del fp
-            if '\r' in data:
-                table = string.maketrans("", "")
-                data = data.translate(table, "\r")
+            data = data.replace("\r", "")
             print(data)
             fn, h = None, None
         print('-'*40)
