From: Marc-André Lemburg <mal@egenix.com>
Date: Fri, 16 May 2003 17:07:51 +0000 (+0000)
Subject: Remove usage of re module from encodings package search function.
X-Git-Tag: v2.3c1~701
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=282012593510a285fec5b8b5e42b04fef3ffffe0;p=python

Remove usage of re module from encodings package search function.
---

diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
index 66bea5c068..666afad6b6 100644
--- a/Lib/encodings/__init__.py
+++ b/Lib/encodings/__init__.py
@@ -27,12 +27,17 @@ Written by Marc-Andre Lemburg (mal@lemburg.com).
 
 """#"
 
-import codecs, exceptions, re
+import codecs, exceptions, types
 
 _cache = {}
 _unknown = '--unknown--'
 _import_tail = ['*']
-_norm_encoding_RE = re.compile('[^a-zA-Z0-9.]')
+_norm_encoding_map = ('                                              . '
+                      '0123456789       ABCDEFGHIJKLMNOPQRSTUVWXYZ     '
+                      ' abcdefghijklmnopqrstuvwxyz                     '
+                      '                                                '
+                      '                                                '
+                      '                ')
 
 class CodecRegistryError(exceptions.LookupError,
                          exceptions.SystemError):
@@ -45,10 +50,20 @@ def normalize_encoding(encoding):
         Normalization works as follows: all non-alphanumeric
         characters except the dot used for Python package names are
         collapsed and replaced with a single underscore, e.g. '  -;#'
-        becomes '_'.
+        becomes '_'. Leading and trailing underscores are removed.
+
+        Note that encoding names should be ASCII only; if they do use
+        non-ASCII characters, these must be Latin-1 compatible.
 
     """
-    return '_'.join(_norm_encoding_RE.split(encoding))
+    # Make sure we have an 8-bit string, because .translate() works
+    # differently for Unicode strings.
+    if type(encoding) is types.UnicodeType:
+        # Note that .encode('latin-1') does *not* use the codec
+        # registry, so this call doesn't recurse. (See unicodeobject.c
+        # PyUnicode_AsEncodedString() for details)
+        encoding = encoding.encode('latin-1')
+    return '_'.join(encoding.translate(_norm_encoding_map).split())
 
 def search_function(encoding):