Marc-Andre Lemburg:

The attached patch set includes a workaround to get Python with
Unicode compile on BSDI 4.x (courtesy Thomas Wouters; the cause
is a bug in the BSDI wchar.h header file) and Python interfaces
for the MBCS codec donated by Mark Hammond.

Also included are some minor corrections w/r to the docs of
the new "es" and "es#" parser markers (use PyMem_Free() instead
of free(); thanks to Mark Hammond for finding these).

The unicodedata tests are now in a separate file
(test_unicodedata.py) to avoid problems if the module cannot
be found.

Lib/test/output/test_unicode

@@ -1,4 +1,5 @@
 test_unicode
 Testing Unicode comparisons... done.
+Testing Unicode contains method... done.
 Testing Unicode formatting strings... done.
-Testing unicodedata module... done.
+Testing builtin codecs... done.

Lib/test/output/test_unicodedata

@@ -0,0 +1,2 @@
+test_unicodedata
+Testing unicodedata module... done.

Lib/test/test_unicode.py

@@ -1,6 +1,5 @@
 """ Test script for the Unicode implementation.
 
-
 Written by Marc-Andre Lemburg (mal@lemburg.com).
 
 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
@@ -250,50 +249,6 @@ assert u"%(x)s, %(y)s" % {'x':u"abc", 'y':"def"} == u'abc, def'
 assert u"%(x)s, %(ä)s" % {'x':u"abc", u'ä'.encode('utf-8'):"def"} == u'abc, def'
 print 'done.'
 
-# Test Unicode database APIs
-try:
-    import unicodedata
-except ImportError:
-    pass
-else:
-    print 'Testing unicodedata module...',
-    
-    assert unicodedata.digit(u'A',None) is None
-    assert unicodedata.digit(u'9') == 9
-    assert unicodedata.digit(u'\u215b',None) is None
-    assert unicodedata.digit(u'\u2468') == 9
-
-    assert unicodedata.numeric(u'A',None) is None
-    assert unicodedata.numeric(u'9') == 9
-    assert unicodedata.numeric(u'\u215b') == 0.125
-    assert unicodedata.numeric(u'\u2468') == 9.0
-
-    assert unicodedata.decimal(u'A',None) is None
-    assert unicodedata.decimal(u'9') == 9
-    assert unicodedata.decimal(u'\u215b',None) is None
-    assert unicodedata.decimal(u'\u2468',None) is None
-
-    assert unicodedata.category(u'\uFFFE') == 'Cn'
-    assert unicodedata.category(u'a') == 'Ll'
-    assert unicodedata.category(u'A') == 'Lu'
-
-    assert unicodedata.bidirectional(u'\uFFFE') == ''
-    assert unicodedata.bidirectional(u' ') == 'WS'
-    assert unicodedata.bidirectional(u'A') == 'L'
-
-    assert unicodedata.decomposition(u'\uFFFE') == ''
-    assert unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034'
-
-    assert unicodedata.mirrored(u'\uFFFE') == 0
-    assert unicodedata.mirrored(u'a') == 0
-    assert unicodedata.mirrored(u'\u2201') == 1
-
-    assert unicodedata.combining(u'\uFFFE') == 0
-    assert unicodedata.combining(u'a') == 0
-    assert unicodedata.combining(u'\u20e1') == 230
-    
-    print 'done.'
-
 # Test builtin codecs
 print 'Testing builtin codecs...',
 

Lib/test/test_unicodedata.py

@@ -0,0 +1,50 @@
+""" Test script for the unicodedata module.
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+
+"""#"
+from test_support import verbose
+import sys
+
+# Test Unicode database APIs
+import unicodedata
+
+print 'Testing unicodedata module...',
+
+assert unicodedata.digit(u'A',None) is None
+assert unicodedata.digit(u'9') == 9
+assert unicodedata.digit(u'\u215b',None) is None
+assert unicodedata.digit(u'\u2468') == 9
+
+assert unicodedata.numeric(u'A',None) is None
+assert unicodedata.numeric(u'9') == 9
+assert unicodedata.numeric(u'\u215b') == 0.125
+assert unicodedata.numeric(u'\u2468') == 9.0
+
+assert unicodedata.decimal(u'A',None) is None
+assert unicodedata.decimal(u'9') == 9
+assert unicodedata.decimal(u'\u215b',None) is None
+assert unicodedata.decimal(u'\u2468',None) is None
+
+assert unicodedata.category(u'\uFFFE') == 'Cn'
+assert unicodedata.category(u'a') == 'Ll'
+assert unicodedata.category(u'A') == 'Lu'
+
+assert unicodedata.bidirectional(u'\uFFFE') == ''
+assert unicodedata.bidirectional(u' ') == 'WS'
+assert unicodedata.bidirectional(u'A') == 'L'
+
+assert unicodedata.decomposition(u'\uFFFE') == ''
+assert unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034'
+
+assert unicodedata.mirrored(u'\uFFFE') == 0
+assert unicodedata.mirrored(u'a') == 0
+assert unicodedata.mirrored(u'\u2201') == 1
+
+assert unicodedata.combining(u'\uFFFE') == 0
+assert unicodedata.combining(u'a') == 0
+assert unicodedata.combining(u'\u20e1') == 230
+
+print 'done.'