This patch changes the way the string .encode() method works slightly

and introduces a new method .decode().

The major change is that strg.encode() will no longer try to convert
Unicode returns from the codec into a string, but instead pass along
the Unicode object as-is. The same is now true for all other codec
return types. The underlying C APIs were changed accordingly.

Note that even though this does have the potential of breaking
existing code, the chances are low since conversion from Unicode
previously took place using the default encoding which is normally
set to ASCII rendering this auto-conversion mechanism useless for
most Unicode encodings.

The good news is that you can now use .encode() and .decode() with
much greater ease and that the door was opened for better accessibility
of the builtin codecs.

As demonstration of the new feature, the patch includes a few new
codecs which allow string to string encoding and decoding (rot13,
hex, zip, uu, base64).

Written by Marc-Andre Lemburg. Copyright assigned to the PSF.

1 files changed, 19 insertions, 0 deletions

diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py
index fcce50f..9b95a8e 100644
--- a/Lib/test/string_tests.py
+++ b/Lib/test/string_tests.py
@@ -1,6 +1,7 @@
 """Common tests shared by test_string and test_userstring"""
 
 import string
+from test_support import verify, verbose, TestFailed
 
 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'
 
@@ -212,3 +213,21 @@ def run_method_tests(test):
     test('endswith', 'helloworld', 0, 'lowo', 3, 8)
     test('endswith', 'ab', 0, 'ab', 0, 1)
     test('endswith', 'ab', 0, 'ab', 0, 0)
+
+    # Encoding/decoding
+    codecs = [('rot13', 'uryyb jbeyq'),
+              ('base64', 'aGVsbG8gd29ybGQ=\n'),
+              ('hex', '68656c6c6f20776f726c64'),
+              ('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')]
+    for encoding, data in codecs:
+        test('encode', 'hello world', data, encoding)
+        test('decode', data, 'hello world', encoding)
+    # zlib is optional, so we make the test optional too...
+    try:
+        import zlib
+    except ImportError:
+        pass
+    else:
+        data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]'
+        verify('hello world'.encode('zlib') == data)
+        verify(data.decode('zlib') == 'hello world')