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.
diff --git a/Lib/encodings/rot_13.py b/Lib/encodings/rot_13.py
new file mode 100644
index 0000000..8c54811
--- /dev/null
+++ b/Lib/encodings/rot_13.py
@@ -0,0 +1,107 @@
+#!/usr/local/bin/python2.1
+""" Python Character Mapping Codec for ROT13.
+
+ See http://ucsub.colorado.edu/~kominek/rot13/ for details.
+
+ Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+
+ return codecs.charmap_decode(input,errors,decoding_map)
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+
+ return (Codec().encode,Codec().decode,StreamReader,StreamWriter)
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0041: 0x004e,
+ 0x0042: 0x004f,
+ 0x0043: 0x0050,
+ 0x0044: 0x0051,
+ 0x0045: 0x0052,
+ 0x0046: 0x0053,
+ 0x0047: 0x0054,
+ 0x0048: 0x0055,
+ 0x0049: 0x0056,
+ 0x004a: 0x0057,
+ 0x004b: 0x0058,
+ 0x004c: 0x0059,
+ 0x004d: 0x005a,
+ 0x004e: 0x0041,
+ 0x004f: 0x0042,
+ 0x0050: 0x0043,
+ 0x0051: 0x0044,
+ 0x0052: 0x0045,
+ 0x0053: 0x0046,
+ 0x0054: 0x0047,
+ 0x0055: 0x0048,
+ 0x0056: 0x0049,
+ 0x0057: 0x004a,
+ 0x0058: 0x004b,
+ 0x0059: 0x004c,
+ 0x005a: 0x004d,
+ 0x0061: 0x006e,
+ 0x0062: 0x006f,
+ 0x0063: 0x0070,
+ 0x0064: 0x0071,
+ 0x0065: 0x0072,
+ 0x0066: 0x0073,
+ 0x0067: 0x0074,
+ 0x0068: 0x0075,
+ 0x0069: 0x0076,
+ 0x006a: 0x0077,
+ 0x006b: 0x0078,
+ 0x006c: 0x0079,
+ 0x006d: 0x007a,
+ 0x006e: 0x0061,
+ 0x006f: 0x0062,
+ 0x0070: 0x0063,
+ 0x0071: 0x0064,
+ 0x0072: 0x0065,
+ 0x0073: 0x0066,
+ 0x0074: 0x0067,
+ 0x0075: 0x0068,
+ 0x0076: 0x0069,
+ 0x0077: 0x006a,
+ 0x0078: 0x006b,
+ 0x0079: 0x006c,
+ 0x007a: 0x006d,
+})
+
+### Encoding Map
+
+encoding_map = {}
+for k,v in decoding_map.items():
+ encoding_map[v] = k
+
+### Filter API
+
+def rot13(infile, outfile):
+ outfile.write(infile.read().encode('rot-13'))
+
+if __name__ == '__main__':
+ import sys
+ rot13(sys.stdin, sys.stdout)