Patch #1359618: Speed-up charmap encoder.

Include/unicodeobject.h

@@ -650,6 +650,11 @@ PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
     const char *errors		/* error handling */
     );
 
+PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap(
+    PyObject* string            /* 256 character map */
+   );
+
+
 /* --- UTF-7 Codecs ------------------------------------------------------- */
 
 PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(

Misc/NEWS

@@ -104,6 +104,9 @@ Extension Modules
 Library
 -------
 
+- Patch #1359618: Speed up charmap encoder by using a trie structure
+  for lookup.
+
 - The functions in the ``pprint`` module now sort dictionaries by key
   before computing the display.  Before 2.5, ``pprint`` sorted a dictionary
   if and only if its display required more than one line, although that

Modules/_codecsmodule.c

@@ -792,6 +792,15 @@ charmap_encode(PyObject *self,
     return v;
 }
 
+static PyObject*
+charmap_build(PyObject *self, PyObject *args)
+{
+    PyObject *map;
+    if (!PyArg_ParseTuple(args, "U:charmap_build", &map))
+        return NULL;
+    return PyUnicode_BuildEncodingMap(map);
+}
+
 #if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T)
 
 static PyObject *
@@ -897,6 +906,7 @@ static PyMethodDef _codecs_functions[] = {
     {"ascii_decode", 		ascii_decode,			METH_VARARGS},
     {"charmap_encode", 		charmap_encode,			METH_VARARGS},
     {"charmap_decode", 		charmap_decode,			METH_VARARGS},
+    {"charmap_build", 		charmap_build,			METH_VARARGS},
     {"readbuffer_encode",	readbuffer_encode,		METH_VARARGS},
     {"charbuffer_encode",	charbuffer_encode,		METH_VARARGS},
 #if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T)

Tools/unicode/Makefile

@@ -78,7 +78,7 @@ cjk:	build/
 ### Cleanup
 
 clean:
-	$(RM) build/*
+	$(RM) -f build/*
 
 distclean:	clean
 	$(RM) -rf MAPPINGS/

Tools/unicode/gencodec.py

@@ -270,6 +270,11 @@ def codegen(name, map, encodingname, comments=1):
         comments=comments,
         precisions=(4, 2))
 
+    if decoding_table_code:
+        suffix = 'table'
+    else:
+        suffix = 'map'
+
     l = [
         '''\
 """ Python Character Mapping Codec %s generated from '%s' with gencodec.py.
@@ -283,30 +288,20 @@ import codecs
 class Codec(codecs.Codec):
 
     def encode(self,input,errors='strict'):
-        return codecs.charmap_encode(input,errors,encoding_map)
-
-    def decode(self,input,errors='strict'):''' % (encodingname, name)
-        ]
-    if decoding_table_code:
-        l.append('''\
-        return codecs.charmap_decode(input,errors,decoding_table)''')
-    else:
-        l.append('''\
-        return codecs.charmap_decode(input,errors,decoding_map)''')
+        return codecs.charmap_encode(input,errors,encoding_%s)
 
-    l.append('''
+    def decode(self,input,errors='strict'):
+        return codecs.charmap_decode(input,errors,decoding_%s)
+''' % (encodingname, name, suffix, suffix)]
+    l.append('''\
 class IncrementalEncoder(codecs.IncrementalEncoder):
     def encode(self, input, final=False):
-        return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+        return codecs.charmap_encode(input,self.errors,encoding_%s)[0]
 
 class IncrementalDecoder(codecs.IncrementalDecoder):
-    def decode(self, input, final=False):''')
-    if decoding_table_code:
-        l.append('''\
-        return codecs.charmap_decode(input,self.errors,decoding_table)[0]''')
-    else:
-        l.append('''\
-        return codecs.charmap_decode(input,self.errors,decoding_map)[0]''')
+    def decode(self, input, final=False):
+        return codecs.charmap_decode(input,self.errors,decoding_%s)[0]''' %
+        (suffix, suffix))
 
     l.append('''
 class StreamWriter(Codec,codecs.StreamWriter):
@@ -319,13 +314,13 @@ class StreamReader(Codec,codecs.StreamReader):
 
 def getregentry():
     return codecs.CodecInfo(
-        Codec().encode,
-        Codec().decode,
         name=%r,
-        streamwriter=StreamWriter,
-        streamreader=StreamReader,
+        encode=Codec().encode,
+        decode=Codec().decode,
         incrementalencoder=IncrementalEncoder,
         incrementaldecoder=IncrementalDecoder,
+        streamreader=StreamReader,
+        streamwriter=StreamWriter,
     )
 ''' % encodingname.replace('_', '-'))
 
@@ -342,10 +337,16 @@ def getregentry():
         l.extend(decoding_table_code)
 
     # Add encoding map
-    l.append('''
+    if decoding_table_code:
+        l.append('''
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
+''')
+    else:
+        l.append('''
 ### Encoding Map
 ''')
-    l.extend(encoding_map_code)
+        l.extend(encoding_map_code)
 
     # Final new-line
     l.append('')