Patch 1280, by Alexandre Vassalotti.

Make PyString's indexing and iteration return integers.
(I changed a few of Alexandre's decisions -- GvR.)

Author: gvanrossum

Lib/dis.py

@@ -117,8 +117,7 @@ def disassemble(co, lasti=-1):
     extended_arg = 0
     free = None
     while i < n:
-        c = code[i]
-        op = ord(c)
+        op = code[i]
         if i in linestarts:
             if i > 0:
                 print()
@@ -134,7 +133,7 @@ def disassemble(co, lasti=-1):
         print(opname[op].ljust(20), end=' ')
         i = i+1
         if op >= HAVE_ARGUMENT:
-            oparg = ord(code[i]) + ord(code[i+1])*256 + extended_arg
+            oparg = code[i] + code[i+1]*256 + extended_arg
             extended_arg = 0
             i = i+2
             if op == EXTENDED_ARG:
@@ -162,8 +161,7 @@ def disassemble_string(code, lasti=-1, varnames=None, names=None,
     n = len(code)
     i = 0
     while i < n:
-        c = code[i]
-        op = ord(c)
+        op = code[i]
         if i == lasti: print('-->', end=' ')
         else: print('   ', end=' ')
         if i in labels: print('>>', end=' ')
@@ -172,7 +170,7 @@ def disassemble_string(code, lasti=-1, varnames=None, names=None,
         print(opname[op].ljust(15), end=' ')
         i = i+1
         if op >= HAVE_ARGUMENT:
-            oparg = ord(code[i]) + ord(code[i+1])*256
+            oparg = code[i] + code[i+1]*256
             i = i+2
             print(repr(oparg).rjust(5), end=' ')
             if op in hasconst:
@@ -208,11 +206,10 @@ def findlabels(code):
     n = len(code)
     i = 0
     while i < n:
-        c = code[i]
-        op = ord(c)
+        op = code[i]
         i = i+1
         if op >= HAVE_ARGUMENT:
-            oparg = ord(code[i]) + ord(code[i+1])*256
+            oparg = code[i] + code[i+1]*256
             i = i+2
             label = -1
             if op in hasjrel:
@@ -230,8 +227,8 @@ def findlinestarts(code):
     Generate pairs (offset, lineno) as described in Python/compile.c.
 
     """
-    byte_increments = [ord(c) for c in code.co_lnotab[0::2]]
-    line_increments = [ord(c) for c in code.co_lnotab[1::2]]
+    byte_increments = list(code.co_lnotab[0::2])
+    line_increments = list(code.co_lnotab[1::2])
 
     lastlineno = None
     lineno = code.co_firstlineno

Lib/encodings/__init__.py

@@ -52,6 +52,8 @@ def normalize_encoding(encoding):
         non-ASCII characters, these must be Latin-1 compatible.
 
     """
+    if isinstance(encoding, str8):
+        encoding = str(encoding, "ascii")
     chars = []
     punct = False
     for c in encoding:

Lib/modulefinder.py

@@ -367,7 +367,7 @@ def scan_opcodes_25(self, co,
         consts = co.co_consts
         LOAD_LOAD_AND_IMPORT = LOAD_CONST + LOAD_CONST + IMPORT_NAME
         while code:
-            c = code[0]
+            c = chr(code[0])
             if c in STORE_OPS:
                 oparg, = unpack('<H', code[1:3])
                 yield "store", (names[oparg],)

Lib/sre_parse.py

@@ -189,12 +189,18 @@ def __next(self):
         if self.index >= len(self.string):
             self.next = None
             return
-        char = self.string[self.index]
-        if char[0] == "\\":
+        char = self.string[self.index:self.index+1]
+        # Special case for the str8, since indexing returns a integer
+        # XXX This is only needed for test_bug_926075 in test_re.py
+        if isinstance(self.string, str8):
+            char = chr(char)
+        if char == "\\":
             try:
                 c = self.string[self.index + 1]
             except IndexError:
                 raise error("bogus escape (end of line)")
+            if isinstance(self.string, str8):
+                char = chr(c)
             char = char + c
         self.index = self.index + len(char)
         self.next = char

Lib/test/string_tests.py

@@ -558,6 +558,10 @@ def test_hash(self):
         a = self.type2test('DNSSEC')
         b = self.type2test('')
         for c in a:
+            # Special case for the str8, since indexing returns a integer
+            # XXX Maybe it would be a good idea to seperate str8's tests...
+            if self.type2test == str8:
+                c = chr(c)
             b += c
             hash(b)
         self.assertEqual(hash(a), hash(b))

Lib/test/test_bytes.py

@@ -348,7 +348,7 @@ def test_from_buffer(self):
         sample = str8("Hello world\n\x80\x81\xfe\xff")
         buf = memoryview(sample)
         b = bytes(buf)
-        self.assertEqual(b, bytes(map(ord, sample)))
+        self.assertEqual(b, bytes(sample))
 
     def test_to_str(self):
         sample = "Hello world\n\x80\x81\xfe\xff"

Lib/test/test_set.py

@@ -72,7 +72,7 @@ def test_union(self):
         self.assertEqual(type(u), self.thetype)
         self.assertRaises(PassThru, self.s.union, check_pass_thru())
         self.assertRaises(TypeError, self.s.union, [[]])
-        for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+        for C in set, frozenset, dict.fromkeys, str, list, tuple:
             self.assertEqual(self.thetype('abcba').union(C('cdc')), set('abcd'))
             self.assertEqual(self.thetype('abcba').union(C('efgfe')), set('abcefg'))
             self.assertEqual(self.thetype('abcba').union(C('ccb')), set('abc'))
@@ -96,7 +96,7 @@ def test_intersection(self):
         self.assertEqual(self.s, self.thetype(self.word))
         self.assertEqual(type(i), self.thetype)
         self.assertRaises(PassThru, self.s.intersection, check_pass_thru())
-        for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+        for C in set, frozenset, dict.fromkeys, str, list, tuple:
             self.assertEqual(self.thetype('abcba').intersection(C('cdc')), set('cc'))
             self.assertEqual(self.thetype('abcba').intersection(C('efgfe')), set(''))
             self.assertEqual(self.thetype('abcba').intersection(C('ccb')), set('bc'))
@@ -121,7 +121,7 @@ def test_difference(self):
         self.assertEqual(type(i), self.thetype)
         self.assertRaises(PassThru, self.s.difference, check_pass_thru())
         self.assertRaises(TypeError, self.s.difference, [[]])
-        for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+        for C in set, frozenset, dict.fromkeys, str, list, tuple:
             self.assertEqual(self.thetype('abcba').difference(C('cdc')), set('ab'))
             self.assertEqual(self.thetype('abcba').difference(C('efgfe')), set('abc'))
             self.assertEqual(self.thetype('abcba').difference(C('ccb')), set('a'))
@@ -146,7 +146,7 @@ def test_symmetric_difference(self):
         self.assertEqual(type(i), self.thetype)
         self.assertRaises(PassThru, self.s.symmetric_difference, check_pass_thru())
         self.assertRaises(TypeError, self.s.symmetric_difference, [[]])
-        for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+        for C in set, frozenset, dict.fromkeys, str, list, tuple:
             self.assertEqual(self.thetype('abcba').symmetric_difference(C('cdc')), set('abd'))
             self.assertEqual(self.thetype('abcba').symmetric_difference(C('efgfe')), set('abcefg'))
             self.assertEqual(self.thetype('abcba').symmetric_difference(C('ccb')), set('a'))
@@ -390,7 +390,7 @@ def test_update(self):
         self.assertRaises(PassThru, self.s.update, check_pass_thru())
         self.assertRaises(TypeError, self.s.update, [[]])
         for p, q in (('cdc', 'abcd'), ('efgfe', 'abcefg'), ('ccb', 'abc'), ('ef', 'abcef')):
-            for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+            for C in set, frozenset, dict.fromkeys, str, list, tuple:
                 s = self.thetype('abcba')
                 self.assertEqual(s.update(C(p)), None)
                 self.assertEqual(s, set(q))
@@ -411,7 +411,7 @@ def test_intersection_update(self):
         self.assertRaises(PassThru, self.s.intersection_update, check_pass_thru())
         self.assertRaises(TypeError, self.s.intersection_update, [[]])
         for p, q in (('cdc', 'c'), ('efgfe', ''), ('ccb', 'bc'), ('ef', '')):
-            for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+            for C in set, frozenset, dict.fromkeys, str, list, tuple:
                 s = self.thetype('abcba')
                 self.assertEqual(s.intersection_update(C(p)), None)
                 self.assertEqual(s, set(q))
@@ -436,7 +436,7 @@ def test_difference_update(self):
         self.assertRaises(TypeError, self.s.difference_update, [[]])
         self.assertRaises(TypeError, self.s.symmetric_difference_update, [[]])
         for p, q in (('cdc', 'ab'), ('efgfe', 'abc'), ('ccb', 'a'), ('ef', 'abc')):
-            for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+            for C in set, frozenset, dict.fromkeys, str, list, tuple:
                 s = self.thetype('abcba')
                 self.assertEqual(s.difference_update(C(p)), None)
                 self.assertEqual(s, set(q))
@@ -460,7 +460,7 @@ def test_symmetric_difference_update(self):
         self.assertRaises(PassThru, self.s.symmetric_difference_update, check_pass_thru())
         self.assertRaises(TypeError, self.s.symmetric_difference_update, [[]])
         for p, q in (('cdc', 'abd'), ('efgfe', 'abcefg'), ('ccb', 'a'), ('ef', 'abcef')):
-            for C in set, frozenset, dict.fromkeys, str, str8, list, tuple:
+            for C in set, frozenset, dict.fromkeys, str, list, tuple:
                 s = self.thetype('abcba')
                 self.assertEqual(s.symmetric_difference_update(C(p)), None)
                 self.assertEqual(s, set(q))

Lib/test/test_struct.py

@@ -674,8 +674,8 @@ def test_bool():
         elif not prefix and verbose:
             print('size of bool in native format is %i' % (len(packed)))
 
-        for c in str8('\x01\x7f\xff\x0f\xf0'):
-            if struct.unpack('>t', c)[0] is not True:
+        for c in b'\x01\x7f\xff\x0f\xf0':
+            if struct.unpack('>t', bytes([c]))[0] is not True:
                 raise TestFailed('%c did not unpack as True' % c)
 
 test_bool()

Objects/stringobject.c

@@ -986,28 +986,6 @@ string_contains(PyObject *str_obj, PyObject *sub_obj)
 	return stringlib_contains_obj(str_obj, sub_obj);
 }
 
-static PyObject *
-string_item(PyStringObject *a, register Py_ssize_t i)
-{
-	char pchar;
-	PyObject *v;
-	if (i < 0 || i >= Py_Size(a)) {
-		PyErr_SetString(PyExc_IndexError, "string index out of range");
-		return NULL;
-	}
-	pchar = a->ob_sval[i];
-	v = (PyObject *)characters[pchar & UCHAR_MAX];
-	if (v == NULL)
-		v = PyString_FromStringAndSize(&pchar, 1);
-	else {
-#ifdef COUNT_ALLOCS
-		one_strings++;
-#endif
-		Py_INCREF(v);
-	}
-	return v;
-}
-
 static PyObject*
 string_richcompare(PyStringObject *a, PyStringObject *b, int op)
 {
@@ -1110,7 +1088,12 @@ string_subscript(PyStringObject* self, PyObject* item)
 			return NULL;
 		if (i < 0)
 			i += PyString_GET_SIZE(self);
-		return string_item(self, i);
+                if (i < 0 || i >= PyString_GET_SIZE(self)) {
+			PyErr_SetString(PyExc_IndexError,
+					"string index out of range");
+			return NULL;
+                }
+                return PyInt_FromLong((unsigned char)self->ob_sval[i]);
 	}
 	else if (PySlice_Check(item)) {
 		Py_ssize_t start, stop, step, slicelength, cur, i;
@@ -1173,7 +1156,7 @@ static PySequenceMethods string_as_sequence = {
 	(lenfunc)string_length, /*sq_length*/
 	(binaryfunc)string_concat, /*sq_concat*/
 	(ssizeargfunc)string_repeat, /*sq_repeat*/
-	(ssizeargfunc)string_item, /*sq_item*/
+	0,		/*sq_item*/
 	0,		/*sq_slice*/
 	0,		/*sq_ass_item*/
 	0,		/*sq_ass_slice*/
@@ -4147,8 +4130,8 @@ striter_next(striterobject *it)
 	assert(PyString_Check(seq));
 
 	if (it->it_index < PyString_GET_SIZE(seq)) {
-		item = PyString_FromStringAndSize(
-			PyString_AS_STRING(seq)+it->it_index, 1);
+		item = PyInt_FromLong(
+			(unsigned char)seq->ob_sval[it->it_index]);
 		if (item != NULL)
 			++it->it_index;
 		return item;