Patch #445762: Support --disable-unicode
- Do not compile unicodeobject, unicodectype, and unicodedata if Unicode is disabled
- check for Py_USING_UNICODE in all places that use Unicode functions
- disables unicode literals, and the builtin functions
- add the types.StringTypes list
- remove Unicode literals from most tests.
diff --git a/Objects/abstract.c b/Objects/abstract.c
index b646c36..f7ade6d 100644
--- a/Objects/abstract.c
+++ b/Objects/abstract.c
@@ -583,8 +583,10 @@
{
if (PyString_Check(v))
return PyString_Format(v, w);
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v))
return PyUnicode_Format(v, w);
+#endif
return binary_op(v, w, NB_SLOT(nb_remainder), "%");
}
@@ -707,8 +709,10 @@
{
if (PyString_Check(v))
return PyString_Format(v, w);
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v))
return PyUnicode_Format(v, w);
+#endif
else
return binary_iop(v, w, NB_SLOT(nb_inplace_remainder),
NB_SLOT(nb_remainder), "%=");
@@ -821,10 +825,12 @@
if (PyString_Check(o))
return int_from_string(PyString_AS_STRING(o),
PyString_GET_SIZE(o));
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(o))
return PyInt_FromUnicode(PyUnicode_AS_UNICODE(o),
PyUnicode_GET_SIZE(o),
10);
+#endif
m = o->ob_type->tp_as_number;
if (m && m->nb_int)
return m->nb_int(o);
@@ -873,11 +879,13 @@
*/
return long_from_string(PyString_AS_STRING(o),
PyString_GET_SIZE(o));
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(o))
/* The above check is done in PyLong_FromUnicode(). */
return PyLong_FromUnicode(PyUnicode_AS_UNICODE(o),
PyUnicode_GET_SIZE(o),
10);
+#endif
m = o->ob_type->tp_as_number;
if (m && m->nb_long)
return m->nb_long(o);
diff --git a/Objects/complexobject.c b/Objects/complexobject.c
index 84eee11..cb081aa 100644
--- a/Objects/complexobject.c
+++ b/Objects/complexobject.c
@@ -611,14 +611,15 @@
int sw_error=0;
int sign;
char buffer[256]; /* For errors */
- char s_buffer[256];
int len;
if (PyString_Check(v)) {
s = PyString_AS_STRING(v);
len = PyString_GET_SIZE(v);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v)) {
+ char s_buffer[256];
if (PyUnicode_GET_SIZE(v) >= sizeof(s_buffer)) {
PyErr_SetString(PyExc_ValueError,
"complex() literal too large to convert");
@@ -632,6 +633,7 @@
s = s_buffer;
len = (int)strlen(s);
}
+#endif
else if (PyObject_AsCharBuffer(v, &s, &len)) {
PyErr_SetString(PyExc_TypeError,
"complex() arg is not a string");
diff --git a/Objects/floatobject.c b/Objects/floatobject.c
index 34b252b..044d1d3 100644
--- a/Objects/floatobject.c
+++ b/Objects/floatobject.c
@@ -109,7 +109,9 @@
const char *s, *last, *end;
double x;
char buffer[256]; /* for errors */
+#ifdef Py_USING_UNICODE
char s_buffer[256]; /* for objects convertible to a char buffer */
+#endif
int len;
if (pend)
@@ -118,6 +120,7 @@
s = PyString_AS_STRING(v);
len = PyString_GET_SIZE(v);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v)) {
if (PyUnicode_GET_SIZE(v) >= sizeof(s_buffer)) {
PyErr_SetString(PyExc_ValueError,
@@ -132,6 +135,7 @@
s = s_buffer;
len = (int)strlen(s);
}
+#endif
else if (PyObject_AsCharBuffer(v, &s, &len)) {
PyErr_SetString(PyExc_TypeError,
"float() needs a string argument");
diff --git a/Objects/intobject.c b/Objects/intobject.c
index f69f81a..e7f618b 100644
--- a/Objects/intobject.c
+++ b/Objects/intobject.c
@@ -202,6 +202,7 @@
return PyInt_FromLong(x);
}
+#ifdef Py_USING_UNICODE
PyObject *
PyInt_FromUnicode(Py_UNICODE *s, int length, int base)
{
@@ -216,6 +217,7 @@
return NULL;
return PyInt_FromString(buffer, NULL, base);
}
+#endif
/* Methods */
@@ -765,10 +767,12 @@
return PyNumber_Int(x);
if (PyString_Check(x))
return PyInt_FromString(PyString_AS_STRING(x), NULL, base);
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(x))
return PyInt_FromUnicode(PyUnicode_AS_UNICODE(x),
PyUnicode_GET_SIZE(x),
base);
+#endif
PyErr_SetString(PyExc_TypeError,
"int() can't convert non-string with explicit base");
return NULL;
diff --git a/Objects/longobject.c b/Objects/longobject.c
index 9f7272c..01a7276 100644
--- a/Objects/longobject.c
+++ b/Objects/longobject.c
@@ -971,6 +971,7 @@
return NULL;
}
+#ifdef Py_USING_UNICODE
PyObject *
PyLong_FromUnicode(Py_UNICODE *u, int length, int base)
{
@@ -986,6 +987,7 @@
return PyLong_FromString(buffer, NULL, base);
}
+#endif
/* forward */
static PyLongObject *x_divrem
@@ -2054,10 +2056,12 @@
return PyNumber_Long(x);
else if (PyString_Check(x))
return PyLong_FromString(PyString_AS_STRING(x), NULL, base);
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(x))
return PyLong_FromUnicode(PyUnicode_AS_UNICODE(x),
PyUnicode_GET_SIZE(x),
base);
+#endif
else {
PyErr_SetString(PyExc_TypeError,
"long() can't convert non-string with explicit base");
diff --git a/Objects/object.c b/Objects/object.c
index fea9ee5..7e4a211 100644
--- a/Objects/object.c
+++ b/Objects/object.c
@@ -246,6 +246,7 @@
res = (*v->ob_type->tp_repr)(v);
if (res == NULL)
return NULL;
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(res)) {
PyObject* str;
str = PyUnicode_AsUnicodeEscapeString(res);
@@ -255,6 +256,7 @@
else
return NULL;
}
+#endif
if (!PyString_Check(res)) {
PyErr_Format(PyExc_TypeError,
"__repr__ returned non-string (type %.200s)",
@@ -283,6 +285,7 @@
res = (*v->ob_type->tp_str)(v);
if (res == NULL)
return NULL;
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(res)) {
PyObject* str;
str = PyUnicode_AsEncodedString(res, NULL, NULL);
@@ -292,6 +295,7 @@
else
return NULL;
}
+#endif
if (!PyString_Check(res)) {
PyErr_Format(PyExc_TypeError,
"__str__ returned non-string (type %.200s)",
@@ -302,6 +306,7 @@
return res;
}
+#ifdef Py_USING_UNICODE
PyObject *
PyObject_Unicode(PyObject *v)
{
@@ -350,6 +355,7 @@
}
return res;
}
+#endif
/* Macro to get the tp_richcompare field of a type if defined */
@@ -523,6 +529,7 @@
return (vv < ww) ? -1 : (vv > ww) ? 1 : 0;
}
+#ifdef Py_USING_UNICODE
/* Special case for Unicode */
if (PyUnicode_Check(v) || PyUnicode_Check(w)) {
c = PyUnicode_Compare(v, w);
@@ -537,6 +544,7 @@
return -2;
PyErr_Clear();
}
+#endif
/* None is smaller than anything */
if (v == Py_None)
@@ -1032,6 +1040,7 @@
{
PyTypeObject *tp = v->ob_type;
+#ifdef Py_USING_UNICODE
/* The Unicode to string conversion is done here because the
existing tp_getattro slots expect a string object as name
and we wouldn't want to break those. */
@@ -1040,6 +1049,8 @@
if (name == NULL)
return NULL;
}
+#endif
+
if (!PyString_Check(name)) {
PyErr_SetString(PyExc_TypeError,
"attribute name must be string");
@@ -1073,6 +1084,7 @@
PyTypeObject *tp = v->ob_type;
int err;
+#ifdef Py_USING_UNICODE
/* The Unicode to string conversion is done here because the
existing tp_setattro slots expect a string object as name
and we wouldn't want to break those. */
@@ -1081,7 +1093,9 @@
if (name == NULL)
return -1;
}
- else if (!PyString_Check(name)){
+ else
+#endif
+ if (!PyString_Check(name)){
PyErr_SetString(PyExc_TypeError,
"attribute name must be string");
return -1;
diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index e2682a0..a8e063e 100644
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -173,8 +173,14 @@
goto onError;
}
- if (encoding == NULL)
+ if (encoding == NULL) {
+#ifdef Py_USING_UNICODE
encoding = PyUnicode_GetDefaultEncoding();
+#else
+ PyErr_SetString(PyExc_ValueError, "no encoding specified");
+ goto onError;
+#endif
+ }
/* Decode via the codec registry */
v = PyCodec_Decode(str, encoding, errors);
@@ -197,6 +203,7 @@
if (v == NULL)
goto onError;
+#ifdef Py_USING_UNICODE
/* Convert Unicode to a string using the default encoding */
if (PyUnicode_Check(v)) {
PyObject *temp = v;
@@ -205,6 +212,7 @@
if (v == NULL)
goto onError;
}
+#endif
if (!PyString_Check(v)) {
PyErr_Format(PyExc_TypeError,
"decoder did not return a string object (type=%.400s)",
@@ -245,8 +253,14 @@
goto onError;
}
- if (encoding == NULL)
+ if (encoding == NULL) {
+#ifdef Py_USING_UNICODE
encoding = PyUnicode_GetDefaultEncoding();
+#else
+ PyErr_SetString(PyExc_ValueError, "no encoding specified");
+ goto onError;
+#endif
+ }
/* Encode via the codec registry */
v = PyCodec_Encode(str, encoding, errors);
@@ -269,6 +283,7 @@
if (v == NULL)
goto onError;
+#ifdef Py_USING_UNICODE
/* Convert Unicode to a string using the default encoding */
if (PyUnicode_Check(v)) {
PyObject *temp = v;
@@ -277,6 +292,7 @@
if (v == NULL)
goto onError;
}
+#endif
if (!PyString_Check(v)) {
PyErr_Format(PyExc_TypeError,
"encoder did not return a string object (type=%.400s)",
@@ -344,12 +360,15 @@
}
if (!PyString_Check(obj)) {
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(obj)) {
obj = _PyUnicode_AsDefaultEncodedString(obj, NULL);
if (obj == NULL)
return -1;
}
- else {
+ else
+#endif
+ {
PyErr_Format(PyExc_TypeError,
"expected string or Unicode object, "
"%.200s found", obj->ob_type->tp_name);
@@ -477,8 +496,10 @@
register unsigned int size;
register PyStringObject *op;
if (!PyString_Check(bb)) {
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(bb))
return PyUnicode_Concat((PyObject *)a, bb);
+#endif
PyErr_Format(PyExc_TypeError,
"cannot add type \"%.200s\" to string",
bb->ob_type->tp_name);
@@ -586,8 +607,10 @@
{
register char *s, *end;
register char c;
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(el))
return PyUnicode_Contains(a, el);
+#endif
if (!PyString_Check(el) || PyString_Size(el) != 1) {
PyErr_SetString(PyExc_TypeError,
"'in <string>' requires character as left operand");
@@ -868,8 +891,10 @@
sub = PyString_AS_STRING(subobj);
n = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj))
return PyUnicode_Split((PyObject *)self, subobj, maxsplit);
+#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &n))
return NULL;
if (n == 0) {
@@ -969,6 +994,7 @@
const size_t old_sz = sz;
item = PySequence_Fast_GET_ITEM(seq, i);
if (!PyString_Check(item)){
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(item)) {
/* Defer to Unicode join.
* CAUTION: There's no gurantee that the
@@ -980,6 +1006,7 @@
Py_DECREF(seq);
return result;
}
+#endif
PyErr_Format(PyExc_TypeError,
"sequence item %i: expected string,"
" %.80s found",
@@ -1046,8 +1073,10 @@
sub = PyString_AS_STRING(subobj);
n = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj))
return PyUnicode_Find((PyObject *)self, subobj, i, last, 1);
+#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &n))
return -2;
@@ -1381,6 +1410,7 @@
sub = PyString_AS_STRING(subobj);
n = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj)) {
int count;
count = PyUnicode_Count((PyObject *)self, subobj, i, last);
@@ -1389,6 +1419,7 @@
else
return PyInt_FromLong((long) count);
}
+#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &n))
return NULL;
@@ -1481,6 +1512,7 @@
table1 = PyString_AS_STRING(tableobj);
tablen = PyString_GET_SIZE(tableobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(tableobj)) {
/* Unicode .translate() does not support the deletechars
parameter; instead a mapping to None will cause characters
@@ -1492,6 +1524,7 @@
}
return PyUnicode_Translate((PyObject *)self, tableobj, NULL);
}
+#endif
else if (PyObject_AsCharBuffer(tableobj, &table1, &tablen))
return NULL;
@@ -1500,11 +1533,13 @@
del_table = PyString_AS_STRING(delobj);
dellen = PyString_GET_SIZE(delobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(delobj)) {
PyErr_SetString(PyExc_TypeError,
"deletions are implemented differently for unicode");
return NULL;
}
+#endif
else if (PyObject_AsCharBuffer(delobj, &del_table, &dellen))
return NULL;
@@ -1729,9 +1764,11 @@
sub = PyString_AS_STRING(subobj);
sub_len = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj))
return PyUnicode_Replace((PyObject *)self,
subobj, replobj, count);
+#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &sub_len))
return NULL;
@@ -1739,9 +1776,11 @@
repl = PyString_AS_STRING(replobj);
repl_len = PyString_GET_SIZE(replobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(replobj))
return PyUnicode_Replace((PyObject *)self,
subobj, replobj, count);
+#endif
else if (PyObject_AsCharBuffer(replobj, &repl, &repl_len))
return NULL;
@@ -1792,6 +1831,7 @@
prefix = PyString_AS_STRING(subobj);
plen = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj)) {
int rc;
rc = PyUnicode_Tailmatch((PyObject *)self,
@@ -1801,6 +1841,7 @@
else
return PyInt_FromLong((long) rc);
}
+#endif
else if (PyObject_AsCharBuffer(subobj, &prefix, &plen))
return NULL;
@@ -1850,6 +1891,7 @@
suffix = PyString_AS_STRING(subobj);
slen = PyString_GET_SIZE(subobj);
}
+#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(subobj)) {
int rc;
rc = PyUnicode_Tailmatch((PyObject *)self,
@@ -1859,6 +1901,7 @@
else
return PyInt_FromLong((long) rc);
}
+#endif
else if (PyObject_AsCharBuffer(subobj, &suffix, &slen))
return NULL;
@@ -2876,7 +2919,10 @@
char *fmt, *res;
int fmtcnt, rescnt, reslen, arglen, argidx;
int args_owned = 0;
- PyObject *result, *orig_args, *v, *w;
+ PyObject *result, *orig_args;
+#ifdef Py_USING_UNICODE
+ PyObject *v, *w;
+#endif
PyObject *dict = NULL;
if (format == NULL || !PyString_Check(format) || args == NULL) {
PyErr_BadInternalCall();
@@ -2926,8 +2972,10 @@
int sign;
int len;
char formatbuf[FORMATBUFLEN]; /* For format{float,int,char}() */
+#ifdef Py_USING_UNICODE
char *fmt_start = fmt;
int argidx_start = argidx;
+#endif
fmt++;
if (*fmt == '(') {
@@ -3078,11 +3126,13 @@
break;
case 's':
case 'r':
+#ifdef Py_USING_UNICODE
if (PyUnicode_Check(v)) {
fmt = fmt_start;
argidx = argidx_start;
goto unicode;
}
+#endif
if (c == 's')
temp = PyObject_Str(v);
else
@@ -3240,6 +3290,7 @@
_PyString_Resize(&result, reslen - rescnt);
return result;
+#ifdef Py_USING_UNICODE
unicode:
if (args_owned) {
Py_DECREF(args);
@@ -3284,6 +3335,7 @@
Py_DECREF(v);
Py_DECREF(args);
return w;
+#endif /* Py_USING_UNICODE */
error:
Py_DECREF(result);