replace_interleave(PyStringObject *self,
const char *to_s, Py_ssize_t to_len,
Py_ssize_t maxcount)
{
char *self_s, *result_s;
Py_ssize_t self_len, result_len;
Py_ssize_t count, i, product;
PyStringObject *result;
self_len = PyString_GET_SIZE(self);
/* 1 at the end plus 1 after every character */
count = self_len+1;
if (maxcount < count)
count = maxcount;
/* Check for overflow */
/* result_len = count * to_len + self_len; */
product = count * to_len;
if (product / to_len != count) {
PyErr_SetString(PyExc_OverflowError,
"replace string is too long");
return NULL;
}
result_len = product + self_len;
if (result_len < 0) {
PyErr_SetString(PyExc_OverflowError,
"replace string is too long");
return NULL;
}
if (! (result = (PyStringObject *)
PyString_FromStringAndSize(NULL, result_len)) )
return NULL;
self_s = PyString_AS_STRING(self);
result_s = PyString_AS_STRING(result);
/* TODO: special case single character, which doesn't need memcpy */
/* Lay the first one down (guaranteed this will occur) */
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
count -= 1;
for (i=0; i<count; i++) {
*result_s++ = *self_s++;
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
}
/* Copy the rest of the original string */
Py_MEMCPY(result_s, self_s, self_len-i);
return result;
}
PyObject* string_repeat(register PyStringObject *a, register Py_ssize_t n)
{
register Py_ssize_t i;
register Py_ssize_t j;
register Py_ssize_t size;
register PyStringObject *op;
size_t nbytes;
if (n < 0)
n = 0;
/* watch out for overflows: the size can overflow int,
* and the # of bytes needed can overflow size_t
*/
size = Py_SIZE(a) * n;
if (n && size / n != Py_SIZE(a)) {
PyErr_SetString(PyExc_OverflowError,
"repeated string is too long");
return NULL;
}
if (size == Py_SIZE(a) && PyString_CheckExact(a)) {
Py_INCREF(a);
return (PyObject *)a;
}
nbytes = (size_t)size;
if (nbytes + PyStringObject_SIZE <= nbytes) {
PyErr_SetString(PyExc_OverflowError,
"repeated string is too long");
return NULL;
}
op = (PyStringObject *)PyObject_MALLOC(PyStringObject_SIZE + nbytes);
if (op == NULL)
return PyErr_NoMemory();
PyObject_INIT_VAR(op, &PyString_Type, size);
op->ob_shash = -1;
op->ob_sstate = SSTATE_NOT_INTERNED;
op->ob_sval[size] = '\0';
if (Py_SIZE(a) == 1 && n > 0) {
memset(op->ob_sval, a->ob_sval[0] , n);
return (PyObject *) op;
}
i = 0;
if (i < size) {
Py_MEMCPY(op->ob_sval, a->ob_sval, Py_SIZE(a));
i = Py_SIZE(a);
}
while (i < size) {
j = (i <= size-i) ? i : size-i;
Py_MEMCPY(op->ob_sval+i, op->ob_sval, j);
i += j;
}
return (PyObject *) op;
}
replace_substring_in_place(PyStringObject *self,
const char *from_s, Py_ssize_t from_len,
const char *to_s, Py_ssize_t to_len,
Py_ssize_t maxcount)
{
char *result_s, *start, *end;
char *self_s;
Py_ssize_t self_len, offset;
PyStringObject *result;
/* The result string will be the same size */
self_s = PyString_AS_STRING(self);
self_len = PyString_GET_SIZE(self);
offset = stringlib_find(self_s, self_len,
from_s, from_len,
0);
if (offset == -1) {
/* No matches; return the original string */
return return_self(self);
}
/* Need to make a new string */
result = (PyStringObject *) PyString_FromStringAndSize(NULL, self_len);
if (result == NULL)
return NULL;
result_s = PyString_AS_STRING(result);
Py_MEMCPY(result_s, self_s, self_len);
/* change everything in-place, starting with this one */
start = result_s + offset;
Py_MEMCPY(start, to_s, from_len);
start += from_len;
end = result_s + self_len;
while ( --maxcount > 0) {
offset = stringlib_find(start, end-start,
from_s, from_len,
0);
if (offset==-1)
break;
Py_MEMCPY(start+offset, to_s, from_len);
start += offset+from_len;
}
return result;
}
replace_delete_substring(PyStringObject *self,
const char *from_s, Py_ssize_t from_len,
Py_ssize_t maxcount) {
char *self_s, *result_s;
char *start, *next, *end;
Py_ssize_t self_len, result_len;
Py_ssize_t count, offset;
PyStringObject *result;
self_len = PyString_GET_SIZE(self);
self_s = PyString_AS_STRING(self);
count = stringlib_count(self_s, self_len,
from_s, from_len,
maxcount);
if (count == 0) {
/* no matches */
return return_self(self);
}
result_len = self_len - (count * from_len);
assert (result_len>=0);
if ( (result = (PyStringObject *)
PyString_FromStringAndSize(NULL, result_len)) == NULL )
return NULL;
result_s = PyString_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
offset = stringlib_find(start, end-start,
from_s, from_len,
0);
if (offset == -1)
break;
next = start + offset;
Py_MEMCPY(result_s, start, next-start);
result_s += (next-start);
start = next+from_len;
}
Py_MEMCPY(result_s, start, end-start);
return result;
}
replace_delete_single_character(PyStringObject *self,
char from_c, Py_ssize_t maxcount)
{
char *self_s, *result_s;
char *start, *next, *end;
Py_ssize_t self_len, result_len;
Py_ssize_t count;
PyStringObject *result;
self_len = PyString_GET_SIZE(self);
self_s = PyString_AS_STRING(self);
count = countchar(self_s, self_len, from_c, maxcount);
if (count == 0) {
return return_self(self);
}
result_len = self_len - count; /* from_len == 1 */
assert(result_len>=0);
if ( (result = (PyStringObject *)
PyString_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyString_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
next = findchar(start, end-start, from_c);
if (next == NULL)
break;
Py_MEMCPY(result_s, start, next-start);
result_s += (next-start);
start = next+1;
}
Py_MEMCPY(result_s, start, end-start);
return result;
}
void
_Py_bytes_upper(char *result, const char *cptr, Py_ssize_t len)
{
Py_ssize_t i;
Py_MEMCPY(result, cptr, len);
for (i = 0; i < len; i++) {
int c = Py_CHARMASK(result[i]);
if (Py_ISLOWER(c))
result[i] = Py_TOUPPER(c);
}
}
static PyObject *get_id(PyObject *obj, void *arg)
{
PyObject *buffer, *item, *result=NULL;
Py_ssize_t i, n, size;
char *p;
buffer = PyList_New(0);
if (buffer == NULL)
return NULL;
if (generate_id(Node(obj), buffer) < 0)
goto finally;
n = PyList_GET_SIZE(buffer);
if (n == 1) {
result = PyList_GET_ITEM(buffer, 0);
Py_INCREF(result);
} else {
for (size = 0, i = 0; i < n; i++) {
item = PyList_GET_ITEM(buffer, i);
if (!PyString_Check(item)) {
PyErr_Format(PyExc_TypeError,
"sequence item %zd: expected string, %s found",
i, item->ob_type->tp_name);
goto finally;
}
size += PyString_GET_SIZE(item);
if (size < 0 || size > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError,
"join() result is too long for a Python string");
goto finally;
}
}
result = PyString_FromStringAndSize(NULL, size);
if (result == NULL)
goto finally;
p = PyString_AS_STRING(result);
for (i = 0; i < n; i++) {
item = PyList_GET_ITEM(buffer, i);
size = PyString_GET_SIZE(item);
Py_MEMCPY(p, PyString_AS_STRING(item), size);
p += size;
}
}
finally:
Py_DECREF(buffer);
return result;
}
replace_single_character_in_place(PyStringObject *self,
char from_c, char to_c,
Py_ssize_t maxcount)
{
char *self_s, *result_s, *start, *end, *next;
Py_ssize_t self_len;
PyStringObject *result;
/* The result string will be the same size */
self_s = PyString_AS_STRING(self);
self_len = PyString_GET_SIZE(self);
next = findchar(self_s, self_len, from_c);
if (next == NULL) {
/* No matches; return the original string */
return return_self(self);
}
/* Need to make a new string */
result = (PyStringObject *) PyString_FromStringAndSize(NULL, self_len);
if (result == NULL)
return NULL;
result_s = PyString_AS_STRING(result);
Py_MEMCPY(result_s, self_s, self_len);
/* change everything in-place, starting with this one */
start = result_s + (next-self_s);
*start = to_c;
start++;
end = result_s + self_len;
while (--maxcount > 0) {
next = findchar(start, end-start, from_c);
if (next == NULL)
break;
*next = to_c;
start = next+1;
}
return result;
}
void
_Py_bytes_upper(char *result, const char *cptr, Py_ssize_t len)
{
Py_ssize_t i;
/*
newobj = PyString_FromStringAndSize(NULL, len);
if (!newobj)
return NULL;
s = PyString_AS_STRING(newobj);
*/
Py_MEMCPY(result, cptr, len);
for (i = 0; i < len; i++) {
int c = Py_CHARMASK(result[i]);
if (Py_ISLOWER(c))
result[i] = Py_TOUPPER(c);
}
}
/* Sets an exception and returns NULL if out of memory. */
static const char *
walk_here_statement(const char *start, const char *p, const char *end)
{
char *end_here, *temp_string;
++p;
/* DEBUG("starting here processing for COMMAND for level 2 at p == '%.10s'",
* p); */
if (p >= end) {
fprintf(stderr, "bailing\n");
return p;
}
if ('<' == *p) {
/* d2printf("correction, it's a third level here. Handing back to "
* "command parsing\n"); */
return ++p;
}
while (p < end && (isspace(*p) || '-' == *p))
++p;
if ('\'' == *p || '"' == *p) {
end_here = (char *)walk_statement_no_parsing(p + 1, end, *p);
++p;
} else {
end_here = (char *)walk_command_complex(start, p, end,
' ', SPACE_PARSING);
if (!end_here)
return NULL;
}
/* INFO("end_here=%.5s",end_here); */
temp_string = malloc(end_here -p + 1);
if (!temp_string) {
PyErr_NoMemory();
return NULL;
}
int here_len = end_here - p;
Py_MEMCPY(temp_string, p, here_len);
temp_string[here_len] = '\0';
/* d2printf("matched len('%zi')/'%s' for a here word\n", end_here - p,
* temp_string); */
/* XXX watch this. potential for horkage. need to do the quote
removal thing.
this sucks.
*/
++end_here;
if (end_here >= end) {
free(temp_string);
return end_here;
}
end_here = (char *)bmh_search((unsigned char*)temp_string,
(unsigned char*)end_here, end - end_here);
while(end_here) {
char *i = end_here + here_len;
if (';' == *i || '\n' == *i || '\r' == *i) {
i = end_here - 1;
while (i != p && ('\t' == *i || ' ' == *i))
--i;
if (i != p && '\n' == *i)
break;
}
end_here = (char *)bmh_search((unsigned char*)temp_string,
(unsigned char*)(end_here + here_len),
end - end_here - here_len);
}
INFO("bmh returned %p", end_here);
free(temp_string);
if (!end_here) {
return end;
}
/* d2printf("bmh = %.10s\n", end_here); */
return end_here + here_len;
}
replace_substring(PyStringObject *self,
const char *from_s, Py_ssize_t from_len,
const char *to_s, Py_ssize_t to_len,
Py_ssize_t maxcount) {
char *self_s, *result_s;
char *start, *next, *end;
Py_ssize_t self_len, result_len;
Py_ssize_t count, offset, product;
PyStringObject *result;
self_s = PyString_AS_STRING(self);
self_len = PyString_GET_SIZE(self);
count = stringlib_count(self_s, self_len,
from_s, from_len,
maxcount);
if (count == 0) {
/* no matches, return unchanged */
return return_self(self);
}
/* Check for overflow */
/* result_len = self_len + count * (to_len-from_len) */
product = count * (to_len-from_len);
if (product / (to_len-from_len) != count) {
PyErr_SetString(PyExc_OverflowError, "replace string is too long");
return NULL;
}
result_len = self_len + product;
if (result_len < 0) {
PyErr_SetString(PyExc_OverflowError, "replace string is too long");
return NULL;
}
if ( (result = (PyStringObject *)
PyString_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyString_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
offset = stringlib_find(start, end-start,
from_s, from_len,
0);
if (offset == -1)
break;
next = start+offset;
if (next == start) {
/* replace with the 'to' */
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
start += from_len;
} else {
/* copy the unchanged old then the 'to' */
Py_MEMCPY(result_s, start, next-start);
result_s += (next-start);
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
start = next+from_len;
}
}
/* Copy the remainder of the remaining string */
Py_MEMCPY(result_s, start, end-start);
return result;
}
replace_single_character(PyStringObject *self,
char from_c,
const char *to_s, Py_ssize_t to_len,
Py_ssize_t maxcount)
{
char *self_s, *result_s;
char *start, *next, *end;
Py_ssize_t self_len, result_len;
Py_ssize_t count, product;
PyStringObject *result;
self_s = PyString_AS_STRING(self);
self_len = PyString_GET_SIZE(self);
count = countchar(self_s, self_len, from_c, maxcount);
if (count == 0) {
/* no matches, return unchanged */
return return_self(self);
}
/* use the difference between current and new, hence the "-1" */
/* result_len = self_len + count * (to_len-1) */
product = count * (to_len-1);
if (product / (to_len-1) != count) {
PyErr_SetString(PyExc_OverflowError, "replace string is too long");
return NULL;
}
result_len = self_len + product;
if (result_len < 0) {
PyErr_SetString(PyExc_OverflowError, "replace string is too long");
return NULL;
}
if ( (result = (PyStringObject *)
PyString_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyString_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
next = findchar(start, end-start, from_c);
if (next == NULL)
break;
if (next == start) {
/* replace with the 'to' */
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
start += 1;
} else {
/* copy the unchanged old then the 'to' */
Py_MEMCPY(result_s, start, next-start);
result_s += (next-start);
Py_MEMCPY(result_s, to_s, to_len);
result_s += to_len;
start = next+1;
}
}
/* Copy the remainder of the remaining string */
Py_MEMCPY(result_s, start, end-start);
return result;
}
PyObject *string_join(PyStringObject *self, PyObject *orig)
{
char *sep = PyString_AS_STRING(self);
const Py_ssize_t seplen = PyString_GET_SIZE(self);
PyObject *res = NULL;
char *p;
Py_ssize_t seqlen = 0;
size_t sz = 0;
Py_ssize_t i;
PyObject *seq, *item;
seq = PySequence_Fast(orig, "");
if (seq == NULL) {
return NULL;
}
seqlen = PySequence_Size(seq);
if (seqlen == 0) {
Py_DECREF(seq);
return PyString_FromString("");
}
if (seqlen == 1) {
item = PySequence_Fast_GET_ITEM(seq, 0);
if (PyString_CheckExact(item) || PyUnicode_CheckExact(item)) {
Py_INCREF(item);
Py_DECREF(seq);
return item;
}
}
/* There are at least two things to join, or else we have a subclass
* of the builtin types in the sequence.
* Do a pre-pass to figure out the total amount of space we'll
* need (sz), see whether any argument is absurd, and defer to
* the Unicode join if appropriate.
*/
for (i = 0; i < seqlen; i++) {
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
* original sequence can be iterated over
* again, so we must pass seq here.
*/
PyObject *result;
result = PyUnicode_Join((PyObject *)self, seq);
Py_DECREF(seq);
return result;
}
#endif
PyErr_Format(PyExc_TypeError,
"sequence item %zd: expected string,"
" %.80s found",
i, Py_TYPE(item)->tp_name);
Py_DECREF(seq);
return NULL;
}
sz += PyString_GET_SIZE(item);
if (i != 0)
sz += seplen;
if (sz < old_sz || sz > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError,
"join() result is too long for a Python string");
Py_DECREF(seq);
return NULL;
}
}
/* Allocate result space. */
res = PyString_FromStringAndSize((char*)NULL, sz);
if (res == NULL) {
Py_DECREF(seq);
return NULL;
}
/* Catenate everything. */
p = PyString_AS_STRING(res);
for (i = 0; i < seqlen; ++i) {
size_t n;
item = PySequence_Fast_GET_ITEM(seq, i);
n = PyString_GET_SIZE(item);
Py_MEMCPY(p, PyString_AS_STRING(item), n);
p += n;
if (i < seqlen - 1) {
Py_MEMCPY(p, sep, seplen);
p += seplen;
}
}
Py_DECREF(seq);
return res;
}
PyObject *
Bytes_Format(PyObject *format, PyObject *args)
{
char *fmt, *res;
Py_ssize_t arglen, argidx;
Py_ssize_t reslen, rescnt, fmtcnt;
int args_owned = 0;
PyObject *result;
PyObject *dict = NULL;
if (format == NULL || !Bytes_Check(format) || args == NULL) {
PyErr_BadInternalCall();
return NULL;
}
fmt = Bytes_AS_STRING(format);
fmtcnt = Bytes_GET_SIZE(format);
reslen = rescnt = fmtcnt + 100;
result = Bytes_FromStringAndSize((char *)NULL, reslen);
if (result == NULL)
return NULL;
res = Bytes_AsString(result);
if (PyTuple_Check(args)) {
arglen = PyTuple_GET_SIZE(args);
argidx = 0;
}
else {
arglen = -1;
argidx = -2;
}
if (Py_TYPE(args)->tp_as_mapping && !PyTuple_Check(args) &&
!PyObject_TypeCheck(args, &Bytes_Type))
dict = args;
while (--fmtcnt >= 0) {
if (*fmt != '%') {
if (--rescnt < 0) {
rescnt = fmtcnt + 100;
reslen += rescnt;
if (_Bytes_Resize(&result, reslen))
return NULL;
res = Bytes_AS_STRING(result)
+ reslen - rescnt;
--rescnt;
}
*res++ = *fmt++;
}
else {
/* Got a format specifier */
Py_ssize_t width = -1;
int c = '\0';
PyObject *v = NULL;
PyObject *temp = NULL;
char *pbuf;
Py_ssize_t len;
fmt++;
if (*fmt == '(') {
char *keystart;
Py_ssize_t keylen;
PyObject *key;
int pcount = 1;
if (dict == NULL) {
PyErr_SetString(PyExc_TypeError,
"format requires a mapping");
goto error;
}
++fmt;
--fmtcnt;
keystart = fmt;
/* Skip over balanced parentheses */
while (pcount > 0 && --fmtcnt >= 0) {
if (*fmt == ')')
--pcount;
else if (*fmt == '(')
++pcount;
fmt++;
}
keylen = fmt - keystart - 1;
if (fmtcnt < 0 || pcount > 0) {
PyErr_SetString(PyExc_ValueError,
"incomplete format key");
goto error;
}
key = Text_FromUTF8AndSize(keystart, keylen);
if (key == NULL)
goto error;
if (args_owned) {
Py_DECREF(args);
args_owned = 0;
}
args = PyObject_GetItem(dict, key);
Py_DECREF(key);
if (args == NULL) {
goto error;
}
args_owned = 1;
arglen = -1;
argidx = -2;
}
while (--fmtcnt >= 0) {
c = *fmt++;
break;
}
if (fmtcnt < 0) {
PyErr_SetString(PyExc_ValueError,
"incomplete format");
goto error;
}
if (c != '%') {
v = getnextarg(args, arglen, &argidx);
if (v == NULL)
goto error;
}
switch (c) {
case '%':
pbuf = "%";
len = 1;
break;
case 's':
/* only bytes! */
if (!Bytes_CheckExact(v)) {
PyErr_Format(PyExc_ValueError,
"only bytes values expected, got %s",
Py_TYPE(v)->tp_name);
goto error;
}
temp = v;
Py_INCREF(v);
pbuf = Bytes_AS_STRING(temp);
len = Bytes_GET_SIZE(temp);
break;
default:
PyErr_Format(PyExc_ValueError,
"unsupported format character '%c' (0x%x) "
"at index " FORMAT_CODE_PY_SSIZE_T,
c, c,
(Py_ssize_t)(fmt - 1 -
Bytes_AsString(format)));
goto error;
}
if (width < len)
width = len;
if (rescnt < width) {
reslen -= rescnt;
rescnt = width + fmtcnt + 100;
reslen += rescnt;
if (reslen < 0) {
Py_DECREF(result);
Py_XDECREF(temp);
return PyErr_NoMemory();
}
if (_Bytes_Resize(&result, reslen)) {
Py_XDECREF(temp);
return NULL;
}
res = Bytes_AS_STRING(result)
+ reslen - rescnt;
}
Py_MEMCPY(res, pbuf, len);
res += len;
rescnt -= len;
while (--width >= len) {
--rescnt;
*res++ = ' ';
}
if (dict && (argidx < arglen) && c != '%') {
PyErr_SetString(PyExc_TypeError,
"not all arguments converted during string formatting");
Py_XDECREF(temp);
goto error;
}
Py_XDECREF(temp);
} /* '%' */
} /* until end */
if (argidx < arglen && !dict) {
PyErr_SetString(PyExc_TypeError,
"not all arguments converted during string formatting");
goto error;
}
if (args_owned) {
Py_DECREF(args);
}
if (_Bytes_Resize(&result, reslen - rescnt))
return NULL;
return result;
error:
Py_DECREF(result);
if (args_owned) {
Py_DECREF(args);
}
return NULL;
}