cpython/Objects/bytearrayobject.c

3320 lines
94 KiB
C
Raw Normal View History

/* PyByteArray (bytearray) implementation */
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "structmember.h"
#include "bytes_methods.h"
static PyByteArrayObject *nullbytes = NULL;
void
PyByteArray_Fini(void)
{
Py_CLEAR(nullbytes);
}
int
PyByteArray_Init(void)
{
nullbytes = PyObject_New(PyByteArrayObject, &PyByteArray_Type);
if (nullbytes == NULL)
return 0;
nullbytes->ob_bytes = NULL;
Py_SIZE(nullbytes) = nullbytes->ob_alloc = 0;
nullbytes->ob_exports = 0;
return 1;
}
/* end nullbytes support */
/* Helpers */
static int
_getbytevalue(PyObject* arg, int *value)
{
long face_value;
if (PyLong_Check(arg)) {
face_value = PyLong_AsLong(arg);
} else {
PyObject *index = PyNumber_Index(arg);
if (index == NULL) {
PyErr_Format(PyExc_TypeError, "an integer is required");
return 0;
}
face_value = PyLong_AsLong(index);
Py_DECREF(index);
}
if (face_value < 0 || face_value >= 256) {
/* this includes the OverflowError in case the long is too large */
PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
return 0;
}
*value = face_value;
return 1;
}
static int
bytes_getbuffer(PyByteArrayObject *obj, Py_buffer *view, int flags)
{
int ret;
void *ptr;
if (view == NULL) {
obj->ob_exports++;
return 0;
}
if (obj->ob_bytes == NULL)
ptr = "";
else
ptr = obj->ob_bytes;
ret = PyBuffer_FillInfo(view, (PyObject*)obj, ptr, Py_SIZE(obj), 0, flags);
if (ret >= 0) {
obj->ob_exports++;
}
return ret;
}
static void
bytes_releasebuffer(PyByteArrayObject *obj, Py_buffer *view)
{
obj->ob_exports--;
}
static Py_ssize_t
_getbuffer(PyObject *obj, Py_buffer *view)
{
PyBufferProcs *buffer = Py_TYPE(obj)->tp_as_buffer;
if (buffer == NULL || buffer->bf_getbuffer == NULL)
{
PyErr_Format(PyExc_TypeError,
"Type %.100s doesn't support the buffer API",
Py_TYPE(obj)->tp_name);
return -1;
}
if (buffer->bf_getbuffer(obj, view, PyBUF_SIMPLE) < 0)
return -1;
return view->len;
}
/* Direct API functions */
PyObject *
PyByteArray_FromObject(PyObject *input)
{
return PyObject_CallFunctionObjArgs((PyObject *)&PyByteArray_Type,
input, NULL);
}
PyObject *
PyByteArray_FromStringAndSize(const char *bytes, Py_ssize_t size)
{
PyByteArrayObject *new;
Py_ssize_t alloc;
if (size < 0) {
PyErr_SetString(PyExc_SystemError,
"Negative size passed to PyByteArray_FromStringAndSize");
return NULL;
}
/* Prevent buffer overflow when setting alloc to size+1. */
if (size == PY_SSIZE_T_MAX) {
return PyErr_NoMemory();
}
new = PyObject_New(PyByteArrayObject, &PyByteArray_Type);
if (new == NULL)
return NULL;
if (size == 0) {
new->ob_bytes = NULL;
alloc = 0;
}
else {
alloc = size + 1;
new->ob_bytes = PyMem_Malloc(alloc);
if (new->ob_bytes == NULL) {
Py_DECREF(new);
return PyErr_NoMemory();
}
if (bytes != NULL)
memcpy(new->ob_bytes, bytes, size);
new->ob_bytes[size] = '\0'; /* Trailing null byte */
}
Py_SIZE(new) = size;
new->ob_alloc = alloc;
new->ob_exports = 0;
return (PyObject *)new;
}
Py_ssize_t
PyByteArray_Size(PyObject *self)
{
assert(self != NULL);
assert(PyByteArray_Check(self));
return PyByteArray_GET_SIZE(self);
}
char *
PyByteArray_AsString(PyObject *self)
{
assert(self != NULL);
assert(PyByteArray_Check(self));
return PyByteArray_AS_STRING(self);
}
int
PyByteArray_Resize(PyObject *self, Py_ssize_t size)
{
void *sval;
Py_ssize_t alloc = ((PyByteArrayObject *)self)->ob_alloc;
assert(self != NULL);
assert(PyByteArray_Check(self));
assert(size >= 0);
if (size < alloc / 2) {
/* Major downsize; resize down to exact size */
alloc = size + 1;
}
else if (size < alloc) {
/* Within allocated size; quick exit */
Py_SIZE(self) = size;
((PyByteArrayObject *)self)->ob_bytes[size] = '\0'; /* Trailing null */
return 0;
}
else if (size <= alloc * 1.125) {
/* Moderate upsize; overallocate similar to list_resize() */
alloc = size + (size >> 3) + (size < 9 ? 3 : 6);
}
else {
/* Major upsize; resize up to exact size */
alloc = size + 1;
}
if (((PyByteArrayObject *)self)->ob_exports > 0) {
/*
fprintf(stderr, "%d: %s", ((PyByteArrayObject *)self)->ob_exports,
((PyByteArrayObject *)self)->ob_bytes);
*/
PyErr_SetString(PyExc_BufferError,
"Existing exports of data: object cannot be re-sized");
return -1;
}
sval = PyMem_Realloc(((PyByteArrayObject *)self)->ob_bytes, alloc);
if (sval == NULL) {
PyErr_NoMemory();
return -1;
}
((PyByteArrayObject *)self)->ob_bytes = sval;
Py_SIZE(self) = size;
((PyByteArrayObject *)self)->ob_alloc = alloc;
((PyByteArrayObject *)self)->ob_bytes[size] = '\0'; /* Trailing null byte */
return 0;
}
PyObject *
PyByteArray_Concat(PyObject *a, PyObject *b)
{
Py_ssize_t size;
Py_buffer va, vb;
PyByteArrayObject *result = NULL;
va.len = -1;
vb.len = -1;
if (_getbuffer(a, &va) < 0 ||
_getbuffer(b, &vb) < 0) {
PyErr_Format(PyExc_TypeError, "can't concat %.100s to %.100s",
Py_TYPE(a)->tp_name, Py_TYPE(b)->tp_name);
goto done;
}
size = va.len + vb.len;
if (size < 0) {
return PyErr_NoMemory();
goto done;
}
result = (PyByteArrayObject *) PyByteArray_FromStringAndSize(NULL, size);
if (result != NULL) {
memcpy(result->ob_bytes, va.buf, va.len);
memcpy(result->ob_bytes + va.len, vb.buf, vb.len);
}
done:
if (va.len != -1)
PyBuffer_Release(&va);
if (vb.len != -1)
PyBuffer_Release(&vb);
return (PyObject *)result;
}
/* Functions stuffed into the type object */
static Py_ssize_t
bytes_length(PyByteArrayObject *self)
{
return Py_SIZE(self);
}
static PyObject *
bytes_iconcat(PyByteArrayObject *self, PyObject *other)
{
Py_ssize_t mysize;
Py_ssize_t size;
Py_buffer vo;
if (_getbuffer(other, &vo) < 0) {
PyErr_Format(PyExc_TypeError, "can't concat %.100s to %.100s",
Py_TYPE(other)->tp_name, Py_TYPE(self)->tp_name);
return NULL;
}
mysize = Py_SIZE(self);
size = mysize + vo.len;
if (size < 0) {
PyBuffer_Release(&vo);
return PyErr_NoMemory();
}
if (size < self->ob_alloc) {
Py_SIZE(self) = size;
self->ob_bytes[Py_SIZE(self)] = '\0'; /* Trailing null byte */
}
else if (PyByteArray_Resize((PyObject *)self, size) < 0) {
PyBuffer_Release(&vo);
return NULL;
}
memcpy(self->ob_bytes + mysize, vo.buf, vo.len);
PyBuffer_Release(&vo);
Py_INCREF(self);
return (PyObject *)self;
}
static PyObject *
bytes_repeat(PyByteArrayObject *self, Py_ssize_t count)
{
PyByteArrayObject *result;
Py_ssize_t mysize;
Py_ssize_t size;
if (count < 0)
count = 0;
mysize = Py_SIZE(self);
size = mysize * count;
if (count != 0 && size / count != mysize)
return PyErr_NoMemory();
result = (PyByteArrayObject *)PyByteArray_FromStringAndSize(NULL, size);
if (result != NULL && size != 0) {
if (mysize == 1)
memset(result->ob_bytes, self->ob_bytes[0], size);
else {
Py_ssize_t i;
for (i = 0; i < count; i++)
memcpy(result->ob_bytes + i*mysize, self->ob_bytes, mysize);
}
}
return (PyObject *)result;
}
static PyObject *
bytes_irepeat(PyByteArrayObject *self, Py_ssize_t count)
{
Py_ssize_t mysize;
Py_ssize_t size;
if (count < 0)
count = 0;
mysize = Py_SIZE(self);
size = mysize * count;
if (count != 0 && size / count != mysize)
return PyErr_NoMemory();
if (size < self->ob_alloc) {
Py_SIZE(self) = size;
self->ob_bytes[Py_SIZE(self)] = '\0'; /* Trailing null byte */
}
else if (PyByteArray_Resize((PyObject *)self, size) < 0)
return NULL;
if (mysize == 1)
memset(self->ob_bytes, self->ob_bytes[0], size);
else {
Py_ssize_t i;
for (i = 1; i < count; i++)
memcpy(self->ob_bytes + i*mysize, self->ob_bytes, mysize);
}
Py_INCREF(self);
return (PyObject *)self;
}
static PyObject *
bytes_getitem(PyByteArrayObject *self, Py_ssize_t i)
{
if (i < 0)
i += Py_SIZE(self);
if (i < 0 || i >= Py_SIZE(self)) {
PyErr_SetString(PyExc_IndexError, "bytearray index out of range");
return NULL;
}
return PyLong_FromLong((unsigned char)(self->ob_bytes[i]));
}
static PyObject *
bytes_subscript(PyByteArrayObject *self, PyObject *index)
{
if (PyIndex_Check(index)) {
Py_ssize_t i = PyNumber_AsSsize_t(index, PyExc_IndexError);
if (i == -1 && PyErr_Occurred())
return NULL;
if (i < 0)
i += PyByteArray_GET_SIZE(self);
if (i < 0 || i >= Py_SIZE(self)) {
PyErr_SetString(PyExc_IndexError, "bytearray index out of range");
return NULL;
}
return PyLong_FromLong((unsigned char)(self->ob_bytes[i]));
}
else if (PySlice_Check(index)) {
Py_ssize_t start, stop, step, slicelength, cur, i;
if (PySlice_GetIndicesEx((PySliceObject *)index,
PyByteArray_GET_SIZE(self),
&start, &stop, &step, &slicelength) < 0) {
return NULL;
}
if (slicelength <= 0)
return PyByteArray_FromStringAndSize("", 0);
else if (step == 1) {
return PyByteArray_FromStringAndSize(self->ob_bytes + start,
slicelength);
}
else {
char *source_buf = PyByteArray_AS_STRING(self);
char *result_buf = (char *)PyMem_Malloc(slicelength);
PyObject *result;
if (result_buf == NULL)
return PyErr_NoMemory();
for (cur = start, i = 0; i < slicelength;
cur += step, i++) {
result_buf[i] = source_buf[cur];
}
result = PyByteArray_FromStringAndSize(result_buf, slicelength);
PyMem_Free(result_buf);
return result;
}
}
else {
PyErr_SetString(PyExc_TypeError, "bytearray indices must be integers");
return NULL;
}
}
static int
bytes_setslice(PyByteArrayObject *self, Py_ssize_t lo, Py_ssize_t hi,
PyObject *values)
{
Py_ssize_t avail, needed;
void *bytes;
Py_buffer vbytes;
int res = 0;
vbytes.len = -1;
if (values == (PyObject *)self) {
/* Make a copy and call this function recursively */
int err;
values = PyByteArray_FromObject(values);
if (values == NULL)
return -1;
err = bytes_setslice(self, lo, hi, values);
Py_DECREF(values);
return err;
}
if (values == NULL) {
/* del b[lo:hi] */
bytes = NULL;
needed = 0;
}
else {
if (_getbuffer(values, &vbytes) < 0) {
PyErr_Format(PyExc_TypeError,
Merged revisions 65012,65035,65037-65040,65048,65057,65077,65091-65095,65097-65099,65127-65128,65131,65133-65136,65139,65149-65151,65155,65158-65159,65176-65178,65183-65184,65187-65190,65192,65194 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r65012 | jesse.noller | 2008-07-16 15:24:06 +0200 (Wed, 16 Jul 2008) | 2 lines Apply patch for issue 3090: ARCHFLAGS parsing incorrect ........ r65035 | georg.brandl | 2008-07-16 23:19:28 +0200 (Wed, 16 Jul 2008) | 2 lines #3045: fix pydoc behavior for TEMP path with spaces. ........ r65037 | georg.brandl | 2008-07-16 23:31:41 +0200 (Wed, 16 Jul 2008) | 2 lines #1608818: errno can get set by every call to readdir(). ........ r65038 | georg.brandl | 2008-07-17 00:04:20 +0200 (Thu, 17 Jul 2008) | 2 lines #3305: self->stream can be NULL. ........ r65039 | georg.brandl | 2008-07-17 00:09:17 +0200 (Thu, 17 Jul 2008) | 2 lines #3345: fix docstring. ........ r65040 | georg.brandl | 2008-07-17 00:33:18 +0200 (Thu, 17 Jul 2008) | 2 lines #3312: fix two sqlite3 crashes. ........ r65048 | georg.brandl | 2008-07-17 01:35:54 +0200 (Thu, 17 Jul 2008) | 2 lines #3388: add a paragraph about using "with" for file objects. ........ r65057 | gregory.p.smith | 2008-07-17 05:13:05 +0200 (Thu, 17 Jul 2008) | 2 lines news note for r63052 ........ r65077 | jesse.noller | 2008-07-17 23:01:05 +0200 (Thu, 17 Jul 2008) | 3 lines Fix issue 3395, update _debugInfo to be _debug_info ........ r65091 | ronald.oussoren | 2008-07-18 07:48:03 +0200 (Fri, 18 Jul 2008) | 2 lines Last bit of a fix for issue3381 (addon for my patch in r65061) ........ r65092 | vinay.sajip | 2008-07-18 10:59:06 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65093 | vinay.sajip | 2008-07-18 11:00:00 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65094 | vinay.sajip | 2008-07-18 11:00:35 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65095 | vinay.sajip | 2008-07-18 11:01:10 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65097 | georg.brandl | 2008-07-18 12:20:59 +0200 (Fri, 18 Jul 2008) | 2 lines Remove duplicate entry in __all__. ........ r65098 | georg.brandl | 2008-07-18 12:29:30 +0200 (Fri, 18 Jul 2008) | 2 lines Correct attribute name. ........ r65099 | georg.brandl | 2008-07-18 13:15:06 +0200 (Fri, 18 Jul 2008) | 3 lines Document the different meaning of precision for {:f} and {:g}. Also document how inf and nan are formatted. #3404. ........ r65127 | raymond.hettinger | 2008-07-19 02:42:03 +0200 (Sat, 19 Jul 2008) | 1 line Improve accuracy of gamma test function ........ r65128 | raymond.hettinger | 2008-07-19 02:43:00 +0200 (Sat, 19 Jul 2008) | 1 line Add recipe to the itertools docs. ........ r65131 | georg.brandl | 2008-07-19 12:08:55 +0200 (Sat, 19 Jul 2008) | 2 lines #3378: in case of no memory, don't leak even more memory. :) ........ r65133 | georg.brandl | 2008-07-19 14:39:10 +0200 (Sat, 19 Jul 2008) | 3 lines #3302: fix segfaults when passing None for arguments that can't be NULL for the C functions. ........ r65134 | georg.brandl | 2008-07-19 14:46:12 +0200 (Sat, 19 Jul 2008) | 2 lines #3303: fix crash with invalid Py_DECREF in strcoll(). ........ r65135 | georg.brandl | 2008-07-19 15:00:22 +0200 (Sat, 19 Jul 2008) | 3 lines #3319: don't raise ZeroDivisionError if number of rounds is so low that benchtime is zero. ........ r65136 | georg.brandl | 2008-07-19 15:09:42 +0200 (Sat, 19 Jul 2008) | 3 lines #3323: mention that if inheriting from a class without __slots__, the subclass will have a __dict__ available too. ........ r65139 | georg.brandl | 2008-07-19 15:48:44 +0200 (Sat, 19 Jul 2008) | 2 lines Add ordering info for findall and finditer. ........ r65149 | raymond.hettinger | 2008-07-20 01:21:57 +0200 (Sun, 20 Jul 2008) | 1 line Fix compress() recipe in docs to use itertools. ........ r65150 | raymond.hettinger | 2008-07-20 01:58:47 +0200 (Sun, 20 Jul 2008) | 1 line Clean-up itertools docs and recipes. ........ r65151 | gregory.p.smith | 2008-07-20 02:22:08 +0200 (Sun, 20 Jul 2008) | 9 lines fix issue3120 - don't truncate handles on 64-bit Windows. This is still messy, realistically PC/_subprocess.c should never cast pointers to python numbers and back at all. I don't have a 64-bit windows build environment because microsoft apparently thinks that should cost money. Time to watch the buildbots. It builds and passes tests on 32-bit windows. ........ r65155 | georg.brandl | 2008-07-20 13:50:29 +0200 (Sun, 20 Jul 2008) | 2 lines #926501: add info where to put the docstring. ........ r65158 | neal.norwitz | 2008-07-20 21:35:23 +0200 (Sun, 20 Jul 2008) | 1 line Fix a couple of names in error messages that were wrong ........ r65159 | neal.norwitz | 2008-07-20 22:39:36 +0200 (Sun, 20 Jul 2008) | 1 line Fix misspeeld method name (negative) ........ r65176 | amaury.forgeotdarc | 2008-07-21 23:36:24 +0200 (Mon, 21 Jul 2008) | 4 lines Increment version number in NEWS file, and move items that were added after 2.6b2. (I thought there was a script to automate this kind of updates) ........ r65177 | amaury.forgeotdarc | 2008-07-22 00:00:38 +0200 (Tue, 22 Jul 2008) | 5 lines Issue2378: pdb would delete free variables when stepping into a class statement. The problem was introduced by r53954, the correction is to restore the symmetry between PyFrame_FastToLocals and PyFrame_LocalsToFast ........ r65178 | benjamin.peterson | 2008-07-22 00:05:34 +0200 (Tue, 22 Jul 2008) | 1 line don't use assert statement ........ r65183 | ronald.oussoren | 2008-07-22 09:06:00 +0200 (Tue, 22 Jul 2008) | 2 lines Fix buglet in fix for issue3381 ........ r65184 | ronald.oussoren | 2008-07-22 09:06:33 +0200 (Tue, 22 Jul 2008) | 2 lines Fix build issue on OSX 10.4, somehow this wasn't committed before. ........ r65187 | raymond.hettinger | 2008-07-22 20:54:02 +0200 (Tue, 22 Jul 2008) | 1 line Remove out-of-date section on Exact/Inexact. ........ r65188 | raymond.hettinger | 2008-07-22 21:00:47 +0200 (Tue, 22 Jul 2008) | 1 line Tuples now have both count() and index(). ........ r65189 | raymond.hettinger | 2008-07-22 21:03:05 +0200 (Tue, 22 Jul 2008) | 1 line Fix credits for math.sum() ........ r65190 | raymond.hettinger | 2008-07-22 21:18:50 +0200 (Tue, 22 Jul 2008) | 1 line One more attribution. ........ r65192 | benjamin.peterson | 2008-07-23 01:44:37 +0200 (Wed, 23 Jul 2008) | 1 line remove unneeded import ........ r65194 | benjamin.peterson | 2008-07-23 15:25:06 +0200 (Wed, 23 Jul 2008) | 1 line use isinstance ........
2008-07-23 13:10:53 -03:00
"can't set bytearray slice from %.100s",
Py_TYPE(values)->tp_name);
return -1;
}
needed = vbytes.len;
bytes = vbytes.buf;
}
if (lo < 0)
lo = 0;
if (hi < lo)
hi = lo;
if (hi > Py_SIZE(self))
hi = Py_SIZE(self);
avail = hi - lo;
if (avail < 0)
lo = hi = avail = 0;
if (avail != needed) {
if (avail > needed) {
/*
0 lo hi old_size
| |<----avail----->|<-----tomove------>|
| |<-needed->|<-----tomove------>|
0 lo new_hi new_size
*/
memmove(self->ob_bytes + lo + needed, self->ob_bytes + hi,
Py_SIZE(self) - hi);
}
/* XXX(nnorwitz): need to verify this can't overflow! */
if (PyByteArray_Resize((PyObject *)self,
Py_SIZE(self) + needed - avail) < 0) {
res = -1;
goto finish;
}
if (avail < needed) {
/*
0 lo hi old_size
| |<-avail->|<-----tomove------>|
| |<----needed---->|<-----tomove------>|
0 lo new_hi new_size
*/
memmove(self->ob_bytes + lo + needed, self->ob_bytes + hi,
Py_SIZE(self) - lo - needed);
}
}
if (needed > 0)
memcpy(self->ob_bytes + lo, bytes, needed);
finish:
if (vbytes.len != -1)
PyBuffer_Release(&vbytes);
return res;
}
static int
bytes_setitem(PyByteArrayObject *self, Py_ssize_t i, PyObject *value)
{
int ival;
if (i < 0)
i += Py_SIZE(self);
if (i < 0 || i >= Py_SIZE(self)) {
PyErr_SetString(PyExc_IndexError, "bytearray index out of range");
return -1;
}
if (value == NULL)
return bytes_setslice(self, i, i+1, NULL);
if (!_getbytevalue(value, &ival))
return -1;
self->ob_bytes[i] = ival;
return 0;
}
static int
bytes_ass_subscript(PyByteArrayObject *self, PyObject *index, PyObject *values)
{
Py_ssize_t start, stop, step, slicelen, needed;
char *bytes;
if (PyIndex_Check(index)) {
Py_ssize_t i = PyNumber_AsSsize_t(index, PyExc_IndexError);
if (i == -1 && PyErr_Occurred())
return -1;
if (i < 0)
i += PyByteArray_GET_SIZE(self);
if (i < 0 || i >= Py_SIZE(self)) {
PyErr_SetString(PyExc_IndexError, "bytearray index out of range");
return -1;
}
if (values == NULL) {
/* Fall through to slice assignment */
start = i;
stop = i + 1;
step = 1;
slicelen = 1;
}
else {
int ival;
if (!_getbytevalue(values, &ival))
return -1;
self->ob_bytes[i] = (char)ival;
return 0;
}
}
else if (PySlice_Check(index)) {
if (PySlice_GetIndicesEx((PySliceObject *)index,
PyByteArray_GET_SIZE(self),
&start, &stop, &step, &slicelen) < 0) {
return -1;
}
}
else {
PyErr_SetString(PyExc_TypeError, "bytearray indices must be integer");
return -1;
}
if (values == NULL) {
bytes = NULL;
needed = 0;
}
else if (values == (PyObject *)self || !PyByteArray_Check(values)) {
/* Make a copy an call this function recursively */
int err;
values = PyByteArray_FromObject(values);
if (values == NULL)
return -1;
err = bytes_ass_subscript(self, index, values);
Py_DECREF(values);
return err;
}
else {
assert(PyByteArray_Check(values));
bytes = ((PyByteArrayObject *)values)->ob_bytes;
needed = Py_SIZE(values);
}
/* Make sure b[5:2] = ... inserts before 5, not before 2. */
if ((step < 0 && start < stop) ||
(step > 0 && start > stop))
stop = start;
if (step == 1) {
if (slicelen != needed) {
if (slicelen > needed) {
/*
0 start stop old_size
| |<---slicelen--->|<-----tomove------>|
| |<-needed->|<-----tomove------>|
0 lo new_hi new_size
*/
memmove(self->ob_bytes + start + needed, self->ob_bytes + stop,
Py_SIZE(self) - stop);
}
if (PyByteArray_Resize((PyObject *)self,
Py_SIZE(self) + needed - slicelen) < 0)
return -1;
if (slicelen < needed) {
/*
0 lo hi old_size
| |<-avail->|<-----tomove------>|
| |<----needed---->|<-----tomove------>|
0 lo new_hi new_size
*/
memmove(self->ob_bytes + start + needed, self->ob_bytes + stop,
Py_SIZE(self) - start - needed);
}
}
if (needed > 0)
memcpy(self->ob_bytes + start, bytes, needed);
return 0;
}
else {
if (needed == 0) {
/* Delete slice */
Py_ssize_t cur, i;
if (step < 0) {
stop = start + 1;
start = stop + step * (slicelen - 1) - 1;
step = -step;
}
for (cur = start, i = 0;
i < slicelen; cur += step, i++) {
Py_ssize_t lim = step - 1;
if (cur + step >= PyByteArray_GET_SIZE(self))
lim = PyByteArray_GET_SIZE(self) - cur - 1;
memmove(self->ob_bytes + cur - i,
self->ob_bytes + cur + 1, lim);
}
/* Move the tail of the bytes, in one chunk */
cur = start + slicelen*step;
if (cur < PyByteArray_GET_SIZE(self)) {
memmove(self->ob_bytes + cur - slicelen,
self->ob_bytes + cur,
PyByteArray_GET_SIZE(self) - cur);
}
if (PyByteArray_Resize((PyObject *)self,
PyByteArray_GET_SIZE(self) - slicelen) < 0)
return -1;
return 0;
}
else {
/* Assign slice */
Py_ssize_t cur, i;
if (needed != slicelen) {
PyErr_Format(PyExc_ValueError,
"attempt to assign bytes of size %zd "
"to extended slice of size %zd",
needed, slicelen);
return -1;
}
for (cur = start, i = 0; i < slicelen; cur += step, i++)
self->ob_bytes[cur] = bytes[i];
return 0;
}
}
}
static int
bytes_init(PyByteArrayObject *self, PyObject *args, PyObject *kwds)
{
static char *kwlist[] = {"source", "encoding", "errors", 0};
PyObject *arg = NULL;
const char *encoding = NULL;
const char *errors = NULL;
Py_ssize_t count;
PyObject *it;
PyObject *(*iternext)(PyObject *);
if (Py_SIZE(self) != 0) {
/* Empty previous contents (yes, do this first of all!) */
if (PyByteArray_Resize((PyObject *)self, 0) < 0)
return -1;
}
/* Parse arguments */
Merged revisions 65012,65035,65037-65040,65048,65057,65077,65091-65095,65097-65099,65127-65128,65131,65133-65136,65139,65149-65151,65155,65158-65159,65176-65178,65183-65184,65187-65190,65192,65194 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r65012 | jesse.noller | 2008-07-16 15:24:06 +0200 (Wed, 16 Jul 2008) | 2 lines Apply patch for issue 3090: ARCHFLAGS parsing incorrect ........ r65035 | georg.brandl | 2008-07-16 23:19:28 +0200 (Wed, 16 Jul 2008) | 2 lines #3045: fix pydoc behavior for TEMP path with spaces. ........ r65037 | georg.brandl | 2008-07-16 23:31:41 +0200 (Wed, 16 Jul 2008) | 2 lines #1608818: errno can get set by every call to readdir(). ........ r65038 | georg.brandl | 2008-07-17 00:04:20 +0200 (Thu, 17 Jul 2008) | 2 lines #3305: self->stream can be NULL. ........ r65039 | georg.brandl | 2008-07-17 00:09:17 +0200 (Thu, 17 Jul 2008) | 2 lines #3345: fix docstring. ........ r65040 | georg.brandl | 2008-07-17 00:33:18 +0200 (Thu, 17 Jul 2008) | 2 lines #3312: fix two sqlite3 crashes. ........ r65048 | georg.brandl | 2008-07-17 01:35:54 +0200 (Thu, 17 Jul 2008) | 2 lines #3388: add a paragraph about using "with" for file objects. ........ r65057 | gregory.p.smith | 2008-07-17 05:13:05 +0200 (Thu, 17 Jul 2008) | 2 lines news note for r63052 ........ r65077 | jesse.noller | 2008-07-17 23:01:05 +0200 (Thu, 17 Jul 2008) | 3 lines Fix issue 3395, update _debugInfo to be _debug_info ........ r65091 | ronald.oussoren | 2008-07-18 07:48:03 +0200 (Fri, 18 Jul 2008) | 2 lines Last bit of a fix for issue3381 (addon for my patch in r65061) ........ r65092 | vinay.sajip | 2008-07-18 10:59:06 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65093 | vinay.sajip | 2008-07-18 11:00:00 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65094 | vinay.sajip | 2008-07-18 11:00:35 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65095 | vinay.sajip | 2008-07-18 11:01:10 +0200 (Fri, 18 Jul 2008) | 1 line Issue #3389: Allow resolving dotted names for handlers in logging configuration files. Thanks to Philip Jenvey for the patch. ........ r65097 | georg.brandl | 2008-07-18 12:20:59 +0200 (Fri, 18 Jul 2008) | 2 lines Remove duplicate entry in __all__. ........ r65098 | georg.brandl | 2008-07-18 12:29:30 +0200 (Fri, 18 Jul 2008) | 2 lines Correct attribute name. ........ r65099 | georg.brandl | 2008-07-18 13:15:06 +0200 (Fri, 18 Jul 2008) | 3 lines Document the different meaning of precision for {:f} and {:g}. Also document how inf and nan are formatted. #3404. ........ r65127 | raymond.hettinger | 2008-07-19 02:42:03 +0200 (Sat, 19 Jul 2008) | 1 line Improve accuracy of gamma test function ........ r65128 | raymond.hettinger | 2008-07-19 02:43:00 +0200 (Sat, 19 Jul 2008) | 1 line Add recipe to the itertools docs. ........ r65131 | georg.brandl | 2008-07-19 12:08:55 +0200 (Sat, 19 Jul 2008) | 2 lines #3378: in case of no memory, don't leak even more memory. :) ........ r65133 | georg.brandl | 2008-07-19 14:39:10 +0200 (Sat, 19 Jul 2008) | 3 lines #3302: fix segfaults when passing None for arguments that can't be NULL for the C functions. ........ r65134 | georg.brandl | 2008-07-19 14:46:12 +0200 (Sat, 19 Jul 2008) | 2 lines #3303: fix crash with invalid Py_DECREF in strcoll(). ........ r65135 | georg.brandl | 2008-07-19 15:00:22 +0200 (Sat, 19 Jul 2008) | 3 lines #3319: don't raise ZeroDivisionError if number of rounds is so low that benchtime is zero. ........ r65136 | georg.brandl | 2008-07-19 15:09:42 +0200 (Sat, 19 Jul 2008) | 3 lines #3323: mention that if inheriting from a class without __slots__, the subclass will have a __dict__ available too. ........ r65139 | georg.brandl | 2008-07-19 15:48:44 +0200 (Sat, 19 Jul 2008) | 2 lines Add ordering info for findall and finditer. ........ r65149 | raymond.hettinger | 2008-07-20 01:21:57 +0200 (Sun, 20 Jul 2008) | 1 line Fix compress() recipe in docs to use itertools. ........ r65150 | raymond.hettinger | 2008-07-20 01:58:47 +0200 (Sun, 20 Jul 2008) | 1 line Clean-up itertools docs and recipes. ........ r65151 | gregory.p.smith | 2008-07-20 02:22:08 +0200 (Sun, 20 Jul 2008) | 9 lines fix issue3120 - don't truncate handles on 64-bit Windows. This is still messy, realistically PC/_subprocess.c should never cast pointers to python numbers and back at all. I don't have a 64-bit windows build environment because microsoft apparently thinks that should cost money. Time to watch the buildbots. It builds and passes tests on 32-bit windows. ........ r65155 | georg.brandl | 2008-07-20 13:50:29 +0200 (Sun, 20 Jul 2008) | 2 lines #926501: add info where to put the docstring. ........ r65158 | neal.norwitz | 2008-07-20 21:35:23 +0200 (Sun, 20 Jul 2008) | 1 line Fix a couple of names in error messages that were wrong ........ r65159 | neal.norwitz | 2008-07-20 22:39:36 +0200 (Sun, 20 Jul 2008) | 1 line Fix misspeeld method name (negative) ........ r65176 | amaury.forgeotdarc | 2008-07-21 23:36:24 +0200 (Mon, 21 Jul 2008) | 4 lines Increment version number in NEWS file, and move items that were added after 2.6b2. (I thought there was a script to automate this kind of updates) ........ r65177 | amaury.forgeotdarc | 2008-07-22 00:00:38 +0200 (Tue, 22 Jul 2008) | 5 lines Issue2378: pdb would delete free variables when stepping into a class statement. The problem was introduced by r53954, the correction is to restore the symmetry between PyFrame_FastToLocals and PyFrame_LocalsToFast ........ r65178 | benjamin.peterson | 2008-07-22 00:05:34 +0200 (Tue, 22 Jul 2008) | 1 line don't use assert statement ........ r65183 | ronald.oussoren | 2008-07-22 09:06:00 +0200 (Tue, 22 Jul 2008) | 2 lines Fix buglet in fix for issue3381 ........ r65184 | ronald.oussoren | 2008-07-22 09:06:33 +0200 (Tue, 22 Jul 2008) | 2 lines Fix build issue on OSX 10.4, somehow this wasn't committed before. ........ r65187 | raymond.hettinger | 2008-07-22 20:54:02 +0200 (Tue, 22 Jul 2008) | 1 line Remove out-of-date section on Exact/Inexact. ........ r65188 | raymond.hettinger | 2008-07-22 21:00:47 +0200 (Tue, 22 Jul 2008) | 1 line Tuples now have both count() and index(). ........ r65189 | raymond.hettinger | 2008-07-22 21:03:05 +0200 (Tue, 22 Jul 2008) | 1 line Fix credits for math.sum() ........ r65190 | raymond.hettinger | 2008-07-22 21:18:50 +0200 (Tue, 22 Jul 2008) | 1 line One more attribution. ........ r65192 | benjamin.peterson | 2008-07-23 01:44:37 +0200 (Wed, 23 Jul 2008) | 1 line remove unneeded import ........ r65194 | benjamin.peterson | 2008-07-23 15:25:06 +0200 (Wed, 23 Jul 2008) | 1 line use isinstance ........
2008-07-23 13:10:53 -03:00
if (!PyArg_ParseTupleAndKeywords(args, kwds, "|Oss:bytearray", kwlist,
&arg, &encoding, &errors))
return -1;
/* Make a quick exit if no first argument */
if (arg == NULL) {
if (encoding != NULL || errors != NULL) {
PyErr_SetString(PyExc_TypeError,
"encoding or errors without sequence argument");
return -1;
}
return 0;
}
if (PyUnicode_Check(arg)) {
/* Encode via the codec registry */
PyObject *encoded, *new;
if (encoding == NULL) {
PyErr_SetString(PyExc_TypeError,
"string argument without an encoding");
return -1;
}
encoded = PyUnicode_AsEncodedString(arg, encoding, errors);
if (encoded == NULL)
return -1;
assert(PyBytes_Check(encoded));
new = bytes_iconcat(self, encoded);
Py_DECREF(encoded);
if (new == NULL)
return -1;
Py_DECREF(new);
return 0;
}
/* If it's not unicode, there can't be encoding or errors */
if (encoding != NULL || errors != NULL) {
PyErr_SetString(PyExc_TypeError,
"encoding or errors without a string argument");
return -1;
}
/* Is it an int? */
count = PyNumber_AsSsize_t(arg, PyExc_ValueError);
if (count == -1 && PyErr_Occurred())
PyErr_Clear();
else {
if (count < 0) {
PyErr_SetString(PyExc_ValueError, "negative count");
return -1;
}
if (count > 0) {
if (PyByteArray_Resize((PyObject *)self, count))
return -1;
memset(self->ob_bytes, 0, count);
}
return 0;
}
/* Use the buffer API */
if (PyObject_CheckBuffer(arg)) {
Py_ssize_t size;
Py_buffer view;
if (PyObject_GetBuffer(arg, &view, PyBUF_FULL_RO) < 0)
return -1;
size = view.len;
if (PyByteArray_Resize((PyObject *)self, size) < 0) goto fail;
if (PyBuffer_ToContiguous(self->ob_bytes, &view, size, 'C') < 0)
goto fail;
PyBuffer_Release(&view);
return 0;
fail:
PyBuffer_Release(&view);
return -1;
}
/* XXX Optimize this if the arguments is a list, tuple */
/* Get the iterator */
it = PyObject_GetIter(arg);
if (it == NULL)
return -1;
iternext = *Py_TYPE(it)->tp_iternext;
/* Run the iterator to exhaustion */
for (;;) {
PyObject *item;
int rc, value;
/* Get the next item */
item = iternext(it);
if (item == NULL) {
if (PyErr_Occurred()) {
if (!PyErr_ExceptionMatches(PyExc_StopIteration))
goto error;
PyErr_Clear();
}
break;
}
/* Interpret it as an int (__index__) */
rc = _getbytevalue(item, &value);
Py_DECREF(item);
if (!rc)
goto error;
/* Append the byte */
if (Py_SIZE(self) < self->ob_alloc)
Py_SIZE(self)++;
else if (PyByteArray_Resize((PyObject *)self, Py_SIZE(self)+1) < 0)
goto error;
self->ob_bytes[Py_SIZE(self)-1] = value;
}
/* Clean up and return success */
Py_DECREF(it);
return 0;
error:
/* Error handling when it != NULL */
Py_DECREF(it);
return -1;
}
/* Mostly copied from string_repr, but without the
"smart quote" functionality. */
static PyObject *
bytes_repr(PyByteArrayObject *self)
{
static const char *hexdigits = "0123456789abcdef";
const char *quote_prefix = "bytearray(b";
const char *quote_postfix = ")";
Py_ssize_t length = Py_SIZE(self);
/* 14 == strlen(quote_prefix) + 2 + strlen(quote_postfix) */
size_t newsize = 14 + 4 * length;
PyObject *v;
if (newsize > PY_SSIZE_T_MAX || newsize / 4 - 3 != length) {
PyErr_SetString(PyExc_OverflowError,
"bytearray object is too large to make repr");
return NULL;
}
v = PyUnicode_FromUnicode(NULL, newsize);
if (v == NULL) {
return NULL;
}
else {
register Py_ssize_t i;
register Py_UNICODE c;
register Py_UNICODE *p;
int quote;
/* Figure out which quote to use; single is preferred */
quote = '\'';
{
char *test, *start;
start = PyByteArray_AS_STRING(self);
for (test = start; test < start+length; ++test) {
if (*test == '"') {
quote = '\''; /* back to single */
goto decided;
}
else if (*test == '\'')
quote = '"';
}
decided:
;
}
p = PyUnicode_AS_UNICODE(v);
while (*quote_prefix)
*p++ = *quote_prefix++;
*p++ = quote;
for (i = 0; i < length; i++) {
/* There's at least enough room for a hex escape
and a closing quote. */
assert(newsize - (p - PyUnicode_AS_UNICODE(v)) >= 5);
c = self->ob_bytes[i];
if (c == '\'' || c == '\\')
*p++ = '\\', *p++ = c;
else if (c == '\t')
*p++ = '\\', *p++ = 't';
else if (c == '\n')
*p++ = '\\', *p++ = 'n';
else if (c == '\r')
*p++ = '\\', *p++ = 'r';
else if (c == 0)
*p++ = '\\', *p++ = 'x', *p++ = '0', *p++ = '0';
else if (c < ' ' || c >= 0x7f) {
*p++ = '\\';
*p++ = 'x';
*p++ = hexdigits[(c & 0xf0) >> 4];
*p++ = hexdigits[c & 0xf];
}
else
*p++ = c;
}
assert(newsize - (p - PyUnicode_AS_UNICODE(v)) >= 1);
*p++ = quote;
while (*quote_postfix) {
*p++ = *quote_postfix++;
}
*p = '\0';
if (PyUnicode_Resize(&v, (p - PyUnicode_AS_UNICODE(v)))) {
Py_DECREF(v);
return NULL;
}
return v;
}
}
static PyObject *
bytes_str(PyObject *op)
{
if (Py_BytesWarningFlag) {
if (PyErr_WarnEx(PyExc_BytesWarning,
"str() on a bytearray instance", 1))
return NULL;
}
return bytes_repr((PyByteArrayObject*)op);
}
static PyObject *
bytes_richcompare(PyObject *self, PyObject *other, int op)
{
Py_ssize_t self_size, other_size;
Py_buffer self_bytes, other_bytes;
PyObject *res;
Py_ssize_t minsize;
int cmp;
/* Bytes can be compared to anything that supports the (binary)
buffer API. Except that a comparison with Unicode is always an
error, even if the comparison is for equality. */
if (PyObject_IsInstance(self, (PyObject*)&PyUnicode_Type) ||
PyObject_IsInstance(other, (PyObject*)&PyUnicode_Type)) {
if (Py_BytesWarningFlag && (op == Py_EQ || op == Py_NE)) {
if (PyErr_WarnEx(PyExc_BytesWarning,
2008-06-04 08:30:26 -03:00
"Comparison between bytearray and string", 1))
return NULL;
}
Py_INCREF(Py_NotImplemented);
return Py_NotImplemented;
}
self_size = _getbuffer(self, &self_bytes);
if (self_size < 0) {
PyErr_Clear();
Py_INCREF(Py_NotImplemented);
return Py_NotImplemented;
}
other_size = _getbuffer(other, &other_bytes);
if (other_size < 0) {
PyErr_Clear();
PyBuffer_Release(&self_bytes);
Py_INCREF(Py_NotImplemented);
return Py_NotImplemented;
}
if (self_size != other_size && (op == Py_EQ || op == Py_NE)) {
/* Shortcut: if the lengths differ, the objects differ */
cmp = (op == Py_NE);
}
else {
minsize = self_size;
if (other_size < minsize)
minsize = other_size;
cmp = memcmp(self_bytes.buf, other_bytes.buf, minsize);
/* In ISO C, memcmp() guarantees to use unsigned bytes! */
if (cmp == 0) {
if (self_size < other_size)
cmp = -1;
else if (self_size > other_size)
cmp = 1;
}
switch (op) {
case Py_LT: cmp = cmp < 0; break;
case Py_LE: cmp = cmp <= 0; break;
case Py_EQ: cmp = cmp == 0; break;
case Py_NE: cmp = cmp != 0; break;
case Py_GT: cmp = cmp > 0; break;
case Py_GE: cmp = cmp >= 0; break;
}
}
res = cmp ? Py_True : Py_False;
PyBuffer_Release(&self_bytes);
PyBuffer_Release(&other_bytes);
Py_INCREF(res);
return res;
}
static void
bytes_dealloc(PyByteArrayObject *self)
{
if (self->ob_exports > 0) {
PyErr_SetString(PyExc_SystemError,
"deallocated bytearray object has exported buffers");
PyErr_Print();
}
if (self->ob_bytes != 0) {
PyMem_Free(self->ob_bytes);
}
Py_TYPE(self)->tp_free((PyObject *)self);
}
/* -------------------------------------------------------------------- */
/* Methods */
#define STRINGLIB_CHAR char
#define STRINGLIB_CMP memcmp
#define STRINGLIB_LEN PyByteArray_GET_SIZE
#define STRINGLIB_STR PyByteArray_AS_STRING
#define STRINGLIB_NEW PyByteArray_FromStringAndSize
#define STRINGLIB_EMPTY nullbytes
#define STRINGLIB_CHECK_EXACT PyByteArray_CheckExact
#define STRINGLIB_MUTABLE 1
Merged revisions 65910,65977,65980,65984,65986,66000,66011-66012,66014,66017,66020 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r65910 | benjamin.peterson | 2008-08-20 09:07:59 -0500 (Wed, 20 Aug 2008) | 1 line fix up the multiprocessing docs a little ........ r65977 | christian.heimes | 2008-08-22 14:47:25 -0500 (Fri, 22 Aug 2008) | 3 lines Silenced compiler warning Objects/stringlib/find.h:97: warning: 'stringlib_contains_obj' defined but not used Reviewed by Benjamin Peterson ........ r65980 | christian.heimes | 2008-08-22 15:10:27 -0500 (Fri, 22 Aug 2008) | 3 lines Fixed two format strings in the _collections module. For example Modules/_collectionsmodule.c:674: warning: format '%i' expects type 'int', but argument 2 has type 'Py_ssize_t' Reviewed by Benjamin Peterson ........ r65984 | christian.heimes | 2008-08-22 16:23:47 -0500 (Fri, 22 Aug 2008) | 1 line d is the correct format string ........ r65986 | mark.hammond | 2008-08-22 19:59:14 -0500 (Fri, 22 Aug 2008) | 2 lines Fix bug 3625: test issues on 64bit windows. r=pitrou ........ r66000 | benjamin.peterson | 2008-08-23 15:27:43 -0500 (Sat, 23 Aug 2008) | 5 lines #3643 add a few more checks to _testcapi to prevent segfaults Author: Victor Stinner Reviewer: Benjamin Peterson ........ r66011 | neal.norwitz | 2008-08-24 12:27:43 -0500 (Sun, 24 Aug 2008) | 1 line Ignore a couple more tests that report leaks inconsistently. ........ r66012 | neal.norwitz | 2008-08-24 12:29:53 -0500 (Sun, 24 Aug 2008) | 1 line Use the actual blacklist of leaky tests ........ r66014 | georg.brandl | 2008-08-24 13:11:07 -0500 (Sun, 24 Aug 2008) | 2 lines #3654: fix duplicate test method name. Review by Benjamin P. ........ r66017 | benjamin.peterson | 2008-08-24 16:55:03 -0500 (Sun, 24 Aug 2008) | 1 line remove note about unimplemented feature ........ r66020 | brett.cannon | 2008-08-24 18:15:19 -0500 (Sun, 24 Aug 2008) | 1 line Clarify that some attributes/methods are listed somewhat separately because they are not part of the threading API. ........
2008-08-25 18:05:21 -03:00
#define FROM_BYTEARRAY 1
#include "stringlib/fastsearch.h"
#include "stringlib/count.h"
#include "stringlib/find.h"
#include "stringlib/partition.h"
#include "stringlib/ctype.h"
#include "stringlib/transmogrify.h"
/* The following Py_LOCAL_INLINE and Py_LOCAL functions
were copied from the old char* style string object. */
Py_LOCAL_INLINE(void)
_adjust_indices(Py_ssize_t *start, Py_ssize_t *end, Py_ssize_t len)
{
if (*end > len)
*end = len;
else if (*end < 0)
*end += len;
if (*end < 0)
*end = 0;
if (*start < 0)
*start += len;
if (*start < 0)
*start = 0;
}
Py_LOCAL_INLINE(Py_ssize_t)
bytes_find_internal(PyByteArrayObject *self, PyObject *args, int dir)
{
PyObject *subobj;
Py_buffer subbuf;
Py_ssize_t start=0, end=PY_SSIZE_T_MAX;
Py_ssize_t res;
if (!PyArg_ParseTuple(args, "O|O&O&:find/rfind/index/rindex", &subobj,
_PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
return -2;
if (_getbuffer(subobj, &subbuf) < 0)
return -2;
if (dir > 0)
res = stringlib_find_slice(
PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self),
subbuf.buf, subbuf.len, start, end);
else
res = stringlib_rfind_slice(
PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self),
subbuf.buf, subbuf.len, start, end);
PyBuffer_Release(&subbuf);
return res;
}
PyDoc_STRVAR(find__doc__,
"B.find(sub[, start[, end]]) -> int\n\
\n\
Return the lowest index in B where subsection sub is found,\n\
such that sub is contained within s[start,end]. Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.");
static PyObject *
bytes_find(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t result = bytes_find_internal(self, args, +1);
if (result == -2)
return NULL;
return PyLong_FromSsize_t(result);
}
PyDoc_STRVAR(count__doc__,
"B.count(sub[, start[, end]]) -> int\n\
\n\
Return the number of non-overlapping occurrences of subsection sub in\n\
bytes B[start:end]. Optional arguments start and end are interpreted\n\
as in slice notation.");
static PyObject *
bytes_count(PyByteArrayObject *self, PyObject *args)
{
PyObject *sub_obj;
const char *str = PyByteArray_AS_STRING(self);
Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
Py_buffer vsub;
PyObject *count_obj;
if (!PyArg_ParseTuple(args, "O|O&O&:count", &sub_obj,
_PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
return NULL;
if (_getbuffer(sub_obj, &vsub) < 0)
return NULL;
_adjust_indices(&start, &end, PyByteArray_GET_SIZE(self));
count_obj = PyLong_FromSsize_t(
stringlib_count(str + start, end - start, vsub.buf, vsub.len)
);
PyBuffer_Release(&vsub);
return count_obj;
}
PyDoc_STRVAR(index__doc__,
"B.index(sub[, start[, end]]) -> int\n\
\n\
Like B.find() but raise ValueError when the subsection is not found.");
static PyObject *
bytes_index(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t result = bytes_find_internal(self, args, +1);
if (result == -2)
return NULL;
if (result == -1) {
PyErr_SetString(PyExc_ValueError,
"subsection not found");
return NULL;
}
return PyLong_FromSsize_t(result);
}
PyDoc_STRVAR(rfind__doc__,
"B.rfind(sub[, start[, end]]) -> int\n\
\n\
Return the highest index in B where subsection sub is found,\n\
such that sub is contained within s[start,end]. Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.");
static PyObject *
bytes_rfind(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t result = bytes_find_internal(self, args, -1);
if (result == -2)
return NULL;
return PyLong_FromSsize_t(result);
}
PyDoc_STRVAR(rindex__doc__,
"B.rindex(sub[, start[, end]]) -> int\n\
\n\
Like B.rfind() but raise ValueError when the subsection is not found.");
static PyObject *
bytes_rindex(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t result = bytes_find_internal(self, args, -1);
if (result == -2)
return NULL;
if (result == -1) {
PyErr_SetString(PyExc_ValueError,
"subsection not found");
return NULL;
}
return PyLong_FromSsize_t(result);
}
static int
bytes_contains(PyObject *self, PyObject *arg)
{
Py_ssize_t ival = PyNumber_AsSsize_t(arg, PyExc_ValueError);
if (ival == -1 && PyErr_Occurred()) {
Py_buffer varg;
int pos;
PyErr_Clear();
if (_getbuffer(arg, &varg) < 0)
return -1;
pos = stringlib_find(PyByteArray_AS_STRING(self), Py_SIZE(self),
varg.buf, varg.len, 0);
PyBuffer_Release(&varg);
return pos >= 0;
}
if (ival < 0 || ival >= 256) {
PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
return -1;
}
return memchr(PyByteArray_AS_STRING(self), ival, Py_SIZE(self)) != NULL;
}
/* Matches the end (direction >= 0) or start (direction < 0) of self
* against substr, using the start and end arguments. Returns
* -1 on error, 0 if not found and 1 if found.
*/
Py_LOCAL(int)
_bytes_tailmatch(PyByteArrayObject *self, PyObject *substr, Py_ssize_t start,
Py_ssize_t end, int direction)
{
Py_ssize_t len = PyByteArray_GET_SIZE(self);
const char* str;
Py_buffer vsubstr;
int rv = 0;
str = PyByteArray_AS_STRING(self);
if (_getbuffer(substr, &vsubstr) < 0)
return -1;
_adjust_indices(&start, &end, len);
if (direction < 0) {
/* startswith */
if (start+vsubstr.len > len) {
goto done;
}
} else {
/* endswith */
if (end-start < vsubstr.len || start > len) {
goto done;
}
if (end-vsubstr.len > start)
start = end - vsubstr.len;
}
if (end-start >= vsubstr.len)
rv = ! memcmp(str+start, vsubstr.buf, vsubstr.len);
done:
PyBuffer_Release(&vsubstr);
return rv;
}
PyDoc_STRVAR(startswith__doc__,
"B.startswith(prefix[, start[, end]]) -> bool\n\
\n\
Return True if B starts with the specified prefix, False otherwise.\n\
With optional start, test B beginning at that position.\n\
With optional end, stop comparing B at that position.\n\
prefix can also be a tuple of strings to try.");
static PyObject *
bytes_startswith(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t start = 0;
Py_ssize_t end = PY_SSIZE_T_MAX;
PyObject *subobj;
int result;
if (!PyArg_ParseTuple(args, "O|O&O&:startswith", &subobj,
_PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
return NULL;
if (PyTuple_Check(subobj)) {
Py_ssize_t i;
for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
result = _bytes_tailmatch(self,
PyTuple_GET_ITEM(subobj, i),
start, end, -1);
if (result == -1)
return NULL;
else if (result) {
Py_RETURN_TRUE;
}
}
Py_RETURN_FALSE;
}
result = _bytes_tailmatch(self, subobj, start, end, -1);
if (result == -1)
return NULL;
else
return PyBool_FromLong(result);
}
PyDoc_STRVAR(endswith__doc__,
"B.endswith(suffix[, start[, end]]) -> bool\n\
\n\
Return True if B ends with the specified suffix, False otherwise.\n\
With optional start, test B beginning at that position.\n\
With optional end, stop comparing B at that position.\n\
suffix can also be a tuple of strings to try.");
static PyObject *
bytes_endswith(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t start = 0;
Py_ssize_t end = PY_SSIZE_T_MAX;
PyObject *subobj;
int result;
if (!PyArg_ParseTuple(args, "O|O&O&:endswith", &subobj,
_PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
return NULL;
if (PyTuple_Check(subobj)) {
Py_ssize_t i;
for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
result = _bytes_tailmatch(self,
PyTuple_GET_ITEM(subobj, i),
start, end, +1);
if (result == -1)
return NULL;
else if (result) {
Py_RETURN_TRUE;
}
}
Py_RETURN_FALSE;
}
result = _bytes_tailmatch(self, subobj, start, end, +1);
if (result == -1)
return NULL;
else
return PyBool_FromLong(result);
}
PyDoc_STRVAR(translate__doc__,
"B.translate(table[, deletechars]) -> bytearray\n\
\n\
Return a copy of B, where all characters occurring in the\n\
optional argument deletechars are removed, and the remaining\n\
characters have been mapped through the given translation\n\
table, which must be a bytes object of length 256.");
static PyObject *
bytes_translate(PyByteArrayObject *self, PyObject *args)
{
register char *input, *output;
register const char *table;
register Py_ssize_t i, c, changed = 0;
PyObject *input_obj = (PyObject*)self;
const char *output_start;
Py_ssize_t inlen;
PyObject *result;
int trans_table[256];
PyObject *tableobj, *delobj = NULL;
Py_buffer vtable, vdel;
if (!PyArg_UnpackTuple(args, "translate", 1, 2,
&tableobj, &delobj))
return NULL;
if (_getbuffer(tableobj, &vtable) < 0)
return NULL;
if (vtable.len != 256) {
PyErr_SetString(PyExc_ValueError,
"translation table must be 256 characters long");
result = NULL;
goto done;
}
if (delobj != NULL) {
if (_getbuffer(delobj, &vdel) < 0) {
result = NULL;
goto done;
}
}
else {
vdel.buf = NULL;
vdel.len = 0;
}
table = (const char *)vtable.buf;
inlen = PyByteArray_GET_SIZE(input_obj);
result = PyByteArray_FromStringAndSize((char *)NULL, inlen);
if (result == NULL)
goto done;
output_start = output = PyByteArray_AsString(result);
input = PyByteArray_AS_STRING(input_obj);
if (vdel.len == 0) {
/* If no deletions are required, use faster code */
for (i = inlen; --i >= 0; ) {
c = Py_CHARMASK(*input++);
if (Py_CHARMASK((*output++ = table[c])) != c)
changed = 1;
}
if (changed || !PyByteArray_CheckExact(input_obj))
goto done;
Py_DECREF(result);
Py_INCREF(input_obj);
result = input_obj;
goto done;
}
for (i = 0; i < 256; i++)
trans_table[i] = Py_CHARMASK(table[i]);
for (i = 0; i < vdel.len; i++)
trans_table[(int) Py_CHARMASK( ((unsigned char*)vdel.buf)[i] )] = -1;
for (i = inlen; --i >= 0; ) {
c = Py_CHARMASK(*input++);
if (trans_table[c] != -1)
if (Py_CHARMASK(*output++ = (char)trans_table[c]) == c)
continue;
changed = 1;
}
if (!changed && PyByteArray_CheckExact(input_obj)) {
Py_DECREF(result);
Py_INCREF(input_obj);
result = input_obj;
goto done;
}
/* Fix the size of the resulting string */
if (inlen > 0)
PyByteArray_Resize(result, output - output_start);
done:
PyBuffer_Release(&vtable);
if (delobj != NULL)
PyBuffer_Release(&vdel);
return result;
}
#define FORWARD 1
#define REVERSE -1
/* find and count characters and substrings */
#define findchar(target, target_len, c) \
((char *)memchr((const void *)(target), c, target_len))
/* Don't call if length < 2 */
#define Py_STRING_MATCH(target, offset, pattern, length) \
(target[offset] == pattern[0] && \
target[offset+length-1] == pattern[length-1] && \
!memcmp(target+offset+1, pattern+1, length-2) )
/* Bytes ops must return a string. */
/* If the object is subclass of bytes, create a copy */
Py_LOCAL(PyByteArrayObject *)
return_self(PyByteArrayObject *self)
{
/* always return a new bytearray */
return (PyByteArrayObject *)PyByteArray_FromStringAndSize(
PyByteArray_AS_STRING(self),
PyByteArray_GET_SIZE(self));
}
Py_LOCAL_INLINE(Py_ssize_t)
countchar(const char *target, Py_ssize_t target_len, char c, Py_ssize_t maxcount)
{
Py_ssize_t count=0;
const char *start=target;
const char *end=target+target_len;
while ( (start=findchar(start, end-start, c)) != NULL ) {
count++;
if (count >= maxcount)
break;
start += 1;
}
return count;
}
Py_LOCAL(Py_ssize_t)
findstring(const char *target, Py_ssize_t target_len,
const char *pattern, Py_ssize_t pattern_len,
Py_ssize_t start,
Py_ssize_t end,
int direction)
{
if (start < 0) {
start += target_len;
if (start < 0)
start = 0;
}
if (end > target_len) {
end = target_len;
} else if (end < 0) {
end += target_len;
if (end < 0)
end = 0;
}
/* zero-length substrings always match at the first attempt */
if (pattern_len == 0)
return (direction > 0) ? start : end;
end -= pattern_len;
if (direction < 0) {
for (; end >= start; end--)
if (Py_STRING_MATCH(target, end, pattern, pattern_len))
return end;
} else {
for (; start <= end; start++)
if (Py_STRING_MATCH(target, start, pattern, pattern_len))
return start;
}
return -1;
}
Py_LOCAL_INLINE(Py_ssize_t)
countstring(const char *target, Py_ssize_t target_len,
const char *pattern, Py_ssize_t pattern_len,
Py_ssize_t start,
Py_ssize_t end,
int direction, Py_ssize_t maxcount)
{
Py_ssize_t count=0;
if (start < 0) {
start += target_len;
if (start < 0)
start = 0;
}
if (end > target_len) {
end = target_len;
} else if (end < 0) {
end += target_len;
if (end < 0)
end = 0;
}
/* zero-length substrings match everywhere */
if (pattern_len == 0 || maxcount == 0) {
if (target_len+1 < maxcount)
return target_len+1;
return maxcount;
}
end -= pattern_len;
if (direction < 0) {
for (; (end >= start); end--)
if (Py_STRING_MATCH(target, end, pattern, pattern_len)) {
count++;
if (--maxcount <= 0) break;
end -= pattern_len-1;
}
} else {
for (; (start <= end); start++)
if (Py_STRING_MATCH(target, start, pattern, pattern_len)) {
count++;
if (--maxcount <= 0)
break;
start += pattern_len-1;
}
}
return count;
}
/* Algorithms for different cases of string replacement */
/* len(self)>=1, from="", len(to)>=1, maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_interleave(PyByteArrayObject *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;
PyByteArrayObject *result;
self_len = PyByteArray_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 = (PyByteArrayObject *)
PyByteArray_FromStringAndSize(NULL, result_len)) )
return NULL;
self_s = PyByteArray_AS_STRING(self);
result_s = PyByteArray_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;
}
/* Special case for deleting a single character */
/* len(self)>=1, len(from)==1, to="", maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_delete_single_character(PyByteArrayObject *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;
PyByteArrayObject *result;
self_len = PyByteArray_GET_SIZE(self);
self_s = PyByteArray_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 = (PyByteArrayObject *)
PyByteArray_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyByteArray_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;
}
/* len(self)>=1, len(from)>=2, to="", maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_delete_substring(PyByteArrayObject *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;
PyByteArrayObject *result;
self_len = PyByteArray_GET_SIZE(self);
self_s = PyByteArray_AS_STRING(self);
count = countstring(self_s, self_len,
from_s, from_len,
0, self_len, 1,
maxcount);
if (count == 0) {
/* no matches */
return return_self(self);
}
result_len = self_len - (count * from_len);
assert (result_len>=0);
if ( (result = (PyByteArrayObject *)
PyByteArray_FromStringAndSize(NULL, result_len)) == NULL )
return NULL;
result_s = PyByteArray_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
offset = findstring(start, end-start,
from_s, from_len,
0, end-start, FORWARD);
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;
}
/* len(self)>=1, len(from)==len(to)==1, maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_single_character_in_place(PyByteArrayObject *self,
char from_c, char to_c,
Py_ssize_t maxcount)
{
char *self_s, *result_s, *start, *end, *next;
Py_ssize_t self_len;
PyByteArrayObject *result;
/* The result string will be the same size */
self_s = PyByteArray_AS_STRING(self);
self_len = PyByteArray_GET_SIZE(self);
next = findchar(self_s, self_len, from_c);
if (next == NULL) {
/* No matches; return the original bytes */
return return_self(self);
}
/* Need to make a new bytes */
result = (PyByteArrayObject *) PyByteArray_FromStringAndSize(NULL, self_len);
if (result == NULL)
return NULL;
result_s = PyByteArray_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;
}
/* len(self)>=1, len(from)==len(to)>=2, maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_substring_in_place(PyByteArrayObject *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;
PyByteArrayObject *result;
/* The result bytes will be the same size */
self_s = PyByteArray_AS_STRING(self);
self_len = PyByteArray_GET_SIZE(self);
offset = findstring(self_s, self_len,
from_s, from_len,
0, self_len, FORWARD);
if (offset == -1) {
/* No matches; return the original bytes */
return return_self(self);
}
/* Need to make a new bytes */
result = (PyByteArrayObject *) PyByteArray_FromStringAndSize(NULL, self_len);
if (result == NULL)
return NULL;
result_s = PyByteArray_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 = findstring(start, end-start,
from_s, from_len,
0, end-start, FORWARD);
if (offset==-1)
break;
Py_MEMCPY(start+offset, to_s, from_len);
start += offset+from_len;
}
return result;
}
/* len(self)>=1, len(from)==1, len(to)>=2, maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_single_character(PyByteArrayObject *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;
PyByteArrayObject *result;
self_s = PyByteArray_AS_STRING(self);
self_len = PyByteArray_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 bytes is too long");
return NULL;
}
result_len = self_len + product;
if (result_len < 0) {
PyErr_SetString(PyExc_OverflowError, "replace bytes is too long");
return NULL;
}
if ( (result = (PyByteArrayObject *)
PyByteArray_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyByteArray_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 bytes */
Py_MEMCPY(result_s, start, end-start);
return result;
}
/* len(self)>=1, len(from)>=2, len(to)>=2, maxcount>=1 */
Py_LOCAL(PyByteArrayObject *)
replace_substring(PyByteArrayObject *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;
PyByteArrayObject *result;
self_s = PyByteArray_AS_STRING(self);
self_len = PyByteArray_GET_SIZE(self);
count = countstring(self_s, self_len,
from_s, from_len,
0, self_len, FORWARD, 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 bytes is too long");
return NULL;
}
result_len = self_len + product;
if (result_len < 0) {
PyErr_SetString(PyExc_OverflowError, "replace bytes is too long");
return NULL;
}
if ( (result = (PyByteArrayObject *)
PyByteArray_FromStringAndSize(NULL, result_len)) == NULL)
return NULL;
result_s = PyByteArray_AS_STRING(result);
start = self_s;
end = self_s + self_len;
while (count-- > 0) {
offset = findstring(start, end-start,
from_s, from_len,
0, end-start, FORWARD);
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 bytes */
Py_MEMCPY(result_s, start, end-start);
return result;
}
Py_LOCAL(PyByteArrayObject *)
replace(PyByteArrayObject *self,
const char *from_s, Py_ssize_t from_len,
const char *to_s, Py_ssize_t to_len,
Py_ssize_t maxcount)
{
if (maxcount < 0) {
maxcount = PY_SSIZE_T_MAX;
} else if (maxcount == 0 || PyByteArray_GET_SIZE(self) == 0) {
/* nothing to do; return the original bytes */
return return_self(self);
}
if (maxcount == 0 ||
(from_len == 0 && to_len == 0)) {
/* nothing to do; return the original bytes */
return return_self(self);
}
/* Handle zero-length special cases */
if (from_len == 0) {
/* insert the 'to' bytes everywhere. */
/* >>> "Python".replace("", ".") */
/* '.P.y.t.h.o.n.' */
return replace_interleave(self, to_s, to_len, maxcount);
}
/* Except for "".replace("", "A") == "A" there is no way beyond this */
/* point for an empty self bytes to generate a non-empty bytes */
/* Special case so the remaining code always gets a non-empty bytes */
if (PyByteArray_GET_SIZE(self) == 0) {
return return_self(self);
}
if (to_len == 0) {
/* delete all occurrences of 'from' bytes */
if (from_len == 1) {
return replace_delete_single_character(
self, from_s[0], maxcount);
} else {
return replace_delete_substring(self, from_s, from_len, maxcount);
}
}
/* Handle special case where both bytes have the same length */
if (from_len == to_len) {
if (from_len == 1) {
return replace_single_character_in_place(
self,
from_s[0],
to_s[0],
maxcount);
} else {
return replace_substring_in_place(
self, from_s, from_len, to_s, to_len, maxcount);
}
}
/* Otherwise use the more generic algorithms */
if (from_len == 1) {
return replace_single_character(self, from_s[0],
to_s, to_len, maxcount);
} else {
/* len('from')>=2, len('to')>=1 */
return replace_substring(self, from_s, from_len, to_s, to_len, maxcount);
}
}
PyDoc_STRVAR(replace__doc__,
"B.replace(old, new[, count]) -> bytearray\n\
\n\
Return a copy of B with all occurrences of subsection\n\
old replaced by new. If the optional argument count is\n\
given, only the first count occurrences are replaced.");
static PyObject *
bytes_replace(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t count = -1;
PyObject *from, *to, *res;
Py_buffer vfrom, vto;
if (!PyArg_ParseTuple(args, "OO|n:replace", &from, &to, &count))
return NULL;
if (_getbuffer(from, &vfrom) < 0)
return NULL;
if (_getbuffer(to, &vto) < 0) {
PyBuffer_Release(&vfrom);
return NULL;
}
res = (PyObject *)replace((PyByteArrayObject *) self,
vfrom.buf, vfrom.len,
vto.buf, vto.len, count);
PyBuffer_Release(&vfrom);
PyBuffer_Release(&vto);
return res;
}
/* Overallocate the initial list to reduce the number of reallocs for small
split sizes. Eg, "A A A A A A A A A A".split() (10 elements) has three
resizes, to sizes 4, 8, then 16. Most observed string splits are for human
text (roughly 11 words per line) and field delimited data (usually 1-10
fields). For large strings the split algorithms are bandwidth limited
so increasing the preallocation likely will not improve things.*/
#define MAX_PREALLOC 12
/* 5 splits gives 6 elements */
#define PREALLOC_SIZE(maxsplit) \
(maxsplit >= MAX_PREALLOC ? MAX_PREALLOC : maxsplit+1)
#define SPLIT_APPEND(data, left, right) \
str = PyByteArray_FromStringAndSize((data) + (left), \
(right) - (left)); \
if (str == NULL) \
goto onError; \
if (PyList_Append(list, str)) { \
Py_DECREF(str); \
goto onError; \
} \
else \
Py_DECREF(str);
#define SPLIT_ADD(data, left, right) { \
str = PyByteArray_FromStringAndSize((data) + (left), \
(right) - (left)); \
if (str == NULL) \
goto onError; \
if (count < MAX_PREALLOC) { \
PyList_SET_ITEM(list, count, str); \
} else { \
if (PyList_Append(list, str)) { \
Py_DECREF(str); \
goto onError; \
} \
else \
Py_DECREF(str); \
} \
count++; }
/* Always force the list to the expected size. */
#define FIX_PREALLOC_SIZE(list) Py_SIZE(list) = count
Py_LOCAL_INLINE(PyObject *)
split_char(const char *s, Py_ssize_t len, char ch, Py_ssize_t maxcount)
{
register Py_ssize_t i, j, count = 0;
PyObject *str;
PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));
if (list == NULL)
return NULL;
i = j = 0;
while ((j < len) && (maxcount-- > 0)) {
for(; j < len; j++) {
/* I found that using memchr makes no difference */
if (s[j] == ch) {
SPLIT_ADD(s, i, j);
i = j = j + 1;
break;
}
}
}
if (i <= len) {
SPLIT_ADD(s, i, len);
}
FIX_PREALLOC_SIZE(list);
return list;
onError:
Py_DECREF(list);
return NULL;
}
Py_LOCAL_INLINE(PyObject *)
split_whitespace(const char *s, Py_ssize_t len, Py_ssize_t maxcount)
{
register Py_ssize_t i, j, count = 0;
PyObject *str;
PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));
if (list == NULL)
return NULL;
for (i = j = 0; i < len; ) {
/* find a token */
while (i < len && ISSPACE(s[i]))
i++;
j = i;
while (i < len && !ISSPACE(s[i]))
i++;
if (j < i) {
if (maxcount-- <= 0)
break;
SPLIT_ADD(s, j, i);
while (i < len && ISSPACE(s[i]))
i++;
j = i;
}
}
if (j < len) {
SPLIT_ADD(s, j, len);
}
FIX_PREALLOC_SIZE(list);
return list;
onError:
Py_DECREF(list);
return NULL;
}
PyDoc_STRVAR(split__doc__,
"B.split([sep[, maxsplit]]) -> list of bytearrays\n\
\n\
Return a list of the sections in B, using sep as the delimiter.\n\
If sep is not given, B is split on ASCII whitespace characters\n\
(space, tab, return, newline, formfeed, vertical tab).\n\
If maxsplit is given, at most maxsplit splits are done.");
static PyObject *
bytes_split(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t len = PyByteArray_GET_SIZE(self), n, i, j;
Py_ssize_t maxsplit = -1, count = 0;
const char *s = PyByteArray_AS_STRING(self), *sub;
PyObject *list, *str, *subobj = Py_None;
Py_buffer vsub;
#ifdef USE_FAST
Py_ssize_t pos;
#endif
if (!PyArg_ParseTuple(args, "|On:split", &subobj, &maxsplit))
return NULL;
if (maxsplit < 0)
maxsplit = PY_SSIZE_T_MAX;
if (subobj == Py_None)
return split_whitespace(s, len, maxsplit);
if (_getbuffer(subobj, &vsub) < 0)
return NULL;
sub = vsub.buf;
n = vsub.len;
if (n == 0) {
PyErr_SetString(PyExc_ValueError, "empty separator");
PyBuffer_Release(&vsub);
return NULL;
}
if (n == 1) {
list = split_char(s, len, sub[0], maxsplit);
PyBuffer_Release(&vsub);
return list;
}
list = PyList_New(PREALLOC_SIZE(maxsplit));
if (list == NULL) {
PyBuffer_Release(&vsub);
return NULL;
}
#ifdef USE_FAST
i = j = 0;
while (maxsplit-- > 0) {
pos = fastsearch(s+i, len-i, sub, n, FAST_SEARCH);
if (pos < 0)
break;
j = i+pos;
SPLIT_ADD(s, i, j);
i = j + n;
}
#else
i = j = 0;
while ((j+n <= len) && (maxsplit-- > 0)) {
for (; j+n <= len; j++) {
if (Py_STRING_MATCH(s, j, sub, n)) {
SPLIT_ADD(s, i, j);
i = j = j + n;
break;
}
}
}
#endif
SPLIT_ADD(s, i, len);
FIX_PREALLOC_SIZE(list);
PyBuffer_Release(&vsub);
return list;
onError:
Py_DECREF(list);
PyBuffer_Release(&vsub);
return NULL;
}
/* stringlib's partition shares nullbytes in some cases.
undo this, we don't want the nullbytes to be shared. */
static PyObject *
make_nullbytes_unique(PyObject *result)
{
if (result != NULL) {
int i;
assert(PyTuple_Check(result));
assert(PyTuple_GET_SIZE(result) == 3);
for (i = 0; i < 3; i++) {
if (PyTuple_GET_ITEM(result, i) == (PyObject *)nullbytes) {
PyObject *new = PyByteArray_FromStringAndSize(NULL, 0);
if (new == NULL) {
Py_DECREF(result);
result = NULL;
break;
}
Py_DECREF(nullbytes);
PyTuple_SET_ITEM(result, i, new);
}
}
}
return result;
}
PyDoc_STRVAR(partition__doc__,
"B.partition(sep) -> (head, sep, tail)\n\
\n\
Search for the separator sep in B, and return the part before it,\n\
the separator itself, and the part after it. If the separator is not\n\
found, returns B and two empty bytearray objects.");
static PyObject *
bytes_partition(PyByteArrayObject *self, PyObject *sep_obj)
{
PyObject *bytesep, *result;
bytesep = PyByteArray_FromObject(sep_obj);
if (! bytesep)
return NULL;
result = stringlib_partition(
(PyObject*) self,
PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self),
bytesep,
PyByteArray_AS_STRING(bytesep), PyByteArray_GET_SIZE(bytesep)
);
Py_DECREF(bytesep);
return make_nullbytes_unique(result);
}
PyDoc_STRVAR(rpartition__doc__,
"B.rpartition(sep) -> (tail, sep, head)\n\
\n\
Search for the separator sep in B, starting at the end of B,\n\
and return the part before it, the separator itself, and the\n\
part after it. If the separator is not found, returns two empty\n\
bytearray objects and B.");
static PyObject *
bytes_rpartition(PyByteArrayObject *self, PyObject *sep_obj)
{
PyObject *bytesep, *result;
bytesep = PyByteArray_FromObject(sep_obj);
if (! bytesep)
return NULL;
result = stringlib_rpartition(
(PyObject*) self,
PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self),
bytesep,
PyByteArray_AS_STRING(bytesep), PyByteArray_GET_SIZE(bytesep)
);
Py_DECREF(bytesep);
return make_nullbytes_unique(result);
}
Py_LOCAL_INLINE(PyObject *)
rsplit_char(const char *s, Py_ssize_t len, char ch, Py_ssize_t maxcount)
{
register Py_ssize_t i, j, count=0;
PyObject *str;
PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));
if (list == NULL)
return NULL;
i = j = len - 1;
while ((i >= 0) && (maxcount-- > 0)) {
for (; i >= 0; i--) {
if (s[i] == ch) {
SPLIT_ADD(s, i + 1, j + 1);
j = i = i - 1;
break;
}
}
}
if (j >= -1) {
SPLIT_ADD(s, 0, j + 1);
}
FIX_PREALLOC_SIZE(list);
if (PyList_Reverse(list) < 0)
goto onError;
return list;
onError:
Py_DECREF(list);
return NULL;
}
Py_LOCAL_INLINE(PyObject *)
rsplit_whitespace(const char *s, Py_ssize_t len, Py_ssize_t maxcount)
{
register Py_ssize_t i, j, count = 0;
PyObject *str;
PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));
if (list == NULL)
return NULL;
for (i = j = len - 1; i >= 0; ) {
/* find a token */
while (i >= 0 && ISSPACE(s[i]))
i--;
j = i;
while (i >= 0 && !ISSPACE(s[i]))
i--;
if (j > i) {
if (maxcount-- <= 0)
break;
SPLIT_ADD(s, i + 1, j + 1);
while (i >= 0 && ISSPACE(s[i]))
i--;
j = i;
}
}
if (j >= 0) {
SPLIT_ADD(s, 0, j + 1);
}
FIX_PREALLOC_SIZE(list);
if (PyList_Reverse(list) < 0)
goto onError;
return list;
onError:
Py_DECREF(list);
return NULL;
}
PyDoc_STRVAR(rsplit__doc__,
"B.rsplit(sep[, maxsplit]) -> list of bytearrays\n\
\n\
Return a list of the sections in B, using sep as the delimiter,\n\
starting at the end of B and working to the front.\n\
If sep is not given, B is split on ASCII whitespace characters\n\
(space, tab, return, newline, formfeed, vertical tab).\n\
If maxsplit is given, at most maxsplit splits are done.");
static PyObject *
bytes_rsplit(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t len = PyByteArray_GET_SIZE(self), n, i, j;
Py_ssize_t maxsplit = -1, count = 0;
const char *s = PyByteArray_AS_STRING(self), *sub;
PyObject *list, *str, *subobj = Py_None;
Py_buffer vsub;
if (!PyArg_ParseTuple(args, "|On:rsplit", &subobj, &maxsplit))
return NULL;
if (maxsplit < 0)
maxsplit = PY_SSIZE_T_MAX;
if (subobj == Py_None)
return rsplit_whitespace(s, len, maxsplit);
if (_getbuffer(subobj, &vsub) < 0)
return NULL;
sub = vsub.buf;
n = vsub.len;
if (n == 0) {
PyErr_SetString(PyExc_ValueError, "empty separator");
PyBuffer_Release(&vsub);
return NULL;
}
else if (n == 1) {
list = rsplit_char(s, len, sub[0], maxsplit);
PyBuffer_Release(&vsub);
return list;
}
list = PyList_New(PREALLOC_SIZE(maxsplit));
if (list == NULL) {
PyBuffer_Release(&vsub);
return NULL;
}
j = len;
i = j - n;
while ( (i >= 0) && (maxsplit-- > 0) ) {
for (; i>=0; i--) {
if (Py_STRING_MATCH(s, i, sub, n)) {
SPLIT_ADD(s, i + n, j);
j = i;
i -= n;
break;
}
}
}
SPLIT_ADD(s, 0, j);
FIX_PREALLOC_SIZE(list);
if (PyList_Reverse(list) < 0)
goto onError;
PyBuffer_Release(&vsub);
return list;
onError:
Py_DECREF(list);
PyBuffer_Release(&vsub);
return NULL;
}
PyDoc_STRVAR(reverse__doc__,
"B.reverse() -> None\n\
\n\
Reverse the order of the values in B in place.");
static PyObject *
bytes_reverse(PyByteArrayObject *self, PyObject *unused)
{
char swap, *head, *tail;
Py_ssize_t i, j, n = Py_SIZE(self);
j = n / 2;
head = self->ob_bytes;
tail = head + n - 1;
for (i = 0; i < j; i++) {
swap = *head;
*head++ = *tail;
*tail-- = swap;
}
Py_RETURN_NONE;
}
PyDoc_STRVAR(insert__doc__,
"B.insert(index, int) -> None\n\
\n\
Insert a single item into the bytearray before the given index.");
static PyObject *
bytes_insert(PyByteArrayObject *self, PyObject *args)
{
PyObject *value;
int ival;
Py_ssize_t where, n = Py_SIZE(self);
if (!PyArg_ParseTuple(args, "nO:insert", &where, &value))
return NULL;
if (n == PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError,
"cannot add more objects to bytes");
return NULL;
}
if (!_getbytevalue(value, &ival))
return NULL;
if (PyByteArray_Resize((PyObject *)self, n + 1) < 0)
return NULL;
if (where < 0) {
where += n;
if (where < 0)
where = 0;
}
if (where > n)
where = n;
memmove(self->ob_bytes + where + 1, self->ob_bytes + where, n - where);
self->ob_bytes[where] = ival;
Py_RETURN_NONE;
}
PyDoc_STRVAR(append__doc__,
"B.append(int) -> None\n\
\n\
Append a single item to the end of B.");
static PyObject *
bytes_append(PyByteArrayObject *self, PyObject *arg)
{
int value;
Py_ssize_t n = Py_SIZE(self);
if (! _getbytevalue(arg, &value))
return NULL;
if (n == PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError,
"cannot add more objects to bytes");
return NULL;
}
if (PyByteArray_Resize((PyObject *)self, n + 1) < 0)
return NULL;
self->ob_bytes[n] = value;
Py_RETURN_NONE;
}
PyDoc_STRVAR(extend__doc__,
"B.extend(iterable_of_ints) -> None\n\
\n\
Append all the elements from the iterator or sequence to the\n\
end of B.");
static PyObject *
bytes_extend(PyByteArrayObject *self, PyObject *arg)
{
PyObject *it, *item, *bytes_obj;
Py_ssize_t buf_size = 0, len = 0;
int value;
char *buf;
/* bytes_setslice code only accepts something supporting PEP 3118. */
if (PyObject_CheckBuffer(arg)) {
if (bytes_setslice(self, Py_SIZE(self), Py_SIZE(self), arg) == -1)
return NULL;
Py_RETURN_NONE;
}
it = PyObject_GetIter(arg);
if (it == NULL)
return NULL;
/* Try to determine the length of the argument. 32 is abitrary. */
buf_size = _PyObject_LengthHint(arg, 32);
bytes_obj = PyByteArray_FromStringAndSize(NULL, buf_size);
if (bytes_obj == NULL)
return NULL;
buf = PyByteArray_AS_STRING(bytes_obj);
while ((item = PyIter_Next(it)) != NULL) {
if (! _getbytevalue(item, &value)) {
Py_DECREF(item);
Py_DECREF(it);
Py_DECREF(bytes_obj);
return NULL;
}
buf[len++] = value;
Py_DECREF(item);
if (len >= buf_size) {
buf_size = len + (len >> 1) + 1;
if (PyByteArray_Resize((PyObject *)bytes_obj, buf_size) < 0) {
Py_DECREF(it);
Py_DECREF(bytes_obj);
return NULL;
}
/* Recompute the `buf' pointer, since the resizing operation may
have invalidated it. */
buf = PyByteArray_AS_STRING(bytes_obj);
}
}
Py_DECREF(it);
/* Resize down to exact size. */
if (PyByteArray_Resize((PyObject *)bytes_obj, len) < 0) {
Py_DECREF(bytes_obj);
return NULL;
}
if (bytes_setslice(self, Py_SIZE(self), Py_SIZE(self), bytes_obj) == -1)
return NULL;
Py_DECREF(bytes_obj);
Py_RETURN_NONE;
}
PyDoc_STRVAR(pop__doc__,
"B.pop([index]) -> int\n\
\n\
Remove and return a single item from B. If no index\n\
Merged revisions 64434-64435,64440-64443,64445,64447-64448,64450,64452,64455,64461,64464,64466,64468 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r64434 | andrew.kuchling | 2008-06-20 18:13:58 -0500 (Fri, 20 Jun 2008) | 1 line Remove request for e-mail; it's unlikely these classes will be saved ........ r64435 | andrew.kuchling | 2008-06-20 18:14:32 -0500 (Fri, 20 Jun 2008) | 1 line Grammar fixes ........ r64440 | andrew.kuchling | 2008-06-21 08:29:12 -0500 (Sat, 21 Jun 2008) | 1 line Docstring typo ........ r64441 | andrew.kuchling | 2008-06-21 08:47:20 -0500 (Sat, 21 Jun 2008) | 1 line Use repr() for bad input strings; this makes the empty string or binary characters more visible ........ r64442 | andrew.kuchling | 2008-06-21 08:48:38 -0500 (Sat, 21 Jun 2008) | 1 line Docstring correction ........ r64443 | georg.brandl | 2008-06-21 09:26:19 -0500 (Sat, 21 Jun 2008) | 2 lines Documentation fix. ........ r64445 | facundo.batista | 2008-06-21 12:30:06 -0500 (Sat, 21 Jun 2008) | 3 lines Reviewed and updated the documentation. Fixes #3017. ........ r64447 | facundo.batista | 2008-06-21 13:58:04 -0500 (Sat, 21 Jun 2008) | 6 lines Now a from submitted via POST that also has a query string will contain both FieldStorage and MiniFieldStorage items. Fixes #1817. ........ r64448 | facundo.batista | 2008-06-21 14:48:19 -0500 (Sat, 21 Jun 2008) | 5 lines In the deprecated functions I added an alert to review specially a section of the subprocess documentation that helps with the replacing of those functionss. ........ r64450 | georg.brandl | 2008-06-22 04:05:29 -0500 (Sun, 22 Jun 2008) | 2 lines Turn section references into proper cross-references. ........ r64452 | facundo.batista | 2008-06-22 08:36:20 -0500 (Sun, 22 Jun 2008) | 5 lines Issue #2722. Now the char buffer to support the path string has not fixed length, it mallocs memory if needed. As a result, we don't have a maximum for the getcwd() method. ........ r64455 | facundo.batista | 2008-06-22 10:27:10 -0500 (Sun, 22 Jun 2008) | 4 lines Issue 3164. Small fix to don't repeat a comparation without necessity. ........ r64461 | georg.brandl | 2008-06-22 13:11:52 -0500 (Sun, 22 Jun 2008) | 2 lines #3085: Fix syntax error. ........ r64464 | georg.brandl | 2008-06-22 13:31:54 -0500 (Sun, 22 Jun 2008) | 2 lines Expand docstrings of sqlite3 functions. ........ r64466 | georg.brandl | 2008-06-22 14:07:59 -0500 (Sun, 22 Jun 2008) | 2 lines Write out "phi" consistently. ........ r64468 | facundo.batista | 2008-06-22 14:35:24 -0500 (Sun, 22 Jun 2008) | 4 lines Just returning nothing instead of rising TestSkipped, because it makes the test fail in the trunk.loewis-sun buildbot. ........
2008-07-02 14:30:14 -03:00
argument is given, will pop the last value.");
static PyObject *
bytes_pop(PyByteArrayObject *self, PyObject *args)
{
int value;
Py_ssize_t where = -1, n = Py_SIZE(self);
if (!PyArg_ParseTuple(args, "|n:pop", &where))
return NULL;
if (n == 0) {
PyErr_SetString(PyExc_OverflowError,
"cannot pop an empty bytes");
return NULL;
}
if (where < 0)
where += Py_SIZE(self);
if (where < 0 || where >= Py_SIZE(self)) {
PyErr_SetString(PyExc_IndexError, "pop index out of range");
return NULL;
}
value = self->ob_bytes[where];
memmove(self->ob_bytes + where, self->ob_bytes + where + 1, n - where);
if (PyByteArray_Resize((PyObject *)self, n - 1) < 0)
return NULL;
return PyLong_FromLong(value);
}
PyDoc_STRVAR(remove__doc__,
"B.remove(int) -> None\n\
\n\
Remove the first occurrence of a value in B.");
static PyObject *
bytes_remove(PyByteArrayObject *self, PyObject *arg)
{
int value;
Py_ssize_t where, n = Py_SIZE(self);
if (! _getbytevalue(arg, &value))
return NULL;
for (where = 0; where < n; where++) {
if (self->ob_bytes[where] == value)
break;
}
if (where == n) {
PyErr_SetString(PyExc_ValueError, "value not found in bytes");
return NULL;
}
memmove(self->ob_bytes + where, self->ob_bytes + where + 1, n - where);
if (PyByteArray_Resize((PyObject *)self, n - 1) < 0)
return NULL;
Py_RETURN_NONE;
}
/* XXX These two helpers could be optimized if argsize == 1 */
static Py_ssize_t
lstrip_helper(unsigned char *myptr, Py_ssize_t mysize,
void *argptr, Py_ssize_t argsize)
{
Py_ssize_t i = 0;
while (i < mysize && memchr(argptr, myptr[i], argsize))
i++;
return i;
}
static Py_ssize_t
rstrip_helper(unsigned char *myptr, Py_ssize_t mysize,
void *argptr, Py_ssize_t argsize)
{
Py_ssize_t i = mysize - 1;
while (i >= 0 && memchr(argptr, myptr[i], argsize))
i--;
return i + 1;
}
PyDoc_STRVAR(strip__doc__,
"B.strip([bytes]) -> bytearray\n\
\n\
Strip leading and trailing bytes contained in the argument\n\
and return the result as a new bytearray.\n\
If the argument is omitted, strip ASCII whitespace.");
static PyObject *
bytes_strip(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t left, right, mysize, argsize;
void *myptr, *argptr;
PyObject *arg = Py_None;
Py_buffer varg;
if (!PyArg_ParseTuple(args, "|O:strip", &arg))
return NULL;
if (arg == Py_None) {
argptr = "\t\n\r\f\v ";
argsize = 6;
}
else {
if (_getbuffer(arg, &varg) < 0)
return NULL;
argptr = varg.buf;
argsize = varg.len;
}
myptr = self->ob_bytes;
mysize = Py_SIZE(self);
left = lstrip_helper(myptr, mysize, argptr, argsize);
if (left == mysize)
right = left;
else
right = rstrip_helper(myptr, mysize, argptr, argsize);
if (arg != Py_None)
PyBuffer_Release(&varg);
return PyByteArray_FromStringAndSize(self->ob_bytes + left, right - left);
}
PyDoc_STRVAR(lstrip__doc__,
"B.lstrip([bytes]) -> bytearray\n\
\n\
Strip leading bytes contained in the argument\n\
and return the result as a new bytearray.\n\
If the argument is omitted, strip leading ASCII whitespace.");
static PyObject *
bytes_lstrip(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t left, right, mysize, argsize;
void *myptr, *argptr;
PyObject *arg = Py_None;
Py_buffer varg;
if (!PyArg_ParseTuple(args, "|O:lstrip", &arg))
return NULL;
if (arg == Py_None) {
argptr = "\t\n\r\f\v ";
argsize = 6;
}
else {
if (_getbuffer(arg, &varg) < 0)
return NULL;
argptr = varg.buf;
argsize = varg.len;
}
myptr = self->ob_bytes;
mysize = Py_SIZE(self);
left = lstrip_helper(myptr, mysize, argptr, argsize);
right = mysize;
if (arg != Py_None)
PyBuffer_Release(&varg);
return PyByteArray_FromStringAndSize(self->ob_bytes + left, right - left);
}
PyDoc_STRVAR(rstrip__doc__,
"B.rstrip([bytes]) -> bytearray\n\
\n\
Strip trailing bytes contained in the argument\n\
and return the result as a new bytearray.\n\
If the argument is omitted, strip trailing ASCII whitespace.");
static PyObject *
bytes_rstrip(PyByteArrayObject *self, PyObject *args)
{
Py_ssize_t left, right, mysize, argsize;
void *myptr, *argptr;
PyObject *arg = Py_None;
Py_buffer varg;
if (!PyArg_ParseTuple(args, "|O:rstrip", &arg))
return NULL;
if (arg == Py_None) {
argptr = "\t\n\r\f\v ";
argsize = 6;
}
else {
if (_getbuffer(arg, &varg) < 0)
return NULL;
argptr = varg.buf;
argsize = varg.len;
}
myptr = self->ob_bytes;
mysize = Py_SIZE(self);
left = 0;
right = rstrip_helper(myptr, mysize, argptr, argsize);
if (arg != Py_None)
PyBuffer_Release(&varg);
return PyByteArray_FromStringAndSize(self->ob_bytes + left, right - left);
}
PyDoc_STRVAR(decode_doc,
"B.decode([encoding[, errors]]) -> str\n\
\n\
Decode B using the codec registered for encoding. encoding defaults\n\
to the default encoding. errors may be given to set a different error\n\
handling scheme. Default is 'strict' meaning that encoding errors raise\n\
a UnicodeDecodeError. Other possible values are 'ignore' and 'replace'\n\
as well as any other name registered with codecs.register_error that is\n\
able to handle UnicodeDecodeErrors.");
static PyObject *
bytes_decode(PyObject *self, PyObject *args)
{
const char *encoding = NULL;
const char *errors = NULL;
if (!PyArg_ParseTuple(args, "|ss:decode", &encoding, &errors))
return NULL;
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
return PyUnicode_FromEncodedObject(self, encoding, errors);
}
PyDoc_STRVAR(alloc_doc,
"B.__alloc__() -> int\n\
\n\
Return the number of bytes actually allocated.");
static PyObject *
bytes_alloc(PyByteArrayObject *self)
{
return PyLong_FromSsize_t(self->ob_alloc);
}
PyDoc_STRVAR(join_doc,
"B.join(iterable_of_bytes) -> bytearray\n\
\n\
Concatenate any number of bytes/bytearray objects, with B\n\
in between each pair, and return the result as a new bytearray.");
static PyObject *
bytes_join(PyByteArrayObject *self, PyObject *it)
{
PyObject *seq;
Py_ssize_t mysize = Py_SIZE(self);
Py_ssize_t i;
Py_ssize_t n;
PyObject **items;
Py_ssize_t totalsize = 0;
PyObject *result;
char *dest;
seq = PySequence_Fast(it, "can only join an iterable");
if (seq == NULL)
return NULL;
n = PySequence_Fast_GET_SIZE(seq);
items = PySequence_Fast_ITEMS(seq);
/* Compute the total size, and check that they are all bytes */
/* XXX Shouldn't we use _getbuffer() on these items instead? */
for (i = 0; i < n; i++) {
PyObject *obj = items[i];
if (!PyByteArray_Check(obj) && !PyBytes_Check(obj)) {
PyErr_Format(PyExc_TypeError,
"can only join an iterable of bytes "
"(item %ld has type '%.100s')",
/* XXX %ld isn't right on Win64 */
(long)i, Py_TYPE(obj)->tp_name);
goto error;
}
if (i > 0)
totalsize += mysize;
totalsize += Py_SIZE(obj);
if (totalsize < 0) {
PyErr_NoMemory();
goto error;
}
}
/* Allocate the result, and copy the bytes */
result = PyByteArray_FromStringAndSize(NULL, totalsize);
if (result == NULL)
goto error;
dest = PyByteArray_AS_STRING(result);
for (i = 0; i < n; i++) {
PyObject *obj = items[i];
Py_ssize_t size = Py_SIZE(obj);
char *buf;
if (PyByteArray_Check(obj))
buf = PyByteArray_AS_STRING(obj);
else
buf = PyBytes_AS_STRING(obj);
if (i) {
memcpy(dest, self->ob_bytes, mysize);
dest += mysize;
}
memcpy(dest, buf, size);
dest += size;
}
/* Done */
Py_DECREF(seq);
return result;
/* Error handling */
error:
Py_DECREF(seq);
return NULL;
}
PyDoc_STRVAR(fromhex_doc,
"bytearray.fromhex(string) -> bytearray (static method)\n\
\n\
Create a bytearray object from a string of hexadecimal numbers.\n\
Spaces between two numbers are accepted.\n\
Example: bytearray.fromhex('B9 01EF') -> bytearray(b'\\xb9\\x01\\xef').");
static int
hex_digit_to_int(Py_UNICODE c)
{
if (c >= 128)
return -1;
if (ISDIGIT(c))
return c - '0';
else {
if (ISUPPER(c))
c = TOLOWER(c);
if (c >= 'a' && c <= 'f')
return c - 'a' + 10;
}
return -1;
}
static PyObject *
bytes_fromhex(PyObject *cls, PyObject *args)
{
PyObject *newbytes, *hexobj;
char *buf;
Py_UNICODE *hex;
Py_ssize_t hexlen, byteslen, i, j;
int top, bot;
if (!PyArg_ParseTuple(args, "U:fromhex", &hexobj))
return NULL;
assert(PyUnicode_Check(hexobj));
hexlen = PyUnicode_GET_SIZE(hexobj);
hex = PyUnicode_AS_UNICODE(hexobj);
byteslen = hexlen/2; /* This overestimates if there are spaces */
newbytes = PyByteArray_FromStringAndSize(NULL, byteslen);
if (!newbytes)
return NULL;
buf = PyByteArray_AS_STRING(newbytes);
for (i = j = 0; i < hexlen; i += 2) {
/* skip over spaces in the input */
while (hex[i] == ' ')
i++;
if (i >= hexlen)
break;
top = hex_digit_to_int(hex[i]);
bot = hex_digit_to_int(hex[i+1]);
if (top == -1 || bot == -1) {
PyErr_Format(PyExc_ValueError,
"non-hexadecimal number found in "
"fromhex() arg at position %zd", i);
goto error;
}
buf[j++] = (top << 4) + bot;
}
if (PyByteArray_Resize(newbytes, j) < 0)
goto error;
return newbytes;
error:
Py_DECREF(newbytes);
return NULL;
}
PyDoc_STRVAR(reduce_doc, "Return state information for pickling.");
static PyObject *
bytes_reduce(PyByteArrayObject *self)
{
PyObject *latin1, *dict;
if (self->ob_bytes)
latin1 = PyUnicode_DecodeLatin1(self->ob_bytes,
Py_SIZE(self), NULL);
else
latin1 = PyUnicode_FromString("");
dict = PyObject_GetAttrString((PyObject *)self, "__dict__");
if (dict == NULL) {
PyErr_Clear();
dict = Py_None;
Py_INCREF(dict);
}
return Py_BuildValue("(O(Ns)N)", Py_TYPE(self), latin1, "latin-1", dict);
}
PyDoc_STRVAR(sizeof_doc,
"B.__sizeof__() -> int\n\
\n\
Returns the size of B in memory, in bytes");
static PyObject *
bytes_sizeof(PyByteArrayObject *self)
{
Py_ssize_t res;
res = sizeof(PyByteArrayObject) + self->ob_alloc * sizeof(char);
return PyLong_FromSsize_t(res);
}
static PySequenceMethods bytes_as_sequence = {
(lenfunc)bytes_length, /* sq_length */
(binaryfunc)PyByteArray_Concat, /* sq_concat */
(ssizeargfunc)bytes_repeat, /* sq_repeat */
(ssizeargfunc)bytes_getitem, /* sq_item */
0, /* sq_slice */
(ssizeobjargproc)bytes_setitem, /* sq_ass_item */
0, /* sq_ass_slice */
(objobjproc)bytes_contains, /* sq_contains */
(binaryfunc)bytes_iconcat, /* sq_inplace_concat */
(ssizeargfunc)bytes_irepeat, /* sq_inplace_repeat */
};
static PyMappingMethods bytes_as_mapping = {
(lenfunc)bytes_length,
(binaryfunc)bytes_subscript,
(objobjargproc)bytes_ass_subscript,
};
static PyBufferProcs bytes_as_buffer = {
(getbufferproc)bytes_getbuffer,
(releasebufferproc)bytes_releasebuffer,
};
static PyMethodDef
bytes_methods[] = {
{"__alloc__", (PyCFunction)bytes_alloc, METH_NOARGS, alloc_doc},
{"__reduce__", (PyCFunction)bytes_reduce, METH_NOARGS, reduce_doc},
{"__sizeof__", (PyCFunction)bytes_sizeof, METH_NOARGS, sizeof_doc},
{"append", (PyCFunction)bytes_append, METH_O, append__doc__},
{"capitalize", (PyCFunction)stringlib_capitalize, METH_NOARGS,
_Py_capitalize__doc__},
{"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__},
{"count", (PyCFunction)bytes_count, METH_VARARGS, count__doc__},
{"decode", (PyCFunction)bytes_decode, METH_VARARGS, decode_doc},
{"endswith", (PyCFunction)bytes_endswith, METH_VARARGS, endswith__doc__},
{"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS,
expandtabs__doc__},
{"extend", (PyCFunction)bytes_extend, METH_O, extend__doc__},
{"find", (PyCFunction)bytes_find, METH_VARARGS, find__doc__},
{"fromhex", (PyCFunction)bytes_fromhex, METH_VARARGS|METH_CLASS,
fromhex_doc},
{"index", (PyCFunction)bytes_index, METH_VARARGS, index__doc__},
{"insert", (PyCFunction)bytes_insert, METH_VARARGS, insert__doc__},
{"isalnum", (PyCFunction)stringlib_isalnum, METH_NOARGS,
_Py_isalnum__doc__},
{"isalpha", (PyCFunction)stringlib_isalpha, METH_NOARGS,
_Py_isalpha__doc__},
{"isdigit", (PyCFunction)stringlib_isdigit, METH_NOARGS,
_Py_isdigit__doc__},
{"islower", (PyCFunction)stringlib_islower, METH_NOARGS,
_Py_islower__doc__},
{"isspace", (PyCFunction)stringlib_isspace, METH_NOARGS,
_Py_isspace__doc__},
{"istitle", (PyCFunction)stringlib_istitle, METH_NOARGS,
_Py_istitle__doc__},
{"isupper", (PyCFunction)stringlib_isupper, METH_NOARGS,
_Py_isupper__doc__},
{"join", (PyCFunction)bytes_join, METH_O, join_doc},
{"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, ljust__doc__},
{"lower", (PyCFunction)stringlib_lower, METH_NOARGS, _Py_lower__doc__},
{"lstrip", (PyCFunction)bytes_lstrip, METH_VARARGS, lstrip__doc__},
{"partition", (PyCFunction)bytes_partition, METH_O, partition__doc__},
{"pop", (PyCFunction)bytes_pop, METH_VARARGS, pop__doc__},
{"remove", (PyCFunction)bytes_remove, METH_O, remove__doc__},
{"replace", (PyCFunction)bytes_replace, METH_VARARGS, replace__doc__},
{"reverse", (PyCFunction)bytes_reverse, METH_NOARGS, reverse__doc__},
{"rfind", (PyCFunction)bytes_rfind, METH_VARARGS, rfind__doc__},
{"rindex", (PyCFunction)bytes_rindex, METH_VARARGS, rindex__doc__},
{"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, rjust__doc__},
{"rpartition", (PyCFunction)bytes_rpartition, METH_O, rpartition__doc__},
{"rsplit", (PyCFunction)bytes_rsplit, METH_VARARGS, rsplit__doc__},
{"rstrip", (PyCFunction)bytes_rstrip, METH_VARARGS, rstrip__doc__},
{"split", (PyCFunction)bytes_split, METH_VARARGS, split__doc__},
{"splitlines", (PyCFunction)stringlib_splitlines, METH_VARARGS,
splitlines__doc__},
{"startswith", (PyCFunction)bytes_startswith, METH_VARARGS ,
startswith__doc__},
{"strip", (PyCFunction)bytes_strip, METH_VARARGS, strip__doc__},
{"swapcase", (PyCFunction)stringlib_swapcase, METH_NOARGS,
_Py_swapcase__doc__},
{"title", (PyCFunction)stringlib_title, METH_NOARGS, _Py_title__doc__},
{"translate", (PyCFunction)bytes_translate, METH_VARARGS,
translate__doc__},
{"upper", (PyCFunction)stringlib_upper, METH_NOARGS, _Py_upper__doc__},
{"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, zfill__doc__},
{NULL}
};
PyDoc_STRVAR(bytes_doc,
"bytearray(iterable_of_ints) -> bytearray\n\
bytearray(string, encoding[, errors]) -> bytearray\n\
bytearray(bytes_or_bytearray) -> mutable copy of bytes_or_bytearray\n\
bytearray(memory_view) -> bytearray\n\
\n\
Construct an mutable bytearray object from:\n\
- an iterable yielding integers in range(256)\n\
- a text string encoded using the specified encoding\n\
- a bytes or a bytearray object\n\
- any object implementing the buffer API.\n\
\n\
bytearray(int) -> bytearray\n\
\n\
Construct a zero-initialized bytearray of the given length.");
static PyObject *bytes_iter(PyObject *seq);
PyTypeObject PyByteArray_Type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"bytearray",
sizeof(PyByteArrayObject),
0,
(destructor)bytes_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
(reprfunc)bytes_repr, /* tp_repr */
0, /* tp_as_number */
&bytes_as_sequence, /* tp_as_sequence */
&bytes_as_mapping, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
bytes_str, /* tp_str */
PyObject_GenericGetAttr, /* tp_getattro */
0, /* tp_setattro */
&bytes_as_buffer, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */
bytes_doc, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
(richcmpfunc)bytes_richcompare, /* tp_richcompare */
0, /* tp_weaklistoffset */
bytes_iter, /* tp_iter */
0, /* tp_iternext */
bytes_methods, /* tp_methods */
0, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc)bytes_init, /* tp_init */
PyType_GenericAlloc, /* tp_alloc */
PyType_GenericNew, /* tp_new */
PyObject_Del, /* tp_free */
};
/*********************** Bytes Iterator ****************************/
typedef struct {
PyObject_HEAD
Py_ssize_t it_index;
PyByteArrayObject *it_seq; /* Set to NULL when iterator is exhausted */
} bytesiterobject;
static void
bytesiter_dealloc(bytesiterobject *it)
{
_PyObject_GC_UNTRACK(it);
Py_XDECREF(it->it_seq);
PyObject_GC_Del(it);
}
static int
bytesiter_traverse(bytesiterobject *it, visitproc visit, void *arg)
{
Py_VISIT(it->it_seq);
return 0;
}
static PyObject *
bytesiter_next(bytesiterobject *it)
{
PyByteArrayObject *seq;
PyObject *item;
assert(it != NULL);
seq = it->it_seq;
if (seq == NULL)
return NULL;
assert(PyByteArray_Check(seq));
if (it->it_index < PyByteArray_GET_SIZE(seq)) {
item = PyLong_FromLong(
(unsigned char)seq->ob_bytes[it->it_index]);
if (item != NULL)
++it->it_index;
return item;
}
Py_DECREF(seq);
it->it_seq = NULL;
return NULL;
}
static PyObject *
bytesiter_length_hint(bytesiterobject *it)
{
Py_ssize_t len = 0;
if (it->it_seq)
len = PyByteArray_GET_SIZE(it->it_seq) - it->it_index;
return PyLong_FromSsize_t(len);
}
PyDoc_STRVAR(length_hint_doc,
"Private method returning an estimate of len(list(it)).");
static PyMethodDef bytesiter_methods[] = {
{"__length_hint__", (PyCFunction)bytesiter_length_hint, METH_NOARGS,
length_hint_doc},
{NULL, NULL} /* sentinel */
};
PyTypeObject PyByteArrayIter_Type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"bytearray_iterator", /* tp_name */
sizeof(bytesiterobject), /* tp_basicsize */
0, /* tp_itemsize */
/* methods */
(destructor)bytesiter_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
PyObject_GenericGetAttr, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
0, /* tp_doc */
(traverseproc)bytesiter_traverse, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
PyObject_SelfIter, /* tp_iter */
(iternextfunc)bytesiter_next, /* tp_iternext */
bytesiter_methods, /* tp_methods */
0,
};
static PyObject *
bytes_iter(PyObject *seq)
{
bytesiterobject *it;
if (!PyByteArray_Check(seq)) {
PyErr_BadInternalCall();
return NULL;
}
it = PyObject_GC_New(bytesiterobject, &PyByteArrayIter_Type);
if (it == NULL)
return NULL;
it->it_index = 0;
Py_INCREF(seq);
it->it_seq = (PyByteArrayObject *)seq;
_PyObject_GC_TRACK(it);
return (PyObject *)it;
}