stringobject.c

python s60 1.4.5版本的源代码

		return string_getbuffer(op);
	return ((PyStringObject *)op) -> ob_sval;
}

DL_EXPORT(int)
PyString_AsStringAndSize(register PyObject *obj,
			 register char **s,
			 register int *len)
{
	if (s == NULL) {
		PyErr_BadInternalCall();
		return -1;
	}

	if (!PyString_Check(obj)) {
#ifdef Py_USING_UNICODE
		if (PyUnicode_Check(obj)) {
			obj = _PyUnicode_AsDefaultEncodedString(obj, NULL);
			if (obj == NULL)
				return -1;
		}
		else
#endif
		{
			PyErr_Format(PyExc_TypeError,
				     "expected string or Unicode object, "
				     "%.200s found", obj->ob_type->tp_name);
			return -1;
		}
	}

	*s = PyString_AS_STRING(obj);
	if (len != NULL)
		*len = PyString_GET_SIZE(obj);
	else if ((int)strlen(*s) != PyString_GET_SIZE(obj)) {
		PyErr_SetString(PyExc_TypeError,
				"expected string without null bytes");
		return -1;
	}
	return 0;
}

/* Methods */

static int
string_print(PyStringObject *op, FILE *fp, int flags)
{
	int i;
	char c;
	int quote;

	/* XXX Ought to check for interrupts when writing long strings */
	if (! PyString_CheckExact(op)) {
		int ret;
		/* A str subclass may have its own __str__ method. */
		op = (PyStringObject *) PyObject_Str((PyObject *)op);
		if (op == NULL)
			return -1;
		ret = string_print(op, fp, flags);
		Py_DECREF(op);
		return ret;
	}
	if (flags & Py_PRINT_RAW) {
		fwrite(op->ob_sval, 1, (int) op->ob_size, fp);
		return 0;
	}

	/* figure out which quote to use; single is preferred */
	quote = '\'';
	if (strchr(op->ob_sval, '\'') &&
	    !strchr(op->ob_sval, '"'))
		quote = '"';

	fputc(quote, fp);
	for (i = 0; i < op->ob_size; i++) {
		c = op->ob_sval[i];
		if (c == quote || c == '\\')
			fprintf(fp, "\\%c", c);
                else if (c == '\t')
                        fprintf(fp, "\\t");
                else if (c == '\n')
                        fprintf(fp, "\\n");
                else if (c == '\r')
                        fprintf(fp, "\\r");
		else if (c < ' ' || c >= 0x7f)
			fprintf(fp, "\\x%02x", c & 0xff);
		else
			fputc(c, fp);
	}
	fputc(quote, fp);
	return 0;
}

static PyObject *
string_repr(register PyStringObject *op)
{
	size_t newsize = 2 + 4 * op->ob_size * sizeof(char);
	PyObject *v;
	if (newsize > INT_MAX) {
		PyErr_SetString(PyExc_OverflowError,
			"string is too large to make repr");
	}
	v = PyString_FromStringAndSize((char *)NULL, newsize);
	if (v == NULL) {
		return NULL;
	}
	else {
		register int i;
		register char c;
		register char *p;
		int quote;

		/* figure out which quote to use; single is preferred */
		quote = '\'';
		if (strchr(op->ob_sval, '\'') &&
		    !strchr(op->ob_sval, '"'))
			quote = '"';

		p = PyString_AS_STRING(v);
		*p++ = quote;
		for (i = 0; i < op->ob_size; i++) {
			/* There's at least enough room for a hex escape
			   and a closing quote. */
			assert(newsize - (p - PyString_AS_STRING(v)) >= 5);
			c = op->ob_sval[i];
			if (c == quote || 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 < ' ' || c >= 0x7f) {
				/* For performance, we don't want to call
				   PyOS_snprintf here (extra layers of
				   function call). */
				sprintf(p, "\\x%02x", c & 0xff);
                                p += 4;
			}
			else
				*p++ = c;
		}
		assert(newsize - (p - PyString_AS_STRING(v)) >= 1);
		*p++ = quote;
		*p = '\0';
		_PyString_Resize(
			&v, (int) (p - PyString_AS_STRING(v)));
		return v;
	}
}

static PyObject *
string_str(PyObject *s)
{
	assert(PyString_Check(s));
	if (PyString_CheckExact(s)) {
		Py_INCREF(s);
		return s;
	}
	else {
		/* Subtype -- return genuine string with the same value. */
		PyStringObject *t = (PyStringObject *) s;
		return PyString_FromStringAndSize(t->ob_sval, t->ob_size);
	}
}

static int
string_length(PyStringObject *a)
{
	return a->ob_size;
}

static PyObject *
string_concat(register PyStringObject *a, register PyObject *bb)
{
	register unsigned int size;
	register PyStringObject *op;
	if (!PyString_Check(bb)) {
#ifdef Py_USING_UNICODE
		if (PyUnicode_Check(bb))
		    return PyUnicode_Concat((PyObject *)a, bb);
#endif
		PyErr_Format(PyExc_TypeError,
			     "cannot concatenate 'str' and '%.200s' objects",
			     bb->ob_type->tp_name);
		return NULL;
	}
#define b ((PyStringObject *)bb)
	/* Optimize cases with empty left or right operand */
	if ((a->ob_size == 0 || b->ob_size == 0) &&
	    PyString_CheckExact(a) && PyString_CheckExact(b)) {
		if (a->ob_size == 0) {
			Py_INCREF(bb);
			return bb;
		}
		Py_INCREF(a);
		return (PyObject *)a;
	}
	size = a->ob_size + b->ob_size;
	/* PyObject_NewVar is inlined */
	op = (PyStringObject *)
		PyObject_MALLOC(sizeof(PyStringObject) + size * sizeof(char));
	if (op == NULL)
		return PyErr_NoMemory();
	PyObject_INIT_VAR(op, &PyString_Type, size);
#ifdef CACHE_HASH
	op->ob_shash = -1;
#endif
#ifdef INTERN_STRINGS
	op->ob_sinterned = NULL;
#endif
	memcpy(op->ob_sval, a->ob_sval, (int) a->ob_size);
	memcpy(op->ob_sval + a->ob_size, b->ob_sval, (int) b->ob_size);
	op->ob_sval[size] = '\0';
	return (PyObject *) op;
#undef b
}

static PyObject *
string_repeat(register PyStringObject *a, register int n)
{
	register int i;
	register int size;
	register PyStringObject *op;
	size_t nbytes;
	if (n < 0)
		n = 0;
	/* watch out for overflows:  the size can overflow int,
	 * and the # of bytes needed can overflow size_t
	 */
	size = a->ob_size * n;
	if (n && size / n != a->ob_size) {
		PyErr_SetString(PyExc_OverflowError,
			"repeated string is too long");
		return NULL;
	}
	if (size == a->ob_size && PyString_CheckExact(a)) {
		Py_INCREF(a);
		return (PyObject *)a;
	}
	nbytes = size * sizeof(char);
	if (nbytes / sizeof(char) != (size_t)size ||
	    nbytes + sizeof(PyStringObject) <= nbytes) {
		PyErr_SetString(PyExc_OverflowError,
			"repeated string is too long");
		return NULL;
	}
	op = (PyStringObject *)
		PyObject_MALLOC(sizeof(PyStringObject) + nbytes);
	if (op == NULL)
		return PyErr_NoMemory();
	PyObject_INIT_VAR(op, &PyString_Type, size);
#ifdef CACHE_HASH
	op->ob_shash = -1;
#endif
#ifdef INTERN_STRINGS
	op->ob_sinterned = NULL;
#endif
	for (i = 0; i < size; i += a->ob_size)
		memcpy(op->ob_sval+i, a->ob_sval, (int) a->ob_size);
	op->ob_sval[size] = '\0';
	return (PyObject *) op;
}

/* String slice a[i:j] consists of characters a[i] ... a[j-1] */

static PyObject *
string_slice(register PyStringObject *a, register int i, register int j)
     /* j -- may be negative! */
{
	if (i < 0)
		i = 0;
	if (j < 0)
		j = 0; /* Avoid signed/unsigned bug in next line */
	if (j > a->ob_size)
		j = a->ob_size;
	if (i == 0 && j == a->ob_size && PyString_CheckExact(a)) {
		/* It's the same as a */
		Py_INCREF(a);
		return (PyObject *)a;
	}
	if (j < i)
		j = i;
	return PyString_FromStringAndSize(a->ob_sval + i, (int) (j-i));
}

static int
string_contains(PyObject *a, PyObject *el)
{
	register char *s, *end;
	register char c;
#ifdef Py_USING_UNICODE
	if (PyUnicode_Check(el))
		return PyUnicode_Contains(a, el);
#endif
	if (!PyString_Check(el) || PyString_Size(el) != 1) {
		PyErr_SetString(PyExc_TypeError,
		    "'in <string>' requires character as left operand");
		return -1;
	}
	c = PyString_AsString(el)[0];
	s = PyString_AsString(a);
	end = s + PyString_Size(a);
	while (s < end) {
		if (c == *s++)
			return 1;
	}
	return 0;
}

static PyObject *
string_item(PyStringObject *a, register int i)
{
	PyObject *v;
	char *pchar;
	if (i < 0 || i >= a->ob_size) {
		PyErr_SetString(PyExc_IndexError, "string index out of range");
		return NULL;
	}
	pchar = a->ob_sval + i;
	v = (PyObject *)characters[*pchar & UCHAR_MAX];
	if (v == NULL)
		v = PyString_FromStringAndSize(pchar, 1);
	else {
#ifdef COUNT_ALLOCS
		one_strings++;
#endif
		Py_INCREF(v);
	}
	return v;
}

static PyObject*
string_richcompare(PyStringObject *a, PyStringObject *b, int op)
{
	int c;
	int len_a, len_b;
	int min_len;
	PyObject *result;

	/* Make sure both arguments are strings. */
	if (!(PyString_Check(a) && PyString_Check(b))) {
		result = Py_NotImplemented;
		goto out;
	}
	if (a == b) {
		switch (op) {
		case Py_EQ:case Py_LE:case Py_GE:
			result = Py_True;
			goto out;
		case Py_NE:case Py_LT:case Py_GT:
			result = Py_False;
			goto out;
		}
	}
	if (op == Py_EQ) {
		/* Supporting Py_NE here as well does not save
		   much time, since Py_NE is rarely used.  */
		if (a->ob_size == b->ob_size
		    && (a->ob_sval[0] == b->ob_sval[0]
			&& memcmp(a->ob_sval, b->ob_sval,
				  a->ob_size) == 0)) {
			result = Py_True;
		} else {
			result = Py_False;
		}
		goto out;
	}
	len_a = a->ob_size; len_b = b->ob_size;
	min_len = (len_a < len_b) ? len_a : len_b;
	if (min_len > 0) {
		c = Py_CHARMASK(*a->ob_sval) - Py_CHARMASK(*b->ob_sval);
		if (c==0)
			c = memcmp(a->ob_sval, b->ob_sval, min_len);
	}else
		c = 0;
	if (c == 0)
		c = (len_a < len_b) ? -1 : (len_a > len_b) ? 1 : 0;
	switch (op) {
	case Py_LT: c = c <  0; break;
	case Py_LE: c = c <= 0; break;
	case Py_EQ: assert(0);  break; /* unreachable */
	case Py_NE: c = c != 0; break;
	case Py_GT: c = c >  0; break;
	case Py_GE: c = c >= 0; break;
	default:
		result = Py_NotImplemented;
		goto out;
	}
	result = c ? Py_True : Py_False;
  out:
	Py_INCREF(result);
	return result;
}

DL_EXPORT(int)
_PyString_Eq(PyObject *o1, PyObject *o2)
{
	PyStringObject *a, *b;
	a = (PyStringObject*)o1;
	b = (PyStringObject*)o2;
        return a->ob_size == b->ob_size
          && *a->ob_sval == *b->ob_sval
          && memcmp(a->ob_sval, b->ob_sval, a->ob_size) == 0;
}

static long
string_hash(PyStringObject *a)
{
	register int len;
	register unsigned char *p;
	register long x;

#ifdef CACHE_HASH
	if (a->ob_shash != -1)
		return a->ob_shash;
#ifdef INTERN_STRINGS
	if (a->ob_sinterned != NULL)
		return (a->ob_shash =
			((PyStringObject *)(a->ob_sinterned))->ob_shash);
#endif
#endif
	len = a->ob_size;
	p = (unsigned char *) a->ob_sval;
	x = *p << 7;
	while (--len >= 0)
		x = (1000003*x) ^ *p++;
	x ^= a->ob_size;
	if (x == -1)
		x = -2;
#ifdef CACHE_HASH
	a->ob_shash = x;
#endif
	return x;
}

static int
string_buffer_getreadbuf(PyStringObject *self, int index, const void **ptr)
{
	if ( index != 0 ) {
		PyErr_SetString(PyExc_SystemError,
				"accessing non-existent string segment");
		return -1;
	}
	*ptr = (void *)self->ob_sval;
	return self->ob_size;
}

static int
string_buffer_getwritebuf(PyStringObject *self, int index, const void **ptr)
{
	PyErr_SetString(PyExc_TypeError,
			"Cannot use string as modifiable buffer");
	return -1;
}

static int
string_buffer_getsegcount(PyStringObject *self, int *lenp)
{
	if ( lenp )
		*lenp = self->ob_size;
	return 1;
}

static int
string_buffer_getcharbuf(PyStringObject *self, int index, const char **ptr)
{
	if ( index != 0 ) {
		PyErr_SetString(PyExc_SystemError,
				"accessing non-existent string segment");
		return -1;
	}
	*ptr = self->ob_sval;
	return self->ob_size;
}

const static PySequenceMethods string_as_sequence = {
	(inquiry)string_length, /*sq_length*/
	(binaryfunc)string_concat, /*sq_concat*/
	(intargfunc)string_repeat, /*sq_repeat*/
	(intargfunc)string_item, /*sq_item*/
	(intintargfunc)string_slice, /*sq_slice*/
	0,		/*sq_ass_item*/
	0,		/*sq_ass_slice*/
	(objobjproc)string_contains /*sq_contains*/
};

const static PyBufferProcs string_as_buffer = {
	(getreadbufferproc)string_buffer_getreadbuf,
	(getwritebufferproc)string_buffer_getwritebuf,
	(getsegcountproc)string_buffer_getsegcount,
	(getcharbufferproc)string_buffer_getcharbuf,
};



#define LEFTSTRIP 0
#define RIGHTSTRIP 1
#define BOTHSTRIP 2

/* Arrays indexed by above */
static const char *const stripformat[] = {"|O:lstrip", "|O:rstrip", "|O:strip"};

#define STRIPNAME(i) (stripformat[i]+3)


static PyObject *
split_whitespace(const char *s, int len, int maxsplit)
{
	int i, j, err;
	PyObject* item;
	PyObject *list = PyList_New(0);

	if (list == NULL)
		return NULL;

	for (i = j = 0; i < len; ) {
		while (i < len && isspace(Py_CHARMASK(s[i])))
			i++;
		j = i;
		while (i < len && !isspace(Py_CHARMASK(s[i])))
			i++;
		if (j < i) {
			if (maxsplit-- <= 0)
				break;
			item = PyString_FromStringAndSize(s+j, (int)(i-j));
			if (item == NULL)
				goto finally;
			err = PyList_Append(list, item);
			Py_DECREF(item);
			if (err < 0)
				goto finally;
			while (i < len && isspace(Py_CHARMASK(s[i])))
				i++;
			j = i;
		}
	}
	if (j < len) {
		item = PyString_FromStringAndSize(s+j, (int)(len - j));
		if (item == NULL)
			goto finally;
		err = PyList_Append(list, item);
		Py_DECREF(item);
		if (err < 0)
			goto finally;
	}
	return list;
  finally:
	Py_DECREF(list);
	return NULL;
}