/**
* g_utf8_to_ucs4:
* @str: a UTF-8 encoded string
* @len: the maximum length of @str to use, in bytes. If @len < 0,
* then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* bytes read, or %NULL.
* If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
* returned in case @str contains a trailing partial
* character. If an error occurs then the index of the
* invalid input is stored here.
* @items_written: (out caller-allocates) (optional): location to store number
* of characters written or %NULL. The value here stored does not include
* the trailing 0 character.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-8 to a 32-bit fixed width
* representation as UCS-4. A trailing 0 character will be added to the
* string after the converted text.
*
* Returns: a pointer to a newly allocated UCS-4 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set.
*/
gunichar *
g_utf8_to_ucs4 (const gchar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
gunichar *result = NULL;
gint n_chars, i;
const gchar *in;
in = str;
n_chars = 0;
while ((len < 0 || str + len - in > 0) && *in)
{
gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
if (wc & 0x80000000)
{
if (wc == (gunichar)-2)
{
if (items_read)
break;
else
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
_("Partial character sequence at end of input"));
}
else
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid byte sequence in conversion input"));
goto err_out;
}
n_chars++;
in = g_utf8_next_char (in);
}
result = try_malloc_n (n_chars + 1, sizeof (gunichar), error);
if (result == NULL)
goto err_out;
in = str;
for (i=0; i < n_chars; i++)
{
result[i] = g_utf8_get_char (in);
in = g_utf8_next_char (in);
}
result[i] = 0;
if (items_written)
*items_written = n_chars;
err_out:
if (items_read)
*items_read = in - str;
return result;
}
/**
* g_ucs4_to_utf8:
* @str: a UCS-4 encoded string
* @len: the maximum length (number of characters) of @str to use.
* If @len < 0, then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* characters read, or %NULL.
* @items_written: (out caller-allocates) (optional): location to store number
* of bytes written or %NULL. The value here stored does not include the
* trailing 0 byte.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from a 32-bit fixed width representation as UCS-4.
* to UTF-8. The result will be terminated with a 0 byte.
*
* Returns: a pointer to a newly allocated UTF-8 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set. In that case, @items_read
* will be set to the position of the first invalid input character.
*/
gchar *
g_ucs4_to_utf8 (const gunichar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
gint result_length;
gchar *result = NULL;
gchar *p;
gint i;
result_length = 0;
for (i = 0; len < 0 || i < len ; i++)
{
if (!str[i])
break;
if (str[i] >= 0x80000000)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Character out of range for UTF-8"));
goto err_out;
}
result_length += UTF8_LENGTH (str[i]);
}
result = try_malloc_n (result_length + 1, 1, error);
if (result == NULL)
goto err_out;
p = result;
i = 0;
while (p < result + result_length)
p += g_unichar_to_utf8 (str[i++], p);
*p = '\0';
if (items_written)
*items_written = p - result;
err_out:
if (items_read)
*items_read = i;
return result;
}
void * simple_segregated_storage<SizeType>::malloc_n(const size_type n,
const size_type partition_size)
{
void * start = &first;
void * iter;
do
{
if (nextof(start) == 0)
return 0;
iter = try_malloc_n(start, n, partition_size);
} while (iter == 0);
void * const ret = nextof(start);
nextof(start) = nextof(iter);
return ret;
}
/**
* g_ucs4_to_utf16:
* @str: a UCS-4 encoded string
* @len: the maximum length (number of characters) of @str to use.
* If @len < 0, then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* bytes read, or %NULL. If an error occurs then the index of the invalid
* input is stored here.
* @items_written: (out caller-allocates) (optional): location to store number
* of #gunichar2 written, or %NULL. The value stored here does not include
* the trailing 0.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UCS-4 to UTF-16. A 0 character will be
* added to the result after the converted text.
*
* Returns: a pointer to a newly allocated UTF-16 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set.
*/
gunichar2 *
g_ucs4_to_utf16 (const gunichar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
gunichar2 *result = NULL;
gint n16;
gint i, j;
n16 = 0;
i = 0;
while ((len < 0 || i < len) && str[i])
{
gunichar wc = str[i];
if (wc < 0xd800)
n16 += 1;
else if (wc < 0xe000)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
else if (wc < 0x10000)
n16 += 1;
else if (wc < 0x110000)
n16 += 2;
else
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Character out of range for UTF-16"));
goto err_out;
}
i++;
}
result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
if (result == NULL)
goto err_out;
for (i = 0, j = 0; j < n16; i++)
{
gunichar wc = str[i];
if (wc < 0x10000)
{
result[j++] = wc;
}
else
{
result[j++] = (wc - 0x10000) / 0x400 + 0xd800;
result[j++] = (wc - 0x10000) % 0x400 + 0xdc00;
}
}
result[j] = 0;
if (items_written)
*items_written = n16;
err_out:
if (items_read)
*items_read = i;
return result;
}
/**
* g_utf8_to_utf16:
* @str: a UTF-8 encoded string
* @len: the maximum length (number of bytes) of @str to use.
* If @len < 0, then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* bytes read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
* be returned in case @str contains a trailing partial character. If
* an error occurs then the index of the invalid input is stored here.
* @items_written: (out caller-allocates) (optional): location to store number
* of #gunichar2 written, or %NULL. The value stored here does not include
* the trailing 0.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-8 to UTF-16. A 0 character will be
* added to the result after the converted text.
*
* Returns: a pointer to a newly allocated UTF-16 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set.
*/
gunichar2 *
g_utf8_to_utf16 (const gchar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
gunichar2 *result = NULL;
gint n16;
const gchar *in;
gint i;
g_return_val_if_fail (str != NULL, NULL);
in = str;
n16 = 0;
while ((len < 0 || str + len - in > 0) && *in)
{
gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
if (wc & 0x80000000)
{
if (wc == (gunichar)-2)
{
if (items_read)
break;
else
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
_("Partial character sequence at end of input"));
}
else
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid byte sequence in conversion input"));
goto err_out;
}
if (wc < 0xd800)
n16 += 1;
else if (wc < 0xe000)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
else if (wc < 0x10000)
n16 += 1;
else if (wc < 0x110000)
n16 += 2;
else
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Character out of range for UTF-16"));
goto err_out;
}
in = g_utf8_next_char (in);
}
result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
if (result == NULL)
goto err_out;
in = str;
for (i = 0; i < n16;)
{
gunichar wc = g_utf8_get_char (in);
if (wc < 0x10000)
{
result[i++] = wc;
}
else
{
result[i++] = (wc - 0x10000) / 0x400 + 0xd800;
result[i++] = (wc - 0x10000) % 0x400 + 0xdc00;
}
in = g_utf8_next_char (in);
}
result[i] = 0;
if (items_written)
*items_written = n16;
err_out:
if (items_read)
*items_read = in - str;
return result;
}
/**
* g_utf16_to_ucs4:
* @str: a UTF-16 encoded string
* @len: the maximum length (number of #gunichar2) of @str to use.
* If @len < 0, then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* words read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
* be returned in case @str contains a trailing partial character. If
* an error occurs then the index of the invalid input is stored here.
* @items_written: (out caller-allocates) (optional): location to store number
* of characters written, or %NULL. The value stored here does not include
* the trailing 0 character.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-16 to UCS-4. The result will be
* nul-terminated.
*
* Returns: a pointer to a newly allocated UCS-4 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set.
*/
gunichar *
g_utf16_to_ucs4 (const gunichar2 *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
const gunichar2 *in;
gchar *out;
gchar *result = NULL;
gint n_bytes;
gunichar high_surrogate;
g_return_val_if_fail (str != NULL, NULL);
n_bytes = 0;
in = str;
high_surrogate = 0;
while ((len < 0 || in - str < len) && *in)
{
gunichar2 c = *in;
if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
{
if (high_surrogate)
{
high_surrogate = 0;
}
else
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
}
else
{
if (high_surrogate)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
{
high_surrogate = c;
goto next1;
}
}
/********** DIFFERENT for UTF8/UCS4 **********/
n_bytes += sizeof (gunichar);
next1:
in++;
}
if (high_surrogate && !items_read)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
_("Partial character sequence at end of input"));
goto err_out;
}
/* At this point, everything is valid, and we just need to convert
*/
/********** DIFFERENT for UTF8/UCS4 **********/
result = try_malloc_n (n_bytes + 4, 1, error);
if (result == NULL)
goto err_out;
high_surrogate = 0;
out = result;
in = str;
while (out < result + n_bytes)
{
gunichar2 c = *in;
gunichar wc;
if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
{
wc = SURROGATE_VALUE (high_surrogate, c);
high_surrogate = 0;
}
else if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
{
high_surrogate = c;
goto next2;
}
else
wc = c;
/********** DIFFERENT for UTF8/UCS4 **********/
*(gunichar *)out = wc;
out += sizeof (gunichar);
next2:
in++;
}
/********** DIFFERENT for UTF8/UCS4 **********/
*(gunichar *)out = 0;
if (items_written)
/********** DIFFERENT for UTF8/UCS4 **********/
*items_written = (out - result) / sizeof (gunichar);
err_out:
if (items_read)
*items_read = in - str;
return (gunichar *)result;
}
/**
* g_utf16_to_utf8:
* @str: a UTF-16 encoded string
* @len: the maximum length (number of #gunichar2) of @str to use.
* If @len < 0, then the string is nul-terminated.
* @items_read: (out caller-allocates) (optional): location to store number of
* words read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
* be returned in case @str contains a trailing partial character. If
* an error occurs then the index of the invalid input is stored here.
* @items_written: (out caller-allocates) (optional): location to store number
* of bytes written, or %NULL. The value stored here does not include the
* trailing 0 byte.
* @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-16 to UTF-8. The result will be
* terminated with a 0 byte.
*
* Note that the input is expected to be already in native endianness,
* an initial byte-order-mark character is not handled specially.
* g_convert() can be used to convert a byte buffer of UTF-16 data of
* ambiguous endianess.
*
* Further note that this function does not validate the result
* string; it may e.g. include embedded NUL characters. The only
* validation done by this function is to ensure that the input can
* be correctly interpreted as UTF-16, i.e. it doesn't contain
* things unpaired surrogates.
*
* Returns: a pointer to a newly allocated UTF-8 string.
* This value must be freed with g_free(). If an error occurs,
* %NULL will be returned and @error set.
**/
gchar *
g_utf16_to_utf8 (const gunichar2 *str,
glong len,
glong *items_read,
glong *items_written,
GError **error)
{
/* This function and g_utf16_to_ucs4 are almost exactly identical -
* The lines that differ are marked.
*/
const gunichar2 *in;
gchar *out;
gchar *result = NULL;
gint n_bytes;
gunichar high_surrogate;
g_return_val_if_fail (str != NULL, NULL);
n_bytes = 0;
in = str;
high_surrogate = 0;
while ((len < 0 || in - str < len) && *in)
{
gunichar2 c = *in;
gunichar wc;
if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
{
if (high_surrogate)
{
wc = SURROGATE_VALUE (high_surrogate, c);
high_surrogate = 0;
}
else
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
}
else
{
if (high_surrogate)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
_("Invalid sequence in conversion input"));
goto err_out;
}
if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
{
high_surrogate = c;
goto next1;
}
else
wc = c;
}
/********** DIFFERENT for UTF8/UCS4 **********/
n_bytes += UTF8_LENGTH (wc);
next1:
in++;
}
if (high_surrogate && !items_read)
{
g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
_("Partial character sequence at end of input"));
goto err_out;
}
/* At this point, everything is valid, and we just need to convert
*/
/********** DIFFERENT for UTF8/UCS4 **********/
result = try_malloc_n (n_bytes + 1, 1, error);
if (result == NULL)
goto err_out;
high_surrogate = 0;
out = result;
in = str;
while (out < result + n_bytes)
{
gunichar2 c = *in;
gunichar wc;
if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
{
wc = SURROGATE_VALUE (high_surrogate, c);
high_surrogate = 0;
}
else if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
{
high_surrogate = c;
goto next2;
}
else
wc = c;
/********** DIFFERENT for UTF8/UCS4 **********/
out += g_unichar_to_utf8 (wc, out);
next2:
in++;
}
/********** DIFFERENT for UTF8/UCS4 **********/
*out = '\0';
if (items_written)
/********** DIFFERENT for UTF8/UCS4 **********/
*items_written = out - result;
err_out:
if (items_read)
*items_read = in - str;
return result;
}
