static int
unicode_mangling_length (const char *name, int len)
{
const unsigned char *ptr;
const unsigned char *limit = (const unsigned char *)name + len;
int need_escapes = 0; /* Whether we need an escape or not */
int num_chars = 0; /* Number of characters in the mangled name */
int uuU = 0; /* Help us to find __U. 0: '_', 1: '__' */
for (ptr = (const unsigned char *) name; ptr < limit; )
{
int ch = UTF8_GET(ptr, limit);
if (ch < 0)
error ("internal error - invalid Utf8 name");
if ((ISALNUM (ch) && ch != 'U') || ch == '$')
num_chars++;
/* Everything else needs encoding */
else
{
int encoding_length = 2;
if (ch == '_' || ch == 'U')
{
/* It's always at least one character. */
num_chars++;
/* Prepare to recognize __U */
if (ch == '_' && (uuU < 3))
uuU++;
/* We recognize __U that we wish to encode __U_, we
count one more character. */
else if (ch == 'U' && (uuU == 2))
{
num_chars++;
need_escapes = 1;
uuU = 0;
}
/* Otherwise, just reset uuU */
else
uuU = 0;
continue;
}
if (ch > 0xff)
encoding_length++;
if (ch > 0xfff)
encoding_length++;
num_chars += (4 + encoding_length);
need_escapes = 1;
uuU = 0;
}
}
if (need_escapes)
return num_chars;
else
return 0;
}
void
append_gpp_mangled_name (const char *name, int len)
{
const unsigned char *ptr;
const unsigned char *limit;
int encoded_len;
char buf [6];
MANGLE_CXX_KEYWORDS (name, len);
limit = (const unsigned char *)name + len;
/* Compute the length of the string we wish to mangle. */
for (encoded_len = 0, ptr = (const unsigned char *) name;
ptr < limit; encoded_len++)
{
int ch = UTF8_GET(ptr, limit);
if (ch < 0)
error ("internal error - invalid Utf8 name");
}
sprintf (buf, "%d", encoded_len);
obstack_grow (mangle_obstack, buf, strlen (buf));
obstack_grow (mangle_obstack, name, len);
}
/* another variant that steps over the index,
* note, currently this also falls back to latin1 for text drawing. */
unsigned int BLI_str_utf8_as_unicode_step(const char *p, size_t *index)
{
int i, mask = 0, len;
unsigned int result;
unsigned char c;
p += *index;
c= (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1) {
/* when called with NULL end, result will never be NULL,
* checks for a NULL character */
char *p_next= BLI_str_find_next_char_utf8(p, NULL);
/* will never return the same pointer unless '\0',
* eternal loop is prevented */
*index += (size_t)(p_next - p);
return BLI_UTF8_ERR;
}
/* this is tricky since there are a few ways we can bail out of bad unicode
* values, 3 possible solutions. */
#if 0
UTF8_GET (result, p, i, mask, len, BLI_UTF8_ERR);
#elif 1
/* WARNING: this is NOT part of glib, or supported by similar functions.
* this is added for text drawing because some filepaths can have latin1
* characters */
UTF8_GET (result, p, i, mask, len, BLI_UTF8_ERR);
if (result == BLI_UTF8_ERR) {
len= 1;
result= *p;
}
/* end warning! */
#else
/* without a fallback like '?', text drawing will stop on this value */
UTF8_GET (result, p, i, mask, len, '?');
#endif
*index += len;
return result;
}
/* variant that increments the length */
unsigned int BLI_str_utf8_as_unicode_and_size(const char *p, size_t *index)
{
int i, mask = 0, len;
unsigned int result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return BLI_UTF8_ERR;
UTF8_GET (result, p, i, mask, len, BLI_UTF8_ERR);
*index += len;
return result;
}
/**
* g_utf8_get_char:
* @p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If @p does not point to a valid UTF-8 encoded character, results are
* undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
* Return value: the resulting character
**/
gunichar
g_utf8_get_char (const gchar *p)
{
int i, mask = 0, len;
gunichar result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return (gunichar)-1;
UTF8_GET (result, p, i, mask, len);
return result;
}
/* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If @p does not point to a valid UTF-8 encoded character, results are
* undefined.
**/
static uint32_t
_utf8_get_char (const unsigned char *p)
{
int i, mask = 0, len;
uint32_t result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return (uint32_t)-1;
UTF8_GET (result, p, i, mask, len);
return result;
}
/**
* g_utf8_get_char:
* @p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If @p does not point to a valid UTF-8 encoded character, results are
* undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
* Return value: the resulting character
**/
wchar_t
g_utf8_get_char (const char *p)
{
int i, mask = 0, len;
wchar_t result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return (wchar_t)-1;
UTF8_GET (result, p, i, mask, len);
return result;
}
static void
append_unicode_mangled_name (const char *name, int len)
{
const unsigned char *ptr;
const unsigned char *limit = (const unsigned char *)name + len;
int uuU = 0;
for (ptr = (const unsigned char *) name; ptr < limit; )
{
int ch = UTF8_GET(ptr, limit);
if ((ISALNUM (ch) && ch != 'U') || ch == '$')
{
obstack_1grow (mangle_obstack, ch);
uuU = 0;
}
/* Everything else needs encoding */
else
{
/* Buffer large enough for UINT_MAX plus the prefix. */
char buf [13];
if (ch == '_' || ch == 'U')
{
/* Prepare to recognize __U */
if (ch == '_' && (uuU < 3))
{
uuU++;
obstack_1grow (mangle_obstack, ch);
}
/* We recognize __U that we wish to encode
__U_. Finish the encoding. */
else if (ch == 'U' && (uuU == 2))
{
uuU = 0;
obstack_grow (mangle_obstack, "U_", 2);
}
/* Otherwise, just reset uuU and emit the character we
have. */
else
{
uuU = 0;
obstack_1grow (mangle_obstack, ch);
}
continue;
}
sprintf (buf, "__U%x_", ch);
obstack_grow (mangle_obstack, buf, strlen (buf));
uuU = 0;
}
}
}
static int
utf8_cmp (const unsigned char *str, int length, const char *name)
{
const unsigned char *limit = str + length;
int i;
for (i = 0; name[i]; ++i)
{
int ch = UTF8_GET (str, limit);
if (ch != name[i])
return ch - name[i];
}
return str == limit ? 0 : 1;
}
tree
java_mangle_resource_name (const char *name)
{
int len = strlen (name);
char *buf = (char *) alloca (2 * len + 1);
char *pos;
const unsigned char *w1 = (const unsigned char *) name;
const unsigned char *w2;
const unsigned char *limit = w1 + len;
pos = buf;
init_mangling ();
MANGLE_RAW_STRING ("Gr");
*pos++ = '_';
while (w1 < limit)
{
int ch;
w2 = w1;
ch = UTF8_GET (w1, limit);
gcc_assert (ch > 0);
switch (ch)
{
case '$':
*pos++ = '$';
*pos++ = '$';
break;
case '.':
*pos++ = '$';
*pos++ = '_';
break;
case '/':
*pos++ = '$';
*pos++ = 'S';
break;
default:
memcpy (pos, w2, w1 - w2);
pos += w1 - w2;
break;
}
}
append_gpp_mangled_name (buf, pos - buf);
return finish_mangling ();
}
/**
* _cairo_utf8_get_char_validated:
* @p: a UTF-8 string
* @unicode: location to store one Unicode character
*
* Decodes the first character of a valid UTF-8 string, and returns
* the number of bytes consumed.
*
* Note that the string should be valid. Do not use this without
* validating the string first.
*
* Returns: the number of bytes forming the character returned.
**/
int
_cairo_utf8_get_char_validated (const char *p,
uint32_t *unicode)
{
int i, mask = 0, len;
uint32_t result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1) {
if (unicode)
*unicode = (uint32_t)-1;
return 1;
}
UTF8_GET (result, p, i, mask, len);
if (unicode)
*unicode = result;
return len;
}