/* Do an invariant conversion of char* -> UChar*, with escape parsing */
U_CAPI int32_t U_EXPORT2
u_unescape(const char* src, UChar* dest, int32_t destCapacity) {
const char* segment = src;
int32_t i = 0;
char c;
while ((c = *src) != 0) {
/* '\\' intentionally written as compiler-specific
* character constant to correspond to compiler-specific
* char* constants. */
if (c == '\\') {
int32_t lenParsed = 0;
UChar32 c32;
if (src != segment) {
if (dest != NULL) {
_appendUChars(dest + i, destCapacity - i,
segment, src - segment);
}
i += src - segment;
}
++src; /* advance past '\\' */
c32 = u_unescapeAt(_charPtr_charAt, &lenParsed, uprv_strlen(src), (void*) src);
if (lenParsed == 0) {
goto err;
}
src += lenParsed; /* advance past escape seq. */
if (dest != NULL && UTF_CHAR_LENGTH(c32) <= (destCapacity - i)) {
UTF_APPEND_CHAR_UNSAFE(dest, i, c32);
} else {
i += UTF_CHAR_LENGTH(c32);
}
segment = src;
} else {
++src;
}
}
if (src != segment) {
if (dest != NULL) {
_appendUChars(dest + i, destCapacity - i,
segment, src - segment);
}
i += src - segment;
}
if (dest != NULL && i < destCapacity) {
dest[i] = 0;
}
return i;
err:
if (dest != NULL && destCapacity > 0) {
*dest = 0;
}
return 0;
}
/* Read a UChar from a UFILE and process escape sequences */
U_CAPI UChar32 U_EXPORT2 /* U_CAPI ... U_EXPORT2 added by Peter Kirk 17 Nov 2001 */
u_fgetcx(UFILE *f)
{
int32_t length;
int32_t offset;
UChar32 c32;
UChar c16;
/* Fill the buffer if it is empty */
if (f->fUCPos >= f->fUCLimit) {
ufile_fill_uchar_buffer(f);
}
/* Get the next character in the buffer */
if (f->fUCPos < f->fUCLimit) {
c16 = *(f->fUCPos)++;
} else {
c16 = U_EOF;
}
/* If it isn't a backslash, return it */
if (c16 != 0x005C /*'\\'*/) {
return c16;
}
/* Determine the amount of data in the buffer */
length = (int32_t)(f->fUCLimit - f->fUCPos);
/* The longest escape sequence is \Uhhhhhhhh; make sure
we have at least that many characters */
if (length < 10) {
/* fill the buffer */
ufile_fill_uchar_buffer(f);
length = (int32_t)(f->fUCLimit - f->fUCPos);
}
/* Process the escape */
offset = 0;
c32 = u_unescapeAt(_charAt, &offset, length, (void*)f);
/* Update the current buffer position */
f->fUCPos += offset;
return c32;
}
/* getc and escape it */
U_CAPI int32_t U_EXPORT2
ucbuf_getcx32(UCHARBUF* buf,UErrorCode* error) {
int32_t length;
int32_t offset;
UChar32 c32,c1,c2;
if(error==NULL || U_FAILURE(*error)){
return FALSE;
}
/* Fill the buffer if it is empty */
if (buf->currentPos >=buf->bufLimit-2) {
ucbuf_fillucbuf(buf,error);
}
/* Get the next character in the buffer */
if (buf->currentPos < buf->bufLimit) {
c1 = *(buf->currentPos)++;
} else {
c1 = U_EOF;
}
c2 = *(buf->currentPos);
/* If it isn't a backslash, return it */
if (c1 != 0x005C) {
return c1;
}
/* Determine the amount of data in the buffer */
length = (int32_t)(buf->bufLimit - buf->currentPos);
/* The longest escape sequence is \Uhhhhhhhh; make sure
we have at least that many characters */
if (length < 10) {
/* fill the buffer */
ucbuf_fillucbuf(buf,error);
length = (int32_t)(buf->bufLimit - buf->buffer);
}
/* Process the escape */
offset = 0;
c32 = u_unescapeAt(_charAt, &offset, length, (void*)buf);
/* check if u_unescapeAt unescaped and converted
* to c32 or not
*/
if(c32==0xFFFFFFFF){
if(buf->showWarning) {
char context[CONTEXT_LEN+1];
int32_t len = CONTEXT_LEN;
if(length < len) {
len = length;
}
context[len]= 0 ; /* null terminate the buffer */
u_UCharsToChars( buf->currentPos, context, len);
fprintf(stderr,"Bad escape: [%c%s]...\n", (int)c1, context);
}
*error= U_ILLEGAL_ESCAPE_SEQUENCE;
return c1;
}else if(c32!=c2 || (c32==0x0075 && c2==0x0075 && c1==0x005C) /* for \u0075 c2=0x0075 and c32==0x0075*/){
/* Update the current buffer position */
buf->currentPos += offset;
}else{
/* unescaping failed so we just return
* c1 and not consume the buffer
* this is useful for rules with escapes
* in resouce bundles
* eg: \' \\ \"
*/
return c1;
}
return c32;
}
/* Parse a single escape sequence. Although this method deals in
* UChars, it does not use C++ or UnicodeString. This allows it to
* be used from C contexts. */
U_CAPI UChar32 U_EXPORT2
u_unescapeAt(UNESCAPE_CHAR_AT charAt,
int32_t* offset,
int32_t length,
void* context) {
int32_t start = *offset;
UChar c;
UChar32 result = 0;
int8_t n = 0;
int8_t minDig = 0;
int8_t maxDig = 0;
int8_t bitsPerDigit = 4;
int8_t dig;
int32_t i;
UBool braces = FALSE;
/* Check that offset is in range */
if (*offset < 0 || *offset >= length) {
goto err;
}
/* Fetch first UChar after '\\' */
c = charAt((*offset)++, context);
/* Convert hexadecimal and octal escapes */
switch (c) {
case 0x0075 /*'u'*/:
minDig = maxDig = 4;
break;
case 0x0055 /*'U'*/:
minDig = maxDig = 8;
break;
case 0x0078 /*'x'*/:
minDig = 1;
if (*offset < length && charAt(*offset, context) == 0x7B /*{*/) {
++(*offset);
braces = TRUE;
maxDig = 8;
} else {
maxDig = 2;
}
break;
default:
dig = _digit8(c);
if (dig >= 0) {
minDig = 1;
maxDig = 3;
n = 1; /* Already have first octal digit */
bitsPerDigit = 3;
result = dig;
}
break;
}
if (minDig != 0) {
while (*offset < length && n < maxDig) {
c = charAt(*offset, context);
dig = (int8_t) ((bitsPerDigit == 3) ? _digit8(c) : _digit16(c));
if (dig < 0) {
break;
}
result = (result << bitsPerDigit) | dig;
++(*offset);
++n;
}
if (n < minDig) {
goto err;
}
if (braces) {
if (c != 0x7D /*}*/) {
goto err;
}
++(*offset);
}
if (result < 0 || result >= 0x110000) {
goto err;
}
/* If an escape sequence specifies a lead surrogate, see if
* there is a trail surrogate after it, either as an escape or
* as a literal. If so, join them up into a supplementary.
*/
if (*offset < length && U16_IS_LEAD(result)) {
int32_t ahead = *offset + 1;
c = charAt(*offset, context);
if (c == 0x5C /*'\\'*/ && ahead < length) {
c = (UChar) u_unescapeAt(charAt, &ahead, length, context);
}
if (U16_IS_TRAIL(c)) {
*offset = ahead;
result = U16_GET_SUPPLEMENTARY(result, c);
}
}
return result;
}
/* Convert C-style escapes in table */
for (i = 0; i < UNESCAPE_MAP_LENGTH; i += 2) {
if (c == UNESCAPE_MAP[i]) {
return UNESCAPE_MAP[i + 1];
} else if (c < UNESCAPE_MAP[i]) {
break;
}
}
/* Map \cX to control-X: X & 0x1F */
if (c == 0x0063 /*'c'*/ && *offset < length) {
c = charAt((*offset)++, context);
if (UTF_IS_FIRST_SURROGATE(c) && *offset < length) {
UChar c2 = charAt(*offset, context);
if (UTF_IS_SECOND_SURROGATE(c2)) {
++(*offset);
c = (UChar) UTF16_GET_PAIR_VALUE(c, c2); /* [sic] */
}
}
return 0x1F & c;
}
/* If no special forms are recognized, then consider
* the backslash to generically escape the next character.
* Deal with surrogate pairs. */
if (UTF_IS_FIRST_SURROGATE(c) && *offset < length) {
UChar c2 = charAt(*offset, context);
if (UTF_IS_SECOND_SURROGATE(c2)) {
++(*offset);
return UTF16_GET_PAIR_VALUE(c, c2);
}
}
return c;
err:
/* Invalid escape sequence */
*offset = start; /* Reset to initial value */
return (UChar32) 0xFFFFFFFF;
}
