String xml_utf8_decode(const XML_Char *s, int len,
const XML_Char *encoding) {
String str = String(len, ReserveString);
char *newbuf = str.mutableData();
char (*decoder)(unsigned short) = nullptr;
xml_encoding *enc = xml_get_encoding(encoding);
int newlen = 0;
if (enc) {
decoder = enc->decoding_function;
}
if (decoder == nullptr) {
/* If the target encoding was unknown, or no decoder function
* was specified, return the UTF-8-encoded data as-is.
*/
memcpy(newbuf, s, len);
str.setSize(len);
return str;
}
UTF8To16Decoder dec(s, len, true);
for (int b = dec.decode(); b != UTF8_END; b = dec.decode()) {
newbuf[newlen] = decoder(b);
++newlen;
}
assert(newlen <= len);
str.shrink(newlen);
return str;
}
bool f_xml_parser_set_option(CObjRef parser, int option, CVarRef value) {
XmlParser * p = parser.getTyped<XmlParser>();
switch (option) {
case PHP_XML_OPTION_CASE_FOLDING:
p->case_folding = value.toInt64();
break;
case PHP_XML_OPTION_SKIP_TAGSTART:
p->toffset = value.toInt64();
break;
case PHP_XML_OPTION_SKIP_WHITE:
p->skipwhite = value.toInt64();
break;
case PHP_XML_OPTION_TARGET_ENCODING: {
xml_encoding *enc;
enc = xml_get_encoding((const XML_Char*)value.toString().data());
if (enc == NULL) {
raise_warning("Unsupported target encoding \"%s\"",
value.toString().data());
return false;
}
p->target_encoding = enc->name;
break;
}
default:
raise_warning("Unknown option");
return false;
}
return true;
}
char *xml_utf8_decode(const XML_Char *s, int len, int *newlen,
const XML_Char *encoding) {
int pos = len;
char *newbuf = (char*)malloc(len+1);
unsigned short c;
char (*decoder)(unsigned short) = NULL;
xml_encoding *enc = xml_get_encoding(encoding);
*newlen = 0;
if (enc) {
decoder = enc->decoding_function;
}
if (decoder == NULL) {
/* If the target encoding was unknown, or no decoder function
* was specified, return the UTF-8-encoded data as-is.
*/
memcpy(newbuf, s, len);
*newlen = len;
newbuf[*newlen] = '\0';
return newbuf;
}
while (pos > 0) {
c = (unsigned char)(*s);
if (c >= 0xf0) { /* four bytes encoded, 21 bits */
if(pos-4 >= 0) {
c = ((s[0]&7)<<18) | ((s[1]&63)<<12) | ((s[2]&63)<<6) | (s[3]&63);
} else {
c = '?';
}
s += 4;
pos -= 4;
} else if (c >= 0xe0) { /* three bytes encoded, 16 bits */
if(pos-3 >= 0) {
c = ((s[0]&63)<<12) | ((s[1]&63)<<6) | (s[2]&63);
} else {
c = '?';
}
s += 3;
pos -= 3;
} else if (c >= 0xc0) { /* two bytes encoded, 11 bits */
if(pos-2 >= 0) {
c = ((s[0]&63)<<6) | (s[1]&63);
} else {
c = '?';
}
s += 2;
pos -= 2;
} else {
s++;
pos--;
}
newbuf[*newlen] = decoder ? decoder(c) : c;
++*newlen;
}
if (*newlen < len) {
newbuf = (char*)realloc(newbuf, *newlen + 1);
}
newbuf[*newlen] = '\0';
return newbuf;
}
/* {{{ xml_utf8_encode() */
PHPAPI zend_string *xml_utf8_encode(const char *s, size_t len, const XML_Char *encoding)
{
size_t pos = len;
zend_string *str;
unsigned int c;
unsigned short (*encoder)(unsigned char) = NULL;
xml_encoding *enc = xml_get_encoding(encoding);
if (enc) {
encoder = enc->encoding_function;
} else {
/* If the target encoding was unknown, fail */
return NULL;
}
if (encoder == NULL) {
/* If no encoder function was specified, return the data as-is.
*/
str = zend_string_init(s, len, 0);
return str;
}
/* This is the theoretical max (will never get beyond len * 2 as long
* as we are converting from single-byte characters, though) */
str = zend_string_alloc(len * 4, 0);
str->len = 0;
while (pos > 0) {
c = encoder ? encoder((unsigned char)(*s)) : (unsigned short)(*s);
if (c < 0x80) {
str->val[str->len++] = (char) c;
} else if (c < 0x800) {
str->val[str->len++] = (0xc0 | (c >> 6));
str->val[str->len++] = (0x80 | (c & 0x3f));
} else if (c < 0x10000) {
String xml_utf8_decode(const XML_Char *s, int len,
const XML_Char *encoding) {
int pos = len;
String str = String(len, ReserveString);
char *newbuf = str.bufferSlice().ptr;
unsigned short c;
char (*decoder)(unsigned short) = NULL;
xml_encoding *enc = xml_get_encoding(encoding);
int newlen = 0;
if (enc) {
decoder = enc->decoding_function;
}
if (decoder == NULL) {
/* If the target encoding was unknown, or no decoder function
* was specified, return the UTF-8-encoded data as-is.
*/
memcpy(newbuf, s, len);
str.setSize(len);
return str;
}
while (pos > 0) {
c = (unsigned char)(*s);
if (c >= 0xf0) { /* four bytes encoded, 21 bits */
if (pos-4 >= 0) {
c = ((s[0]&7)<<18) | ((s[1]&63)<<12) | ((s[2]&63)<<6) | (s[3]&63);
} else {
c = '?';
}
s += 4;
pos -= 4;
} else if (c >= 0xe0) { /* three bytes encoded, 16 bits */
if (pos-3 >= 0) {
c = ((s[0]&63)<<12) | ((s[1]&63)<<6) | (s[2]&63);
} else {
c = '?';
}
s += 3;
pos -= 3;
} else if (c >= 0xc0) { /* two bytes encoded, 11 bits */
if (pos-2 >= 0) {
c = ((s[0]&63)<<6) | (s[1]&63);
} else {
c = '?';
}
s += 2;
pos -= 2;
} else {
s++;
pos--;
}
newbuf[newlen] = decoder ? decoder(c) : c;
++newlen;
}
assert(newlen <= len);
str.shrink(newlen);
return str;
}
