void myhtml_string_append_lowercase_with_preprocessing(myhtml_string_t* str, const char* buff, size_t length)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 32);
unsigned char *data = (unsigned char*)str->data;
const unsigned char *u_buff = (unsigned char*)buff;
for (size_t i = 0; i < length; i++)
{
if(u_buff[i] == 0x0D)
{
data[str->length] = 0x0A;
if((i+1) < length && u_buff[(i + 1)] == 0x0A) {
i++;
}
}
else if(u_buff[i] == 0x00)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 4), 32);
// Unicode Character 'REPLACEMENT CHARACTER' (U+FFFD)
data[str->length] = 0xEF; str->length++;
data[str->length] = 0xBF; str->length++;
data[str->length] = 0xBD;
}
else {
data[str->length] = myhtml_string_chars_lowercase_map[ u_buff[i] ];
}
str->length++;
}
str->data[str->length] = '\0';
}
void myhtml_string_append_with_replacement_null_characters_only(myhtml_string_t* str, const char* buff, size_t length)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 0);
unsigned char *data = (unsigned char*)str->data;
const unsigned char *u_buff = (const unsigned char*)buff;
for (size_t i = 0; i < length; i++)
{
if(u_buff[i] == 0x00) {
myhtml_string_realloc(str, (str->size + 5));
data = (unsigned char*)str->data;
// Unicode Character 'REPLACEMENT CHARACTER' (U+FFFD)
data[str->length] = 0xEF; str->length++;
data[str->length] = 0xBF; str->length++;
data[str->length] = 0xBD;
}
else
data[str->length] = u_buff[i];
str->length++;
}
str->data[str->length] = '\0';
}
size_t myhtml_string_append_lowercase_chunk_with_convert_encoding_with_preprocessing(myhtml_string_t* str, myhtml_encoding_result_t* res, const char* buff, size_t length, myhtml_encoding_t encoding, bool emit_null_chars)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 0);
unsigned const char* u_buff = (unsigned const char*)buff;
const myhtml_encoding_custom_f func = myhtml_encoding_get_function_by_id(encoding);
for (size_t i = 0; i < length; i++)
{
if(func(u_buff[i], res) == MyHTML_ENCODING_STATUS_OK) {
MyHTML_STRING_REALLOC_IF_NEED(str, 5, 1);
size_t len = myhtml_encoding_codepoint_to_lowercase_ascii_utf_8(res->result, &str->data[str->length]);
if(len == 1) {
if(str->data[str->length] == '\r') {
str->data[str->length] = '\n';
if((i + 1) < length) {
if(buff[(i + 1)] == '\n')
i++;
}
else {
str->length++;
return str->length;
}
}
else if(str->data[str->length] == 0x00 && emit_null_chars == false)
{
myhtml_string_realloc(str, (str->size + 5));
// Unicode Character 'REPLACEMENT CHARACTER' (U+FFFD)
str->data[str->length] = (char)0xEF; str->length++;
str->data[str->length] = (char)0xBF; str->length++;
str->data[str->length] = (char)0xBD;
}
}
str->length += len;
}
}
MyHTML_STRING_APPEND_BYTE_WITHOUT_INCREMENT('\0', str, 1);
return 0;
}
/////////////////////////////////////////////////////////
//// Append API
////
/////////////////////////////////////////////////////////
void myhtml_string_append(myhtml_string_t* str, const char* buff, size_t length)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 0);
memcpy(&str->data[str->length], buff, (sizeof(char) * length));
str->length += length;
str->data[str->length] = '\0';
}
void _myhtml_string_charef_append(myhtml_string_t* str, const char sm)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (str->length + 2), 32);
str->data[str->length] = sm;
str->length++;
str->data[str->length] = '\0';
}
void _myhtml_string_append_char_references_state_end(myhtml_string_char_ref_chunk_t *chunk, myhtml_string_t* str)
{
str->length = chunk->begin;
/* 4 is max utf8 byte + \0 */
MyHTML_STRING_REALLOC_IF_NEED(str, (chunk->begin + 5), 12);
str->length += myhtml_encoding_codepoint_to_ascii_utf_8(chunk->l_data, &str->data[str->length]);
str->data[str->length] = '\0';
}
void myhtml_string_append_chunk_with_convert_encoding_with_preprocessing(myhtml_string_t* str, myhtml_encoding_result_t* res, const char* buff, size_t length, myhtml_encoding_t encoding)
{
unsigned const char* u_buff = (unsigned const char*)buff;
myhtml_encoding_custom_f func = myhtml_encoding_get_function_by_id(encoding);
for (size_t i = 0; i < length; i++)
{
if(func(u_buff[i], res) == MyHTML_ENCODING_STATUS_OK) {
MyHTML_STRING_REALLOC_IF_NEED(str, 4, 32);
size_t len = myhtml_encoding_codepoint_to_ascii_utf_8(res->result, &str->data[str->length]);
if(len == 1) {
// change \r\n to \n
if(str->length > 0) {
if(str->data[(str->length - 1)] == '\r') {
str->data[(str->length - 1)] = '\n';
if(str->data[str->length] == '\n')
str->length--;
str->length += len;
continue;
}
}
if(str->data[str->length] == 0x00)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 4), 32);
// Unicode Character 'REPLACEMENT CHARACTER' (U+FFFD)
str->data[str->length] = 0xEF; str->length++;
str->data[str->length] = 0xBF; str->length++;
str->data[str->length] = 0xBD;
}
}
str->length += len;
}
}
MyHTML_STRING_APPEND_BYTE_WITHOUT_INCREMENT('\0', str, 1);
}
void myhtml_string_append_one_with_convert_encoding(myhtml_string_t* str, myhtml_encoding_result_t* res, const char data, myhtml_encoding_t encoding)
{
const myhtml_encoding_custom_f func = myhtml_encoding_get_function_by_id(encoding);
if(func((unsigned const char)data, res) == MyHTML_ENCODING_STATUS_OK) {
MyHTML_STRING_REALLOC_IF_NEED(str, 5, 0);
str->length += myhtml_encoding_codepoint_to_ascii_utf_8(res->result, &str->data[str->length]);
MyHTML_STRING_APPEND_BYTE_WITHOUT_INCREMENT_REALLOC('\0', str);
}
}
size_t _myhtml_string_append_char_references_state_2(myhtml_string_char_ref_chunk_t *chunk, myhtml_string_t* str, const char* buff, size_t offset, size_t size)
{
size_t tmp_offset = offset;
const charef_entry_t *current_entry = myhtml_charef_find_by_pos(chunk->charef_res.curr_entry->next, buff, &offset, size, &chunk->charef_res);
if(chunk->charef_res.is_done) {
chunk->state = 0;
if(buff[offset] == ';')
offset++;
else {
if(chunk->is_attributes &&
(buff[offset] == '=' || myhtml_string_alphanumeric_character[ (unsigned char)buff[offset] ] != 0xff))
{
if(chunk->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append_with_preprocessing(str, &buff[tmp_offset], (offset - tmp_offset));
else
myhtml_string_append_chunk_with_convert_encoding_with_preprocessing(str, &chunk->res, &buff[tmp_offset], (offset - tmp_offset), chunk->encoding);
return offset;
}
}
if(current_entry->codepoints_len)
{
for (size_t i = 0; i < current_entry->codepoints_len; i++) {
MyHTML_STRING_REALLOC_IF_NEED(str, (chunk->begin + 4), 32);
chunk->begin += myhtml_encoding_codepoint_to_ascii_utf_8(current_entry->codepoints[i], &str->data[chunk->begin]);
}
str->length = chunk->begin;
}
else {
if(chunk->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append_with_preprocessing(str, &buff[tmp_offset], (offset - tmp_offset));
else
myhtml_string_append_chunk_with_convert_encoding_with_preprocessing(str, &chunk->res, &buff[tmp_offset], (offset - tmp_offset), chunk->encoding);
}
chunk->charef_res.last_entry = NULL;
}
else {
if(chunk->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append_with_preprocessing(str, &buff[tmp_offset], (offset - tmp_offset));
else
myhtml_string_append_chunk_with_convert_encoding_with_preprocessing(str, &chunk->res, &buff[tmp_offset], (offset - tmp_offset), chunk->encoding);
}
return offset;
}
void myhtml_string_append_chunk_with_convert_encoding(myhtml_string_t* str, myhtml_encoding_result_t* res, const char* buff, size_t length, myhtml_encoding_t encoding)
{
unsigned const char* u_buff = (unsigned const char*)buff;
const myhtml_encoding_custom_f func = myhtml_encoding_get_function_by_id(encoding);
for (size_t i = 0; i < length; i++)
{
if(func(u_buff[i], res) == MyHTML_ENCODING_STATUS_OK) {
MyHTML_STRING_REALLOC_IF_NEED(str, 5, 0);
str->length += myhtml_encoding_codepoint_to_ascii_utf_8(res->result, &str->data[str->length]);
}
}
MyHTML_STRING_APPEND_BYTE_WITHOUT_INCREMENT('\0', str, 1);
}
void myhtml_string_append_lowercase(myhtml_string_t* str, const char* data, size_t length)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 0);
unsigned char *ref = (unsigned char*)&str->data[str->length];
const unsigned char *buf = (const unsigned char*)data;
size_t i;
for(i = 0; i < length; i++) {
ref[i] = myhtml_string_chars_lowercase_map[ buf[i] ];
}
ref[i] = '\0';
str->length += length;
}
size_t myhtml_string_append_with_preprocessing(myhtml_string_t* str, const char* buff, size_t length, bool emit_null_chars)
{
MyHTML_STRING_REALLOC_IF_NEED(str, (length + 1), 0);
unsigned char *data = (unsigned char*)str->data;
const unsigned char *u_buff = (const unsigned char*)buff;
/* 0x0D == \r */
/* 0x0A == \n */
for (size_t i = 0; i < length; i++)
{
if(u_buff[i] == 0x0D) {
data[str->length] = 0x0A;
if((i + 1) < length) {
if(u_buff[(i + 1)] == 0x0A)
i++;
}
else {
str->length++;
return str->length;
}
}
else if(u_buff[i] == 0x00 && emit_null_chars == false)
{
myhtml_string_realloc(str, (str->size + 5));
data = (unsigned char*)str->data;
// Unicode Character 'REPLACEMENT CHARACTER' (U+FFFD)
data[str->length] = 0xEF; str->length++;
data[str->length] = 0xBF; str->length++;
data[str->length] = 0xBD;
}
else
data[str->length] = u_buff[i];
str->length++;
}
str->data[str->length] = '\0';
return 0;
}
void _myhtml_string_append_char_references_state_end(myhtml_string_char_ref_chunk_t *chunk, myhtml_string_t* str)
{
str->length = chunk->begin;
/* 4 is max utf8 byte + \0 */
MyHTML_STRING_REALLOC_IF_NEED(str, (chunk->begin + 5), 12);
if(chunk->l_data <= 0x9F)
chunk->l_data = replacement_character[chunk->l_data];
else if(chunk->l_data >= 0xD800 && chunk->l_data <= 0xDFFF)
chunk->l_data = replacement_character[0];
else if(chunk->l_data > 0x10FFFF)
chunk->l_data = replacement_character[0];
// if(chunk->l_data == 0x10FFFE)
// chunk->l_data = replacement_character[0];
str->length += myhtml_encoding_codepoint_to_ascii_utf_8(chunk->l_data, &str->data[chunk->begin]);
str->data[str->length] = '\0';
}
size_t _myhtml_string_append_char_references_state_2(myhtml_string_char_ref_chunk_t *chunk, myhtml_string_t* str, const char* buff, size_t offset, size_t size)
{
int is_done = 0;
size_t tmp_offset = offset;
chunk->entry = myhtml_charef_find_by_pos(chunk->entry->next, buff, &offset, size, &is_done);
if(is_done) {
chunk->state = 0;
if(chunk->entry->codepoints_len)
{
for (size_t i = 0; i < chunk->entry->codepoints_len; i++) {
MyHTML_STRING_REALLOC_IF_NEED(str, (chunk->begin + 4), 32);
chunk->begin += myhtml_encoding_codepoint_to_ascii_utf_8(chunk->entry->codepoints[i], &str->data[chunk->begin]);
}
str->length = chunk->begin;
}
else {
if(chunk->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append(str, &buff[tmp_offset], (offset - tmp_offset));
else
myhtml_string_append_chunk_with_convert_encoding(str, &chunk->res, &buff[tmp_offset], (offset - tmp_offset), chunk->encoding);
}
}
else {
if(chunk->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append(str, &buff[tmp_offset], (offset - tmp_offset));
else
myhtml_string_append_chunk_with_convert_encoding(str, &chunk->res, &buff[tmp_offset], (offset - tmp_offset), chunk->encoding);
}
return offset;
}
void myhtml_string_append_charef_end(myhtml_string_char_ref_chunk_t *chunk, myhtml_string_t* str)
{
if(chunk->state == 4 || chunk->state == 5) {
_myhtml_string_append_char_references_state_end(chunk, str);
}
else if(chunk->state == 2 && chunk->charef_res.last_entry)
{
const charef_entry_t *entry = chunk->charef_res.last_entry;
for (size_t i = 0; i < entry->codepoints_len; i++) {
MyHTML_STRING_REALLOC_IF_NEED(str, (chunk->begin + 4), 32);
chunk->begin += myhtml_encoding_codepoint_to_ascii_utf_8(entry->codepoints[i], &str->data[chunk->begin]);
}
str->length = chunk->begin;
}
if(str->length) {
if(str->data[ (str->length - 1) ] == '\r') {
str->data[ (str->length - 1) ] = '\n';
}
}
}
void myhtml_string_append_one(myhtml_string_t* str, const char data)
{
MyHTML_STRING_REALLOC_IF_NEED(str, 2, 1);
MyHTML_STRING_APPEND_BYTE_WITHOUT_REALLOC(data, str);
MyHTML_STRING_APPEND_BYTE_WITHOUT_INCREMENT_REALLOC('\0', str);
}
