size_t _myhtml_string_append_char_references_state_0(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;
while(offset < size)
{
if(buff[offset] == '&')
{
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);
myhtml_encoding_result_clean(&chunk->res);
}
chunk->begin = str->length;
chunk->state = 1;
_myhtml_string_charef_append(str, buff[offset]);
offset++;
return offset;
}
offset++;
}
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;
}
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;
}
myhtml_string_t * myhtml_node_text_set(myhtml_tree_t* tree, myhtml_tree_node_t *node, const char* text, size_t length, myhtml_encoding_t encoding)
{
if(node == NULL)
return NULL;
if(encoding >= MyHTML_ENCODING_LAST_ENTRY)
return NULL;
if(node->token == NULL) {
mcobject_async_status_t mcstatus;
node->token = (myhtml_token_node_t*)mcobject_async_malloc(tree->token->nodes_obj, tree->mcasync_token_id, &mcstatus);
if(mcstatus)
return NULL;
myhtml_token_node_clean(node->token);
}
if(node->token->my_str_tm.data == NULL) {
myhtml_string_init(tree->mchar, tree->mchar_node_id, &node->token->my_str_tm, (length + 2));
}
else {
if(node->token->my_str_tm.size < length) {
mchar_async_free(tree->mchar, node->token->my_str_tm.node_idx, node->token->my_str_tm.data);
myhtml_string_init(tree->mchar, tree->mchar_node_id, &node->token->my_str_tm, length);
}
else
node->token->my_str_tm.length = 0;
}
if(encoding != MyHTML_ENCODING_UTF_8) {
myhtml_string_append_with_convert_encoding(&node->token->my_str_tm, text, length, encoding);
}
else {
myhtml_string_append(&node->token->my_str_tm, text, length);
}
node->token->begin = 0;
node->token->length = node->token->my_str_tm.length;
return &node->token->my_str_tm;
}
void myhtml_string_copy(myhtml_string_t* dest, myhtml_string_t* target)
{
myhtml_string_append(dest, target->data, target->length);
}
size_t myhtml_parser_add_text(myhtml_tree_t *tree, myhtml_string_t* string, const char *text, size_t begin, size_t length)
{
myhtml_incoming_buf_t *inc_buf = myhtml_parser_find_first_buf(tree, begin);
size_t current_buf_offset = begin - inc_buf->offset;
size_t save_str_len = string->length;
if((current_buf_offset + length) <= inc_buf->size)
{
if(tree->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append(string, &inc_buf->data[current_buf_offset], length);
else
myhtml_string_append_with_convert_encoding(string,
&inc_buf->data[current_buf_offset],
length, tree->encoding);
return (string->length - save_str_len);
}
size_t buf_next_offset = inc_buf->size - current_buf_offset;
myhtml_encoding_result_t res;
myhtml_encoding_result_clean(&res);
if(tree->encoding == MyHTML_ENCODING_UTF_8)
myhtml_string_append(string, &inc_buf->data[current_buf_offset], buf_next_offset);
else
myhtml_string_append_chunk_with_convert_encoding(string, &res, &inc_buf->data[current_buf_offset],
buf_next_offset, tree->encoding);
length = length - buf_next_offset;
inc_buf = inc_buf->next;
if(tree->encoding == MyHTML_ENCODING_UTF_8) {
while (inc_buf && length)
{
if(length > inc_buf->size) {
myhtml_string_append(string, inc_buf->data, inc_buf->size);
length -= inc_buf->size;
}
else {
myhtml_string_append(string, inc_buf->data, length);
break;
}
inc_buf = inc_buf->next;
}
}
else {
while (inc_buf && length)
{
if(length > inc_buf->size) {
myhtml_string_append_chunk_with_convert_encoding(string, &res, inc_buf->data,
inc_buf->size, tree->encoding);
length -= inc_buf->size;
}
else {
myhtml_string_append_chunk_with_convert_encoding(string, &res, inc_buf->data,
length, tree->encoding);
break;
}
inc_buf = inc_buf->next;
}
}
return (string->length - save_str_len);
}
