HTML-MyHTML

 view release on metacpan or  search on metacpan

source/myhtml/tokenizer.c  view on Meta::CPAN

    }
    else {
        myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_DATA;
    }
}

/////////////////////////////////////////////////////////
//// RCDATA
////
/////////////////////////////////////////////////////////
size_t myhtml_tokenizer_state_rcdata(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    if(tree->tmp_tag_id == 0) {
        token_node->raw_begin = (html_offset + tree->global_offset);
        
        mythread_queue_node_t* prev_qnode = mythread_queue_get_prev_node(tree->current_qnode);
        
        if(prev_qnode && prev_qnode->token) {
            tree->tmp_tag_id = prev_qnode->token->tag_id;
        }
        else if(tree->fragment) {

source/myhtml/tokenizer.c  view on Meta::CPAN

            
            break;
        }
        
        html_offset++;
    }
    
    return html_offset;
}

size_t myhtml_tokenizer_state_rcdata_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    if(html[html_offset] == '/')
    {
        html_offset++;
        myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_OPEN;
    }
    else {
        myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_RCDATA;
    }
    
    return html_offset;
}

size_t myhtml_tokenizer_state_rcdata_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    if(myhtml_tokenizer_chars_map[ (unsigned char)html[html_offset] ] == MyHTML_TOKENIZER_CHAR_A_Z_a_z)
    {
        myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_NAME;
    }
    else {
        myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_RCDATA;
    }
    
    return html_offset;

source/myhtml/tokenizer.c  view on Meta::CPAN

        myhtml_queue_add(tree, *html_offset, token_node);
        token_node = tree->current_token_node;
    }
    
    token_node->tag_id = tree->tmp_tag_id;
    token_node->type |= MyHTML_TOKEN_TYPE_CLOSE;
    
    return true;
}

size_t myhtml_tokenizer_state_rcdata_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    size_t tmp_begin = token_node->raw_begin;
    token_node->raw_begin = html_offset + tree->global_offset;
    
    while(html_offset < html_size)
    {
        if(myhtml_tokenizer_chars_map[ (unsigned char)html[html_offset] ] == MyHTML_TOKENIZER_CHAR_WHITESPACE)
        {
            if(_myhtml_tokenizer_state_andata_end_tag_name(tree, token_node, html, &html_offset, tmp_begin, MyHTML_TOKEN_TYPE_RCDATA)) {
                myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_BEFORE_ATTRIBUTE_NAME;

source/myhtml/tokenizer.c  view on Meta::CPAN

    myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_DATA;
    myhtml_queue_add(tree, html_size, token_node);
    
    return html_size;
}

/////////////////////////////////////////////////////////
//// CDATA
////
/////////////////////////////////////////////////////////
size_t myhtml_tokenizer_state_cdata_section(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    if((token_node->type & MyHTML_TOKEN_TYPE_CDATA) == 0)
        token_node->type |= MyHTML_TOKEN_TYPE_CDATA;
    
    while(html_offset < html_size)
    {
        if(html[html_offset] == '>')
        {
            const char *tagname;
            if(html_offset < 2)

source/myhtml/tokenizer.c  view on Meta::CPAN

    
    // comments
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT_START]                 = myhtml_tokenizer_state_comment_start;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT_START_DASH]            = myhtml_tokenizer_state_comment_start_dash;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT]                       = myhtml_tokenizer_state_comment;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT_END]                   = myhtml_tokenizer_state_comment_end;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT_END_DASH]              = myhtml_tokenizer_state_comment_end_dash;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_COMMENT_END_BANG]              = myhtml_tokenizer_state_comment_end_bang;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_BOGUS_COMMENT]                 = myhtml_tokenizer_state_bogus_comment;
    
    // cdata
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_CDATA_SECTION]                 = myhtml_tokenizer_state_cdata_section;
    
    // rcdata
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RCDATA]                        = myhtml_tokenizer_state_rcdata;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RCDATA_LESS_THAN_SIGN]         = myhtml_tokenizer_state_rcdata_less_than_sign;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_OPEN]           = myhtml_tokenizer_state_rcdata_end_tag_open;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_NAME]           = myhtml_tokenizer_state_rcdata_end_tag_name;
    
    // rawtext
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RAWTEXT]                        = myhtml_tokenizer_state_rawtext;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RAWTEXT_LESS_THAN_SIGN]         = myhtml_tokenizer_state_rawtext_less_than_sign;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RAWTEXT_END_TAG_OPEN]           = myhtml_tokenizer_state_rawtext_end_tag_open;
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_RAWTEXT_END_TAG_NAME]           = myhtml_tokenizer_state_rawtext_end_tag_name;
    
    // plaintext
    myhtml->parse_state_func[MyHTML_TOKENIZER_STATE_PLAINTEXT]                     = myhtml_tokenizer_state_plaintext;
    

source/myhtml/tokenizer.c  view on Meta::CPAN

                              + MyHTML_TOKENIZER_STATE_COMMENT)]                       = myhtml_tokenizer_end_state_comment;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_COMMENT_END)]                   = myhtml_tokenizer_end_state_comment_end;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_COMMENT_END_DASH)]              = myhtml_tokenizer_end_state_comment_end_dash;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_COMMENT_END_BANG)]              = myhtml_tokenizer_end_state_comment_end_bang;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_BOGUS_COMMENT)]                 = myhtml_tokenizer_end_state_bogus_comment;
    
    // for ends cdata
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_CDATA_SECTION)]                 = myhtml_tokenizer_end_state_cdata_section;
    
    // rcdata
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RCDATA)]                        = myhtml_tokenizer_end_state_rcdata;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RCDATA_LESS_THAN_SIGN)]         = myhtml_tokenizer_end_state_rcdata_less_than_sign;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_OPEN)]           = myhtml_tokenizer_end_state_rcdata_end_tag_open;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RCDATA_END_TAG_NAME)]           = myhtml_tokenizer_end_state_rcdata_end_tag_name;
    
    // rawtext
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RAWTEXT)]                        = myhtml_tokenizer_end_state_rawtext;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RAWTEXT_LESS_THAN_SIGN)]         = myhtml_tokenizer_end_state_rawtext_less_than_sign;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RAWTEXT_END_TAG_OPEN)]           = myhtml_tokenizer_end_state_rawtext_end_tag_open;
    myhtml->parse_state_func[(MyHTML_TOKENIZER_STATE_LAST_ENTRY
                              + MyHTML_TOKENIZER_STATE_RAWTEXT_END_TAG_NAME)]           = myhtml_tokenizer_end_state_rawtext_end_tag_name;

source/myhtml/tokenizer_end.c  view on Meta::CPAN

size_t myhtml_tokenizer_end_state_bogus_comment(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    token_node->raw_length = ((html_offset + tree->global_offset) - token_node->raw_begin);
    myhtml_queue_add(tree, html_offset, token_node);
    
    return html_offset;
}

size_t myhtml_tokenizer_end_state_cdata_section(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    token_node->raw_length = ((html_offset + tree->global_offset) - token_node->raw_begin);
    
    if(token_node->raw_length) {
        myhtml_queue_add(tree, html_offset, token_node);
    }
    
    return html_offset;
}

size_t myhtml_tokenizer_end_state_rcdata(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    if(token_node->raw_begin < (html_size + tree->global_offset)) {
        token_node->type |= MyHTML_TOKEN_TYPE_RCDATA;
        token_node->tag_id = MyHTML_TAG__TEXT;
        token_node->raw_length = (html_size + tree->global_offset) - token_node->raw_begin;
        
        myhtml_queue_add(tree, 0, token_node);
    }
    
    return html_offset;
}

size_t myhtml_tokenizer_end_state_rcdata_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, (html_offset + tree->global_offset), MyHTML_TOKEN_TYPE_RCDATA);
    return html_offset;
}

size_t myhtml_tokenizer_end_state_rcdata_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, (html_offset + tree->global_offset), MyHTML_TOKEN_TYPE_RCDATA);
    return html_offset;
}

size_t myhtml_tokenizer_end_state_rcdata_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;
    
    myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, (html_offset + tree->global_offset), MyHTML_TOKEN_TYPE_RCDATA);
    return html_offset;
}

size_t myhtml_tokenizer_end_state_rawtext(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size)
{
    token_node->element_length = (tree->global_offset + html_size) - token_node->element_begin;

source/myhtml/tokenizer_end.h  view on Meta::CPAN

size_t myhtml_tokenizer_end_state_attribute_value_double_quoted(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_attribute_value_single_quoted(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_attribute_value_unquoted(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment_start(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment_start_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment_end(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment_end_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_comment_end_bang(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_bogus_comment(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_cdata_section(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);

size_t myhtml_tokenizer_end_state_rcdata(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rcdata_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rcdata_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rcdata_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);

size_t myhtml_tokenizer_end_state_rawtext(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rawtext_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rawtext_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_rawtext_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);

size_t myhtml_tokenizer_end_state_plaintext(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_doctype(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_before_doctype_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);
size_t myhtml_tokenizer_end_state_doctype_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size);