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; }
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; }