f808279769
This patch implements the HTML specification's "encoding sniffing algorithm", which is used when no encoding can be obtained from the Content-Type header (either because it doesn't contain a charset=...) value or the file has not been opened via HTTP (as with local files). It also modifies the creator of the HTMLDocumentParser to use the new HTMLDocumentParser::create_with_uncertain_encoding static method, which runs the encoding sniffing algorithm before instantiating the parser. This now allows us to load local HTML pages (or remote pages without a charset specified in the 'Content-Type' header) with a non-UTF-8 encoding such as 'windows-1252'. This would previously crash the browser. :^)
22 lines
671 B
C++
22 lines
671 B
C++
/*
|
|
* Copyright (c) 2021, Max Wipfli <mail@maxwipfli.ch>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/Optional.h>
|
|
#include <AK/String.h>
|
|
#include <LibWeb/DOM/Attribute.h>
|
|
|
|
namespace Web::HTML {
|
|
|
|
bool prescan_should_abort(const ByteBuffer& input, const size_t& position);
|
|
bool prescan_is_whitespace_or_slash(const u8& byte);
|
|
bool prescan_skip_whitespace_and_slashes(const ByteBuffer& input, size_t& position);
|
|
Optional<Attribute> prescan_get_attribute(const ByteBuffer& input, size_t& position);
|
|
Optional<String> run_prescan_byte_stream_algorithm(const ByteBuffer& input);
|
|
String run_encoding_sniffing_algorithm(const ByteBuffer& input);
|
|
|
|
}
|