beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-26 09:30:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

LibWeb: Begin work on a spec-compliant HTML parser

Browse source 
In order to actually view the web as it is, we're gonna need a proper
HTML parser. So let's build one!

This patch introduces the Web::HTMLTokenizer class, which currently
operates on a StringView input stream where it fetches (ASCII only atm)
codepoints and tokenizes acccording to the HTML spec tokenization algo.

The tokenizer state machine looks a bit weird but is written in a way
that tries to mimic the spec as closely as possible, in order to make
development easier and bugs less likely.

This initial version is far from finished, but it can parse a trivial
document with a DOCTYPE and open/close tags. :^)
This commit is contained in:
Andreas Kling 2020-05-22 21:46:13 +02:00
parent 120cd44011
commit 272b35d2e1
Notes: sideshowbarker 2024-07-19 06:14:55 +09:00 
Author: https://github.com/awesomekling
Commit: https://github.com/SerenityOS/serenity/commit/272b35d2e10
7 changed files with 562 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
Base/home/anon/www/simple.html Normal file
View file

@ -0,0 +1,3 @@
<!DOCTYPE html>
<html>
</html>

1
Libraries/LibWeb/CMakeLists.txt
View file

@ -85,6 +85,7 @@ set(SOURCES
Layout/LineBoxFragment.cpp
Parser/CSSParser.cpp
Parser/HTMLParser.cpp
Parser/HTMLTokenizer.cpp
ResourceLoader.cpp
StylePropertiesModel.cpp
URLEncoder.cpp

76
Libraries/LibWeb/Parser/HTMLToken.h Normal file
View file

@ -0,0 +1,76 @@
/*
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#pragma once
#include <AK/String.h>
#include <AK/StringBuilder.h>
#include <AK/Types.h>
#include <AK/Vector.h>
#include <LibWeb/DOM/Attribute.h>
namespace Web {
class HTMLToken {
friend class HTMLTokenizer;
public:
enum class Type {
DOCTYPE,
StartTag,
EndTag,
Comment,
Character,
EndOfFile,
};
Type type() const { return m_type; }
private:
Type m_type;
// Type::DOCTYPE
struct {
StringBuilder name;
StringBuilder public_identifier;
StringBuilder system_public_identifier;
bool force_quirks { false };
} m_doctype;
// Type::StartTag
// Type::EndTag
struct {
StringBuilder tag_name;
bool self_closing { false };
Vector<Attribute> attributes;
} m_tag;
struct {
StringBuilder data;
} m_comment_or_character;
};
}

305
Libraries/LibWeb/Parser/HTMLTokenizer.cpp Normal file
View file

@ -0,0 +1,305 @@
/*
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <LibWeb/Parser/HTMLToken.h>
#include <LibWeb/Parser/HTMLTokenizer.h>
#include <ctype.h>
//#define TOKENIZER_TRACE
#define SWITCH_TO(new_state) \
will_switch_to(State::new_state); \
m_state = State::new_state; \
current_input_character = next_codepoint(); \
goto new_state;
#define RECONSUME_IN(new_state) \
will_reconsume_in(State::new_state); \
m_state = State::new_state; \
goto new_state;
#define DONT_CONSUME_NEXT_INPUT_CHARACTER --m_cursor;
#define IGNORE_CHARACTER_AND_CONTINUE_IN(x) SWITCH_TO(x)
#define ON(codepoint) \
if (current_input_character.has_value() && current_input_character.value() == codepoint)
#define ON_EOF \
if (!current_input_character.has_value())
#define ON_ASCII_ALPHA \
if (current_input_character.has_value() && isalpha(current_input_character.value()))
#define ON_WHITESPACE \
if (current_input_character.has_value() && (current_input_character.value() == '\t' || current_input_character.value() == '\a' || current_input_character.value() == '\f' || current_input_character.value() == ' '))
#define ANYTHING_ELSE if (1)
#define EMIT_EOF_AND_RETURN \
create_new_token(HTMLToken::Type::EndOfFile); \
emit_current_token(); \
return;
#define BEGIN_STATE(state) \
state: \
case State::state:
#define END_STATE \
ASSERT_NOT_REACHED(); \
break;
namespace Web {
Optional<u32> HTMLTokenizer::next_codepoint()
{
if (m_cursor >= m_input.length())
return {};
return m_input[m_cursor++];
}
Optional<u32> HTMLTokenizer::peek_codepoint(size_t offset) const
{
if ((m_cursor + offset) >= m_input.length())
return {};
return m_input[m_cursor + offset];
}
void HTMLTokenizer::run()
{
for (;;) {
auto current_input_character = next_codepoint();
switch (m_state) {
BEGIN_STATE(Data)
{
ON('&')
{
m_return_state = State::Data;
SWITCH_TO(CharacterReference);
}
ON('<')
{
SWITCH_TO(TagOpen);
}
ON_EOF
{
EMIT_EOF_AND_RETURN;
}
ANYTHING_ELSE
{
create_new_token(HTMLToken::Type::Character);
m_current_token.m_comment_or_character.data.append(current_input_character.value());
emit_current_token();
continue;
}
}
END_STATE
BEGIN_STATE(TagOpen)
{
ON('!')
{
SWITCH_TO(MarkupDeclarationOpen);
}
ON('/')
{
SWITCH_TO(EndTagOpen);
}
ON_ASCII_ALPHA
{
create_new_token(HTMLToken::Type::StartTag);
RECONSUME_IN(TagName);
}
}
END_STATE
BEGIN_STATE(TagName)
{
ON('>')
{
emit_current_token();
SWITCH_TO(Data);
}
ANYTHING_ELSE
{
m_current_token.m_tag.tag_name.append(current_input_character.value());
continue;
}
}
BEGIN_STATE(EndTagOpen)
{
ON_ASCII_ALPHA
{
create_new_token(HTMLToken::Type::EndTag);
RECONSUME_IN(TagName);
}
}
END_STATE
BEGIN_STATE(MarkupDeclarationOpen)
{
DONT_CONSUME_NEXT_INPUT_CHARACTER;
if (next_few_characters_are("DOCTYPE")) {
consume("DOCTYPE");
SWITCH_TO(DOCTYPE);
}
}
END_STATE
BEGIN_STATE(DOCTYPE)
{
ON_WHITESPACE
{
SWITCH_TO(BeforeDOCTYPEName);
}
}
END_STATE
BEGIN_STATE(BeforeDOCTYPEName)
{
ON_WHITESPACE
{
continue;
}
ANYTHING_ELSE
{
create_new_token(HTMLToken::Type::DOCTYPE);
m_current_token.m_doctype.name.append(current_input_character.value());
SWITCH_TO(DOCTYPEName);
}
}
END_STATE
BEGIN_STATE(DOCTYPEName)
{
ON('>')
{
emit_current_token();
SWITCH_TO(Data);
}
ANYTHING_ELSE
{
m_current_token.m_doctype.name.append(current_input_character.value());
continue;
}
}
END_STATE
BEGIN_STATE(CharacterReference)
{
}
END_STATE
default:
ASSERT_NOT_REACHED();
}
}
}
void HTMLTokenizer::consume(const StringView& string)
{
ASSERT(next_few_characters_are(string));
m_cursor += string.length();
}
bool HTMLTokenizer::next_few_characters_are(const StringView& string) const
{
for (size_t i = 0; i < string.length(); ++i) {
auto codepoint = peek_codepoint(i);
if (!codepoint.has_value())
return false;
// FIXME: This should be more Unicode-aware.
if (codepoint.value() != (u32)string[i])
return false;
}
return true;
}
void HTMLTokenizer::emit_current_token()
{
StringBuilder builder;
switch (m_current_token.type()) {
case HTMLToken::Type::DOCTYPE:
builder.append("DOCTYPE");
builder.append(" { name: '");
builder.append(m_current_token.m_doctype.name.to_string());
builder.append("' }");
break;
case HTMLToken::Type::StartTag:
builder.append("StartTag");
break;
case HTMLToken::Type::EndTag:
builder.append("EndTag");
break;
case HTMLToken::Type::Comment:
builder.append("Comment");
break;
case HTMLToken::Type::Character:
builder.append("Character");
break;
case HTMLToken::Type::EndOfFile:
builder.append("EndOfFile");
break;
}
if (m_current_token.type() == HTMLToken::Type::StartTag || m_current_token.type() == HTMLToken::Type::EndTag) {
builder.append(" { name: '");
builder.append(m_current_token.m_tag.tag_name.to_string());
builder.append("' }");
}
dbg() << "[" << String::format("%42s", state_name(m_state)) << "] " << builder.to_string();
m_current_token = {};
}
void HTMLTokenizer::create_new_token(HTMLToken::Type type)
{
m_current_token = {};
m_current_token.m_type = type;
}
HTMLTokenizer::HTMLTokenizer(const StringView& input)
: m_input(input)
{
}
void HTMLTokenizer::will_switch_to([[maybe_unused]] State new_state)
{
#ifdef TOKENIZER_TRACE
dbg() << "[" << state_name(m_state) << "] Switch to " << state_name(new_state);
#endif
}
void HTMLTokenizer::will_reconsume_in([[maybe_unused]] State new_state)
{
#ifdef TOKENIZER_TRACE
dbg() << "[" << state_name(m_state) << "] Reconsume in " << state_name(new_state);
#endif
}
}

160
Libraries/LibWeb/Parser/HTMLTokenizer.h Normal file
View file

@ -0,0 +1,160 @@
/*
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#pragma once
#include <AK/StringView.h>
#include <AK/Types.h>
#include <LibWeb/Parser/HTMLToken.h>
#define ENUMERATE_TOKENIZER_STATES \
__ENUMERATE_TOKENIZER_STATE(Data) \
__ENUMERATE_TOKENIZER_STATE(RCDATA) \
__ENUMERATE_TOKENIZER_STATE(RAWTEXT) \
__ENUMERATE_TOKENIZER_STATE(ScriptData) \
__ENUMERATE_TOKENIZER_STATE(PLAINTEXT) \
__ENUMERATE_TOKENIZER_STATE(TagOpen) \
__ENUMERATE_TOKENIZER_STATE(EndTagOpen) \
__ENUMERATE_TOKENIZER_STATE(TagName) \
__ENUMERATE_TOKENIZER_STATE(RCDATALessThanSign) \
__ENUMERATE_TOKENIZER_STATE(RCDATAEndTagOpen) \
__ENUMERATE_TOKENIZER_STATE(RCDATAEndTagName) \
__ENUMERATE_TOKENIZER_STATE(RAWTEXTLessThanSign) \
__ENUMERATE_TOKENIZER_STATE(RAWTEXTEndTagOpen) \
__ENUMERATE_TOKENIZER_STATE(RAWTEXTEndTagName) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataLessThanSign) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEndTagOpen) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEndTagName) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapeStart) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapeStartDash) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscaped) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapedDash) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapedDashDash) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapedLessThanSign) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapedEndTagOpen) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataEscapedEndTagName) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscapeStart) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscaped) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscapedDash) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscapedDashDash) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscapedLessThanSign) \
__ENUMERATE_TOKENIZER_STATE(ScriptDataDoubleEscapeEnd) \
__ENUMERATE_TOKENIZER_STATE(BeforeAttributeName) \
__ENUMERATE_TOKENIZER_STATE(AttributeName) \
__ENUMERATE_TOKENIZER_STATE(AfterAttributeName) \
__ENUMERATE_TOKENIZER_STATE(BeforeAttributeValue) \
__ENUMERATE_TOKENIZER_STATE(AttributeValueDoubleQuoted) \
__ENUMERATE_TOKENIZER_STATE(AttributeValueSingleQuoted) \
__ENUMERATE_TOKENIZER_STATE(AttributeValueUnquoted) \
__ENUMERATE_TOKENIZER_STATE(AfterAttributeValueQuoted) \
__ENUMERATE_TOKENIZER_STATE(SelfClosingStartTag) \
__ENUMERATE_TOKENIZER_STATE(BogusComment) \
__ENUMERATE_TOKENIZER_STATE(MarkupDeclarationOpen) \
__ENUMERATE_TOKENIZER_STATE(CommentStart) \
__ENUMERATE_TOKENIZER_STATE(CommentStartDash) \
__ENUMERATE_TOKENIZER_STATE(Comment) \
__ENUMERATE_TOKENIZER_STATE(CommentLessThanSign) \
__ENUMERATE_TOKENIZER_STATE(CommentLessThanSignBang) \
__ENUMERATE_TOKENIZER_STATE(CommentLessThanSignBangDash) \
__ENUMERATE_TOKENIZER_STATE(CommentLessThanSignBangDashDash) \
__ENUMERATE_TOKENIZER_STATE(CommentEndDash) \
__ENUMERATE_TOKENIZER_STATE(CommentEnd) \
__ENUMERATE_TOKENIZER_STATE(CommentEndBang) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPE) \
__ENUMERATE_TOKENIZER_STATE(BeforeDOCTYPEName) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPEName) \
__ENUMERATE_TOKENIZER_STATE(AfterDOCTYPEName) \
__ENUMERATE_TOKENIZER_STATE(AfterDOCTYPEPublicKeyword) \
__ENUMERATE_TOKENIZER_STATE(BeforeDOCTYPEPublicIdentifier) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPEPublicIdentifierDoubleQuoted) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPEPublicIdentifierSingleQuoted) \
__ENUMERATE_TOKENIZER_STATE(AfterDOCTYPEPublicIdentifier) \
__ENUMERATE_TOKENIZER_STATE(BetweenDOCTYPEPublicAndSystemIdentifiers) \
__ENUMERATE_TOKENIZER_STATE(AfterDOCTYPESystemKeyword) \
__ENUMERATE_TOKENIZER_STATE(BeforeDOCTYPESystemIdentifier) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPESystemIdentifierDoubleQuoted) \
__ENUMERATE_TOKENIZER_STATE(DOCTYPESystemIdentifierSingleQuoted) \
__ENUMERATE_TOKENIZER_STATE(AfterDOCTYPESystemIdentifier) \
__ENUMERATE_TOKENIZER_STATE(BogusDOCTYPE) \
__ENUMERATE_TOKENIZER_STATE(CDATASection) \
__ENUMERATE_TOKENIZER_STATE(CDATASectionBracket) \
__ENUMERATE_TOKENIZER_STATE(CDATASectionEnd) \
__ENUMERATE_TOKENIZER_STATE(CharacterReference) \
__ENUMERATE_TOKENIZER_STATE(NamedCharacterReference) \
__ENUMERATE_TOKENIZER_STATE(AmbiguousAmpersand) \
__ENUMERATE_TOKENIZER_STATE(NumericCharacterReference) \
__ENUMERATE_TOKENIZER_STATE(HexadecimalCharacterReferenceStart) \
__ENUMERATE_TOKENIZER_STATE(DecimalCharacterReferenceStart) \
__ENUMERATE_TOKENIZER_STATE(HexadecimalCharacterReference) \
__ENUMERATE_TOKENIZER_STATE(DecimalCharacterReference) \
__ENUMERATE_TOKENIZER_STATE(NumericCharacterReferenceEnd)
namespace Web {
class HTMLTokenizer {
public:
explicit HTMLTokenizer(const StringView& input);
void run();
private:
Optional<u32> next_codepoint();
Optional<u32> peek_codepoint(size_t offset) const;
bool next_few_characters_are(const StringView&) const;
void consume(const StringView&);
void emit_current_token();
void create_new_token(HTMLToken::Type);
enum class State {
#define __ENUMERATE_TOKENIZER_STATE(state) state,
ENUMERATE_TOKENIZER_STATES
#undef __ENUMERATE_TOKENIZER_STATE
};
static const char* state_name(State state)
{
switch (state) {
#define __ENUMERATE_TOKENIZER_STATE(state) \
case State::state: \
return #state;
ENUMERATE_TOKENIZER_STATES
#undef __ENUMERATE_TOKENIZER_STATE
};
ASSERT_NOT_REACHED();
}
void will_switch_to(State);
void will_reconsume_in(State);
State m_state { State::Data };
State m_return_state { State::Data };
StringView m_input;
size_t m_cursor { 0 };
HTMLToken m_current_token;
};
}

1
Userland/CMakeLists.txt
View file

@ -13,6 +13,7 @@ target_link_libraries(copy LibGUI)
target_link_libraries(disasm LibX86)
target_link_libraries(functrace LibDebug LibX86)
target_link_libraries(html LibWeb)
target_link_libraries(ht LibWeb)
target_link_libraries(lspci LibPCIDB)
target_link_libraries(man LibMarkdown)
target_link_libraries(md LibMarkdown)

16
Userland/ht.cpp Normal file
View file

@ -0,0 +1,16 @@
#include <LibWeb/Parser/HTMLTokenizer.h>
#include <LibCore/File.h>
#include <AK/ByteBuffer.h>
#include <AK/LogStream.h>
int main(int, char**)
{
// This is a temporary test program to aid with bringing up the new HTML parser. :^)
auto file_or_error = Core::File::open("/home/anon/www/simple.html", Core::File::ReadOnly);
if (file_or_error.is_error())
return 1;
auto contents = file_or_error.value()->read_all();
Web::HTMLTokenizer tokenizer(contents);
tokenizer.run();
return 0;
}