mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-22 07:30:19 +00:00
55450055d8
This commit is a mix of several commits, squashed into one because the commits before 'Move regex to own Library and fix all the broken stuff' were not fixable in any elegant way. The commits are listed below for "historical" purposes: - AK: Add options/flags and Errors for regular expressions Flags can be provided for any possible flavour by adding a new scoped enum. Handling of flags is done by templated Options class and the overloaded '|' and '&' operators. - AK: Add Lexer for regular expressions The lexer parses the input and extracts tokens needed to parse a regular expression. - AK: Add regex Parser and PosixExtendedParser This patchset adds a abstract parser class that can be derived to implement different parsers. A parser produces bytecode to be executed within the regex matcher. - AK: Add regex matcher This patchset adds an regex matcher based on the principles of the T-REX VM. The bytecode pruduced by the respective Parser is put into the matcher and the VM will recursively execute the bytecode according to the available OpCodes. Possible improvement: the recursion could be replaced by multi threading capabilities. To match a Regular expression, e.g. for the Posix standard regular expression matcher use the following API: ``` Pattern<PosixExtendedParser> pattern("^.*$"); auto result = pattern.match("Well, hello friends!\nHello World!"); // Match whole needle EXPECT(result.count == 1); EXPECT(result.matches.at(0).view.starts_with("Well")); EXPECT(result.matches.at(0).view.end() == "!"); result = pattern.match("Well, hello friends!\nHello World!", PosixFlags::Multiline); // Match line by line EXPECT(result.count == 2); EXPECT(result.matches.at(0).view == "Well, hello friends!"); EXPECT(result.matches.at(1).view == "Hello World!"); EXPECT(pattern.has_match("Well,....")); // Just check if match without a result, which saves some resources. ``` - AK: Rework regex to work with opcodes objects This patchsets reworks the matcher to work on a more structured base. For that an abstract OpCode class and derived classes for the specific OpCodes have been added. The respective opcode logic is contained in each respective execute() method. - AK: Add benchmark for regex - AK: Some optimization in regex for runtime and memory - LibRegex: Move regex to own Library and fix all the broken stuff Now regex works again and grep utility is also in place for testing. This commit also fixes the use of regex.h in C by making `regex_t` an opaque (-ish) type, which makes its behaviour consistent between C and C++ compilers. Previously, <regex.h> would've blown C compilers up, and even if it didn't, would've caused a leak in C code, and not in C++ code (due to the existence of `OwnPtr` inside the struct). To make this whole ordeal easier to deal with (for now), this pulls the definitions of `reg*()` into LibRegex. pros: - The circular dependency between LibC and LibRegex is broken - Eaiser to test (without accidentally pulling in the host's libc!) cons: - Using any of the regex.h functions will require the user to link -lregex - The symbols will be missing from libc, which will be a big surprise down the line (especially with shared libs). Co-Authored-By: Ali Mohammad Pur <ali.mpfard@gmail.com>
145 lines
4.5 KiB
C++
145 lines
4.5 KiB
C++
/*
|
|
* Copyright (c) 2020, Emanuel Sprung <emanuel.sprung@gmail.com>
|
|
* 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 "RegexByteCode.h"
|
|
#include "RegexError.h"
|
|
#include "RegexLexer.h"
|
|
#include "RegexOptions.h"
|
|
|
|
#include <AK/Forward.h>
|
|
#include <AK/StringBuilder.h>
|
|
#include <AK/Types.h>
|
|
#include <AK/Vector.h>
|
|
|
|
namespace regex {
|
|
|
|
class PosixExtendedParser;
|
|
|
|
template<typename T>
|
|
struct GenericParserTraits {
|
|
using OptionsType = T;
|
|
};
|
|
|
|
template<typename T>
|
|
struct ParserTraits : public GenericParserTraits<T> {
|
|
};
|
|
|
|
template<>
|
|
struct ParserTraits<PosixExtendedParser> : public GenericParserTraits<PosixOptions> {
|
|
};
|
|
|
|
class Parser {
|
|
public:
|
|
struct Result {
|
|
ByteCode bytecode;
|
|
size_t capture_groups_count;
|
|
size_t named_capture_groups_count;
|
|
size_t match_length_minimum;
|
|
Error error;
|
|
Token error_token;
|
|
};
|
|
|
|
explicit Parser(Lexer& lexer)
|
|
: m_parser_state(lexer)
|
|
{
|
|
}
|
|
|
|
Parser(Lexer& lexer, AllOptions regex_options)
|
|
: m_parser_state(lexer, regex_options)
|
|
{
|
|
}
|
|
|
|
virtual ~Parser() = default;
|
|
|
|
Result parse(Optional<AllOptions> regex_options = {});
|
|
bool has_error() const { return m_parser_state.error != Error::NoError; }
|
|
Error error() const { return m_parser_state.error; }
|
|
|
|
protected:
|
|
virtual bool parse_internal(ByteCode&, size_t& match_length_minimum) = 0;
|
|
|
|
ALWAYS_INLINE bool match(TokenType type) const;
|
|
ALWAYS_INLINE bool match(char ch) const;
|
|
ALWAYS_INLINE Token consume();
|
|
ALWAYS_INLINE Token consume(TokenType type, Error error);
|
|
ALWAYS_INLINE bool consume(const String&);
|
|
ALWAYS_INLINE void reset();
|
|
ALWAYS_INLINE bool done() const;
|
|
ALWAYS_INLINE bool set_error(Error error);
|
|
|
|
struct ParserState {
|
|
Lexer& lexer;
|
|
Token current_token;
|
|
Error error = Error::NoError;
|
|
Token error_token { TokenType::Eof, 0, StringView(nullptr) };
|
|
ByteCode bytecode;
|
|
size_t capture_groups_count { 0 };
|
|
size_t named_capture_groups_count { 0 };
|
|
size_t match_length_minimum { 0 };
|
|
AllOptions regex_options;
|
|
explicit ParserState(Lexer& lexer)
|
|
: lexer(lexer)
|
|
, current_token(lexer.next())
|
|
{
|
|
}
|
|
explicit ParserState(Lexer& lexer, AllOptions regex_options)
|
|
: lexer(lexer)
|
|
, current_token(lexer.next())
|
|
, regex_options(regex_options)
|
|
{
|
|
}
|
|
};
|
|
|
|
ParserState m_parser_state;
|
|
};
|
|
|
|
class PosixExtendedParser final : public Parser {
|
|
public:
|
|
explicit PosixExtendedParser(Lexer& lexer)
|
|
: Parser(lexer) {};
|
|
PosixExtendedParser(Lexer& lexer, Optional<typename ParserTraits<PosixExtendedParser>::OptionsType> regex_options)
|
|
: Parser(lexer, regex_options.value_or({})) {};
|
|
~PosixExtendedParser() = default;
|
|
|
|
private:
|
|
ALWAYS_INLINE bool match_repetition_symbol();
|
|
ALWAYS_INLINE bool match_ordinary_characters();
|
|
|
|
bool parse_internal(ByteCode&, size_t&) override;
|
|
|
|
bool parse_root(ByteCode&, size_t&);
|
|
ALWAYS_INLINE bool parse_sub_expression(ByteCode&, size_t&);
|
|
ALWAYS_INLINE bool parse_bracket_expression(ByteCode&, size_t&);
|
|
ALWAYS_INLINE bool parse_repetition_symbol(ByteCode&, size_t&);
|
|
};
|
|
|
|
using PosixExtended = PosixExtendedParser;
|
|
|
|
}
|
|
|
|
using regex::PosixExtended;
|