lexer.h (3806B)
1 // Copyright (c) 2013-2014 Sandstorm Development Group, Inc. and contributors 2 // Licensed under the MIT License: 3 // 4 // Permission is hereby granted, free of charge, to any person obtaining a copy 5 // of this software and associated documentation files (the "Software"), to deal 6 // in the Software without restriction, including without limitation the rights 7 // to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 8 // copies of the Software, and to permit persons to whom the Software is 9 // furnished to do so, subject to the following conditions: 10 // 11 // The above copyright notice and this permission notice shall be included in 12 // all copies or substantial portions of the Software. 13 // 14 // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 15 // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 16 // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 17 // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 18 // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 19 // OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN 20 // THE SOFTWARE. 21 22 #pragma once 23 24 #include <capnp/compiler/lexer.capnp.h> 25 #include <kj/parse/common.h> 26 #include <kj/arena.h> 27 #include "error-reporter.h" 28 29 CAPNP_BEGIN_HEADER 30 31 namespace capnp { 32 namespace compiler { 33 34 bool lex(kj::ArrayPtr<const char> input, LexedStatements::Builder result, 35 ErrorReporter& errorReporter); 36 bool lex(kj::ArrayPtr<const char> input, LexedTokens::Builder result, ErrorReporter& errorReporter); 37 // Lex the given source code, placing the results in `result`. Returns true if there 38 // were no errors, false if there were. Even when errors are present, the file may have partial 39 // content which can be fed into later stages of parsing in order to find more errors. 40 // 41 // There are two versions, one that parses a list of statements, and one which just parses tokens 42 // that might form a part of one statement. In other words, in the later case, the input should 43 // not contain semicolons or curly braces, unless they are in string literals of course. 44 45 class Lexer { 46 // Advanced lexer interface. This interface exposes the inner parsers so that you can embed them 47 // into your own parsers. 48 49 public: 50 Lexer(Orphanage orphanage, ErrorReporter& errorReporter); 51 // `orphanage` is used to allocate Cap'n Proto message objects in the result. `inputStart` is 52 // a pointer to the beginning of the input, used to compute byte offsets. 53 54 ~Lexer() noexcept(false); 55 56 class ParserInput: public kj::parse::IteratorInput<char, const char*> { 57 // Like IteratorInput<char, const char*> except that positions are measured as byte offsets 58 // rather than pointers. 59 60 public: 61 ParserInput(const char* begin, const char* end) 62 : IteratorInput<char, const char*>(begin, end), begin(begin) {} 63 explicit ParserInput(ParserInput& parent) 64 : IteratorInput<char, const char*>(parent), begin(parent.begin) {} 65 66 inline uint32_t getBest() { 67 return IteratorInput<char, const char*>::getBest() - begin; 68 } 69 inline uint32_t getPosition() { 70 return IteratorInput<char, const char*>::getPosition() - begin; 71 } 72 73 private: 74 const char* begin; 75 }; 76 77 template <typename Output> 78 using Parser = kj::parse::ParserRef<ParserInput, Output>; 79 80 struct Parsers { 81 Parser<kj::Tuple<>> emptySpace; 82 Parser<Orphan<Token>> token; 83 Parser<kj::Array<Orphan<Token>>> tokenSequence; 84 Parser<Orphan<Statement>> statement; 85 Parser<kj::Array<Orphan<Statement>>> statementSequence; 86 }; 87 88 const Parsers& getParsers() { return parsers; } 89 90 private: 91 Orphanage orphanage; 92 kj::Arena arena; 93 Parsers parsers; 94 }; 95 96 } // namespace compiler 97 } // namespace capnp 98 99 CAPNP_END_HEADER