llvm/mlir/lib/AsmParser/Lexer.cpp

//===- Lexer.cpp - MLIR Lexer Implementation ------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the lexer for the MLIR textual form.
//
//===----------------------------------------------------------------------===//

#include "Lexer.h"
#include "Token.h"
#include "mlir/AsmParser/CodeComplete.h"
#include "mlir/IR/Diagnostics.h"
#include "mlir/IR/Location.h"
#include "mlir/IR/MLIRContext.h"
#include "mlir/Support/LLVM.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/SourceMgr.h"
#include <cassert>
#include <cctype>

usingnamespacemlir;

// Returns true if 'c' is an allowable punctuation character: [$._-]
// Returns false otherwise.
static bool isPunct(char c) { … }

Lexer::Lexer(const llvm::SourceMgr &sourceMgr, MLIRContext *context,
             AsmParserCodeCompleteContext *codeCompleteContext)
    : … { … }

/// Encode the specified source location information into an attribute for
/// attachment to the IR.
Location Lexer::getEncodedSourceLocation(SMLoc loc) { … }

/// emitError - Emit an error message and return an Token::error token.
Token Lexer::emitError(const char *loc, const Twine &message) { … }

Token Lexer::lexToken() { … }

/// Lex an '@foo' identifier.
///
///   symbol-ref-id ::= `@` (bare-id | string-literal)
///
Token Lexer::lexAtIdentifier(const char *tokStart) { … }

/// Lex a bare identifier or keyword that starts with a letter.
///
///   bare-id ::= (letter|[_]) (letter|digit|[_$.])*
///   integer-type ::= `[su]?i[1-9][0-9]*`
///
Token Lexer::lexBareIdentifierOrKeyword(const char *tokStart) { … }

/// Skip a comment line, starting with a '//'.
///
///   TODO: add a regex for comments here and to the spec.
///
void Lexer::skipComment() { … }

/// Lex an ellipsis.
///
///   ellipsis ::= '...'
///
Token Lexer::lexEllipsis(const char *tokStart) { … }

/// Lex a number literal.
///
///   integer-literal ::= digit+ | `0x` hex_digit+
///   float-literal ::= [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
///
Token Lexer::lexNumber(const char *tokStart) { … }

/// Lex an identifier that starts with a prefix followed by suffix-id.
///
///   attribute-id  ::= `#` suffix-id
///   ssa-id        ::= '%' suffix-id
///   block-id      ::= '^' suffix-id
///   type-id       ::= '!' suffix-id
///   suffix-id     ::= digit+ | (letter|id-punct) (letter|id-punct|digit)*
///   id-punct      ::= `$` | `.` | `_` | `-`
///
Token Lexer::lexPrefixedIdentifier(const char *tokStart) { … }

/// Lex a string literal.
///
///   string-literal ::= '"' [^"\n\f\v\r]* '"'
///
/// TODO: define escaping rules.
Token Lexer::lexString(const char *tokStart) { … }