llvm学习日记四：使用lexer

参考书：《Getting Started with LLVM Core Libraries》

词法分析器使用，参考上一小节。

一、makefile

使用上一节的makefile：

二、cpp源代码

extern "C" {
#include "clang-c/Index.h"
}
#include "llvm/Support/CommandLine.h"
#include <iostream>
using namespace llvm;
static cl::opt<std::string> FileName(cl::Positional ,cl::desc("Input file"),cl::Required);
int main(int argc, char** argv)
{

    cl::ParseCommandLineOptions(argc, argv, "My tokenizer\n");
    CXIndex index = clang_createIndex(0,0);
    const char *args[] = {"-I/usr/include","-I." };

    CXTranslationUnit translationUnit = clang_parseTranslationUnit(index, FileName.c_str(),args, 2, NULL, 0, CXTranslationUnit_None);

    CXFile file = clang_getFile(translationUnit, FileName.c_str());
    CXSourceLocation loc_start = clang_getLocationForOffset(translationUnit, file, 0);
    CXSourceLocation loc_end = clang_getLocationForOffset(translationUnit, file, 62);
    CXSourceRange range = clang_getRange(loc_start, loc_end);

    unsigned numTokens = 0;
    CXToken *tokens = NULL;
    clang_tokenize (translationUnit, range, &tokens, &numTokens);
    for (unsigned i = 0; i < numTokens; ++i) {
      
        enum CXTokenKind kind = clang_getTokenKind(tokens[i]);

        CXString name = clang_getTokenSpelling(translationUnit,tokens[i]);

        switch (kind) {
            case CXToken_Punctuation:
              std::cout << "PUNCTUATION(" << clang_getCString(name) << ") ";
              break;
            case CXToken_Keyword:
              std::cout << "KEYWORD(" << clang_getCString(name) << ") ";
              break;
            case CXToken_Identifier:
              std::cout << "IDENTIFIER(" << clang_getCString(name) << ") ";
              break;
            case CXToken_Literal:
              std::cout << "COMMENT(" << clang_getCString(name) << ") ";
              break;
            default:
              std::cout << "UNKNOWN(" << clang_getCString(name) << ") ";
            break; 
        }
        clang_disposeString(name);
    }
    std::cout << std::endl;
    clang_disposeTokens (translationUnit, tokens, numTokens);
    clang_disposeTranslationUnit(translationUnit);
    return 0;
}

clang_getLocationForOffset 参数要注意62代表下边hello.c 的字节数。

三、执行结果：

hello.c

#include <stdio.h>
int main() {
    printf("hello, world!");
}

image.png