C语言词法分析器
这是老师布置的编译原理的实验课任务,课余时间花了近一个星期的时间去编写代码(主要是C++太久没有用了,好多函数都不熟悉,查阅了很多资料),这次的词法分析只有简单的语法错误判断功能,约等于没有.如果想要增加功能可以在相关函数代码段增加即可.
而且token的种别码只做了粗略的区分,想要加上也很简单
c语言词法分析流程如图所示:
代码如下:这次的代码算是我对代码整洁之道前期知识的一个练习,特别是变量的命名以及函数的编写,如果觉得写的不错可以看看我关于代码整洁之道的相关文章
这次的代码基本没有写注释,但是我相信大家结合流程图也能看懂,如果觉得太长可以将代码复制到visual studio中将函数代码块闭合起来这样看起来就逻辑清楚了
#include <iostream>
#include <string>
#include <map>
#include <ctype.h>
#include <algorithm>
using namespace std;
string readFile(string fileName);
string fileFilter();
string singleLineCommentsFilter();
string multilineCommmentsFileter();
string specialCharacterFilter();
void separateAndJudge();
bool isReservedWord(string vocabulary);
void separateAndJudge();
void showTokenData();
int digitStarted(int cnt);
bool isBoundSymbol(char ch);
bool isOperator(char ch);
int judgeStartingCharactorType(char ch);
bool isDigit(char ch);
bool isAlpha(char ch);
int alphaStarted(int cnt);
int underlineStarted(int cnt);
string transCharToString(char ch);
int operatorStarted(int cnt);
string codeSource;
map<string, int> tokens;//identifier is 1,reservedWord 2,digit 3,borderSymbol 4,operator 5
int main()
{
codeSource = readFile("d:\\testCode.txt");
cout << "This is source code" << endl << "---------------------------------" << endl << endl;
cout << codeSource << endl;
cout << "This is code filtered" << endl << "---------------------------------" << endl;
codeSource = fileFilter();
cout << codeSource << endl;
cout << "-----------------------" << endl;
separateAndJudge();
cout << "this is tokens " << endl;
cout << "-----------------------" << endl;
showTokenData();
return 0;
}
string readFile(string fileName)
{
FILE* fp;
if ((fp = fopen(fileName.c_str(), "r")) == NULL)
{
cout << "cant open file";
exit(0);
}
else
{
string codeSource;
char ch;
while ((ch = fgetc(fp)) != EOF)
{
codeSource += ch;
}
return codeSource;
}
};
string fileFilter()
{
string filteredCode = singleLineCommentsFilter();
filteredCode = multilineCommmentsFileter();
filteredCode = specialCharacterFilter();
return filteredCode;
};
string singleLineCommentsFilter()
{
long cnt = 0;
for (; cnt < codeSource.length(); cnt++)
{
while (codeSource[cnt] == '/' and codeSource[cnt + 1] == '/' and cnt < codeSource.length())
{
while (codeSource[cnt] != '\n')
{
codeSource.erase(cnt, 1);
}
}
}
return codeSource;
}
string multilineCommmentsFileter()
{
int cnt = 0;
for (; cnt < codeSource.length(); cnt++)
{
if (codeSource[cnt] == '/' and codeSource[cnt + 1] == '*' )
{
do
{
codeSource.erase(cnt, 1);
if ((codeSource[cnt + 1] == '*' and codeSource[cnt + 2] != '/'))
{
cout << "multilineCommments unmatch"<<endl;
exit(0);
};
} while ((codeSource[cnt + 1] != '*' and codeSource[cnt + 2] != '/'));
codeSource.erase(cnt, 4);
}
}
return codeSource;
}
string specialCharacterFilter()
{
for (int cnt = 0; cnt < codeSource.length(); cnt++)
{
if (codeSource[cnt] == '\n' or codeSource[cnt] == '\t' or codeSource[cnt] == '\v' or codeSource[cnt] == '\r')
{
codeSource.erase(cnt, 1);
cnt--;
}
}
return codeSource;
}
void separateAndJudge()
{
int cnt = 0;
for (; cnt < codeSource.length(); cnt++)
{
int nowCnt = 0;
while (codeSource[cnt] != ' ' and cnt < codeSource.length())
{
string a = "";
switch (judgeStartingCharactorType(codeSource[cnt]))
{
case 1:
cnt = digitStarted(cnt);
break;
case 2:
cnt = alphaStarted(cnt);
break;
case 3:
cnt = underlineStarted(cnt);
break;
case 4:
tokens[transCharToString(codeSource[cnt])] = 4;
cnt++;
break;
case 5:
cnt = operatorStarted(cnt);
//tokens[transCharToString(codeSource[cnt])] = 5;
//cnt++;
break;
case 6:
cout << "unrecognizable charactor!!!" << endl;
cout << "please check grammer again." << endl;
exit(0);
cnt++;
break;
default:
cnt++;
break;
}
}
}
}
int judgeStartingCharactorType(char ch)
{
int type = 0;
if (isDigit(ch)) {
type = 1; }
else
{
if (isAlpha(ch)) {
type = 2; }
else
{
if (ch == '_') {
type = 3; }
else
{
if (isBoundSymbol(ch)) {
type = 4; }
else
{
if (isOperator(ch)) {
type = 5; }
else {
type = 6; }
}
}
}
}
return type;
}
bool isBoundSymbol(char ch)
{
string temp = "";
temp += ch;
bool flag = false;
string boundSymbol[7] =
{
"(", ")", ",", ";", "{", "}","\"",
};
for (int i = 0; i < 7; i++)
{
if (boundSymbol[i] == temp)
{
flag = true;
}
}
return flag;
}
bool isOperator(char ch)
{
string temp = transCharToString(ch);
bool flag = false;
string operators[9]=
{
"+","-","*","/","=","%",">","<","=",
};
for (int i = 0; i < 9; i++)
{
if (operators[i] == temp)
{
flag = true;
}
}
return flag;
}
bool isDigit(char ch)
{
bool flag = false;
if (ch >= '0' and ch <= '9')
{
flag = true;
}
return flag;
}
bool isAlpha(char ch)
{
bool flag = false;
if ((ch >= 'a' and ch <= 'z') or (ch >= 'A' and ch <= 'Z'))
{
flag = true;
};
return flag;
}
int digitStarted(int cnt)
{
string digit;
digit += codeSource[cnt];
cnt++;
while (isDigit(codeSource[cnt]) or codeSource[cnt] == '.')
{
digit += codeSource[cnt];
++cnt;
}
tokens[digit] = 3;
return cnt;
}
int alphaStarted(int cnt)
{
string alpha;
alpha += codeSource[cnt];
cnt++;
while (isAlpha(codeSource[cnt]) or isDigit(codeSource[cnt]) or codeSource[cnt] == '_')
{
alpha += codeSource[cnt];
++cnt;
}
if (isReservedWord(alpha)) {
tokens[alpha] = 2; }
else {
tokens[alpha] = 1; }
return cnt;
}
int underlineStarted(int cnt)
{
string word;
word += codeSource[cnt];
cnt++;
while (isAlpha(codeSource[cnt]) or isDigit(codeSource[cnt]))
{
word += codeSource[cnt];
++cnt;
}
tokens[word] = 1;
return cnt;
}
int operatorStarted(int cnt)
{
bool flag = false;
string operators = "";
if (codeSource[cnt]=='=' and codeSource[cnt+1]=='=' )
{
operators = "==";
cnt++;
}
else
{
operators = transCharToString(codeSource[cnt]);
cnt++;
}
tokens[operators] = 5;
return cnt;
}
string transCharToString(char ch)
{
string temp = " ";
temp[0] = ch;
return temp;
}
bool isReservedWord(string vocabulary)
{
string reserveWords[32] = {
"auto", "break", "case", "char", "const", "continue",
"default", "do", "double", "else", "enum", "extern",
"float", "for", "goto", "if", "int", "long",
"register", "return", "short", "signed", "sizeof", "static",
"struct", "switch", "typedef", "union", "unsigned", "void",
"volatile", "while"
};
bool flag = false;
for (int i = 0; i < 32; i++)
{
if (reserveWords[i] == vocabulary)
{
flag = true;
}
}
return flag;
};
void showTokenData()
{
map<string, int>::iterator iter;
for (iter = tokens.begin(); iter != tokens.end(); iter++)
cout <<"<"<< iter->first << ',' << iter->second<<">" << endl;
}