scan.c

这是个自己写的一个此法分析器

#include "scan.h"
#include "globals.h"
#include "stdio.h"

void Do_Tag(char *strSource);
void Do_Digit(char *strSource);
void Do_NDigit(char *strSource);
void Do_EndOfTag(char *strSource);
void Do_EndOfDigit(char *strSource);
void Do_EndOfEqual(char *strSource);
void Do_EndOfPlus(char *strSource);
void Do_EndOfSubtraction(char *strSource);
void Do_EndOfMutiply(char *strSource);
void Do_EndOfDivide(char *strSource);
void Do_EndOfLParen(char *strSource);
void Do_EndOfRParen(char *strSource);
void Do_EndOfLeftBracket1(char *strSource);
void Do_EndOfRightBracket1(char *strSource);
void Do_EndOfLeftBracket2(char *strSource);
void Do_EndOfRihtBracket2(char *strSource);
void Do_EndOfColon(char *strSource);
void Do_EndOfComma(char *strSource);
void Do_EndOfSemicolon(char *strSource);
void Do_EndOfMore(char *strSource);
void Do_EndOfLess(char *strSource);
void Do_EndOfEnd(char *strSource);
void PrintError(int nColumn,int nRow,char chInput);
void Scaner(void);

char *strSource;  char a;
FILE *fw;
FILE *inpute_file;
int gnColumn,gnRow,gnLocate,gnLocateStart;

Word uWord;

char *KEY_WORDS[20]={"main","int","char","if","else","for","while","void","float","long",_KEY_WORD_END};

int IsDigit(char chInput)
{
    if(chInput <= '9' && chInput >= '0') return 1;
    else return 0;
}

int IsChar(char chInput)
{
    if((chInput <= 'z' && chInput >= 'a') ||  (chInput <= 'Z' && chInput >= 'A')) return 1;
    else return 0;
}

void Do_Start(char *strSource)
{
    gnLocateStart = gnLocate;
    switch(strSource[gnLocate]){
    case'+': Do_EndOfPlus(strSource);       break;
    case'-':
    {    if ( strSource[gnLocate-1]=='=' || strSource[gnLocate-1]=='(')
        {
            gnLocate++;
            gnRow++;
            uWord.value.T2 = -(strSource[gnLocate]-'0');
            Do_NDigit(strSource);
            break;
        }
        else Do_EndOfSubtraction(strSource);        break;
    }
    case'*': Do_EndOfMutiply(strSource);        break;
    case'/':
    {
            if( strSource[gnLocate+1] == '*')
            {
                int j=0;
                uWord.value.T1[j++]='/';
                uWord.value.T1[j++]='*';
                gnLocate+=2;
                gnRow+=2;
                do
                {
                    printf("%c",strSource[gnLocate]);
                    uWord.value.T1[j++]=strSource[gnLocate++];
                    gnRow++;
                }while (!((strSource[gnLocate]=='*') && (strSource[gnLocate+1]=='/')));
                uWord.value.T1[j++]='*';
                uWord.value.T1[j++]='/';
                uWord.value.T1[j++]='\0';
                uWord.syn=1122;
                gnLocate+=2;
                gnRow+=2;
                break;
            }
            else Do_EndOfDivide(strSource);  break;
    }
    case'(': Do_EndOfLParen(strSource);     break;
    case')': Do_EndOfRParen(strSource);     break;
    case'[': Do_EndOfLeftBracket1(strSource);       break;
    case']': Do_EndOfRightBracket1(strSource);      break;
    case'{': Do_EndOfLeftBracket2(strSource);       break;
    case'}': Do_EndOfLeftBracket2(strSource);       break;
    case':': Do_EndOfColon(strSource);      break;
    case',': Do_EndOfComma(strSource);      break;
    case';': Do_EndOfSemicolon(strSource);      break;
    case'>': Do_EndOfMore(strSource);       break;
    case'<': Do_EndOfLess(strSource);       break;
    case'=': Do_EndOfEqual(strSource);      break;
    case'\0': Do_EndOfEnd(strSource);       break;

    default:
    if(IsChar(strSource[gnLocate])){
        Do_Tag(strSource);
    }
    else if (IsDigit(strSource[gnLocate])){        uWord.value.T2 = strSource[gnLocate]-'0';

        Do_Digit(strSource);
    }
    else{
        if(strSource[gnLocate] != '\n' &&
            strSource[gnLocate] != '\t' &&
            strSource[gnLocate] != '\r' &&
            strSource[gnLocate] != ' ' ){
        PrintError( gnColumn, gnRow,strSource[gnLocate]);
         }
    if (strSource[gnLocate] == '\n' || strSource[gnLocate] != '\r'){
        gnColumn++;
        gnRow=1;
    }
    else if (strSource[gnLocate] != '\t'){
        gnColumn += _TAB_LEGNTH;
    }
    else gnRow++;
    gnLocate++;
    Do_Start(strSource);
     }
     break;
     }
     return;
}

void Do_Tag(char *strSource)   /* 识别标示符的中间状态 */
{
    gnLocate++;
    gnRow++;
    if (IsChar(strSource[gnLocate])||IsDigit(strSource[gnLocate])){
        Do_Tag(strSource);
    }
    else Do_EndOfTag(strSource);
    return;
}

void Do_Digit(char *strSource)   /* 识别整数的中间状态 */
{
    gnLocate++;
    gnRow++;
    if (IsDigit(strSource[gnLocate])){
        uWord.value.T2=uWord.value.T2*10+strSource[gnLocate]-'0';
        Do_Digit(strSource);
    }
    else Do_EndOfDigit(strSource);
    return;
}

void Do_NDigit(char *strSource)   /* 识别整数的中间状态 */
{
    gnLocate++;
    gnRow++;
    if (IsDigit(strSource[gnLocate])){
        uWord.value.T2=uWord.value.T2*10-(strSource[gnLocate]-'0');
        Do_NDigit(strSource);
    }
    else Do_EndOfDigit(strSource);
    return;
}

void Do_EndOfTag(char *strSource)   /* 标示符的最后状态 */
{
    int nLoop;
    uWord.syn=_SYN_ID;

    strncpy(uWord.value.T1,strSource+gnLocateStart,gnLocate-gnLocateStart);
    uWord.value.T1[gnLocate-gnLocateStart]='\0';

    nLoop=0;
    while(strcmp(KEY_WORDS[nLoop],_KEY_WORD_END)) {
        if (!strcmp(KEY_WORDS[nLoop],uWord.value.T1)) {
            uWord.syn=nLoop+1;
            break;
        }
        nLoop++;
    }
    return;
}

void Do_EndOfDigit(char *strSource)   /* 识别数字的最后状态 */
{
    uWord.syn=_SYN_NUM;
    return;
}

void Do_EndOfEqual(char *strSource)   /* = */
{
    if (strSource[gnLocate+1]!='='){
        uWord.syn=_SYN_ASSIGN;
        uWord.value.T3=strSource[gnLocate];
    }
    else{
        gnLocate++;
        gnRow++;
        uWord.syn=_SYN_EQ;
        strcpy(uWord.value.T1,"==");
    }
    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfPlus(char *strSource)  /* + */
{

    uWord.syn=_SYN_PLUS;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfSubtraction(char *strSource)  /* - */
{
    uWord.syn=_SYN_MINUS;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfMutiply(char *strSource)  /* * */
{
    uWord.syn=_SYN_TIMES;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfDivide(char *strSource)  /* / */
{
    uWord.syn=_SYN_DIVIDE;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfLParen(char *strSource)  /* ( */
{
    uWord.syn=_SYN_LPAREN;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfRParen(char *strSource)  /* ) */
{
    uWord.syn=_SYN_RPAREN;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfLeftBracket1(char *strSource)  /* [ */
{
    uWord.syn=_SYN_LEFTBRACKET1;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfRightBracket1(char *strSource)  /* ] */
{
    uWord.syn=_SYN_RIGHTBRACKET1;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfLeftBracket2(char *strSource)  /* { */
{
    uWord.syn=_SYN_LEFTBRACKET2;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfRightBracket2(char *strSource)  /* } */
{
    uWord.syn=_SYN_RIGHTBRACKET2;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfColon(char *strSource)  /* : */
{
    uWord.syn=_SYN_COLON;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfComma(char *strSource)  /* , */
{
    uWord.syn=_SYN_COMMA;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfSemicolon(char *strSource)  /* ; */
{
    uWord.syn=_SYN_SEMICOLON;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfMore(char *strSource)  /* >= */
{
    if (strSource[gnLocate+1]!='='){    /* > */
        uWord.syn=_SYN_LG;
        uWord.value.T3=strSource[gnLocate];
    }
    else{           /* >= */
        gnLocate++;
        gnRow++;
        uWord.syn=_SYN_ME;
        strcpy(uWord.value.T1,">=");
    }
    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfLess(char *strSource)  /* <= */
{
    if (strSource[gnLocate+1]!='='){    /* < */
        uWord.syn=_SYN_LT;
        uWord.value.T3=strSource[gnLocate];
    }
    else{           /* <= */
        gnLocate++;
        gnRow++;
        uWord.syn=_SYN_LE;
        strcpy(uWord.value.T1,"<=");
    }
    gnLocate++;
    gnRow++;
    return;
}

void Do_EndOfEnd(char *strSource)  /* 读到/0，源文件结束 */
{
    uWord.syn=_SYN_END;
    uWord.value.T3=strSource[gnLocate];

    gnLocate++;
    gnRow++;
    return;
}

void PrintWord(Word uWord)  /* 打印二元组 */
{
    if (uWord.syn<=_SYN_ID || uWord.syn==_SYN_ME || uWord.syn==_SYN_LE || uWord.syn==_SYN_EQ || uWord.syn==1122) {
        fprintf(fw,"\n(%d,\t%s)",uWord.syn,uWord.value.T1);
    }
    else if (uWord.syn==_SYN_NUM) {
        fprintf(fw,"\n(%d,\t%d)",uWord.syn,uWord.value.T2);
    }
    else{
        fprintf(fw,"\n(%d,\t%c)",uWord.syn,uWord.value.T3);
    }
    return;
}

void ApartWord(char *strSource)  /* 根据输入的程序识别所有的单词 */
{
    gnColumn=gnRow=1;
    gnLocate=gnLocateStart=0;
    printf("%s",strSource);
    while (strSource[gnLocate]) {
        printf("%c",strSource[gnLocate]);
        Scaner();
    }
    return;
}

void Scaner(void) /* 词法扫描函数 */
{
    Do_Start(strSource);
    PrintWord(uWord);
    return;
}

void PrintError (int nColumn, int nRow, char chInput)   /* 打印词法发现的错误 */
{
    fprintf(fw,"\nError-->Col:%d\t Row:%d\t Char:%c",nColumn,nRow,chInput);
}





int main()
{
    char input_array[255];
    char content;
    char filename[20];
    int p=0;
    if((fw=fopen("result.txt","w+"))==NULL)
    {
        printf("file open error");
        exit(0);
    }
    printf("Enter filename:");
    scanf("%s",filename);
    if((inpute_file=fopen(filename,"r"))==NULL)
    {
        printf("file open error");
        getchar();
        exit(0);
    }
    while ((content = fgetc(inpute_file)) != EOF){
        input_array[p++]=content;
    }
    input_array[p]='\0';
    fclose(inpute_file);
    strSource = input_array;
    ApartWord(strSource);
    fclose(fw);
    getchar();
    /*getchar();  */
}