编译原理实验之词法分析

实验目的

设计、编制并调试一个词法分析程序, 加深对词法分析原理的理解

代码

#include <stdio.h>
#include <stdlib.h> //related library
#include <string.h>

#define _KEY_WORD_END "waiting for your expanding"

typedef struct{
    int typenum; //Signture
    char* word; //corresponding string
}WORD;

char input[255];
char token[255]="";
int p_input;
int p_token;

char ch;
char* rwtab[] = {"begin", "if", "then", "while", "do", "end", _KEY_WORD_END};
WORD* scanner();

void main(){
    int over = 1;
    WORD* oneword = malloc(sizeof(WORD)); //error 01
    printf("Enter Your words(end with $):");
    scanf("%[^#s]", input);
    p_input = 0;
    printf("Your words:\n%s\n", input);
    while(over < 1000 && over != -1){
        oneword = scanner();
        if(oneword->typenum < 1000){
            printf("(%d, %s)", oneword->typenum, oneword->word);
        }
        over = oneword->typenum;
    }
    printf("\npress#to exit:");
    scanf("%[^#]s", input);
}

/* return a character*/
char m_getch(){
    ch = input[p_input];
    p_input = p_input + 1;
    return (ch);
}

/*filter space and newline character*/
void getbc(){
    while(ch == ' ' || ch == 10){
        ch = input[p_input];
        p_input = p_input + 1;
    }
}

/* */
void concat(){
    token[p_token] = ch;
    p_token = p_token + 1;
    token[p_token] = '\x0';
}

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

int digit(){
    if(ch >= '0' && ch <= '9'){
        return 1;
    } else {
        return 0;
    }
}

/*reverse a string*/
int reserve(){
    int i = 0;
    while(strcmp(rwtab[i], _KEY_WORD_END)){
        if(!strcmp(rwtab[i], token)){
            return i+1;
        }
        i++;
    }
    return 10;
}

void retract(){
    p_input = p_input - 1;
}

char* dtb(){
    return NULL;
}

WORD* scanner(){
    WORD* myword = malloc(sizeof(WORD)); //error
    myword -> typenum = 10;
    myword -> word = "";
    p_token = 0;
    m_getch();
    getbc();
    if(letter()){
        while(letter() || digit()){

            concat();
            m_getch();
        }

        retract();
        myword->typenum = reserve();
        myword->word = token;
        return (myword);

    } else if(digit()) {

        while(digit()){
            concat();
            m_getch();
        }
        retract();
        myword -> typenum = 11;
        myword -> word = token;
        return (myword);

    } else {
        switch(ch){
            case '=': /* continuous　equal sign*/
                myword -> typenum = 25;
                myword -> word = "=";
                return (myword);

            case '+':
                myword -> typenum = 13;
                myword -> word = "+";
                return (myword);

            case '-':
                myword -> typenum = 14;
                myword -> word = "-";
                return (myword);

            case '*':
                myword -> typenum = 15;
                myword -> word = "*";
                return (myword);

            case '/': //对多行注释的的实现
                m_getch();
                if(ch == '*'){
                    while(1){
                        m_getch();
                        if(ch == '*'){
                            m_getch();
                            if(ch == '/'){
                                myword -> typenum = 29;
                                myword -> word = "/**/";
                                return (myword);
                            }
                            retract();
                        }
                    }
                }
                retract();
                myword -> typenum = 16;
                myword -> word = "/";
                return (myword);

            case '(':
                myword -> typenum = 27;
                myword -> word = "(";
                return (myword);

            case ')':
                myword -> typenum = 28;
                myword -> word = ")";
                return (myword);

            case ':':
                m_getch();
                if(ch == '='){
                    myword -> typenum = 18;
                    myword -> word = ":=";
                    return (myword);
                }
                retract();
                myword -> typenum = 17;
                myword -> word = ":";
                return (myword);

            case ';':
                myword -> typenum = 26;
                myword -> word = ";";
                return (myword);

            case '>':
                m_getch();
                if(ch == '='){
                    myword -> typenum = 24;
                    myword -> word = ">=";
                    return (myword);
                }
                retract();
                myword -> typenum = 23;
                myword -> word = ">";
                return (myword);

            case '<':
                m_getch();
                if(ch == '='){
                    myword -> typenum = 22;
                    myword -> word = "<=";
                    return (myword);
                }
                if(ch == '>'){
                    myword -> typenum = 21;
                    myword -> word = "<>";
                    return (myword);
                }
                retract();
                myword -> typenum = 20;
                myword -> word = "<";
                return (myword);

            case '\0':
                myword -> typenum = 1000;
                myword -> word = "OVER";
                return (myword);
            default:
                myword -> typenum = -1;
                myword -> word = "ERROR";
                return (myword);
        }
    }
}