2017-04-13

编译原理实验二

实验二词法分析（小组验收）

实验目的

根据 PL/0 语言的文法规范,编写 PL/0 语言的词法分析程序。
通过设计调试词法分析程序,实现从源程序中分出各种单词的方法;
加深对课堂教学的理解;提高词法分析方法的实践能力。
掌握从源程序文件中读取有效字符的方法和产生源程序的内部表示
文件的法。
掌握词法分析的实现方法。
上机调试编出的词法分析程序。

实验时间

4学时

实验内容

输入 PL/0 语言程序,输出程序中各个单词符号(关键字、专用符号以及
其它标记)。
实验要求
确定编译中单词种类、使用的表格、标识符与关键字的区分方法等。
词法分析器读入 PL/0 语言源程序(文本文件),识别结果也以文本
文件保存。
词法分析器的输出形式采用二元式序列,即:
(单词种类, 单词的值)
源程序中字符不区分大小写,即:“a1”和“A1”是同一个标识符。
准备至少 5 组测试用例,每组测试用例包括:输入源程序文件和输
出结果。
测试用例必须包含所有的基本字、运算符、界符、以及各种标识符
和常数。对不合法单词进行分类考虑测试用例,特别是对一些运算
符要充分考虑各种组合。

输入输出样例

实验代码

help.h 代码链接

//
// Created by 高松 on 2017/4/6.
//

#ifndef EX02_HELP_H
#define EX02_HELP_H

bool IsAlpha(char ch){
    if((ch >='a'&&ch<='z')||(ch>='A'&&ch<='Z')){
        return true;
    }
    return false;
}

bool IsDigit(char ch){
    if( ch>='0'&&ch<='9'){
        return true;
    }
    return false;
}

bool IsAlphOrNum(char ch){
    if(IsAlpha(ch)){
        return true;
    }
    if(IsDigit(ch)){
        return true;
    }
    return false;
}
#endif //EX02_HELP_H

main.cpp 代码链接

#include <iostream>
using namespace std;
#include <cstring>
#include <cstdio>
#include <fstream>
#include <string>
#include <map>
#include "help.h"
#define FILEPATH "test.txt"
#define TOKENPATH "Mapper.txt"
#define TABSIZE 10

char prog[80],token[10];
char ch;
int syn,p,m = 0,n,row,sum = 0;
char *rwtab[TABSIZE] = {
        "begin","if","then","while","do","end","read","write","const","var",
};

map<int ,string> Mapper;



void scaner(){
    for(n = 0;n<8;n++){
        token[n] = NULL;
    }
    ch = prog[p++];
    while(ch == ' '){
        ch = prog[p];
        p++;
    }
    if(IsAlpha(ch)){
        m = 0;
        while(IsAlphOrNum(ch)){
            token[m++] = ch;
            ch = prog[p++];
        }
        token[m++] = 0;
        p--;
        syn = 10;
        for(n = 0;n<TABSIZE;n++){
            if(strcmp(token,rwtab[n])==0){
                syn = n+31;
                break;
            }
        }
    }
    else if( IsDigit(ch)){
        sum  = 0;
        while(isdigit(ch)){
            sum = sum*10 +ch-'0';
            ch = prog[p++];
        }
        p--;
        syn = 11;
        if(sum>32767){
            syn = -1;
        }
    }else switch(ch){
            case '<': m = 0; token[m++] = ch;
                ch = prog[p++];
                if(ch == '>'){
                    syn = 21;
                    token[m++]  = ch;
                }
                else if(ch == '='){
                    syn = 2;;
                    token[m++] = ch;
                }
                else {
                    syn = 23;
                    p--;
                }
                break;
            case '>': m = 0; token[m++] = ch;
                ch = prog[p++];
                if( ch == '='){
                    syn = 24;
                    token[m++] = ch;
                }
                else{
                    syn = 20;
                    p--;
                }
                break;
            case ':': m = 0;token[m++] = ch;
                ch = prog[p++];
                if( ch =='='){
                    syn = 18;
                    token[m++] = ch;
                }
                else{
                    syn = 17;
                    p--;
                }
                break;
            case ',' : syn=19;token[0] = ch; break;
            case '*' : syn=13;token[0] = ch; break;
            case '/' : syn=14;token[0] = ch; break;
            case '+' : syn=15;token[0] = ch; break;
            case '-' : syn=16;token[0] = ch; break;
            case '=' : syn=25;token[0] = ch; break;
            case ';' : syn=26;token[0] = ch; break;
            case '(' : syn=27;token[0] = ch; break;
            case ')' : syn=28;token[0] = ch; break;
            case '.' : syn=0; token[0] = ch; break;
            default: syn = -1; break;
        }
}

int main() {
    Mapper.clear();
    p = 0;
    row = 1;
    ifstream MapFile(TOKENPATH);
    string line;
    if(MapFile){
        while(getline(MapFile,line)){
            bool IsNum = false;
            int sum = 0;
            string token = "";
            for(int  i =0;i<line.size();i++){
                if( line[i] ==' '){
                    IsNum = true;
                    continue;
                }
                if(IsNum == true ){
                    sum = sum*10+(char)line[i]-'0';
                }
                else {
                    token += line[i];
                }
            }
            Mapper[sum] = token;
        }
    }
    Mapper[0] = "peroid";

//    map<int,string>:: iterator it;
//    for(it = Mapper.begin();it!=Mapper.end();it++){
//        cout<<it->first<<","<<it->second<<endl;
//    }
//    return 0 ;

    ifstream in(FILEPATH);
    if(in){
        while(getline(in,line)){
            char c[100];
            strcpy(c,line.c_str());
            for(int i = 0;i<strlen(c);i++){
                ch = line[i];
                prog[p++] = ch;
                if(ch == '.'){
                    goto A;
                }
            }
        }
    }
//    for(int i = 0;i<p;i++){
//        cout<<prog[i];
//    }
//    return 0;

    A:
    p = 0;
    do {
        scaner();
//        cout<<"syn = "<<syn<<endl;
        switch(syn){
            case 11: cout<<"("<<Mapper[11]<<" "<<sum<<")"<<endl;break;
            case -1: cout<<" Error in row "<<endl;
            default: cout<<"("<<Mapper[syn]<<" "<<token<<")"<<endl;break;
        }
    }while(syn!=0);

    return 0;
}

测试样例

样例1

题目给的样例

const a = 10;
var b,c;
begin
 read(b);
 c:=a+b;
 wrrite(c)
 end.

输出结果

(const const)
(Identity a)
(Equal =)
(Digit 10)
(semicolon ;)
(var var)
(Identity b)
(comma ,)
(Identity c)
(semicolon ;)
(Beginsys begin)
(read read)
(lparen ()
(Identity b)
(rparen ))
(semicolon ;)
(Identity c)
(becomes :=)
(Identity a)
(Plus +)
(Identity b)
(semicolon ;)
(Identity wrrite)
(lparen ()
(Identity c)
(rparen ))
(End end)
(peroid .)

样例2

包含大写的样例

CONST a=10;
VAR b,c;
begin
 read(b);
 c:=a+b;
 wrrite(c)
 end.

输出结果

(Identity CONST)
(Identity a)
(Equal =)
(Digit 10)
(semicolon ;)
(Identity VAR)
(Identity b)
(comma ,)
(Identity c)
(semicolon ;)
(Beginsys begin)
(read read)
(lparen ()
(Identity b)
(rparen ))
(semicolon ;)
(Identity c)
(becomes :=)
(Identity a)
(Plus +)
(Identity b)
(semicolon ;)
(Identity wrrite)
(lparen ()
(Identity c)
(rparen ))
(End end)
(peroid .)

样例3

拼写有错的样例

cons a = 10;
var b,c;
begin
 read(b);
 c:=a+b;
 wrrite(c)
 end.

输出结果

(Identity cons)
(Identity a)
(Equal =)
(Digit 10)
(semicolon ;)
(var var)
(Identity b)
(comma ,)
(Identity c)
(semicolon ;)
(Beginsys begin)
(read read)
(lparen ()
(Identity b)
(rparen ))
(semicolon ;)
(Identity c)
(becomes :=)
(Identity a)
(Plus +)
(Identity b)
(semicolon ;)
(Identity wrrite)
(lparen ()
(Identity c)
(rparen ))
(End end)
(peroid .)

样例4

包含大于等于号的样例

const a = 10;
var b,c;
begin
read(b);
if(a>=b) then
```
c:=b+a;
```
write(c);
end.
输出结果

(const const)
(Identity a)
(Equal =)
(Digit 10)
(semicolon ;)
(var var)
(Identity b)
(comma ,)
(Identity c)
(semicolon ;)
(Beginsys begin)
(read read)
(lparen ()
(Identity b)
(rparen ))
(semicolon ;)
(Ifsys if)
(lparen ()
(Identity a)
(EqualOrGreat >=)
(Identity b)
(rparen ))
(Thensys then)
(Identity c)
(becomes :=)
(Identity b)
(Plus +)
(Identity a)
(semicolon ;)
(write write)
(lparen ()
(Identity c)
(rparen ))
(semicolon ;)
(End end)
(peroid .)

样例5

包含空格回车的样例

const a = 10;
var b, c;



begin
 read(b);
 if(a>=b) then
   c:=b+a;
 write(c);
end.

输出结果

(const const)
(Identity a)
(Equal =)
(Digit 10)
(semicolon ;)
(var var)
(Identity b)
(comma ,)
(Identity c)
(semicolon ;)
(Beginsys begin)
(read read)
(lparen ()
(Identity b)
(rparen ))
(semicolon ;)
(Ifsys if)
(lparen ()
(Identity a)
(EqualOrGreat >=)
(Identity b)
(rparen ))
(Thensys then)
(Identity c)
(becomes :=)
(Identity b)
(Plus +)
(Identity a)
(semicolon ;)
(write write)
(lparen ()
(Identity c)
(rparen ))
(semicolon ;)
(End end)
(peroid .)

实验二词法分析（小组验收）

实验目的

实验时间

实验内容

实验要求

输入输出样例

实验代码

测试样例

样例1

样例2

样例3

样例4

样例5