词法分析程序的设计与实现
词法分析程序(Lexical Analyzer)要求:
- 从左至右扫描构成源程序的字符流
- 识别出有词法意义的单词(Lexemes)
- 返回单词记录(单词类别,单词本身)
- 滤掉空格
- 跳过注释
- 发现词法错误
程序结构:
输入:字符流(什么输入方式,什么数据结构保存)
处理:
–遍历(什么遍历方式)
–词法规则
输出:单词流(什么输出形式)
–二元组
单词类别:
1.标识符(10)
2.无符号数(11)
3.保留字(一词一码)
4.运算符(一词一码)
5.界符(一词一码)
|
单词符号 |
种别码 |
单词符号 |
种别码 |
|
begin |
1 |
: |
17 |
|
if |
2 |
:= |
18 |
|
then |
3 |
< |
20 |
|
while |
4 |
<= |
21 |
|
do |
5 |
<> |
22 |
|
end |
6 |
> |
23 |
|
l(l|d)* |
10 |
>= |
24 |
|
dd* |
11 |
= |
25 |
|
+ |
13 |
; |
26 |
|
- |
14 |
( |
27 |
|
* |
15 |
) |
28 |
|
/ |
16 |
# |
0
|
#include<stdio.h>
#include<string.h>
#include<stdlib.h>
char savearray[100],outarray[100];
char ch;
int row,arrays,count,m,i,p;//count为计数器 p为指针
char *wordsymbol[6] = {"if", "begin", "then", "while", "do", "end"};
void getarrays(){
for(i = 0; i < 8; i++){
outarray[i] == NULL;
}
ch = savearray[p++];
while(ch == ' '){
ch = savearray[p];
p++;
}
if((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <='Z')){
m = 0;
while((ch <= '9' && ch>= '0') || (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z')){
outarray[m++] = ch;
ch = savearray[p++];
}
outarray[m++] = '\0';
p--;
arrays = 10;
for(i = 0; i < 6; i++){
if(strcmp(wordsymbol[i],outarray) == 0){
arrays =1 + i;
break;
}
}
}else if(ch <= '9' && ch>= '0'){
count = 0;
while(ch >= '0' && ch <='9'){
count *= 10 + (ch - '0');
ch = savearray[p++];
}
p--;
arrays = 11;
} else switch(ch){
case '+':
outarray[0] = ch;
arrays = 13;
return;
case '-':
outarray[0] = ch;
arrays = 14;
return;
case '*':
outarray[0] = ch;
arrays = 15;
break;
case '/':
outarray[0] = ch;
arrays = 16;
break;
case ':':
i = 0;
outarray[i++] = ch;
ch = savearray[p++];
if(ch == '='){
outarray[i++] = ch;
arrays = 18;
}else{
arrays = 17;
p--;
}
return;
case '<':
i = 0;
outarray[i++] = ch;
ch = savearray[p++];
if(ch == '='){
outarray[i++] = ch;
arrays = 21;
}else if(ch == '='){
outarray[i++] = ch;
arrays = 22;
}else{
arrays = 20;
p--;
}
return;
case '>':
i = 0;
outarray[i++] = ch;
ch = savearray[p++];
if(ch == '='){
outarray[i++] = ch;
arrays = 24;
}else{
arrays = 23;
p--;
}
return;
case '=':
outarray[0] = ch;
arrays = 25;
break;
case ';':
outarray[0] = ch;
arrays = 26;
break;
case '(':
outarray[0] = ch;
arrays = 27;
break;
case ')':
outarray[0] = ch;
arrays = 28;
break;
case '#':
outarray[0] = ch;
arrays = 0;
break;
case '\n':
arrays = 100;
break;
default:
arrays = -1;
}
}
int main(){
int p = 0,
row = 1;
printf("输入测试语句:");
do{
ch = getchar();
savearray[p++] = ch;
}while(ch != '#');
p = 0;
do{
getarrays();
switch(arrays){
case -1:
printf("第%d行有问题",row);
break;
case 100:
row += 1;
break;
case 11:
printf("(%d,%d)\n", count,arrays);
break;
default:
printf("(%s,%d)\n",outarray,arrays);
}
}while(arrays != 0);
}

转载自https://www.cnblogs.com/lingcode/p/11656587.html
周五今天做了一天,还是没能做出来
浙公网安备 33010602011771号