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：文件读取
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 |
单词符号 |
种别码 |
|
char |
12 |
: |
17 |
{ |
42 |
|
int |
13 |
/\ |
37 |
} |
43 |
|
if |
14 |
< |
30 |
[ |
44 |
|
else |
15 |
<= |
28 |
] |
43 |
|
return |
16 |
<> |
29 |
" |
47 |
|
END |
3 |
> |
32 |
, |
48 |
|
l(l|d)* |
25 |
>= |
31 |
' |
49 |
|
dd* |
26 |
= |
27 |
& |
50 |
|
+ |
33 |
; |
39 |
&& |
51 |
|
- |
34 |
( |
40 |
\\ |
52 |
|
* |
35 |
) |
41 |
||
|
/ |
36 |
: |
38 |
源代码如下：
#include<stdio.h>
#include<conio.h>
#include<math.h>
#include<string.h>
#include<stdlib.h>
int i, row = 0, line = 0;
char test[1000]; //test文件中的字符
int number[100]; //常数表
char mark[100][5]; //标识符表
//词法分析
int wordanalysis()
{
//标识符和保留字
if ((test[i] >= 'A'&&test[i] <= 'Z')||(test[i]>='a'&&test[i]<='z'))
{
char word[10];
//保留字表
char pro[100][100] = { "PROGRAM", "BEGIN", "END", "VAR", "INTEGER", "WHILE",
"IF", "THEN", "ELSE", "DO", "PROCEDURE" ,"char",
"int","if","else","var" ,"return","break",
"do","while","for","double","float","short"};
int n = 0;
word[n++] = test[i++];
while ((test[i] >= 'A'&&test[i] <= 'Z') || (test[i] >= '0' && test[i] <= '9')||(test[i]>='a'&&test[i]<='z'))
{
word[n++] = test[i++];
}
word[n] = '\0';
i--;
//判断该标识符是否为保留字
for (n = 0; n < 100; n++)
{
if (strcmp(word, pro[n]) == 0)
{
printf(">> %s\t(%d,-) 保留字\n", pro[n], n + 1);
return 3;
}
}
//判断该标识符是否在标识符表中
int m = 0;
if (line != 0)
{
int q = 0;
while (q<line)
{
if (strcmp(word, mark[q++]) == 0)
{
printf(">> %s\t(25,%d) 标识符\n", word, q);
return 3;
}
}
}
//将该标识符保存到标识符表中
strcpy(mark[line], word);
printf(">> %s\t(25, %d) 标识符\n", word, line + 1);
line++;
return 3;
}
//数字
else if (test[i] >= '0' && test[i] <= '9')
{
char x[100];
int n = 0;
x[n++] = test[i++];
while (test[i] >= '0' && test[i] <= '9')
{
x[n++] = test[i++];
}
x[n] = '\0';
i--;
int num = atoi(x); //将字符串转换成int型
//判断该常数是否存在于常数表中
if (row != 0)
{
for(int y=0;y<row;y++)
{
if(number[y]==num)
{
printf(">> %d\t(26,%d) 数字\n", num, y + 1);
return 3;
}
}
}
//将该常数保存到标识符表中
number[row]=num;
int line = row;
printf(">> %d\t(26,%d) 数字\n", num, line + 1);
row++;
return 3;
}
//各种符号
else
switch (test[i])
{
case ' ':
case '\n':
return -1;
case '#': return 0;
case '=':printf(">> =\t(27,-)\n"); return 3;
case '<':
i++;
if (test[i] == '=')
{
printf(">> <= \t(28,-)\n");
return 3;
}
else if (test[i] == '>')
{
printf(">> <>\t(29,-)\n");
return 3;
}
else
{
i--;
printf(">> <\t(30,-)\n");
return 3;
}
case '>':
i++;
if (test[i] == '=')
{
printf(">> >=\t(31,-)\n");
return 3;
}
else
{
i--;
printf(">> >\t(32,-)\n");
return 3;
}
case '+': printf(">> +\t(33,-)\n"); return 3;
case '-': printf(">> -\t(34,-)\n"); return 3;
case '*': printf(">> *\t(35,-)\n"); return 3;
case '/':
i++;
if(test[i]!='/'){
i--;
printf(">> /\t(36,-)\n"); return 3;
}
else{
while(1){
if(test[i++]=='\n')
return -1;
}
printf(">> //\t(37,-)\n");return 3;
}
case ':': printf(">> :\t(38,-)\n"); return 3;
case ';': printf(">> ;\t(39,-)\n"); return 3;
case '(': printf(">> (\t(40,-)\n"); return 3;
case ')': printf(">> )\t(41,-)\n"); return 3;
case '{': printf(">> {\t(42,-)\n"); return 3;
case '}': printf(">> }\t(43,-)\n"); return 3;
case '[': printf(">> [\t(44,-)\n"); return 3;
case ']': printf(">> ]\t(45,-)\n"); return 3;
case '|': printf(">> |\t(46,-)\n"); return 3;
case '"': printf(">> \"\t(47,-)\n"); return 3;
case ',': printf(">> ,\t(48,-)\n"); return 3;
case '\'': printf(">> '\t(49,-)\n"); return 3;//单引号
case '&':
i++;
if(test[i]!='&'){
i--;
printf(">> &\t(50,-)\n"); return 3;
}
else{
printf(">> &&\t(51,-)\n");return 3;
}
case '\\': printf(">> \\\t(52,-)\n"); return 3;
}
}
int main()
{
int c = 0;
int m;
i = 0;
FILE *fp;
fp=fopen("test.txt","r");
if (fp == NULL)
{
printf("can't open file!\n");
exit(0);
}
while (!feof(fp))
{
test[c++] = fgetc(fp);
}
test[c] = '#';
do
{
m = wordanalysis();
switch (m)
{
case -1:i++; break;
case 0: i++; break;
case 3: i++; break;
}
} while (m != 0);
return 0;
}
test.txt文件内容：
int i, row = 0, line = 0;
char test[1000]; //test文件中的字符
int number[100]; //常数表
char mark[100][5]; //标识符表
//词法分析
int wordanalysis()
{
//标识符和保留字
if ((test[i] >= 'A'&&test[i] <= 'Z')||(test[i]>='a'&&test[i]<='z'))
{
char word[10];
//保留字表
结果：
>> int (13,-) 保留字
>> i (25, 1) 标识符
>> , (48,-)
>> row (25, 2) 标识符
>> = (27,-)
>> 0 (26,1) 数字
>> , (48,-)
>> line (25, 3) 标识符
>> = (27,-)
>> 0 (26,1) 数字
>> ; (39,-)
>> char (12,-) 保留字
>> test (25, 4) 标识符
>> [ (44,-)
>> 1000 (26,2) 数字
>> ] (45,-)
>> ; (39,-)
>> nt (25, 5) 标识符
>> number (25, 6) 标识符
>> [ (44,-)
>> 100 (26,3) 数字
>> ] (45,-)
>> ; (39,-)
>> har (25, 7) 标识符
>> mark (25, 8) 标识符
>> [ (44,-)
>> 100 (26,3) 数字
>> ] (45,-)
>> [ (44,-)
>> 5 (26,4) 数字
>> ] (45,-)
>> ; (39,-)
>> nt (25,5) 标识符
>> wordanalysis (25, 9) 标识符
>> ( (40,-)
>> ) (41,-)
>> { (42,-)
>> if (14,-) 保留字
>> ( (40,-)
>> ( (40,-)
>> test (25,4) 标识符
>> [ (44,-)
>> i (25,1) 标识符
>> ] (45,-)
>> >= (31,-)
>> ' (49,-)
>> A (25, 10) 标识符
>> ' (49,-)
>> && (51,-)
>> test (25,4) 标识符
>> [ (44,-)
>> i (25,1) 标识符
>> ] (45,-)
>> <= (28,-)
>> ' (49,-)
>> Z (25, 11) 标识符
>> ' (49,-)
>> ) (41,-)
>> | (46,-)
>> | (46,-)
>> ( (40,-)
>> test (25,4) 标识符
>> [ (44,-)
>> i (25,1) 标识符
>> ] (45,-)
>> >= (31,-)
>> ' (49,-)
>> a (25, 12) 标识符
>> ' (49,-)
>> && (51,-)
>> test (25,4) 标识符
>> [ (44,-)
>> i (25,1) 标识符
>> ] (45,-)
>> <= (28,-)
>> ' (49,-)
>> z (25, 13) 标识符
>> ' (49,-)
>> ) (41,-)
>> ) (41,-)
>> { (42,-)
>> char (12,-) 保留字
>> word (25, 14) 标识符
>> [ (44,-)
>> 10 (26,5) 数字
>> ] (45,-)
>> ; (39,-)
来源：https://www.cnblogs.com/SZZZ/p/11656551.html