Question

编译原理词法分析

输入：输入是一个文本文件，里面的内容是符合某个语言语法、词法要求的源代码（语法可参考课本P104，包括语句表、for循环和赋值语句等），例如“position := initial + rate * 60;”；
输出：设计并实现对输入文件的处理（禁用正则表达式），以获得如下输出，输出是一个文本文件，对前面例子，里面内容是：
(标识符，position)
(赋值运算符，:=)
(标识符，initial)
(加法运算符，+)
(标识符，rate)
(乘法运算符，*)
(整数，60)
(分隔符，; )

• 你的回答被采纳后将获得：
• 系统奖励15（财富值+成长值）+难题奖励30（财富值+成长值）

Answer 1

编译的词法分析，一般是先画一个状态转换图，一般是有多少分支，就有多少if语句，分支里面再分（可能有循环语句）。注意记住词的类别和词的字符串，请以以下代码为例，理会一下词法分析的大致过程。
while(s[i]!='#')
{
while(s[i]==' '||s[i]=='\t'||s[i]=='\n')
{
if(s[i]=='\n')
line++;
i++;
}
if(s[i]=='#')
break;
j=i;
if(s[i]>='a'&&s[i]<='z'||s[i]>='A'&&s[i]<='Z')
{
i++;
while(s[i]>='a'&&s[i]<='z'||s[i]>='A'&&s[i]<='Z'||s[i]>='0'&&s[i]<='9')
i++;
if((i-j)==2&&s[j]=='i'&&s[j+1]=='f')
{
strcpy(dancishuzu[dancigeshu].name,"if");
dancishuzu[dancigeshu].bianhao=4;
dancigeshu++;
}
else if((i-j)==3&&s[j]=='i'&&s[j+1]=='n'&&s[j+2]=='t')
{
strcpy(dancishuzu[dancigeshu].name,"int");
dancishuzu[dancigeshu].bianhao=2;
dancigeshu++;
}
else if((i-j)==3&&s[j]=='f'&&s[j+1]=='o'&&s[j+2]=='r')
{
strcpy(dancishuzu[dancigeshu].name,"for");
dancishuzu[dancigeshu].bianhao=6;
dancigeshu++;
}
else if((i-j)==4&&s[j]=='m'&&s[j+1]=='a'&&s[j+2]=='i'&&s[j+3]=='n')
{
strcpy(dancishuzu[dancigeshu].name,"main");
dancishuzu[dancigeshu].bianhao=1;
dancigeshu++;
}
else if ((i-j)==4&&s[j]=='c'&&s[j+1]=='h'&&s[j+2]=='a'&&s[j+3]=='r')
{
strcpy(dancishuzu[dancigeshu].name,"char");
dancishuzu[dancigeshu].bianhao=3;
dancigeshu++;
}
else if ((i-j)==4&&s[j]=='e'&&s[j+1]=='l'&&s[j+2]=='s'&&s[j+3]=='e')
{
strcpy(dancishuzu[dancigeshu].name,"else");
dancishuzu[dancigeshu].bianhao=5;
dancigeshu++;
}
else if ((i-j)==5&&s[j]=='w'&&s[j+1]=='h'&&s[j+2]=='i'&&s[j+3]=='l'&&s[j+4]=='e')
{
strcpy(dancishuzu[dancigeshu].name,"while");
dancishuzu[dancigeshu].bianhao=7;
dancigeshu++;
}
else{
dancishuzu[dancigeshu].bianhao=10;
count=0;
while(j<i)
{
dancishuzu[dancigeshu].name[count++]=s[j];
j++;
}
dancishuzu[dancigeshu].name[count]='\0';
dancigeshu++;
}
}
else if(s[i]>='0'&&s[i]<='9')
{
while(s[i]>='0'&&s[i]<='9')
i++;
dancishuzu[dancigeshu].bianhao=11;
count=0;
while(j<i)
{
dancishuzu[dancigeshu].name[count++]=s[j];
j++;
}
dancishuzu[dancigeshu].name[count]='\0';
dancigeshu++;
}

else if(s[i]=='=')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=30;
strcpy(dancishuzu[dancigeshu].name,"==");
dancigeshu++;
i+=2;
}
else
{
dancishuzu[dancigeshu].bianhao=12;
strcpy(dancishuzu[dancigeshu].name,"=");
dancigeshu++;
i++;
}
}
else if(s[i]=='+')
{
dancishuzu[dancigeshu].bianhao=13;
strcpy(dancishuzu[dancigeshu].name,"+");
dancigeshu++;
i++;
}
else if(s[i]=='-')
{
dancishuzu[dancigeshu].bianhao=14;
strcpy(dancishuzu[dancigeshu].name,"-");
dancigeshu++;
i++;
}
else if(s[i]=='*')
{
dancishuzu[dancigeshu].bianhao=15;
strcpy(dancishuzu[dancigeshu].name,"*");
dancigeshu++;
i++;
}
else if(s[i]=='/')
{
dancishuzu[dancigeshu].bianhao=16;
strcpy(dancishuzu[dancigeshu].name,"/");
dancigeshu++;
i++;
}
else if(s[i]=='(')
{
i++;
dancishuzu[dancigeshu].bianhao=17;
strcpy(dancishuzu[dancigeshu].name,"(");
dancigeshu++;
}
else if(s[i]==')')
{
i++;
dancishuzu[dancigeshu].bianhao=18;
strcpy(dancishuzu[dancigeshu].name,")");
dancigeshu++;
}
else if(s[i]=='[')
{
i++;
dancishuzu[dancigeshu].bianhao=19;
strcpy(dancishuzu[dancigeshu].name,"[");
dancigeshu++;
}
else if(s[i]==']')
{
i++;
dancishuzu[dancigeshu].bianhao=20;
strcpy(dancishuzu[dancigeshu].name,"]");
dancigeshu++;
}
else if(s[i]=='{')
{
i++;
dancishuzu[dancigeshu].bianhao=21;
strcpy(dancishuzu[dancigeshu].name,"{");
dancigeshu++;
}
else if(s[i]=='}')
{
i++;
dancishuzu[dancigeshu].bianhao=22;
strcpy(dancishuzu[dancigeshu].name,"}");
dancigeshu++;
}
else if(s[i]==',')
{
i++;
dancishuzu[dancigeshu].bianhao=23;
strcpy(dancishuzu[dancigeshu].name,",");
dancigeshu++;
}
else if(s[i]==':')
{
i++;
dancishuzu[dancigeshu].bianhao=24;
strcpy(dancishuzu[dancigeshu].name,":");
dancigeshu++;
}
else if(s[i]==';')
{
i++;
dancishuzu[dancigeshu].bianhao=25;
strcpy(dancishuzu[dancigeshu].name,";");
dancigeshu++;
}
else if(s[i]=='>')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=28;
strcpy(dancishuzu[dancigeshu].name,">=");
dancigeshu++;
i+=2;
}
else
{
i++;
dancishuzu[dancigeshu].bianhao=26;
strcpy(dancishuzu[dancigeshu].name,">");
dancigeshu++;
}
}
else if(s[i]=='<')
{
if(s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=29;
strcpy(dancishuzu[dancigeshu].name,"<=");
dancigeshu++;
i+=2;
}
else
{
i++;
dancishuzu[dancigeshu].bianhao=27;
strcpy(dancishuzu[dancigeshu].name,"<");
dancigeshu++;
}
}
else if(s[i]=='!'&&s[i+1]=='=')
{
dancishuzu[dancigeshu].bianhao=31;
strcpy(dancishuzu[dancigeshu].name,"!=");
dancigeshu++;
i+=2;
}
else
{
printf("\nline:%derror!",line);
i++;
return;
}
}