www.pudn.com > zdf.rar > cafa.cpp
#include
#include
#include
#include
using namespace std;
#define NUM 10 /*保留字最大长度为9*/
#define LINEMAX 255 /*读取一行最大为255*/
typedef struct entry /*定义结构*/
{
char word[10]; /*关键字，长度最大为10*/
int token; /*token值*/
} entry;
typedef struct SymbolNode /*符号表*/
{
int token;
char name[NUM];
int len;
struct SymbolNode *next;
} symbol;
typedef struct TokenNode /*token字表*/
{
char string[NUM];
int token;
struct TokenNode *next;
} TokenTable;
entry words[]=
{
"and",1, "array",2, "begin",3, "bool",4, "call",5, "case",6,
"char",7, "constant",8, "do",9, "else",10, "end",11, "false",12,
"for",13, "if",14, "input",15, "integer",16, "not",17, "of",18,
"or",19, "output",20, "procedure",21, "program",22, "read",23,
"real",24, "repeat",25, "set",26, "then",27, "to",28, "true",29,
"until",30, "var",31, "while",32, "write",33,
"标识符",34,"整常数",35,"实常数",36, "字符常数",37,
"'",38, "(",39, ")",40, "*",41, "*/",42, "+",43, ",",44,
"-",45, ".",46, "..",47, "/",48, "/*",49, ":",50, ":=",51,
";",52, "<",53, "<=",54, "<>",55, "=",56, ">",57,">=",58,
"[",59, "]",60
};
class csort
{
protected:
char *bf; /*用于存储标识符,数字, 字符常量*/
int row;
int col;
char *str; /*只是个指针,不为其分配存储空间*/
char strline[LINEMAX]; /*文件中读入的一行字符串,其允许的最大字符个数为255*/
public:
csort();
~csort();
int sort();
int is_sign(char ch);
int IsKeyword(char *str);
int IsDelimeter();
int recogid();
int recogdig();
int recogstr();
int handlecom();
char *NewMem(int len);
int error_pro(int errorno);
};
csort::csort()
{
bf=NULL;
row=0;
col=0;
str=NULL;
}
csort::~csort()
{
delete [] bf;
}
class cifa:public csort
{
protected:
int len;
int token;
char *p; /*所要查找的符号表时的符号*/
symbol *symbollink,*sym_head; /*指向符号表的指针*/
TokenTable *tokenlink,*token_head; /*指向token表的指针*/
FILE *fp;
public:
cifa();//symbol *symbollink, TokenTable *tokenlink);
~cifa();
int cifa_main();
int string_process(); /*处理读取的行字符串,消除行首空格及TAB,及行中TAB*/
int lookup_sym(char *sym);
void ins_sym(char *sym);
void print_sym();
void ins_token(char *p); /*插入符号表*/
void print_token();
};
cifa :: cifa()//symbol *symbollink, TokenTable *tokenlink)
{
len=0;
token=-1;
p=NULL;
fp=NULL;
symbollink=new symbol;
sym_head=symbollink;
tokenlink=new TokenTable;
token_head=tokenlink;
symbollink->token=0;
strcpy(symbollink->name, "Token");
symbollink->len=0; /*头指针记录符号个数*/
symbollink->next=NULL;
strcpy(tokenlink->string, "Symbol");
tokenlink->token=0; //头指针记录token 个数
tokenlink->next=NULL;
}
cifa::~cifa()
{
TokenTable *temp=token_head->next;
while(temp!=NULL)
{
delete token_head;
token_head=temp;
temp=token_head->next;
}
symbol *temps=sym_head->next;
while(temps!=NULL)
{
delete sym_head;
sym_head=temps;
if(sym_head==NULL) printf("#");
temps=sym_head->next;
}
};
int cifa::cifa_main()
{
int findflag; //是否查找到相同的符号, 0存在相同的符号,1不存在相同的符号
char filename[20];
cout<<"请输入源文件名:"<>filename;
ifstream in(filename);
if(!in)
{ cout<<"can't open file.\n";
return 1;
}
while(in)
{
in.getline(strline,255);//读出源文件中一行字符串,默认行结束符为'\n'
row++;
if(in) //开始行处理
{ len=string_process(); //消除行中的TAB键以及行首的空格，返回剩余字符串长度
col = 0; //指向行首
while(col < len) //对一行字符串进行处理
{
bf=NULL;
token=sort();//根据单词的第一个字符进行分类，判断该单词是属于哪一类，返回单词的token值
if(token!=-1)
{
if(bf!=NULL)
p=bf;
else p=words[token-1].word;
cout<=NUM) colno=-3;
state = '2';
}
break;
}
}
return colno;
}
//识别并去掉注释
int csort::handlecom()
{
char ch;
int colno=0;
ch=str[++colno];
if(ch=='*')
{ do
{ //注释只有一行中有效,行结束也认为注释结束
ch=str[++colno];
}while(!(ch=='*'&&str[colno+1]=='/')&&ch!='\0');
colno+=3;
}
else colno=-1; //返回-1则表明是除号
return colno;
}
//识别字符常数
int csort::recogstr()
{
char state='0'; //初始状态为0
char ch ;
int colno=-1;
while(state!='2')
{
ch = str[++colno];
switch( state )
{
case '0': state = '1'; break;
case '1': if( ch == '\'' ) state = '2'; //读到最后一个单引号,结束
else state = '1'; //否则一直是字符串部分
}
}
return colno+1;
}
//查找关键字
int csort::IsKeyword(char *str)
{
int i=0; /* 查找次数 */
int flag = -1;
while(i<33) /*字符串表没有结束*/
{
if(!strcmp(str,words[i].word))
{
flag = i;
break;
}
else i++;
}
return flag;
}
//查找界符
int csort::IsDelimeter()
{
int i=37;
int flag = -1;
char temp[3];
while(i<60) //字符串表没有结束
{
if(str[0]==words[i].word[0])
{
strncpy(temp, str, 2);
temp[2]='\0';
if(!strcmp(temp,words[i+1].word))
i++;
flag = i;
break;/*返回与str相同的keyword的数组位置*/
}
else i++;
}
return flag;
}
//为单词申请存储空间返回指向该空间首地址的指针
char *csort::NewMem(int len)
{
bf=new char[len];
strncpy(bf, str, len-1);
bf[len-1]='\0';
return bf;
}
//查找符号表,查找指定的字符串是否在符号表中,flag为标识符
int cifa::lookup_sym(char *sym)
{
int flag=0;
if( IsDelimeter()==-1 && IsKeyword(sym)==-1)
{
flag=1;
while( symbollink!=NULL )
{ if( !strcmp(symbollink->name, sym) ) /*符号相同时*/
{
flag=0;
break;
}
symbollink=symbollink->next;
}
}
return flag;
}
//填入符号表
void cifa::ins_sym(char *sym)
{
symbollink->len++; /*符号个数加1*/
while(symbollink->next!=NULL)
symbollink=symbollink->next;
symbollink->next=new symbol;
symbollink=symbollink->next;
symbollink->token=token;
symbollink->len=strlen(sym);
strcpy(symbollink->name, sym);
symbollink->name[NUM-1]='\0';
symbollink->next=NULL;
}
void cifa::print_sym() /*打印符号表*/
{
FILE *fp;
symbol *temp=sym_head->next;
fp=fopen("symbol.txt","w+");
while(temp!=NULL)
{
fprintf(fp, "(%d\t%s\t%d)\n",
temp->token, temp->name, temp->len);
temp=temp->next;
}
fclose(fp);
}
void cifa::ins_token(char *p) /*插入符号表*/
{
token_head->token++; /*token个数加1*/
tokenlink->next=new TokenTable;
tokenlink=tokenlink->next;
strcpy(tokenlink->string, p); /*赋值*/
tokenlink->string[NUM-1]='\0';
tokenlink->token=token;
tokenlink->next=NULL;
}
void cifa::print_token() /*打印token表*/
{
FILE *fp;
TokenTable *temp=token_head->next;
fp=fopen("token.txt","w+");
while(temp!=NULL)
{
fprintf(fp, "%s\n",temp->string);
temp=temp->next;
}
fclose(fp);
}
int csort::error_pro(int errorno)
{
switch(errorno)
{
case -2: cout<<"Row="<"
<