www.pudn.com > 李广军-0201-20-词法分析.rar > cifa.c
/********************************************/ /* 词法分析程序 */ /* 作者：李广军 */ /* 学号：1402093120 */ /* 计算机科学与信息工程系 0201班 */ /* Copyright (C) 2005 by loverlife workroom*/ /* ALL Rights Reserved. */ /********************************************/ #include#include #include int key_count; int id_count; /**********************************************/ /* 初始化函数 */ /*1 保留字、2 标识符、3 常数、4 运算符、5 界符*/ /**********************************************/ void initialize() { char *keywords[] = {" ", /*0号单元不用*/ "auto","break","case","char","const", "continue","default","do","double","else", "enum","extern","float","for","goto", "if","int","long","register","return", "short","signed","sizeof","static","struct", "switch","typedef","union","unsigned","void", "volatile","while"}; /*C语言所有关键字，共32个*/ char *operators[] = {" ", "(", ")", "[", "]", ".", "->", "!", "~", "++", "--", "-", "&", "*", "(type)", "sizeof()", "/", "%", "+", "<<", ">>", "<", "<=", ">", ">=", "==", "!=", "^", "|", "&&", "||", "?:", "=", "+=", "-=", "*=", "/=", ","}; /*运算符,共37个*/ char *seperators[] = {" ", ";", "{", "}", "#", ".", "'"}; /*限界符，共7个*/ FILE *fp; int i; char c; fp = fopen("E:\\cifa\\keyword.txt", "w"); for(i = 1; i <= 32; i ++) fprintf(fp, "%s\n", keywords[i]); fclose(fp); /*初始化关键字表*/ fp = fopen("E:\\cifa\\operator.txt", "w"); for(i = 1; i <= 37; i ++) fprintf(fp, "%s\n", operators[i]); fclose(fp); /*初始化运算符表*/ fp = fopen("E:\\cifa\\seperator.txt", "w"); for(i = 1; i <= 6; i ++) fprintf(fp, "%s\n", seperators[i]); c = '"'; fprintf(fp, "%c\n", c); fclose(fp); /*初始化限界符表*/ fp = fopen("E:\\cifa\\identity.txt", "w"); fclose(fp); /*初始化标识符表*/ fp = fopen("E:\\cifa\\constant.txt", "w"); fclose(fp); /*初始化常数表*/ fp = fopen("E:\\cifa\\output.txt", "w"); fclose(fp); /*初始化输出文件*/ } /********************************************/ /* 查表或造表函数 */ /********************************************/ int find(char *buf, int type, int command) { int number = 0; FILE *fp; char c; char temp[30]; int i = 0; switch(type) { case 1: fp = fopen("E:\\cifa\\keyword.txt", "r");break; case 2: fp = fopen("E:\\cifa\\identity.txt", "r");break; case 3: fp = fopen("E:\\cifa\\constant.txt", "r");break; case 4: fp = fopen("E:\\cifa\\operator.txt", "r");break; case 5: fp = fopen("E:\\cifa\\seperator.txt", "r"); } c = fgetc(fp); while(c != EOF) { while(c != '\n') { temp[i++] = c; c = fgetc(fp); } temp[i] = '\0'; i = 0; number ++; if(strcmp(temp,buf) == 0) { fclose(fp); return(number); /*若找到，返回在相应表中的序号*/ } else c = fgetc(fp); } if(command == 1) { fclose(fp); return(0); /*找不到，当只需查表，返回0，否则还需造表*/ } fclose(fp); switch(type) { case 1: fp = fopen("E:\\cifa\\keyword.txt", "a");break; case 2: fp = fopen("E:\\cifa\\identity.txt", "a");id_count++;break; case 3: fp = fopen("E:\\cifa\\constant.txt", "a");break; case 4: fp = fopen("E:\\cifa\\operator.txt", "a");break; case 5: fp = fopen("E:\\cifa\\seperator.txt", "a"); } fprintf(fp, "%s\n", buf); fclose(fp); return(number+1); /*造表时，将字符串添加到表尾并返回序号值*/ } /*******************************************/ /* 数字串处理函数 */ /*******************************************/ void constant_manage(char *buffer) { FILE *fp; int result; result = find(buffer, 3, 2); /*先查常数表，若找不到则造入常数表并返回序号值*/ fp = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp, "3\t\t\t%s\t\t\t%d\n", buffer, result); fclose(fp); /*写入输出文件*/ } /*******************************************/ /* 字符串处理函数 */ /*******************************************/ void char_manage(char *buffer) { FILE *fp; int result; result = find(buffer, 1, 1); /*先查关键字表*/ fp = fopen("E:\\cifa\\output.txt", "a"); if(result != 0) { fprintf(fp, "1\t\t\t%s\t\t\t%d\n", buffer, result); /*若找到，写入输出文件*/ key_count++; } else { result = find(buffer, 2, 2); /*若找不到，则非关键字，查标识符表，还找不到则造入标识符表*/ fprintf(fp, "2\t\t\t%s\t\t\t%d\n", buffer, result); /*写入输出文件*/ } fclose(fp); } /******************************************/ /* 出错处理函数 */ /******************************************/ void error_manage(char error, int lineno) { FILE *fp; fp = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp, "error: %c ,line %d\n", error, lineno); /*报告出错符号和所在行数*/ fclose(fp); } /*******************************************/ /* 扫描输入源程序 */ /*******************************************/ void scanner() { FILE *fp, *fp1, *fp2; char filename[30]; char ch; int i = 0, line = 1; int count, result, errorno = 0; char array[30]; char *word; printf("\nPlease input the file name:"); scanf("%s", filename); if((fp1 = fopen(filename, "r")) == NULL) { printf("Cannot open file!"); exit(0); } ch = fgetc(fp1); while(ch != EOF) /*按字符依次扫描源程序，直至结束*/ { i = 0; if( ((ch>='A') && (ch<='Z')) || ((ch>='a') && (ch<='z')) || (ch=='_') ) { /*以字母或下划线开头*/ while( ((ch >= 'A')&&( ch <= 'Z' )) || ((ch>='a')&&(ch<='z')) || (ch == '_') || ((ch >= '0')&&(ch <= '9')) ) { array[i++] = ch; ch = fgetc(fp1); } /*字母数字下划线的组合*/ word = (char *)malloc( (i+1)*sizeof(char) ); memcpy(word, array, i); /*将array中的前i个字符拷贝到指针word中*/ word[i] = '\0'; char_manage(word); /*字符串处理*/ word=NULL; free(word); if(ch != EOF) fseek(fp1, -1L, SEEK_CUR); /*文件指针定位在前的一个位置*/ }/*判断关键字、标识符结束*/ else if(ch >= '0' && ch <= '9') /*以数字开头*/ { while( ((ch>='0')&&(ch<='9')) || ch == '.' || ch == 'e' || ch == 'E' || ch == '-') { array[i++] = ch; ch = fgetc(fp1); } /*数字的组合*/ word = (char *)malloc( (i+1)*sizeof(char) ); memcpy(word, array, i); word[i] = '\0'; constant_manage(word); word=NULL; free(word); if(ch != EOF) fseek(fp1, -1L, SEEK_CUR); }/*判断数字组合结束*/ else if( (ch == ' ') || (ch == '\t') ) ; /*滤除空格符和水平制表符*/ else if(ch == '\n') line++; /*滤除回车符，行数加1*/ else if(ch == '/') /*过滤注释*/ { ch = fgetc(fp1); if(ch == '=') /* 若为'/='符号*/ { fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "4\t\t\t/=\t\t\t32\n"); fclose(fp2); } else if(ch != '*') { /*若为除号，写入输出文件*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "4\t\t\t/\t\t\t13\n"); fclose(fp2); fseek(fp1, -1L, SEEK_CUR); } else if(ch == '*') { /*若为注释的开始，消除包含在里面的所有字符*/ count = 0; ch = fgetc(fp1); while(count != 2) { /*当扫描到'*'且紧接着下一个字符为'/'才是注释的结束*/ count = 0; while(ch != '*') ch = fgetc(fp1); count++; ch = fgetc(fp1); if(ch == '/') count++; else ch = fgetc(fp1); } } }/*过滤注释结束*/ else if(ch == '"') { /*消除包含在双引号中的字符串常量*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "5\t\t\t%c\t\t\t7\n", ch); ch = fgetc(fp1); while(ch != '"') ch = fgetc(fp1); fprintf(fp2, "5\t\t\t%c\t\t\t7\n", ch); fclose(fp2); } else { /*首字符为其它字符,即运算限界符或非法字符*/ array[0] = ch; ch = fgetc(fp1); /*再读入下一个字符，判断是否为双目运算符、限界符*/ if(ch != EOF) { /*若该字符非文件结束符*/ array[1] = ch; word = (char *)malloc( 3 * sizeof(char) ); memcpy(word, array, 2); word[2] = '\0'; result = find(word, 4, 1); /*先检索是否为双目运算符*/ if(result == 0) { /*若不是双目运算符*/ /*word = (char *)malloc( 2 * sizeof(char) );*/ memcpy(word, array, 1); word[1] = '\0'; result = find(word, 4, 1); /*检索是否为单目运算符*/ if(result == 0) /*若不是单目运算符*/ { /*检索是否为限界符 */ result = find(word, 5, 1); if(result == 0) /*若不是限界符，则为非法字符*/ { error_manage(array[0], line); errorno++; fseek(fp1, -1L, SEEK_CUR); } else { /*若为限界符，写输出文件*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "5\t\t\t%s\t\t\t%d\t\n", word, result); fclose(fp2); fseek(fp1, -1L, SEEK_CUR); } } else { /*若为单目运算符,写入输出文件并将扫描文件指针回退一个字符*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "4\t\t\t%s\t\t\t%d\t\n", word, result); fclose(fp2); fseek(fp1, -1L, SEEK_CUR); } } else { /*若为双目运算符，写输出文件*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "4\t\t\t%s\t\t\t%d\n", word, result); fclose(fp2); } word=NULL; free(word); } else { /*若读入的下一个字符为文件结束符,当前字符是否为 '}'*/ if(array[0] != '}') /*若不是，转出错处理*/ error_manage(array[0], line); else { /*若是'}'，写输出文件*/ fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "5\t\t\t%s\t\t\t%d\n", '}', 2); fclose(fp2); } } }/*运算限界非法字符判断结束*/ ch = fgetc(fp1); } fclose(fp1); fp2 = fopen("E:\\cifa\\output.txt", "a"); fprintf(fp2, "Number of error(s): %d .\n", errorno); /*报告错误字符个数*/ fprintf(fp2, "NUmber of identities: %d.\n", id_count); fprintf(fp2, "Number of keywords: %d.\n", key_count); fclose(fp2); } /*******************************************/ /* 主函数 */ /*******************************************/ main() { initialize(); /*初始化*/ scanner(); /*扫描源程序*/ printf("Succeed!\n"); getch(); }