?? scan.c
字號:
/** * @file scan.c * @brief cmm語言的掃描器實現 * @author Shiquan Ye, yeshiquan@gmail.com * @date 2008-11-12 *//* * Copyright (C) 2008 - Shiquan Ye, yeshiquan@gmail.com * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */#include "globals.h"#include "util.h"#include "scan.h"/* DFA的狀態 */typedef enum {START,INID,INEQ,INNEQ,INLEQ,INGEQ,ININTORREAL,INREAL,INSLASHORCOMMENT,INCOMMENT,DONE} StateType;/* 源代碼中每行字符數的最大值 */#define BUFFLEN 256static char lineBuf[BUFFLEN]; /* 存放當前行 */static int linepos = 0; /* 在lineBuf的當前位置 */static int bufsize = 0; /* 當前行的長度 */static int EOF_flag = FALSE; /* *//** * @brief 獲取當前行的下一個非空格字符，如果已到行尾， * 讀取下一行 * * @returns 字符所在的位置,如果到文件的末尾，返回-1 */static int getNextChar(void) { if (!(linepos < bufsize)) { /* 已到行尾 */ if (fgets(lineBuf,BUFFLEN-1,source)) { /* 讀取新的一行 */ lineno++; bufsize = strlen(lineBuf); linepos = 0; return lineBuf[linepos++]; } else{ /* 到達文件尾 */ return EOF; } } else return lineBuf[linepos++];}/** * @brief 回到前一個字符 */static void ungetNextChar(void) { if (!EOF_flag) linepos--;}/* 用于查找保留字的表 */static struct { char * str; TokenType tok;} reservedWords[MAXRESERVED]= { {"if",IF},{"else",ELSE},{"while",WHILE},{"write",WRITE}, {"read",READ},{"int",INT},{"real",REAL}};/** * @brief 搜索一個標識符看它是否為保留字 * * @param s 標識符 * * @returns 如果是保留字，返回對應的保留子類型，否則返回ID */static TokenType reservedLookup (char * s) { int i; for (i = 0; i < MAXRESERVED; i++) { if (!strcmp(s,reservedWords[i].str)) return reservedWords[i].tok; } return ID;}TokenType getToken(void) { /* 多字符token存入tokenString時用到的索引 */ int tokenStringIndex = 0; /* 保存當前token，最后返回 */ TokenType currentToken; /* 當前DFA的狀態，總是以START開頭 */ StateType state = START; /* 是否將字符存入tokenString */ int save; while (state != DONE) { char c = getNextChar(); save = TRUE; switch (state) { case START: if (c >= '0' && c <= '9') state = ININTORREAL; else if (c >= 'a' && c <= 'z') state = INID; else if (c == ' ' || c == '\t' || c == '\n') save = FALSE; else if (c == '!') state = INNEQ; else if (c == '<') state = INLEQ; else if (c == '>') state = INGEQ; else if (c == '=') state = INEQ; else if (c == '/') state = INSLASHORCOMMENT; else { state = DONE; switch(c) { case EOF: /* 文件結束 */ save = FALSE; currentToken = ENDFILE; break; case '+': currentToken = PLUS; break; case '-': currentToken = MINUS; break; case '*': currentToken = TIMES; break; case '(': currentToken = LPAREN; break; case ')': currentToken = RPAREN; break; case '[': currentToken = LBRACKET; break; case ']': currentToken = RBRACKET; break; case ',': currentToken = COMMA; break; case ';': currentToken = SEMI; break; case '{': currentToken = LBRACE; break; case '}': currentToken = RBRACE; break; default: currentToken = ERROR; break; } } break; case INID: if ((c > 'z' || c < 'a') && c != '_') { ungetNextChar(); save = FALSE; state = DONE; currentToken = ID; } break; case INNEQ: if (c != '=') { ungetNextChar(); save = FALSE; state = DONE; currentToken = NEQ; } break; case INLEQ: if (c == '=') { state = DONE; currentToken = LEQ; } else { ungetNextChar(); save = FALSE; state = DONE; currentToken = LSS; } break; case INGEQ: if (c == '=') { state = DONE; currentToken = GEQ; } else { ungetNextChar(); save = FALSE; state = DONE; currentToken = GTR; } break; case INEQ: if (c == '=') { state = DONE; currentToken = EQL; } else { ungetNextChar(); save = FALSE; state = DONE; currentToken = ASSIGN; } break; case ININTORREAL: if (c == '.') state = INREAL; else if (c != '.' && (c < '0' || c > '9')) { ungetNextChar(); save = FALSE; state = DONE; currentToken = INTNUM; } break; case INSLASHORCOMMENT: save = FALSE; if (c != '*') { ungetNextChar(); state = DONE; save = FALSE; currentToken = SLASH; } else { save = FALSE; tokenString[tokenStringIndex-1] = 0; state = INCOMMENT; } break; case INREAL: if (c > '9' || c < '0') { ungetNextChar(); state = DONE; save = FALSE; currentToken = REALNUM; } break; case INCOMMENT: save = FALSE; if (c == '*') { c = getNextChar(); if (c == '/') { return getToken(); } } if (c == -1) { state = DONE; currentToken = ERROR; } } if ( (save && tokenStringIndex <= MAXTOKENLEN)) tokenString[tokenStringIndex++] = c; if ( state == DONE) { tokenString[tokenStringIndex] = '\0'; if (currentToken == ID) { currentToken = reservedLookup(tokenString); } } } return currentToken;}?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -