CocoRoboDesktop/js/UDC/U.DC.LEX.js

//全局变量
var type = new Array('IDENT', 'INT', 'REAL', 'RESERVED WORD', 'UNRECOGNIZED SYMBOL','EOF');
var word = new Array('if', 'else', 'while', 'read', 'write', 'int', 'real','return');
var specWord = new Array('==', '/*', '*/', '<>');
//用于存储token序列
var tokens;
//用于存储错误token序列
var err;
var js_cmm = new Token('有思', '20130305', 0, 0);
//用于格式化打印
var tab = '&nbsp;&nbsp;&nbsp;&nbsp;';
//行号和列号
var rowNum, colNum;
//用于读字符的一些变量
//row 存放 \n 分段的字符数组
var rows, row, ch;

//javascript token类
function Token(t, v, r, c) {
    this.type = t;
    this.value = v;
  //位置参数
    this.rowNum = r;//行数
    this.colNum = c;//第几位
};

//初始化
function init() {
    U.CD.Obj('UD_CD_Source').focus();
    word.sort();
    specWord.sort();
};


window.onload = init;

//归零
function relex() {
    //一些归零操作
    rowNum = 0;
    colNum = 0;
    rows = U.CD.Obj('UD_CD_Source').value.split('\n');
    row = rows[rowNum] + ' ';
    ch = row[colNum];
    tokens = null;
    tokens = new Array();
    tokens.push(js_cmm);
    err = null;
    err = new Array();
    //清屏函数
    cls();
};


//词法分析入口函数
function lex() {
    relex();
    getSym();
};

//取字符函数
function getCh() {
    ch = row[colNum];
    if (colNum < row.length) {
        
        colNum++;
    }
    if (colNum == row.length) {
        if (rowNum != rows.length - 1) {
            rowNum++;
            colNum = 0;
            row = rows[rowNum] + ' ';
        }
    }
    return ch;
};

//处理字符函数
function getSym() {
    //一些准备工作，初始化节点类和节点类型。
    var token = new Token();
    var tokenType;
    //读入一个字符
    ch = getCh();
    //定义一维数组As
    var As = new Array();
    var A;
    while (1) {
        var r = rowNum + 1;
        var c = colNum;
        //滤空格和制表符
        if (ch == ' ' || ch == '\t') {
            ch = getCh();
            continue;
        }
        //检测是否为标识符或保留字，标识符或保留字以字母开头
        else if (ch >= 'a' && ch <= 'z' || ch >= 'A' && ch <= 'Z') {
            As = new Array();
            do {
                As.push(ch);
                ch = getCh();
            } while ( ch >= 'a' && ch <= 'z' || ch >= 'A' && ch <= 'Z' || ch >= "0" && ch <= '9' || ch == '_');
            A = As.join('');
            //使用折半搜索检查当前符号是否为保留字
            var i = 0,k = 0;
            var j = word.length - 1;
            do {
                k = Math.floor((i + j) / 2);
                Math.floor(k);
                if (A <= word[k]) j = k - 1;
                if (A >= word[k]) i = k + 1;
            } while ( i <= j );
            //匹配成功
            if (i - 1 > j) {
                tokenType = A;
                //存储进tokens数组
            }
            //匹配不成功则为标识符
            else {
                tokenType = type[0];
            }
        }
        //匹配数字
        else if (ch >= '0' && ch <= '9') {
            As = new Array();
            do {
                As.push(ch);
                ch = getCh();
            } while ( ch >= '0' && ch <= '9' || ch == '.');
            A = As.join('');
            var patrn1 = /^\d+$/; //整数
            var patrn2 = /\d+(\.)?((E|e)((\+|-)?))?\d+/;//实数
            if ( patrn1.test(A)) {
                tokenType = type[1];
            }
            else if ( patrn2.test(A)){
            		tokenType = type[2];
            }
            else {
                tokenType = type[4];
            }
        }
        //匹配特殊字符
        else if (ch == '+' || ch == '-' || ch == '(' || ch == ')' || ch == ';' || ch == '{' || 
        	ch == '}' || ch == '[' || ch == ']' || ch == '<' || ch == '>' || ch == '^' || ch == ',' || ch == '*' || ch == '/' || ch == '=') {
            tokenType = ch;
            A = ch;
            if (ch == '/' || ch == '=' || ch == '<') {
                As = new Array();
                As.push(ch);
                ch = getCh();
                As.push(ch);
                A = As.join('');
                //使用折半搜索检查当前符号是否为特殊符号
                var i = 0,
                k = 0;
                var j = specWord.length - 1;
                do {
                    k = Math.floor((i + j) / 2);
                    if (A <= specWord[k]) j = k - 1;
                    if (A >= specWord[k]) i = k + 1;
                } while ( i <= j );
                //匹配成功
                if (i - 1 > j) {
                    tokenType = specWord[k];
                }
                //匹配不成功则无法识别
                else {
                    A = As[0];
                    colNum--;
                }
            }
            //匹配注释
            if (tokenType == '/*') {
                do {ch = getCh();} while ( typeof(ch)!='undefined' /*匹配注释没有正确结尾的情况*/
                && ( ch != '*' || getCh() != '/' )/*遇到/*结束*/ )
                tokenType = 'comment';
                A = 'ignore';
            }
            ch = getCh();
        }
        //ch为undefined则读完源程序,退出循环体
        else if (typeof(ch) == 'undefined') {
        		token = new Token(type[5], 'EOF', r, c);
        		tokens.push(token);
        		token=null;
            break;
        }
        //都不能匹配则无法识别
        else {
            tokenType = type[4];
            A=ch;
            ch = getCh();
        }
        token = new Token(tokenType, A, r, c);
        if(tokenType==type[4]){
        	err.push(token);
        }
        else if(tokenType=='comment'){
        	//不做任何动作
        }
        else{
        	tokens.push(token);
        }
        //javascript没有内存回收机制，手动释放内存
        token = null;
    }
   // printall();
};

//打印所有Token对象
function printall() {
//    lexresult('<ul>');
//    if(err.length==0){
//    	for (var n = 1; n != tokens.length; n++) {
//        if (tokens[n].rowNum > tokens[n - 1].rowNum) {
//            lexresult('<li><b>' + tokens[n].rowNum + '.' + rows[tokens[n].rowNum - 1] + '</b></li>');
//        }
//        lexresult('<li>' + tab + tokens[n].rowNum + '.' + tokens[n].type + ':' + tokens[n].value + '</li>');
//    	}
//    }
//    else{
//      for (var n = 0; n != err.length; n++) {
//        console('<li><font color=red>Lexical error at row' + err[n].rowNum + ',col' + err[n].colNum + ':unrecognized symbol '+err[n].value+'</font></li>');
//    	}
//    }
//    lexresult('</ul>');
};