javascript – 解析半结构化值

(1,3,2,1,'John (Finances)'),(2,7,'Mary Jane'),(3,'Gerald (Janitor),Broflowski'),

你不能(读大概不应该)使用正则表达式为此.如果括号中包含另外一个或另一对不匹配,该怎么办？

好消息是,您可以轻松构建一个tokenizer /解析器.
这个想法是跟踪你当前的状态并采取相应的行动.

这里是我刚才在这里写的解析器的草图,重点是向大家展示一般的想法.如果您有任何概念性问题,请告诉我们.

它工作demo here,但我要求你不要在生产中使用它,然后才能理解和修补它.

怎么运行的

那么,我们如何构建解析器呢？

var State = { // remember which state the parser is at.
     BeforeRecord:0,// at the (
     DuringInts:1,// at one of the Integers
     DuringString:2,// reading the name String
     AfterRecord:3 // after the )
};

我们需要跟踪输出和当前工作对象,因为我们一次解析这些输出.

var records = []; // to contain the results
var state = State.beforeRecord;

现在,我们迭代字符串,继续进行并读取下一个字符

for(var i = 0;i < input.length; i++){
    if(state === State.beforeRecord){
        // handle logic when in (
    }
    ...
    if(state === State.AfterRecord){
        // handle that state
    }
}

现在,剩下的就是在每个状态下将它消耗到对象中：

>如果它在(我们开始解析和跳过任何空白
>读取所有的整数和沟槽,
>四个整数之后,读取字符串从’到下一个’到达它的结尾
>字符串后,读取直到),存储对象,并重新开始循环.

实施也不是很困难.

解析器

var State = { // keep track of the state
     BeforeRecord:0,DuringInts:1,DuringString:2,AfterRecord:3
};
var records = []; // to contain the results
var state = State.beforeRecord;
var input = " (1," // sample input

var workingRecord = {}; // what we're reading into.

for(var i = 0;i < input.length; i++){
    var token = input[i]; // read the current input
    if(state === State.beforeRecord){ // before reading a record
        if(token === ' ') conTinue; // ignore whitespaces between records
        if(token === '('){ state = State.DuringInts; conTinue; }
        throw new Error("Expected ( before new record");
    }
    if(state === State.DuringInts){
        if(token === ' ') conTinue; // ignore whitespace
        for(var j = 0; j < 4; j++){
            if(token === ' ') {token = input[++i]; j--; conTinue;} // ignore whitespace 
             var curNum = '';
             while(token != ","){
                  if(!/[0-9]/.test(token)) throw new Error("Expected number,got " + token);
                  curNum += token;
                  token = input[++i]; // get the next token
             }
             workingRecord[j] = number(curNum); // set the data on the record
             token = input[++i]; // remove the comma
        }
        state = State.DuringString;
        conTinue; // progress the loop
    }
    if(state === State.DuringString){
         if(token === ' ') conTinue; // skip whitespace
         if(token === "'"){
             var str = "";
             token = input[++i];
             var lenGuard = 1000;
             while(token !== "'"){
                 str+=token;
                 if(lenGuard-- === 0) throw new Error("Error,String length bounded by 1000");
                 token = input[++i];
             }
             workingRecord.str = str;
             token = input[++i]; // remove )
             state = State.AfterRecord;
             conTinue;
         }
    }
    if(state === State.AfterRecord){
        if(token === ' ') conTinue; // ignore whitespace
        if(token === ',') { // got the "," between records
            state = State.beforeRecord;
            records.push(workingRecord);
            workingRecord = {}; // new record;
            conTinue;
        }
        throw new Error("Invalid token found " + token);
    }
}
console.log(records); // logs [Object,Object,Object]
                      // each object has four numbers and a String,for example
                      // records[0][0] is 1,records[0][1] is 3 and so on,// records[0].str is "John (Finances)"