javascript - 使用 javascript 和 regex 消除数组中的换行符

Question

我有一个如下所示的文件:

QUERY:1
DATABASE:geoquery
NL:What are the capitals of the states that border the most populated states?
SQL:something

QUERY:2
DATABASE:geoquery
NL:What are the capitals of the states bordering New York?
SQL:SELECT state.Capital FROM state JOIN borderinfo ON state.State_Name = borderinfo.State_Name          
WHERE borderinfo.Border = 'New York'

QUERY:3
DATABASE:geoquery
NL:Show the state capitals and populations.
SQL:SELECT state.Capital, state.Population FROM state

etc...

生成此文件的人拒绝以可用的格式(例如 XML 或 JSON)将其提供给我。所以我用 REGEX 解析它几次以获得我想要的结果。

剥离数据库以填充选择列表(工作正常):

$.get('inputQueryExamples.txt',
        function(data){
            var string = data;
            var dbDynamo ='';
            dbExp = new RegExp('(DATABASE:.*)','gm');
            dbDynamo = string.match(dbExp);
            cleanBreaks = new RegExp('(\r?\n|\r)','gm');
            stringNow = dbDynamo.toString();
            //console.log(dbDynamo);
            dbDynamo = dbDynamo.map(function(el){return el.replace('DATABASE:','');});

            var outArray = [];
            for(i=0; i < dbDynamo.length; i++){
                if ($.inArray(dbDynamo[i],outArray)== -1){
                    outArray.push(dbDynamo[i]);
                    }
                }

            dbDynamo = outArray.sort();

            var options = '';
            for(i=0; i<dbDynamo.length; i++){
                options += '<option value="' + dbDynamo[i] + '">' + dbDynamo[i] + '</option>';
            };
            $(select).append(options);


});

当我第二次解析以获取与特定数据库关联的所有字符串时，问题就出现了。我最终在每个字符串前面都有一个换行符，这样当我用自动完成文本填充文本区域时，它就会从第二行开始:

Array [ "

NL:Show company with complaint against Debt collection product.,DATABASE:consumer", "

NL:Show issues and dates of complaints about HSBC companies.,DATABASE:consumer", "

NL:Show companies, issues and dates with consumer concerns.,DATABASE:consumer", "

NL:Show issues and companies with complaints in MA state." ]

$(document).ready(function(){
        $.get('inputQueryExamples.txt',function(data){
            var queryString = data;
            var cleanString = "";
            var db = '';
            $('#database-list').change(function(){
               db = $('#database-list').val();

               // /(^DATABASE:.*\r\n)(^NL.*)/gm
               // http://regex101.com/r/mN4hS2

               regex = new RegExp('(^DATABASE:'+ db +'\r\n)(^NL.*)' ,'gm');

               cleanString = queryString.match(regex);
               //console.log(cleanString);
               //cleanBreaks = new RegExp('(\r\n|\r|\n)(^NL.*)','gm');
               //stringNow = cleanString.toString();
               //var dirtyString
               //dirtyString = stringNow.match(cleanBreaks);
               //console.log(dirtyString); 

               var nlString = cleanString.map(function(el) {return el.replace('DATABASE:' + db,'');});
               nlString = nlString.map(function(el){return el.replace('NL:',''); });
               //nlString = nlString.map(function(el){return      el.replace('\\r','').replace('\\n','');});

               console.log(nlString.pop());
               $('#query-list').autocomplete({
                source:nlString,

                }); 

             }); // end change

我已经尝试了所有我能想到的方法来消除换行符，但没有成功。任何想法，将不胜感激。不幸的是，服务器端仅以可用格式提供数据的方式是不可行的。其中有很多额外的代码只是为了让您了解我所尝试的内容。无用的东西我都注释掉了。提前致谢。

Answer 1

首先使用 JavaScript 将给定的数据结构解析为 JavaScript 对象是有意义的，然后您可以更轻松地处理数据。

Here is a jsfiddle演示如何将数据解析为 JavaScript 对象。下面是进行解析的相关代码:

var datasources = {};

var parseData = function(block) {
    var db = block.match(/DATABASE:(.*)/)[1];
    var dbdata = {id: 0, nl: "", sql: ""};

    if (!datasources[db]) {
        datasources[db] = [];
    }

    dbdata.id = block.match(/QUERY:(.*)/)[1];
    dbdata.nl = block.match(/NL:(.*)/)[1];
    dbdata.sql = block.match(/SQL:(.*)/)[1];

    datasources[db].push(dbdata);
};

var parseBlocks = function(data) {
    var result = data.split('\n\n');
    for(var i=0; i < result.length; i++) {
       parseData(result[i]);
    };
};