匹配引号内逗号的 JS RegEx

Question

我正在尝试获取基于文本的日志文件，如下所示：

type: 'click', category: 'REFRESH_DOOR', desc: '点击刷新 门 0124'，站点：'mysite'，路径名：'/load_areas/all/doors'，参数： '?sort_by=code&layout=view_by_4'，时间：'1515838628166'，手机： '假'，bp：'xlarge'，大小：'[1920, 935]'，区域：'全部'，sid： '15158225889'，设施：'MMMM'，IP 地址：'XXX.XXX.XXX.XXX'， 创建时间：'2018 年 1 月 13 日 04:17'

并遍历它以从中构建一个 JSON 对象。当我在上面的条目上log.split(",") 以从字符串的各个部分中创建单独的对象时，它会获取日期并将其拆分，从而破坏数据。

什么是在单引号中查找逗号的正则表达式，我可以在尝试将此字符串拆分为 JS 数组之前替换它？

我基本上想改：'January 13, 2018 04:17' to 'January 13; 2018 04:17'，稍后再担心转换。

我试过这样的表达方式：

'([^']*)'

在引号之间取所有内容，但我无法仅针对引号之间的逗号。

Answer 1

您可以先将有问题的逗号替换为某个独特的名称，然后再以此分割。最后，我们遍历各个部分并实际构建我们的对象：

var subject = "type: 'click', category: 'REFRESH_DOOR', desc: 'clicked refresh from door 0124', site: 'mysite', pathname: '/load_areas/all/doors', params: '?sort_by=code&layout=view_by_4', time: '1515838628166', mobile: 'false', bp: 'xlarge', size: '[1920, 935]', area: 'all', sid: '15158225889', facility: 'MMMM', IP Address: 'XXX.XXX.XXX.XXX', created: 'January 13, 2018 04:17'";

var regex = /'[^']+'|(,)/g;
var kv = /(\w+):\s*'([^']+)'/;

replaced = subject.replace(regex, function(m, group1) {
    if (typeof group1 == 'undefined') return m;
    else return 'SUPERMAN';
});

// create an object that holds our values
var jsonObject = {};

// create a function that splits the individual items
function splitter(item) {
	var match = kv.exec(item);
  jsonObject[match[1]] = match[2];
}

parts = replaced.split("SUPERMAN");
parts.forEach(splitter);
console.log(jsonObject);

---

产生：

{
  "type": "click",
  "category": "REFRESH_DOOR",
  "desc": "clicked refresh from door 0124",
  "site": "mysite",
  "pathname": "/load_areas/all/doors",
  "params": "?sort_by=code&layout=view_by_4",
  "time": "1515838628166",
  "mobile": "false",
  "bp": "xlarge",
  "size": "[1920, 935]",
  "area": "all",
  "sid": "15158225889",
  "facility": "MMMM",
  "Address": "XXX.XXX.XXX.XXX",
  "created": "January 13, 2018 04:17"
}

---

改编自The Best Regex Trick。

Answer 2

我将正则表达式稍微更改为/'.*?'/g，以便它选择引号内的任何内容，然后我们只需对其进行替换以查找所有逗号并用分号替换它们。

var str = "type: 'click', category: 'REFRESH_DOOR', desc: 'clicked refresh from door 0124', site: 'mysite', pathname: '/load_areas/all/doors', params: '?sort_by=code&layout=view_by_4', time: '1515838628166', mobile: 'false', bp: 'xlarge', size: '[1920, 935]', area: 'all', sid: '15158225889', facility: 'MMMM', IP Address: 'XXX.XXX.XXX.XXX', created: 'January 13, 2018 04:17'";

//Select all quoted strings...
var replacedCommas = str.replace(/'.*?'/g, function(match){
  //Now replace any commas found in each match with semicolons
  return match.replace(/,/g, ';');
});

console.log(replacedCommas);