仅当分隔符未用引号括起时才拆分字符串

时间:2009-12-30 19:10:09

标签: javascript regex

我需要在JavaScript中编写一个split函数,它将一个字符串拆分为一个逗号中的数组...但是逗号不能用引号括起来('")。

以下是三个示例以及结果(数组)应该如何:

"peanut, butter, jelly"
  -> ["peanut", "butter", "jelly"]

"peanut, 'butter, bread', 'jelly'"
  -> ["peanut", "butter, bread", "jelly"]

'peanut, "butter, bread", "jelly"'
  -> ["peanut", 'butter, bread', "jelly"]

我无法使用JavaScript split方法的原因是因为当分隔符用引号括起来时它也会分裂。

我怎样才能做到这一点,也许是用正则表达式?


关于上下文,我将使用它来分割从传递给你在扩展jQuery的$.expr[':']时创建的函数的第三个参数的第三个元素传递的参数。通常,为此参数指定的名称称为meta,这是一个包含有关过滤器的某些信息的数组。

无论如何,这个数组的第三个元素是一个字符串,其中包含与过滤器一起传递的参数;并且由于字符串格式的参数,我需要能够正确地拆分它们进行解析。

4 个答案:

答案 0 :(得分:3)

您要求的内容本质上是一个Javascript CSV解析器。在“Javascript CSV Parser”上进行谷歌搜索,您将获得大量的点击,其中很多都有完整的脚本。另请参阅Javascript code to parse CSV data

答案 1 :(得分:1)

var str = 'text, foo, "haha, dude", bar';
var fragments = str.match(/[a-z]+|(['"]).*?\1/g);

更好(支持字符串中的转义"' ):

var str = 'text_123 space, foo, "text, here\", dude", bar, \'one, two\', blob';
var fragments = str.match(/[^"', ][^"',]+[^"', ]|(["'])(?:[^\1\\\\]|\\\\.)*\1/g);

// Result:
0: text_123 space
1: foo
2: "text, here\", dude"
3: bar
4: 'one, two'
5: blob

答案 2 :(得分:1)

好吧,我已经有一个解决方案的手提钻(一般代码写的东西),所以只是为了踢。 。

function Lexer () {
  this.setIndex = false;
  this.useNew = false;
  for (var i = 0; i < arguments.length; ++i) {
    var arg = arguments [i];
    if (arg === Lexer.USE_NEW) {
      this.useNew = true;
    }
    else if (arg === Lexer.SET_INDEX) {
      this.setIndex = Lexer.DEFAULT_INDEX;
    }
    else if (arg instanceof Lexer.SET_INDEX) {
      this.setIndex = arg.indexProp;
    }
  }
  this.rules = [];
  this.errorLexeme = null;
}

Lexer.NULL_LEXEME = {};

Lexer.ERROR_LEXEME = { 
  toString: function () {
    return "[object Lexer.ERROR_LEXEME]";
  }
};

Lexer.DEFAULT_INDEX = "index";

Lexer.USE_NEW = {};

Lexer.SET_INDEX = function (indexProp) {
  if ( !(this instanceof arguments.callee)) {
    return new arguments.callee.apply (this, arguments);
  }
  if (indexProp === undefined) {
    indexProp = Lexer.DEFAULT_INDEX;
  }
  this.indexProp = indexProp;
};

(function () {
  var New = (function () {
    var fs = [];
    return function () {
      var f = fs [arguments.length];
      if (f) {
        return f.apply (this, arguments);
      }
      var argStrs = [];
      for (var i = 0; i < arguments.length; ++i) {
        argStrs.push ("a[" + i + "]");
      }
      f = new Function ("var a=arguments;return new this(" + argStrs.join () + ");");
      if (arguments.length < 100) {
        fs [arguments.length] = f;
      }
      return f.apply (this, arguments);
    };
  }) ();

  var flagMap = [
      ["global", "g"]
    , ["ignoreCase", "i"]
    , ["multiline", "m"]
    , ["sticky", "y"]
    ];

  function getFlags (regex) {
    var flags = "";
    for (var i = 0; i < flagMap.length; ++i) {
      if (regex [flagMap [i] [0]]) {
        flags += flagMap [i] [1];
      }
    }
    return flags;
  }

  function not (x) {
    return function (y) {
      return x !== y;
    };
  }

  function Rule (regex, lexeme) {
    if (!regex.global) {
      var flags = "g" + getFlags (regex);
      regex = new RegExp (regex.source, flags);
    }
    this.regex = regex;
    this.lexeme = lexeme;
  }

  Lexer.prototype = {
      constructor: Lexer

    , addRule: function (regex, lexeme) {
        var rule = new Rule (regex, lexeme);
        this.rules.push (rule);
      }

    , setErrorLexeme: function (lexeme) {
        this.errorLexeme = lexeme;
      }

    , runLexeme: function (lexeme, exec) {
        if (typeof lexeme !== "function") {
          return lexeme;
        }
        var args = exec.concat (exec.index, exec.input);
        if (this.useNew) {
          return New.apply (lexeme, args);
        }
        return lexeme.apply (null, args);
      }

    , lex: function (str) {
        var index = 0;
        var lexemes = [];
        if (this.setIndex) {
          lexemes.push = function () {
            for (var i = 0; i < arguments.length; ++i) {
              if (arguments [i]) {
                arguments [i] [this.setIndex] = index;
              }
            }
            return Array.prototype.push.apply (this, arguments);
          };
        }
        while (index < str.length) {
          var bestExec = null;
          var bestRule = null;
          for (var i = 0; i < this.rules.length; ++i) {
            var rule = this.rules [i];
            rule.regex.lastIndex = index;
            var exec = rule.regex.exec (str);
            if (exec) {
              var doUpdate = !bestExec 
                || (exec.index < bestExec.index)
                || (exec.index === bestExec.index && exec [0].length > bestExec [0].length)
                ;
              if (doUpdate) {
                bestExec = exec;
                bestRule = rule;
              }
            }
          }
          if (!bestExec) {
            if (this.errorLexeme) {
              lexemes.push (this.errorLexeme);
              return lexemes.filter (not (Lexer.NULL_LEXEME));
            }
            ++index;
          }
          else {
            if (this.errorLexeme && index !== bestExec.index) {
              lexemes.push (this.errorLexeme);
            }
            var lexeme = this.runLexeme (bestRule.lexeme, bestExec);
            lexemes.push (lexeme);
          }
          index = bestRule.regex.lastIndex;
        }
        return lexemes.filter (not (Lexer.NULL_LEXEME));
      }
  };
}) ();

if (!Array.prototype.filter) {
  Array.prototype.filter = function (fun) {
    var len = this.length >>> 0;
    var res = [];
    var thisp = arguments [1];
    for (var i = 0; i < len; ++i) {
      if (i in this) {
        var val = this [i];
        if (fun.call (thisp, val, i, this)) {
          res.push (val);
        }
      }
    }
    return res;
  };
}

现在使用代码解决问题:

function trim (str) {
  str = str.replace (/^\s+/, "");
  str = str.replace (/\s+$/, "");
  return str;
}

var splitter = new Lexer ();
splitter.setErrorLexeme (Lexer.ERROR_LEXEME);
splitter.addRule (/[^,"]*"[^"]*"[^,"]*/g, trim);
splitter.addRule (/[^,']*'[^']*'[^,']*/g, trim);
splitter.addRule (/[^,"']+/g, trim);
splitter.addRule (/,/g, Lexer.NULL_LEXEME);

var strs = [
    "peanut, butter, jelly"
  , "peanut, 'butter, bread', 'jelly'"
  , 'peanut, "butter, bread", "jelly"'
  ];

// NOTE: I'm lazy here, so I'm using Array.prototype.map, 
//       which isn't supported in all browsers.
var splitStrs = strs.map (function (str) {
  return splitter.lex (str);
});

答案 3 :(得分:-1)

如果您可以控制输入以强制将字符串括在双引号"中,并且所有带字符串的元素将用单引号'括起来,并且没有元素可以包含单引号,然后您可以拆分, '。如果你无法控制输入,那么使用正则表达式对输入进行排序/过滤/拆分与使用正则表达式匹配xhtml一样有用(参见:RegEx match open tags except XHTML self-contained tags