jQuery-CSV

它是一个jQuery插件，设计用于将CSV解析为JavaScript数据的端到端解决方案。它处理RFC 4180中提出的每一个边缘情况，以及一些Excel/谷歌电子表格导出中弹出的情况(即，大多数涉及空值)，这些都是规范所缺少的。

例子:

轨道,艺术家,专辑, 危险，“巴斯塔韵脚”，“当灾难袭来”，1997年

// Calling this
music = $.csv.toArrays(csv)

// Outputs...
[
  ["track", "artist", "album", "year"],
  ["Dangerous", "Busta Rhymes", "When Disaster Strikes", "1997"]
]

console.log(music[1][2]) // Outputs: 'When Disaster Strikes'

更新:

哦，是的，我还应该提一下，它是完全可配置的。

music = $.csv.toArrays(csv, {
  delimiter: "'", // Sets a custom value delimiter character
  separator: ';', // Sets a custom field separator character
});

更新2:

它现在也可以在Node.js上使用jQuery。因此，您可以选择使用相同的库进行客户端或服务器端解析。

更新3:

自从谷歌代码关闭后，jquery-csv已经迁移到GitHub。

免责声明:我也是jQuery-CSV的作者。

我有一个实现作为电子表格项目的一部分。

此代码尚未经过全面测试，但欢迎任何人使用它。

正如一些答案所指出的那样，如果您实际上有DSV或TSV文件，您的实现可以简单得多，因为它们不允许在值中使用记录和字段分隔符。另一方面，CSV实际上可以在字段中使用逗号和换行符，这打破了大多数正则表达式和基于分割的方法。

var CSV = {
    parse: function(csv, reviver) {
        reviver = reviver || function(r, c, v) { return v; };
        var chars = csv.split(''), c = 0, cc = chars.length, start, end, table = [], row;
        while (c < cc) {
            table.push(row = []);
            while (c < cc && '\r' !== chars[c] && '\n' !== chars[c]) {
                start = end = c;
                if ('"' === chars[c]){
                    start = end = ++c;
                    while (c < cc) {
                        if ('"' === chars[c]) {
                            if ('"' !== chars[c+1]) {
                                break;
                            }
                            else {
                                chars[++c] = ''; // unescape ""
                            }
                        }
                        end = ++c;
                    }
                    if ('"' === chars[c]) {
                        ++c;
                    }
                    while (c < cc && '\r' !== chars[c] && '\n' !== chars[c] && ',' !== chars[c]) {
                        ++c;
                    }
                } else {
                    while (c < cc && '\r' !== chars[c] && '\n' !== chars[c] && ',' !== chars[c]) {
                        end = ++c;
                    }
                }
                row.push(reviver(table.length-1, row.length, chars.slice(start, end).join('')));
                if (',' === chars[c]) {
                    ++c;
                }
            }
            if ('\r' === chars[c]) {
                ++c;
            }
            if ('\n' === chars[c]) {
                ++c;
            }
        }
        return table;
    },

    stringify: function(table, replacer) {
        replacer = replacer || function(r, c, v) { return v; };
        var csv = '', c, cc, r, rr = table.length, cell;
        for (r = 0; r < rr; ++r) {
            if (r) {
                csv += '\r\n';
            }
            for (c = 0, cc = table[r].length; c < cc; ++c) {
                if (c) {
                    csv += ',';
                }
                cell = replacer(r, c, table[r][c]);
                if (/[,\r\n"]/.test(cell)) {
                    cell = '"' + cell.replace(/"/g, '""') + '"';
                }
                csv += (cell || 0 === cell) ? cell : '';
            }
        }
        return csv;
    }
};

您可以使用本博客条目中提到的CSVToArray()函数。

<script type="text/javascript">
    // ref: http://stackoverflow.com/a/1293163/2343
    // This will parse a delimited string into an array of
    // arrays. The default delimiter is the comma, but this
    // can be overriden in the second argument.
    function CSVToArray( strData, strDelimiter ){
        // Check to see if the delimiter is defined. If not,
        // then default to comma.
        strDelimiter = (strDelimiter || ",");

        // Create a regular expression to parse the CSV values.
        var objPattern = new RegExp(
            (
                // Delimiters.
                "(\\" + strDelimiter + "|\\r?\\n|\\r|^)" +

                // Quoted fields.
                "(?:\"([^\"]*(?:\"\"[^\"]*)*)\"|" +

                // Standard fields.
                "([^\"\\" + strDelimiter + "\\r\\n]*))"
            ),
            "gi"
            );


        // Create an array to hold our data. Give the array
        // a default empty first row.
        var arrData = [[]];

        // Create an array to hold our individual pattern
        // matching groups.
        var arrMatches = null;


        // Keep looping over the regular expression matches
        // until we can no longer find a match.
        while (arrMatches = objPattern.exec( strData )){

            // Get the delimiter that was found.
            var strMatchedDelimiter = arrMatches[ 1 ];

            // Check to see if the given delimiter has a length
            // (is not the start of string) and if it matches
            // field delimiter. If id does not, then we know
            // that this delimiter is a row delimiter.
            if (
                strMatchedDelimiter.length &&
                strMatchedDelimiter !== strDelimiter
                ){

                // Since we have reached a new row of data,
                // add an empty row to our data array.
                arrData.push( [] );

            }

            var strMatchedValue;

            // Now that we have our delimiter out of the way,
            // let's check to see which kind of value we
            // captured (quoted or unquoted).
            if (arrMatches[ 2 ]){

                // We found a quoted value. When we capture
                // this value, unescape any double quotes.
                strMatchedValue = arrMatches[ 2 ].replace(
                    new RegExp( "\"\"", "g" ),
                    "\""
                    );

            } else {

                // We found a non-quoted value.
                strMatchedValue = arrMatches[ 3 ];

            }


            // Now that we have our value string, let's add
            // it to the data array.
            arrData[ arrData.length - 1 ].push( strMatchedValue );
        }

        // Return the parsed data.
        return( arrData );
    }

</script>

只需使用.split('，'):

var str = "How are you doing today?";
var n = str.split(" ");

正则表达式拯救你!这几行代码根据RFC 4180标准处理带有嵌入逗号、引号和换行符的正确引用字段。

function parseCsv(data, fieldSep, newLine) {
    fieldSep = fieldSep || ',';
    newLine = newLine || '\n';
    var nSep = '\x1D';
    var qSep = '\x1E';
    var cSep = '\x1F';
    var nSepRe = new RegExp(nSep, 'g');
    var qSepRe = new RegExp(qSep, 'g');
    var cSepRe = new RegExp(cSep, 'g');
    var fieldRe = new RegExp('(?<=(^|[' + fieldSep + '\\n]))"(|[\\s\\S]+?(?<![^"]"))"(?=($|[' + fieldSep + '\\n]))', 'g');
    var grid = [];
    data.replace(/\r/g, '').replace(/\n+$/, '').replace(fieldRe, function(match, p1, p2) {
        return p2.replace(/\n/g, nSep).replace(/""/g, qSep).replace(/,/g, cSep);
    }).split(/\n/).forEach(function(line) {
        var row = line.split(fieldSep).map(function(cell) {
            return cell.replace(nSepRe, newLine).replace(qSepRe, '"').replace(cSepRe, ',');
        });
        grid.push(row);
    });
    return grid;
}

const csv = 'A1,B1,C1\n"A ""2""","B, 2","C\n2"';
const separator = ',';      // field separator, default: ','
const newline = ' <br /> '; // newline representation in case a field contains newlines, default: '\n' 
var grid = parseCsv(csv, separator, newline);
// expected: [ [ 'A1', 'B1', 'C1' ], [ 'A "2"', 'B, 2', 'C <br /> 2' ] ]

您不需要像lex/yacc这样的解析器-生成器。正则表达式可以正确地处理RFC 4180，这要归功于正向向后查找、反向向后查找和正向向前查找。

克隆/下载代码https://github.com/peterthoeny/parse-csv-js

我不知道为什么我不能让Kirtan的例子对我有用。它似乎在空字段或带尾随逗号的字段上失败了……

这个似乎可以同时处理这两个问题。

我没有编写解析器代码，只是对解析器函数进行了包装，以使其适用于文件。看到归因。

    var Strings = {
        /**
         * Wrapped CSV line parser
         * @param s      String delimited CSV string
         * @param sep    Separator override
         * @attribution: http://www.greywyvern.com/?post=258 (comments closed on blog :( )
         */
        parseCSV : function(s,sep) {
            // http://stackoverflow.com/questions/1155678/javascript-string-newline-character
            var universalNewline = /\r\n|\r|\n/g;
            var a = s.split(universalNewline);
            for(var i in a){
                for (var f = a[i].split(sep = sep || ","), x = f.length - 1, tl; x >= 0; x--) {
                    if (f[x].replace(/"\s+$/, '"').charAt(f[x].length - 1) == '"') {
                        if ((tl = f[x].replace(/^\s+"/, '"')).length > 1 && tl.charAt(0) == '"') {
                            f[x] = f[x].replace(/^\s*"|"\s*$/g, '').replace(/""/g, '"');
                          } else if (x) {
                        f.splice(x - 1, 2, [f[x - 1], f[x]].join(sep));
                      } else f = f.shift().split(sep).concat(f);
                    } else f[x].replace(/""/g, '"');
                  } a[i] = f;
        }
        return a;
        }
    }