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>

就我个人而言，我喜欢使用deno std库，因为大多数模块都与浏览器正式兼容

问题是std是typescript，但官方解决方案可能会在未来发生https://github.com/denoland/deno_std/issues/641 https://github.com/denoland/dotland/issues/1728

目前有一个积极维护的飞行转译器https://bundle.deno.dev/

你可以像这样简单地使用它

<script type="module">
import { parse } from "https://bundle.deno.dev/https://deno.land/std@0.126.0/encoding/csv.ts"
console.log(await parse("a,b,c\n1,2,3"))
</script>

csvToArray v1.3

一个紧凑(645字节)，但兼容的函数，将CSV字符串转换为2D数组，符合RFC4180标准。

https://code.google.com/archive/p/csv-to-array/downloads

常用用法:jQuery

 $.ajax({
        url: "test.csv",
        dataType: 'text',
        cache: false
 }).done(function(csvAsString){
        csvAsArray=csvAsString.csvToArray();
 });

常用用法:JavaScript

csvAsArray = csvAsString.csvToArray();

覆盖字段分隔符

csvAsArray = csvAsString.csvToArray("|");

覆盖记录分离器

csvAsArray = csvAsString.csvToArray("", "#");

覆盖跳过报头

csvAsArray = csvAsString.csvToArray("", "", 1);

覆盖所有

csvAsArray = csvAsString.csvToArray("|", "#", 1);

这是另一个解决方案。这个用途:

一个粗略的全局正则表达式，用于分割CSV字符串(包括引号和逗号) 用于清除周围引号和尾随逗号的细粒度正则表达式 此外，还具有区分字符串、数字、布尔值和空值的类型更正

对于以下输入字符串:

"This is\, a value",Hello,4,-123,3.1415,'This is also\, possible',true,

代码输出:

[
  "This is, a value",
  "Hello",
  4,
  -123,
  3.1415,
  "This is also, possible",
  true,
  null
]

下面是我在一个可运行的代码片段中实现的parseCSVLine():

function parseCSVLine(text) { return text.match( /\s*(\"[^"]*\"|'[^']*'|[^,]*)\s*(,|$)/g ).map( function (text) { let m; if (m = text.match(/^\s*,?$/)) return null; // null value if (m = text.match(/^\s*\"([^"]*)\"\s*,?$/)) return m[1]; // Double Quoted Text if (m = text.match(/^\s*'([^']*)'\s*,?$/)) return m[1]; // Single Quoted Text if (m = text.match(/^\s*(true|false)\s*,?$/)) return m[1] === "true"; // Boolean if (m = text.match(/^\s*((?:\+|\-)?\d+)\s*,?$/)) return parseInt(m[1]); // Integer Number if (m = text.match(/^\s*((?:\+|\-)?\d*\.\d*)\s*,?$/)) return parseFloat(m[1]); // Floating Number if (m = text.match(/^\s*(.*?)\s*,?$/)) return m[1]; // Unquoted Text return text; } ); } let data = `"This is\, a value",Hello,4,-123,3.1415,'This is also\, possible',true,`; let obj = parseCSVLine(data); console.log( JSON.stringify( obj, undefined, 2 ) );