用于解析CSV数据的Javascript代码

Question

有人知道我在哪里可以找到一些解析CSV数据的JavaScript代码吗？

Answer 1

您可以使用此博客条目中提到的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>

Answer 2

我想我可以充分击败Kirtan的答案

输入jQuery-CSV

它是一个jquery插件,旨在用作将CSV解析为Javascript数据的端到端解决方案.它处理RFC 4180中提供的每个边缘情况,以及一些弹出Excel/Google Spreadsheed导出(即大多数涉及空值)的规范缺少的情况.

例:

曲目,艺术家,专辑,年份

危险,'Busta押韵','当灾难来袭',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,我也应该提一下,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:

它现在也适用于Node.js上的jQuery.因此,您可以选择使用相同的lib进行客户端或服务器端解析.

更新3:

自Google代码关闭以来,jquery-csv已迁移到GitHub.

免责声明:我也是jQuery-CSV的作者.

Answer 3

我有一个实现作为电子表格项目的一部分.

此代码尚未经过彻底测试,但欢迎任何人使用它.

正如一些答案所指出的那样,如果您实际拥有DSV或TSV文件,那么您的实现可以更加简单,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实际上可以在字段内部使用逗号和换行符,从而打破了大多数正则表达式和基于拆分的方法.

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;
}
};

Answer 4

这是一个非常简单的CSV解析器,可以使用逗号,换行符和转义双引号来处理带引号的字段.没有分裂或RegEx.它一次扫描输入字符串1-2个字符并构建一个数组.

在http://jsfiddle.net/vHKYH/进行测试.

function parseCSV(str) {
    var arr = [];
    var quote = false;  // true means we're inside a quoted field

    // iterate over each character, keep track of current row and column (of the returned array)
    for (var row = 0, col = 0, c = 0; c < str.length; c++) {
        var cc = str[c], nc = str[c+1];        // current character, next character
        arr[row] = arr[row] || [];             // create a new row if necessary
        arr[row][col] = arr[row][col] || '';   // create a new column (start with empty string) if necessary

        // If the current character is a quotation mark, and we're inside a
        // quoted field, and the next character is also a quotation mark,
        // add a quotation mark to the current column and skip the next character
        if (cc == '"' && quote && nc == '"') { arr[row][col] += cc; ++c; continue; }  

        // If it's just one quotation mark, begin/end quoted field
        if (cc == '"') { quote = !quote; continue; }

        // If it's a comma and we're not in a quoted field, move on to the next column
        if (cc == ',' && !quote) { ++col; continue; }

        // If it's a newline (CRLF) and we're not in a quoted field, skip the next character
        // and move on to the next row and move to column 0 of that new row
        if (cc == '\r' && nc == '\n' && !quote) { ++row; col = 0; ++c; continue; }

        // If it's a newline (LF or CR) and we're not in a quoted field,
        // move on to the next row and move to column 0 of that new row
        if (cc == '\n' && !quote) { ++row; col = 0; continue; }
        if (cc == '\r' && !quote) { ++row; col = 0; continue; }

        // Otherwise, append the current character to the current column
        arr[row][col] += cc;
    }
    return arr;
}

Answer 5

这是我的PEG(.js)语法,似乎在RFC 4180上可以正常运行(即它处理http://en.wikipedia.org/wiki/Comma-separated_values上的示例):

start
  = [\n\r]* first:line rest:([\n\r]+ data:line { return data; })* [\n\r]* { rest.unshift(first); return rest; }

line
  = first:field rest:("," text:field { return text; })*
    & { return !!first || rest.length; } // ignore blank lines
    { rest.unshift(first); return rest; }

field
  = '"' text:char* '"' { return text.join(''); }
  / text:[^\n\r,]* { return text.join(''); }

char
  = '"' '"' { return '"'; }
  / [^"]

在http://jsfiddle.net/knvzk/10或http://pegjs.majda.cz/online上试一试.通过https://gist.github.com/3362830下载生成的解析器.

Answer 6

csvToArray v1.3

紧凑(645字节)但兼容的功能,可将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

常见用法:jQuery

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

常见用法:Javascript

csvAsArray = csvAsString.csvToArray();

覆盖字段分隔符

csvAsArray = csvAsString.csvToArray("|");

覆盖记录分隔符

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

覆盖跳过标题

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

覆盖所有

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

Answer 7

这是另一个解决方案。这使用：

• 用于分割 CSV 字符串的粗略全局正则表达式（包括周围的引号和尾随逗号）
• 细粒度正则表达式，用于清理周围的引号和尾随逗号
• 此外，还具有区分字符串、数字、布尔值和空值的类型校正

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
]

这是我在可运行代码片段中对 parseCSVLine() 的实现：

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

Answer 8

这是我的简单 JavaScript 代码：

let a = 'one,two,"three, but with a comma",four,"five, with ""quotes"" in it.."'
console.log(splitQuotes(a))

function splitQuotes(line) {
  if(line.indexOf('"') < 0) 
    return line.split(',')

  let result = [], cell = '', quote = false;
  for(let i = 0; i < line.length; i++) {
    char = line[i]
    if(char == '"' && line[i+1] == '"') {
      cell += char
      i++
    } else if(char == '"') {
      quote = !quote;
    } else if(!quote && char == ',') {
      result.push(cell)
      cell = ''
    } else {
      cell += char
    }
    if ( i == line.length-1 && cell) {
      result.push(cell)
    }
  }
  return result
}