Javascript代码来解析CSV数据

有人对我在哪里可以找到一些JavaScript代码来解析CSV数据有想法吗？

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>

jQuery的CSV

这是一个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中出现的每个单边情况，以及为规范丢失的Excel / Google Spreadsheed导出而弹出的一些情况（即主要涉及空值）。

例：

跟踪，艺术家，专辑，年

危险，“ Busta Rhymes”，“灾难发生时”，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，我可能还应该提到它是完全可配置的。

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

更新2：

现在，它也可以在Node.js上使用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 Code关闭以来，jquery-csv已迁移到GitHub。

免责声明：我也是jQuery-CSV的作者。

作为电子表格项目的一部分，我有一个实现。

该代码尚未经过全面测试，但是欢迎任何人使用。

正如一些答案指出的那样，如果您实际上有DSV或TSV文件，则实现可能会简单得多，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包含逗号和换行符，这会破坏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;
}
};

这是一个非常简单的CSV解析器，用于处理带逗号，换行和转义双引号的带引号的字段。没有拆分或正则表达式。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/上进行测试。

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;
}

这是我的PEG（.js）语法，在RFC 4180上似乎没问题（即，它处理了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上尝试一下。在https://gist.github.com/3362830下载生成的解析器。

csvToArray v1.3

紧凑（645字节）但兼容的功能，用于将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("|");

覆盖记录分隔符

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

覆盖跳过标题

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

覆盖所有

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

我不确定为什么我不能选择kirtans。为我工作。它似乎在空字段或带有尾随逗号的字段上都失败了...

这似乎可以同时解决这两个问题。

我没有编写解析器代码，只是编写了解析器函数周围的包装器，以使该工作适用于文件。参见归因

    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;
        }
    }

正则表达式可以解救！这几行代码根据RFC 4180标准使用嵌入的逗号，引号和换行符来正确处理带引号的字段。

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' ] ]

您不需要解析器生成器，例如lex / yacc。由于使用正向后向查找，负向后向查找和正向提前查找，因此正则表达式可以正确处理RFC 4180。

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

我已经构造了这个JavaScript脚本来将字符串中的CSV解析为数组对象。我发现最好将整个CSV分解为行，字段并进行相应处理。我认为这将使您轻松更改代码以适合您的需求。

希望对您有帮助。谢谢。

    //
    //
    // CSV to object
    //
    //

    const new_line_char = '\n';
    const field_separator_char = ',';

    function parse_csv(csv_str) {

        var result = [];

        let line_end_index_moved = false;
        let line_start_index = 0;
        let line_end_index = 0;
        let csr_index = 0;
        let cursor_val = csv_str[csr_index];
        let found_new_line_char = get_new_line_char(csv_str);
        let in_quote = false;

        // handle \r\n
        if (found_new_line_char == '\r\n') {
            csv_str = csv_str.split(found_new_line_char).join(new_line_char);
        }
        // handle last char is not \n
        if (csv_str[csv_str.length - 1] !== new_line_char) {
            csv_str += new_line_char;
        }

        while (csr_index < csv_str.length) {
            if (cursor_val === '"') {
                in_quote = !in_quote;
            } else if (cursor_val === new_line_char) {
                if (in_quote === false) {
                    if (line_end_index_moved && (line_start_index <= line_end_index)) {
                        result.push(parse_csv_line(csv_str.substring(line_start_index, line_end_index)));
                        line_start_index = csr_index + 1;
                    } // else: just ignore line_end_index has not moved or line has not been sliced for parsing the line
                } // else: just ignore because we are in quote
            }
            csr_index++;
            cursor_val = csv_str[csr_index];
            line_end_index = csr_index;
            line_end_index_moved = true;
        }

        // handle \r\n
        if (found_new_line_char == '\r\n') {
            let new_result = [];
            let curr_row;
            for (var i = 0; i < result.length; i++) {
                curr_row = [];
                for (var j = 0; j < result[i].length; j++) {
                    curr_row.push(result[i][j].split(new_line_char).join('\r\n'));
                }
                new_result.push(curr_row);
            }
            result = new_result;
        }

        return result;
    }

    function parse_csv_line(csv_line_str) {

        var result = [];

        // let field_end_index_moved = false;
        let field_start_index = 0;
        let field_end_index = 0;
        let csr_index = 0;
        let cursor_val = csv_line_str[csr_index];
        let in_quote = false;

        // Pretend that the last char is the separator_char to complete the loop
        csv_line_str += field_separator_char;

        while (csr_index < csv_line_str.length) {
            if (cursor_val === '"') {
                in_quote = !in_quote;
            } else if (cursor_val === field_separator_char) {
                if (in_quote === false) {
                    if (field_start_index <= field_end_index) {
                        result.push(parse_csv_field(csv_line_str.substring(field_start_index, field_end_index)));
                        field_start_index = csr_index + 1;
                    } // else: just ignore field_end_index has not moved or field has not been sliced for parsing the field
                } // else: just ignore because we are in quote
            }
            csr_index++;
            cursor_val = csv_line_str[csr_index];
            field_end_index = csr_index;
            field_end_index_moved = true;
        }

        return result;
    }

    function parse_csv_field(csv_field_str) {
        with_quote = (csv_field_str[0] === '"');

        if (with_quote) {
            csv_field_str = csv_field_str.substring(1, csv_field_str.length - 1); // remove the start and end quotes
            csv_field_str = csv_field_str.split('""').join('"'); // handle double quotes
        }

        return csv_field_str;
    }

    // initial method: check the first newline character only
    function get_new_line_char(csv_str) {
        if (csv_str.indexOf('\r\n') > -1) {
            return '\r\n';
        } else {
            return '\n'
        }
    }

为什么不只使用.split（'，'）？

http://www.w3schools.com/jsref/jsref_split.asp

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