我可以在哪里找到一些JavaScript代码来解析CSV数据?


当前回答

下面是一个极其简单的CSV解析器,它处理带有逗号、新行和转义双引号的引号字段。没有分裂或正则表达式。它每次扫描输入字符串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;
}

其他回答

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;
        }
    }

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 ) );

下面是我的PEG(.js)语法,它在RFC 4180中似乎做得不错(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上试试吧。从https://gist.github.com/3362830下载生成的解析器。

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;
    }
};

只需使用.split(','):

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