我可以在哪里找到一些JavaScript代码来解析CSV数据?


当前回答

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>

其他回答

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。

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。

下面是我简单的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
}

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;
    }
};

我已经构造了这个JavaScript脚本来解析字符串到数组对象中的CSV。我发现最好将整个CSV分解成行、字段并相应地处理它们。我认为这将使您更容易更改代码以满足您的需要。

    //
    //
    // 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 the last character 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 a 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'
        }
    }