我可以在哪里找到一些JavaScript代码来解析CSV数据?


当前回答

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'
        }
    }

其他回答

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>

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
}

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。

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。

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