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
}

其他回答

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;
}

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
}

csvToArray v1.3

一个紧凑(645字节),但兼容的函数,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("|");

覆盖记录分离器

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

覆盖跳过报头

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

覆盖所有

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

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

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>