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。
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;
}
}
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;
}
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
}
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
推荐文章
- 我如何使用Jest模拟JavaScript的“窗口”对象?
- 我如何等待一个承诺完成之前返回一个函数的变量?
- 在JavaScript中根据键值查找和删除数组中的对象
- 使嵌套JavaScript对象平放/不平放的最快方法
- 如何以及为什么'a'['toUpperCase']()在JavaScript工作?
- 有Grunt生成index.html不同的设置
- 文档之间的区别。addEventListener和window。addEventListener?
- 如何检查动态附加的事件监听器是否存在?
- 如何写setTimeout与参数Coffeescript
- 将JavaScript字符串中的多个空格替换为单个空格
- JavaScript: override alert()
- 重置setTimeout
- 如何确保<select>表单字段被禁用时提交?
- jQuery有不聚焦的方法吗?
- 反应钩子-正确的方式清除超时和间隔