我可以在哪里找到一些JavaScript代码来解析CSV数据?
当前回答
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 ) );
其他回答
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);
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;
}
只需使用.split(','):
var str = "How are you doing today?";
var n = str.split(" ");
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。