我的CSV数据是这样的:
heading1,heading2,heading3,heading4,heading5
value1_1,value2_1,value3_1,value4_1,value5_1
value1_2,value2_2,value3_2,value4_2,value5_2
...
如何使用JavaScript读取数据并将其转换为这样的数组?:
[
heading1: value1_1,
heading2: value2_1,
heading3: value3_1,
heading4: value4_1
heading5: value5_1
],[
heading1: value1_2,
heading2: value2_2,
heading3: value3_2,
heading4: value4_2,
heading5: value5_2
]
....
我试过这个代码,但运气不好!:
<script type="text/javascript">
var allText =[];
var allTextLines = [];
var Lines = [];
var txtFile = new XMLHttpRequest();
txtFile.open("GET", "file://d:/data.txt", true);
txtFile.onreadystatechange = function()
{
allText = txtFile.responseText;
allTextLines = allText.split(/\r\n|\n/);
};
document.write(allTextLines);
document.write(allText);
document.write(txtFile);
</script>
下面是一个JavaScript函数,用于解析CSV数据,计算引号内的逗号。
// Parse a CSV row, accounting for commas inside quotes
function parse(row){
var insideQuote = false,
entries = [],
entry = [];
row.split('').forEach(function (character) {
if(character === '"') {
insideQuote = !insideQuote;
} else {
if(character == "," && !insideQuote) {
entries.push(entry.join(''));
entry = [];
} else {
entry.push(character);
}
}
});
entries.push(entry.join(''));
return entries;
}
函数解析CSV文件的示例如下:
"foo, the column",bar
2,3
"4, the value",5
数组:
// csv could contain the content read from a csv file
var csv = '"foo, the column",bar\n2,3\n"4, the value",5',
// Split the input into lines
lines = csv.split('\n'),
// Extract column names from the first line
columnNamesLine = lines[0],
columnNames = parse(columnNamesLine),
// Extract data from subsequent lines
dataLines = lines.slice(1),
data = dataLines.map(parse);
// Prints ["foo, the column","bar"]
console.log(JSON.stringify(columnNames));
// Prints [["2","3"],["4, the value","5"]]
console.log(JSON.stringify(data));
下面是如何将数据转换为对象,就像D3的csv解析器(这是一个可靠的第三方解决方案):
var dataObjects = data.map(function (arr) {
var dataObject = {};
columnNames.forEach(function(columnName, i){
dataObject[columnName] = arr[i];
});
return dataObject;
});
// Prints [{"foo":"2","bar":"3"},{"foo":"4","bar":"5"}]
console.log(JSON.stringify(dataObjects));
这是这段代码的工作原理。
享受吧!——伦
这是一个老问题,在2022年,有很多方法可以实现这一目标。首先,我认为D3是数据操作的最佳替代品之一。它是开源的,可以免费使用,但它也是模块化的,所以我们可以只导入fetch模块。
这里有一个基本的例子。我们将使用遗留模式,所以我将导入整个D3库。现在调用d3。csv函数,就完成了。该函数在内部调用fetch方法,因此它可以打开dataURL、url、files、blob等。
const fileInput = document.getElementById('csv')
const outElement = document.getElementById('out')
const previewCSVData = async dataurl => {
const d = await d3.csv(dataurl)
console.log({
d
})
outElement.textContent = d.columns
}
const readFile = e => {
const file = fileInput.files[0]
const reader = new FileReader()
reader.onload = () => {
const dataUrl = reader.result;
previewCSVData(dataUrl)
}
reader.readAsDataURL(file)
}
fileInput.onchange = readFile
<script type="text/javascript" src="https://unpkg.com/d3@7.6.1/dist/d3.min.js"></script>
<div>
<p>Select local CSV File:</p>
<input id="csv" type="file" accept=".csv">
</div>
<pre id="out"><p>File headers will appear here</p></pre>
If we don't want to use any library and we just want to use pain JavaScrip (Vanilla JS) and we managed to get the text content of a file as data and we don't want to use d3 we can implement a simple function that will split the data into a text array then we will extract the first line and split into a headers array and the rest of the text will be the lines we will process. After, we map each line and extract its values and create a row object from an array created from mapping each header to its correspondent value from values[index].
注意:
We also we going to use a little trick array objects in JavaScript can also have attributes. Yes so we will define an attribute rows.headers and assign the headers to it.
const data = `heading_1,heading_2,heading_3,heading_4,heading_5
value_1_1,value_2_1,value_3_1,value_4_1,value_5_1
value_1_2,value_2_2,value_3_2,value_4_2,value_5_2
value_1_3,value_2_3,value_3_3,value_4_3,value_5_3`
const csvParser = data => {
const text = data.split(/\r\n|\n/)
const [first, ...lines] = text
const headers = first.split(',')
const rows = []
rows.headers = headers
lines.map(line => {
const values = line.split(',')
const row = Object.fromEntries(headers.map((header, i) => [header, values[i]]))
rows.push(row)
})
return rows
}
const d = csvParser(data)
// Accessing to the theaders attribute
const headers = d.headers
console.log({headers})
console.log({d})
最后,让我们使用获取和解析csv文件来实现一个普通的JS文件加载器。
const fetchFile = async dataURL => {
return await fetch(dataURL).then(response => response.text())
}
const csvParser = data => {
const text = data.split(/\r\n|\n/)
const [first, ...lines] = text
const headers = first.split(',')
const rows = []
rows.headers = headers
lines.map(line => {
const values = line.split(',')
const row = Object.fromEntries(headers.map((header, i) => [header, values[i]]))
rows.push(row)
})
return rows
}
const fileInput = document.getElementById('csv')
const outElement = document.getElementById('out')
const previewCSVData = async dataURL => {
const data = await fetchFile(dataURL)
const d = csvParser(data)
console.log({ d })
outElement.textContent = d.headers
}
const readFile = e => {
const file = fileInput.files[0]
const reader = new FileReader()
reader.onload = () => {
const dataURL = reader.result;
previewCSVData(dataURL)
}
reader.readAsDataURL(file)
}
fileInput.onchange = readFile
<script type="text/javascript" src="https://unpkg.com/d3@7.6.1/dist/d3.min.js"></script>
<div>
<p>Select local CSV File:</p>
<input id="csv" type="file" accept=".csv">
</div>
<pre id="out"><p>File contents will appear here</p></pre>
我用这个文件进行了测试
function CSVParse(csvFile)
{
this.rows = [];
var fieldRegEx = new RegExp('(?:\s*"((?:""|[^"])*)"\s*|\s*((?:""|[^",\r\n])*(?:""|[^"\s,\r\n]))?\s*)(,|[\r\n]+|$)', "g");
var row = [];
var currMatch = null;
while (currMatch = fieldRegEx.exec(this.csvFile))
{
row.push([currMatch[1], currMatch[2]].join('')); // concatenate with potential nulls
if (currMatch[3] != ',')
{
this.rows.push(row);
row = [];
}
if (currMatch[3].length == 0)
break;
}
}
我喜欢尽可能多地使用正则表达式。此正则表达式将所有项视为带引号或不带引号,后跟列分隔符或行分隔符。或者文本的结尾。
这就是为什么最后一个条件——没有它,它将是一个无限循环,因为模式可以匹配零长度字段(在csv中完全有效)。但由于$是一个零长度断言,它不会进展到不匹配并结束循环。
仅供参考,我必须使第二种选择排除引号周围的值;似乎它在我的javascript引擎上的第一个替代方案之前执行,并考虑将引号作为未加引号的值的一部分。我不会问的,我刚弄好了。
使用csvToObjs函数,您可以将数据条目从CSV格式转换为对象数组。
function csvToObjs(string) {
const lines = data.split(/\r\n|\n/);
let [headings, ...entries] = lines;
headings = headings.split(',');
const objs = [];
entries.map(entry=>{
obj = entry.split(',');
objs.push(Object.fromEntries(headings.map((head, i)=>[head, obj[i]])));
})
return objs;
}
data = `heading1,heading2,heading3,heading4,heading5
value1_1,value2_1,value3_1,value4_1,value5_1
value1_2,value2_2,value3_2,value4_2,value5_2`
console.log(csvToObjs(data));
下面是一个JavaScript函数,用于解析CSV数据,计算引号内的逗号。
// Parse a CSV row, accounting for commas inside quotes
function parse(row){
var insideQuote = false,
entries = [],
entry = [];
row.split('').forEach(function (character) {
if(character === '"') {
insideQuote = !insideQuote;
} else {
if(character == "," && !insideQuote) {
entries.push(entry.join(''));
entry = [];
} else {
entry.push(character);
}
}
});
entries.push(entry.join(''));
return entries;
}
函数解析CSV文件的示例如下:
"foo, the column",bar
2,3
"4, the value",5
数组:
// csv could contain the content read from a csv file
var csv = '"foo, the column",bar\n2,3\n"4, the value",5',
// Split the input into lines
lines = csv.split('\n'),
// Extract column names from the first line
columnNamesLine = lines[0],
columnNames = parse(columnNamesLine),
// Extract data from subsequent lines
dataLines = lines.slice(1),
data = dataLines.map(parse);
// Prints ["foo, the column","bar"]
console.log(JSON.stringify(columnNames));
// Prints [["2","3"],["4, the value","5"]]
console.log(JSON.stringify(data));
下面是如何将数据转换为对象,就像D3的csv解析器(这是一个可靠的第三方解决方案):
var dataObjects = data.map(function (arr) {
var dataObject = {};
columnNames.forEach(function(columnName, i){
dataObject[columnName] = arr[i];
});
return dataObject;
});
// Prints [{"foo":"2","bar":"3"},{"foo":"4","bar":"5"}]
console.log(JSON.stringify(dataObjects));
这是这段代码的工作原理。
享受吧!——伦