我拥有的最小文件> 850k线和每条线的长度未知.目标是在浏览器中从该文件中读取n行.完全阅读它不会发生.
这是HTML< input type =“file”name =“file”id =“file”>和JS我有：
var n = 10;
var reader = new FileReader();
reader.onload = function(progressEvent) {
// Entire file
console.log(this.result);
// By lines
var lines = this.result.split('\n');
for (var line = 0; line < n; line++) {
console.log(lines[line]);
}
};
显然,这里的问题是它试图首先实现整个文件,然后用换行符拆分它.因此,无论n,它都会尝试读取整个文件,并在文件很大时最终不读取任何内容.
我该怎么办？
注意：我愿意删除整个函数并从头开始,因为我将能够在我们阅读的每一行中调用console.log().
*“每行都是未知长度” – >意味着该文件是这样的：
(0,(1,2)) (1,(4,5,6)) (2,(7)) (3,(8))
编辑：
要走的路就像filereader api on big files,但我看不出如何修改它来读取文件的n行……
通过使用Uint8Array to string in Javascript,可以从那里做到：
var view = new Uint8Array(fr.result);
var string = new TextDecoder("utf-8").decode(view);
console.log("Chunk " + string);
但这可能无法读取整个最后一行,那么您将如何确定以后的行？例如,这是它打印的内容：
((7202),(u'11330875493',u'2554375661')) ((1667),(u'9079074735',u'6883914476',
解决方法
逻辑非常类似于我在
filereader api on big files的回答中所写的内容,除了你需要跟踪到目前为止已处理的行数(以及到目前为止读取的最后一行,因为它可能尚未结束) .下一个示例适用于与UTF-8兼容的任何编码;如果您需要其他编码,请查看
TextDecoder构造函数的选项.
如果您确定输入是ASCII(或任何其他单字节编码),那么您也可以跳过使用TextDecoder并使用FileReader‘s readAsText method直接将输入读取为文本.
// This is just an example of the function below.
document.getElementById('start').onclick = function() {
var file = document.getElementById('infile').files[0];
if (!file) {
console.log('No file selected.');
return;
}
var maxlines = parseInt(document.getElementById('maxlines').value,10);
var lineno = 1;
// readSomeLines is defined below.
readSomeLines(file,maxlines,function(line) {
console.log("Line: " + (lineno++) + line);
},function onComplete() {
console.log('Read all lines');
});
};
/**
* Read up to and including |maxlines| lines from |file|.
*
* @param {Blob} file - The file to be read.
* @param {integer} maxlines - The maximum number of lines to read.
* @param {function(string)} forEachLine - Called for each line.
* @param {function(error)} onComplete - Called when the end of the file
* is reached or when |maxlines| lines have been read.
*/
function readSomeLines(file,forEachLine,onComplete) {
var CHUNK_SIZE = 50000; // 50kb,arbitrarily chosen.
var decoder = new TextDecoder();
var offset = 0;
var linecount = 0;
var linenumber = 0;
var results = '';
var fr = new FileReader();
fr.onload = function() {
// Use stream:true in case we cut the file
// in the middle of a multi-byte character
results += decoder.decode(fr.result,{stream: true});
var lines = results.split('\n');
results = lines.pop(); // In case the line did not end yet.
linecount += lines.length;
if (linecount > maxlines) {
// Read too many lines? Truncate the results.
lines.length -= linecount - maxlines;
linecount = maxlines;
}
for (var i = 0; i < lines.length; ++i) {
forEachLine(lines[i] + '\n');
}
offset += CHUNK_SIZE;
seek();
};
fr.onerror = function() {
onComplete(fr.error);
};
seek();
function seek() {
if (linecount === maxlines) {
// We found enough lines.
onComplete(); // Done.
return;
}
if (offset !== 0 && offset >= file.size) {
// We did not find all lines,but there are no more lines.
forEachLine(results); // This is from lines.pop(),before.
onComplete(); // Done
return;
}
var slice = file.slice(offset,offset + CHUNK_SIZE);
fr.readAsArrayBuffer(slice);
}
}
Read <input type="number" id="maxlines"> lines from <input type="file" id="infile">. <input type="button" id="start" value="Print lines to console">
