更新：请检查我的第二个答案中的LineNavigator，那个阅读器要好得多。
我制作了自己的阅读器，满足了我的需求。
性能
由于问题仅与大文件有关，因此性能是最重要的部分。
如您所见，性能几乎与直接读取相同（如上所述）。
目前我正在努力让它变得更好，因为更大的时间消费者是异步调用以避免调用堆栈限制命中，这对于执行问题不是不必要的。性能问题已解决。
质量
测试了以下案例：
- 空文件
- 单行文件
- 文件末尾有换行符，没有
- 检查解析的行
- 在同一页面上多次运行
- 没有线路丢失，也没有订单问题
代码和用法
HTML：
<input type="file" id="file-test" name="files[]" />
<div id="output-test"></div>
用法：
$("#file-test").on('change', function(evt) {
var startProcessing = new Date();
var index = 0;
var file = evt.target.files[0];
var reader = new FileLineStreamer();
$("#output-test").html("");
reader.open(file, function (lines, err) {
if (err != null) {
$("#output-test").append('<span style="color:red;">' + err + "</span><br />");
return;
}
if (lines == null) {
var milisecondsSpend = new Date() - startProcessing;
$("#output-test").append("<strong>" + index + " lines are processed</strong> Miliseconds spend: " + milisecondsSpend + "<br />");
return;
}
// output every line
lines.forEach(function (line) {
index++;
//$("#output-test").append(index + ": " + line + "<br />");
});
reader.getNextBatch();
});
reader.getNextBatch();
});
代码：
function FileLineStreamer() {
var loopholeReader = new FileReader();
var chunkReader = new FileReader();
var delimiter = "\n".charCodeAt(0);
var expectedChunkSize = 15000000; // Slice size to read
var loopholeSize = 200; // Slice size to search for line end
var file = null;
var fileSize;
var loopholeStart;
var loopholeEnd;
var chunkStart;
var chunkEnd;
var lines;
var thisForClosure = this;
var handler;
// Reading of loophole ended
loopholeReader.onloadend = function(evt) {
// Read error
if (evt.target.readyState != FileReader.DONE) {
handler(null, new Error("Not able to read loophole (start: )"));
return;
}
var view = new DataView(evt.target.result);
var realLoopholeSize = loopholeEnd - loopholeStart;
for(var i = realLoopholeSize - 1; i >= 0; i--) {
if (view.getInt8(i) == delimiter) {
chunkEnd = loopholeStart + i + 1;
var blob = file.slice(chunkStart, chunkEnd);
chunkReader.readAsText(blob);
return;
}
}
// No delimiter found, looking in the next loophole
loopholeStart = loopholeEnd;
loopholeEnd = Math.min(loopholeStart + loopholeSize, fileSize);
thisForClosure.getNextBatch();
};
// Reading of chunk ended
chunkReader.onloadend = function(evt) {
// Read error
if (evt.target.readyState != FileReader.DONE) {
handler(null, new Error("Not able to read loophole"));
return;
}
lines = evt.target.result.split(/\r?\n/);
// Remove last new line in the end of chunk
if (lines.length > 0 && lines[lines.length - 1] == "") {
lines.pop();
}
chunkStart = chunkEnd;
chunkEnd = Math.min(chunkStart + expectedChunkSize, fileSize);
loopholeStart = Math.min(chunkEnd, fileSize);
loopholeEnd = Math.min(loopholeStart + loopholeSize, fileSize);
thisForClosure.getNextBatch();
};
this.getProgress = function () {
if (file == null)
return 0;
if (chunkStart == fileSize)
return 100;
return Math.round(100 * (chunkStart / fileSize));
}
// Public: open file for reading
this.open = function (fileToOpen, linesProcessed) {
file = fileToOpen;
fileSize = file.size;
loopholeStart = Math.min(expectedChunkSize, fileSize);
loopholeEnd = Math.min(loopholeStart + loopholeSize, fileSize);
chunkStart = 0;
chunkEnd = 0;
lines = null;
handler = linesProcessed;
};
// Public: start getting new line async
this.getNextBatch = function() {
// File wasn't open
if (file == null) {
handler(null, new Error("You must open a file first"));
return;
}
// Some lines available
if (lines != null) {
var linesForClosure = lines;
setTimeout(function() { handler(linesForClosure, null) }, 0);
lines = null;
return;
}
// End of File
if (chunkStart == fileSize) {
handler(null, null);
return;
}
// File part bigger than expectedChunkSize is left
if (loopholeStart < fileSize) {
var blob = file.slice(loopholeStart, loopholeEnd);
loopholeReader.readAsArrayBuffer(blob);
}
// All file can be read at once
else {
chunkEnd = fileSize;
var blob = file.slice(chunkStart, fileSize);
chunkReader.readAsText(blob);
}
};
};