如何在 Dart 中逐行读取文件

Question

这个问题是上一个问题的延续。我编写了以下代码来确定是否File.openRead()创建了可以逐行流式传输的 Stream。事实证明答案是否定的。读取整个文件，然后传递到下一个转换。我的问题是：如何在 Dart 中逐行流式传输文件？

import 'dart:async';
import 'dart:convert';
import 'dart:io';


void main(List<String> arguments) {

  Stream<List<int>> stream = new File('Data.txt').openRead();

   stream
      .transform(const Utf8InterceptDecoder())
        .transform(const LineSplitterIntercept())
          .listen((line) {
//            stdout.writeln(line);
          }).asFuture().catchError((_) => print(_));
}

int lineSplitCount = 0;

class LineSplitterIntercept extends LineSplitter {

  const LineSplitterIntercept() : super();
  // Never gets called
  List<String> convert(String data) {
    stdout.writeln("LineSplitterIntercept.convert : Data:" + data);
    return super.convert(data);
  }

  StringConversionSink startChunkedConversion(ChunkedConversionSink<String> sink) {
    stdout.writeln("LineSplitterIntercept.startChunkedConversion Count:"+lineSplitCount.toString()+ " Sink: " + sink.toString());
    lineSplitCount++;
    return super.startChunkedConversion(sink);
  }
}

int utfCount = 0;

class Utf8InterceptDecoder extends Utf8Decoder {

  const Utf8InterceptDecoder() : super();

  //never gets called
  String convert(List<int> codeUnits) {
    stdout.writeln("Utf8InterceptDecoder.convert : codeUnits.length:" + codeUnits.length.toString());
    return super.convert(codeUnits);
  }


  ByteConversionSink startChunkedConversion(ChunkedConversionSink<String> sink) {
    stdout.writeln("Utf8InterceptDecoder.startChunkedConversion Count:"+ utfCount.toString() + " Sink: "+ sink.toString());
    utfCount++;
    return super.startChunkedConversion(sink);
  }
}

Answer 1

我认为这段代码很有用：

import 'dart:io';
import 'dart:convert';
import 'dart:async';

main() {
  final file = new File('file.txt');
  Stream<List<int>> inputStream = file.openRead();

  inputStream
    .transform(utf8.decoder)       // Decode bytes to UTF-8.
    .transform(new LineSplitter()) // Convert stream to individual lines.
    .listen((String line) {        // Process results.
        print('$line: ${line.length} bytes');
      },
      onDone: () { print('File is now closed.'); },
      onError: (e) { print(e.toString()); });
}

Answer 2

startChunkedConversion当转换开始时，转换器仅被调用一次。但是，返回的接收器的add方法会使用文件的某些部分多次调用。

由源决定块有多大，但 37MB 文件（如您上一个问题中提到的）肯定会以较小的块发送。

如果你想查看块，你可以拦截并返回一个包裹的接收器，或者你可以将自己放在和 变压器startChunkedConversion之间。openRead

截距：

class InterceptSink {
  static int lineSplitCount = 0;

  final _sink;
  InterceptSink(this._sink);
  add(x) {
    print("InterceptSink.add Count: $lineSplitCount");
    lineSplitCount++;
    _sink.add(x);
  }
  close() { _sink.close(); }
}

class LineSplitterIntercept extends Converter {
  convert(x) { throw "unimplemented"; }
  startChunkedConversion(outSink) {
    var lineSink = new LineSplitter().startChunkedConversion(outSink);
    return new InterceptSink(lineSink);
  }
}

后openRead：

file.openRead()
  .transform(UTF8.decoder)
  .map(x) {
    print("chunk size: ${x.length)");
    return x;
  }
  .transform(new LineSplitter())
  ...