我想解决同样的问题，基本上在Perl中是这样的:

while (<>) {
    process_line($_);
}

我的用例只是一个独立的脚本，而不是服务器，所以同步就可以了。以下是我的标准:

可以在许多项目中重用的最小同步代码。 不限制文件大小或行数。 不限制线的长度。 能够处理UTF-8的完整Unicode，包括BMP以外的字符。 能够处理*nix和Windows行结束符(老式Mac对我来说不需要)。 行中要包含的行结束字符。 能够处理带有或不带有行尾字符的最后一行。 不要使用node.js发行版中不包含的任何外部库。

这是一个让我在node.js中感受低级脚本类型代码的项目，并决定它作为其他脚本语言(如Perl)的替代品的可行性。

经过惊人的努力和一些错误的开始，这是我提出的代码。它非常快，但没有我预期的那么琐碎:(在GitHub上分叉)

var fs            = require('fs'),
    StringDecoder = require('string_decoder').StringDecoder,
    util          = require('util');

function lineByLine(fd) {
  var blob = '';
  var blobStart = 0;
  var blobEnd = 0;

  var decoder = new StringDecoder('utf8');

  var CHUNK_SIZE = 16384;
  var chunk = new Buffer(CHUNK_SIZE);

  var eolPos = -1;
  var lastChunk = false;

  var moreLines = true;
  var readMore = true;

  // each line
  while (moreLines) {

    readMore = true;
    // append more chunks from the file onto the end of our blob of text until we have an EOL or EOF
    while (readMore) {

      // do we have a whole line? (with LF)
      eolPos = blob.indexOf('\n', blobStart);

      if (eolPos !== -1) {
        blobEnd = eolPos;
        readMore = false;

      // do we have the last line? (no LF)
      } else if (lastChunk) {
        blobEnd = blob.length;
        readMore = false;

      // otherwise read more
      } else {
        var bytesRead = fs.readSync(fd, chunk, 0, CHUNK_SIZE, null);

        lastChunk = bytesRead !== CHUNK_SIZE;

        blob += decoder.write(chunk.slice(0, bytesRead));
      }
    }

    if (blobStart < blob.length) {
      processLine(blob.substring(blobStart, blobEnd + 1));

      blobStart = blobEnd + 1;

      if (blobStart >= CHUNK_SIZE) {
        // blobStart is in characters, CHUNK_SIZE is in octets
        var freeable = blobStart / CHUNK_SIZE;

        // keep blob from growing indefinitely, not as deterministic as I'd like
        blob = blob.substring(CHUNK_SIZE);
        blobStart -= CHUNK_SIZE;
        blobEnd -= CHUNK_SIZE;
      }
    } else {
      moreLines = false;
    }
  }
}

它可能会被进一步清理，这是试验和错误的结果。

这是我最喜欢的浏览文件的方式，是使用现代async/await进行渐进式(不是“slurp”或全内存方式)文件读取的简单本机解决方案。在处理大型文本文件时，我发现这是一种“自然”的解决方案，而不必求助于readline包或任何非核心依赖项。

let buf = '';
for await ( const chunk of fs.createReadStream('myfile') ) {
    const lines = buf.concat(chunk).split(/\r?\n/);
    buf = lines.pop();
    for( const line of lines ) {
        console.log(line);
    }
}
if(buf.length) console.log(buf);  // last line, if file does not end with newline

您可以在fs中调整编码。creatererestream或使用chunk.toString(<arg>)。这也让你更好地微调线分裂到你的口味，即。使用.split(/\n+/)跳过空行，用{highWaterMark: <chunkSize>}控制块大小。

Don't forget to create a function like processLine(line) to avoid repeating the line processing code twice due to the ending buf leftover. Unfortunately, the ReadStream instance does not update its end-of-file flags in this setup, so there's no way, afaik, to detect within the loop that we're in the last iteration without some more verbose tricks like comparing the file size from a fs.Stats() with .bytesRead. Hence the final buf processing solution, unless you're absolutely sure your file ends with a newline \n, in which case the for await loop should suffice.

★如果你更喜欢事件异步版本，这将是它:

let buf = '';
fs.createReadStream('myfile')
.on('data', chunk => {
    const lines = buf.concat(chunk).split(/\r?\n/);
    buf = lines.pop();
    for( const line of lines ) {
        console.log(line);
    }
})
.on('end', () => buf.length && console.log(buf) );

★现在如果你不介意导入流核心包，那么这是等效的管道流版本，它允许链接转换，如gzip解压:

const { Writable } = require('stream');
let buf = '';
fs.createReadStream('myfile').pipe(
    new Writable({
        write: (chunk, enc, next) => {
            const lines = buf.concat(chunk).split(/\r?\n/);
            buf = lines.pop();
            for (const line of lines) {
                console.log(line);
            }
            next();
        }
    })
).on('finish', () => buf.length && console.log(buf) );

如果你想逐行读取一个文件，并将其写入另一个文件:

var fs = require('fs');
var readline = require('readline');
var Stream = require('stream');

function readFileLineByLine(inputFile, outputFile) {

   var instream = fs.createReadStream(inputFile);
   var outstream = new Stream();
   outstream.readable = true;
   outstream.writable = true;

   var rl = readline.createInterface({
      input: instream,
      output: outstream,
      terminal: false
   });

   rl.on('line', function (line) {
        fs.appendFileSync(outputFile, line + '\n');
   });
};

您不必打开文件，而是必须创建一个ReadStream。

fs.createReadStream

然后将该流传递给Lazy

自从发布了我最初的答案后，我发现split是一个非常容易使用的节点模块，用于文件中的行读取;它也接受可选参数。

var split = require('split');
fs.createReadStream(file)
    .pipe(split())
    .on('data', function (line) {
      //each chunk now is a seperate line! 
    });

还没有对非常大的文件进行测试。如果有，请告诉我们。

我对缺乏全面的解决方案感到沮丧，所以我把自己的尝试(git / npm)放在一起。复制粘贴功能列表:

Interactive line processing (callback-based, no loading the entire file into RAM) Optionally, return all lines in an array (detailed or raw mode) Interactively interrupt streaming, or perform map/filter like processing Detect any newline convention (PC/Mac/Linux) Correct eof / last line treatment Correct handling of multi-byte UTF-8 characters Retrieve byte offset and byte length information on per-line basis Random access, using line-based or byte-based offsets Automatically map line-offset information, to speed up random access Zero dependencies Tests

国家卫生研究院?你决定:-)