我使用下面的代码读取行后，验证它不是一个目录，它不包括在文件列表不需要检查。

(function () {
  var fs = require('fs');
  var glob = require('glob-fs')();
  var path = require('path');
  var result = 0;
  var exclude = ['LICENSE',
    path.join('e2e', 'util', 'db-ca', 'someother-file'),
    path.join('src', 'favicon.ico')];
  var files = [];
  files = glob.readdirSync('**');

  var allFiles = [];

  var patternString = [
    'trade',
    'order',
    'market',
    'securities'
  ];

  files.map((file) => {
    try {
      if (!fs.lstatSync(file).isDirectory() && exclude.indexOf(file) === -1) {
        fs.readFileSync(file).toString().split(/\r?\n/).forEach(function(line){
          patternString.map((pattern) => {
            if (line.indexOf(pattern) !== -1) {
              console.log(file + ' contain `' + pattern + '` in in line "' + line +'";');
              result = 1;
            }
          });
        });
      }
    } catch (e) {
      console.log('Error:', e.stack);
    }
  });
  process.exit(result);

})();

我有一个小模块，它做得很好，被相当多的其他项目使用npm readline注意，在节点v10中有一个本地readline模块，所以我重新发布了我的模块linebyline https://www.npmjs.com/package/linebyline

如果你不想使用这个模块，函数很简单:

var fs = require('fs'),
EventEmitter = require('events').EventEmitter,
util = require('util'),
newlines = [
  13, // \r
  10  // \n
];
var readLine = module.exports = function(file, opts) {
if (!(this instanceof readLine)) return new readLine(file);

EventEmitter.call(this);
opts = opts || {};
var self = this,
  line = [],
  lineCount = 0,
  emit = function(line, count) {
    self.emit('line', new Buffer(line).toString(), count);
  };
  this.input = fs.createReadStream(file);
  this.input.on('open', function(fd) {
    self.emit('open', fd);
  })
  .on('data', function(data) {
   for (var i = 0; i < data.length; i++) {
    if (0 <= newlines.indexOf(data[i])) { // Newline char was found.
      lineCount++;
      if (line.length) emit(line, lineCount);
      line = []; // Empty buffer.
     } else {
      line.push(data[i]); // Buffer new line data.
     }
   }
 }).on('error', function(err) {
   self.emit('error', err);
 }).on('end', function() {
  // Emit last line if anything left over since EOF won't trigger it.
  if (line.length){
     lineCount++;
     emit(line, lineCount);
  }
  self.emit('end');
 }).on('close', function() {
   self.emit('close');
 });
};
util.inherits(readLine, EventEmitter);

function createLineReader(fileName){
    var EM = require("events").EventEmitter
    var ev = new EM()
    var stream = require("fs").createReadStream(fileName)
    var remainder = null;
    stream.on("data",function(data){
        if(remainder != null){//append newly received data chunk
            var tmp = new Buffer(remainder.length+data.length)
            remainder.copy(tmp)
            data.copy(tmp,remainder.length)
            data = tmp;
        }
        var start = 0;
        for(var i=0; i<data.length; i++){
            if(data[i] == 10){ //\n new line
                var line = data.slice(start,i)
                ev.emit("line", line)
                start = i+1;
            }
        }
        if(start<data.length){
            remainder = data.slice(start);
        }else{
            remainder = null;
        }
    })

    stream.on("end",function(){
        if(null!=remainder) ev.emit("line",remainder)
    })

    return ev
}


//---------main---------------
fileName = process.argv[2]

lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
    console.log(line.toString())
    //console.log("++++++++++++++++++++")
})

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) );

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。

在进行此类操作时，我们必须问自己两个问题:

执行它需要多少内存? 内存消耗是否随着文件大小的增加而急剧增加?

require('fs'). readfilesync()等解决方案将整个文件加载到内存中。这意味着执行操作所需的内存量将几乎等同于文件大小。对于大于50mbs的数据，我们应该避免使用这种方法

通过在函数调用之后放置以下代码行，我们可以很容易地跟踪函数所使用的内存量:

    const used = process.memoryUsage().heapUsed / 1024 / 1024;
    console.log(
      `The script uses approximately ${Math.round(used * 100) / 100} MB`
    );

现在，从大文件中读取特定行最好的方法是使用node的readline。文档中有一些惊人的例子。