在Node.js v18.11.0中添加了一个逐行读取文件的新函数

filehandle.readLines([选项])

这就是如何将此功能用于想要读取的文本文件

import { open } from 'node:fs/promises';
myFileReader();
async function myFileReader() {
    const file = await open('./TextFileName.txt');
    for await (const line of file.readLines()) {
        console.log(line)
    }
}

为了了解更多read Node.js文档，这里有文件系统readlines()的链接: https://nodejs.org/api/fs.html#filehandlereadlinesoptions

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);

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:-)

我用这个:

function emitLines(stream, re){
    re = re && /\n/;
    var buffer = '';

    stream.on('data', stream_data);
    stream.on('end', stream_end);

    function stream_data(data){
        buffer += data;
        flush();
    }//stream_data

    function stream_end(){
        if(buffer) stream.emmit('line', buffer);
    }//stream_end


    function flush(){
        var re = /\n/;
        var match;
        while(match = re.exec(buffer)){
            var index = match.index + match[0].length;
            stream.emit('line', buffer.substring(0, index));
            buffer = buffer.substring(index);
            re.lastIndex = 0;
        }
    }//flush

}//emitLines

在流上使用此函数并侦听将发出的行事件。

gr-

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) );

var fs = require('fs');

function readfile(name,online,onend,encoding) {
    var bufsize = 1024;
    var buffer = new Buffer(bufsize);
    var bufread = 0;
    var fd = fs.openSync(name,'r');
    var position = 0;
    var eof = false;
    var data = "";
    var lines = 0;

    encoding = encoding || "utf8";

    function readbuf() {
        bufread = fs.readSync(fd,buffer,0,bufsize,position);
        position += bufread;
        eof = bufread ? false : true;
        data += buffer.toString(encoding,0,bufread);
    }

    function getLine() {
        var nl = data.indexOf("\r"), hasnl = nl !== -1;
        if (!hasnl && eof) return fs.closeSync(fd), online(data,++lines), onend(lines); 
        if (!hasnl && !eof) readbuf(), nl = data.indexOf("\r"), hasnl = nl !== -1;
        if (!hasnl) return process.nextTick(getLine);
        var line = data.substr(0,nl);
        data = data.substr(nl+1);
        if (data[0] === "\n") data = data.substr(1);
        online(line,++lines);
        process.nextTick(getLine);
    }
    getLine();
}

我也有同样的问题，想出了上面的解决方案 看起来类似于其他，但是异步的，可以读取大文件非常快

希望这能有所帮助