我试图读取一个大文件一行在一次。我在Quora上找到了一个关于这个主题的问题,但我错过了一些联系,把整个事情联系在一起。

 var Lazy=require("lazy");
 new Lazy(process.stdin)
     .lines
     .forEach(
          function(line) { 
              console.log(line.toString()); 
          }
 );
 process.stdin.resume();

我想要弄清楚的是如何一次从文件中读取一行,而不是像本例中那样读取STDIN。

我试着:

 fs.open('./VeryBigFile.csv', 'r', '0666', Process);

 function Process(err, fd) {
    if (err) throw err;
    // DO lazy read 
 }

但这并不奏效。我知道在必要时我可以使用PHP之类的东西,但我想弄清楚这个问题。

我不认为其他答案会起作用,因为文件比我运行它的服务器的内存大得多。


当前回答

虽然您可能应该像上面的答案所建议的那样使用readline模块,但readline似乎面向命令行接口,而不是行读取。关于缓冲,它也有点不透明。(任何需要流式行阅读器的人可能都想调整缓冲区大小)。readline模块大约有1000行,而这个,加上统计和测试,是34行。

const EventEmitter = require('events').EventEmitter;
class LineReader extends EventEmitter{
    constructor(f, delim='\n'){
        super();
        this.totalChars = 0;
        this.totalLines = 0;
        this.leftover = '';

        f.on('data', (chunk)=>{
            this.totalChars += chunk.length;
            let lines = chunk.split(delim);
            if (lines.length === 1){
                this.leftover += chunk;
                return;
            }
            lines[0] = this.leftover + lines[0];
            this.leftover = lines[lines.length-1];
            if (this.leftover) lines.pop();
            this.totalLines += lines.length;
            for (let l of lines) this.onLine(l);
        });
        // f.on('error', ()=>{});
        f.on('end', ()=>{console.log('chars', this.totalChars, 'lines', this.totalLines)});
    }
    onLine(l){
        this.emit('line', l);
    }
}
//Command line test
const f = require('fs').createReadStream(process.argv[2], 'utf8');
const delim = process.argv[3];
const lineReader = new LineReader(f, delim);
lineReader.on('line', (line)=> console.log(line));

下面是一个更短的版本,没有统计数据,只有19行:

class LineReader extends require('events').EventEmitter{
    constructor(f, delim='\n'){
        super();
        this.leftover = '';
        f.on('data', (chunk)=>{
            let lines = chunk.split(delim);
            if (lines.length === 1){
                this.leftover += chunk;
                return;
            }
            lines[0] = this.leftover + lines[0];
            this.leftover = lines[lines.length-1];
            if (this.leftover) 
                lines.pop();
            for (let l of lines)
                this.emit('line', l);
        });
    }
}

其他回答

从Node.js v0.12和Node.js v4.0.0开始,有一个稳定的readline核心模块。下面是从文件中读取行,不需要任何外部模块的最简单方法:

const fs = require('fs');
const readline = require('readline');

async function processLineByLine() {
  const fileStream = fs.createReadStream('input.txt');

  const rl = readline.createInterface({
    input: fileStream,
    crlfDelay: Infinity
  });
  // Note: we use the crlfDelay option to recognize all instances of CR LF
  // ('\r\n') in input.txt as a single line break.

  for await (const line of rl) {
    // Each line in input.txt will be successively available here as `line`.
    console.log(`Line from file: ${line}`);
  }
}

processLineByLine();

或者:

var lineReader = require('readline').createInterface({
  input: require('fs').createReadStream('file.in')
});

lineReader.on('line', function (line) {
  console.log('Line from file:', line);
});

最后一行被正确读取(截至Node v0.12或更高版本),即使没有最后的\n。

更新:此示例已添加到Node的API官方文档中。

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:-)

const fs = require("fs")

fs.readFile('./file', 'utf-8', (err, data) => {
var innerContent;
    console.log("Asynchronous read: " + data.toString());
    const lines = data.toString().split('\n')
    for (let line of lines)
        innerContent += line + '<br>';


});

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);

在大多数情况下,这应该足够了:

const fs = require("fs")

fs.readFile('./file', 'utf-8', (err, file) => {
  const lines = file.split('\n')

  for (let line of lines)
    console.log(line)
});