关于使用fs.readdir进行异步目录搜索有什么想法吗?我意识到我们可以引入递归,并调用read目录函数来读取下一个目录,但我有点担心它不是异步的…

什么好主意吗?我已经看了node-walk,它很棒,但它不能像readdir那样只给我数组中的文件。虽然

寻找这样的输出…

['file1.txt', 'file2.txt', 'dir/file3.txt']

当前回答

它使用了节点8中最多的新功能,包括Promises、util/promisify、destructuring、async-await、map+reduce等等,让你的同事在试图弄清楚发生了什么时挠头。

节点 8+

没有外部依赖。

const { promisify } = require('util');
const { resolve } = require('path');
const fs = require('fs');
const readdir = promisify(fs.readdir);
const stat = promisify(fs.stat);

async function getFiles(dir) {
  const subdirs = await readdir(dir);
  const files = await Promise.all(subdirs.map(async (subdir) => {
    const res = resolve(dir, subdir);
    return (await stat(res)).isDirectory() ? getFiles(res) : res;
  }));
  return files.reduce((a, f) => a.concat(f), []);
}

使用

getFiles(__dirname)
  .then(files => console.log(files))
  .catch(e => console.error(e));

节点 10.10+

更新到节点10+,甚至更多的whizbang:

const { resolve } = require('path');
const { readdir } = require('fs').promises;

async function getFiles(dir) {
  const dirents = await readdir(dir, { withFileTypes: true });
  const files = await Promise.all(dirents.map((dirent) => {
    const res = resolve(dir, dirent.name);
    return dirent.isDirectory() ? getFiles(res) : res;
  }));
  return Array.prototype.concat(...files);
}

请注意,从节点11.15.0开始,您可以使用files.flat()而不是array. prototype.concat(…files)来扁平化files数组。

11 +节点

如果你想让所有人都大吃一惊,你可以使用下面使用异步迭代器的版本。除了非常酷之外,它还允许使用者每次提取一个结果,这使得它更适合于真正大的目录。

const { resolve } = require('path');
const { readdir } = require('fs').promises;

async function* getFiles(dir) {
  const dirents = await readdir(dir, { withFileTypes: true });
  for (const dirent of dirents) {
    const res = resolve(dir, dirent.name);
    if (dirent.isDirectory()) {
      yield* getFiles(res);
    } else {
      yield res;
    }
  }
}

用法发生了变化,因为返回类型现在是异步迭代器而不是promise

;(async () => {
  for await (const f of getFiles('.')) {
    console.log(f);
  }
})()

如果有人感兴趣,我在这里写了更多关于异步迭代器的文章:https://qwtel.com/posts/software/async-generators-in-the-wild/

其他回答

因为每个人都应该写自己的,所以我写了一个。

步行(dir, cb, endCb) cb(文件) 零endCb (err |)

module.exports = walk;

function walk(dir, cb, endCb) {
  var fs = require('fs');
  var path = require('path');

  fs.readdir(dir, function(err, files) {
    if (err) {
      return endCb(err);
    }

    var pending = files.length;
    if (pending === 0) {
      endCb(null);
    }
    files.forEach(function(file) {
      fs.stat(path.join(dir, file), function(err, stats) {
        if (err) {
          return endCb(err)
        }

        if (stats.isDirectory()) {
          walk(path.join(dir, file), cb, function() {
            pending--;
            if (pending === 0) {
              endCb(null);
            }
          });
        } else {
          cb(path.join(dir, file));
          pending--;
          if (pending === 0) {
            endCb(null);
          }
        }
      })
    });

  });
}

用递归

var fs = require('fs')
var path = process.cwd()
var files = []

var getFiles = function(path, files){
    fs.readdirSync(path).forEach(function(file){
        var subpath = path + '/' + file;
        if(fs.lstatSync(subpath).isDirectory()){
            getFiles(subpath, files);
        } else {
            files.push(path + '/' + file);
        }
    });     
}

调用

getFiles(path, files)
console.log(files) // will log all files in directory

谁想要一个公认答案的同步替代方案(我知道我做过):

var fs = require('fs');
var path = require('path');
var walk = function(dir) {
    let results = [], err = null, list;
    try {
        list = fs.readdirSync(dir)
    } catch(e) {
        err = e.toString();
    }
    if (err) return err;
    var i = 0;
    return (function next() {
        var file = list[i++];

        if(!file) return results;
        file = path.resolve(dir, file);
        let stat = fs.statSync(file);
        if (stat && stat.isDirectory()) {
          let res = walk(file);
          results = results.concat(res);
          return next();
        } else {
          results.push(file);
           return next();
        }

    })();

};

console.log(
    walk("./")
)

香草ES6 +异步/等待+小和可读

我没有在这篇文章中找到我想要的答案;在不同的答案中有一些相似的元素,但我只想要一些简单易读的东西。

为了防止它在未来帮助到任何人(比如几个月后的我自己),这就是我最终使用的:

const { readdir } = require('fs/promises');
const { join } = require('path');

const readdirRecursive = async dir => {
  const files = await readdir( dir, { withFileTypes: true } );

  const paths = files.map( async file => {
    const path = join( dir, file.name );

    if ( file.isDirectory() ) return await readdirRecursive( path );

    return path;
  } );

  return ( await Promise.all( paths ) ).flat( Infinity );
}

module.exports = {
  readdirRecursive,
}

There are basically two ways of accomplishing this. In an async environment you'll notice that there are two kinds of loops: serial and parallel. A serial loop waits for one iteration to complete before it moves onto the next iteration - this guarantees that every iteration of the loop completes in order. In a parallel loop, all the iterations are started at the same time, and one may complete before another, however, it is much faster than a serial loop. So in this case, it's probably better to use a parallel loop because it doesn't matter what order the walk completes in, just as long as it completes and returns the results (unless you want them in order).

一个平行循环看起来是这样的:

var fs = require('fs');
var path = require('path');
var walk = function(dir, done) {
  var results = [];
  fs.readdir(dir, function(err, list) {
    if (err) return done(err);
    var pending = list.length;
    if (!pending) return done(null, results);
    list.forEach(function(file) {
      file = path.resolve(dir, file);
      fs.stat(file, function(err, stat) {
        if (stat && stat.isDirectory()) {
          walk(file, function(err, res) {
            results = results.concat(res);
            if (!--pending) done(null, results);
          });
        } else {
          results.push(file);
          if (!--pending) done(null, results);
        }
      });
    });
  });
};

一个串行循环看起来像这样:

var fs = require('fs');
var path = require('path');
var walk = function(dir, done) {
  var results = [];
  fs.readdir(dir, function(err, list) {
    if (err) return done(err);
    var i = 0;
    (function next() {
      var file = list[i++];
      if (!file) return done(null, results);
      file = path.resolve(dir, file);
      fs.stat(file, function(err, stat) {
        if (stat && stat.isDirectory()) {
          walk(file, function(err, res) {
            results = results.concat(res);
            next();
          });
        } else {
          results.push(file);
          next();
        }
      });
    })();
  });
};

并且在你的主目录中测试它(警告:如果你的主目录中有很多东西,结果列表将会非常大):

walk(process.env.HOME, function(err, results) {
  if (err) throw err;
  console.log(results);
});

编辑:改进的示例。