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

有一个名为cup-readdir的新模块,可以快速递归地搜索目录。它使用异步承诺,在处理深层目录结构时性能优于许多流行的模块。

它可以返回数组中的所有文件,并根据它们的属性对它们进行排序,但缺乏文件过滤和进入符号链接目录等功能。这对于只想从目录中获取每个文件的大型项目非常有用。这里是他们项目主页的链接。

其他回答

这是另一个实现。上述解决方案都没有任何限制,因此如果您的目录结构很大,它们都会崩溃并最终耗尽资源。

var async = require('async');
var fs = require('fs');
var resolve = require('path').resolve;

var scan = function(path, concurrency, callback) {
    var list = [];

    var walker = async.queue(function(path, callback) {
        fs.stat(path, function(err, stats) {
            if (err) {
                return callback(err);
            } else {
                if (stats.isDirectory()) {
                    fs.readdir(path, function(err, files) {
                        if (err) {
                            callback(err);
                        } else {
                            for (var i = 0; i < files.length; i++) {
                                walker.push(resolve(path, files[i]));
                            }
                            callback();
                        }
                    });
                } else {
                    list.push(path);
                    callback();
                }
            }
        });
    }, concurrency);

    walker.push(path);

    walker.drain = function() {
        callback(list);
    }
};

使用50的并发工作得非常好,并且几乎和小型目录结构的简单实现一样快。

看看装载机 https://npmjs.org/package/loaddir

npm无处不在

  loaddir = require('loaddir')

  allJavascripts = []
  loaddir({
    path: __dirname + '/public/javascripts',
    callback: function(){  allJavascripts.push(this.relativePath + this.baseName); }
  })

如果还需要扩展名,可以使用fileName而不是baseName。

一个额外的好处是,它也会监视文件,并再次调用回调。有大量的配置选项使它非常灵活。

我只是在短时间内用加载器从红宝石重造了守卫宝石

异步

const fs = require('fs')
const path = require('path')

const readdir = (p, done, a = [], i = 0) => fs.readdir(p, (e, d = []) =>
  d.map(f => readdir(a[a.push(path.join(p, f)) - 1], () =>
    ++i == d.length && done(a), a)).length || done(a))

readdir(__dirname, console.log)

Sync

const fs = require('fs')
const path = require('path')

const readdirSync = (p, a = []) => {
  if (fs.statSync(p).isDirectory())
    fs.readdirSync(p).map(f => readdirSync(a[a.push(path.join(p, f)) - 1], a))
  return a
}

console.log(readdirSync(__dirname))

异步读

function readdir (currentPath, done, allFiles = [], i = 0) {
  fs.readdir(currentPath, function (e, directoryFiles = []) {
    if (!directoryFiles.length)
      return done(allFiles)
    directoryFiles.map(function (file) {
      var joinedPath = path.join(currentPath, file)
      allFiles.push(joinedPath)
      readdir(joinedPath, function () {
        i = i + 1
        if (i == directoryFiles.length)
          done(allFiles)}
      , allFiles)
    })
  })
}

readdir(__dirname, console.log)

注意:两个版本都将跟随符号链接(与原始fs.readdir相同)

短小、现代、高效:

import {readdir} from 'node:fs/promises'
import {join} from 'node:path'

const deepReadDir = async (dirPath) => await Promise.all(
  (await readdir(dirPath, {withFileTypes: true})).map(async (dirent) => {
    const path = join(dirPath, dirent.name)
    return dirent.isDirectory() ? await deepReadDir(path) : path
  }),
)

特别感谢函数提示使用{withFileTypes: true}。


这将自动将每个嵌套路径折叠成一个新的嵌套数组。例如,如果:

await deepReadDir('src')

返回如下内容:

[
  [
    'src/client/api.js',
    'src/client/http-constants.js',
    'src/client/index.html',
    'src/client/index.js',
    [ 'src/client/res/favicon.ico' ],
    'src/client/storage.js'
  ],
  [ 'src/crypto/keygen.js' ],
  'src/discover.js',
  [
    'src/mutations/createNewMutation.js',
    'src/mutations/newAccount.js',
    'src/mutations/transferCredit.js',
    'src/mutations/updateApp.js'
  ],
  [
    'src/server/authentication.js',
    'src/server/handlers.js',
    'src/server/quick-response.js',
    'src/server/server.js',
    'src/server/static-resources.js'
  ],
  [ 'src/util/prompt.js', 'src/util/safeWriteFile.js' ],
  'src/util.js'
]

但如果你想,你可以很容易地把它压平:

(await deepReadDir('src')).flat(Number.POSITIVE_INFINITY)
[
  'src/client/api.js',
  'src/client/http-constants.js',
  'src/client/index.html',
  'src/client/index.js',
  'src/client/res/favicon.ico',
  'src/client/storage.js',
  'src/crypto/keygen.js',
  'src/discover.js',
  'src/mutations/createNewMutation.js',
  'src/mutations/newAccount.js',
  'src/mutations/transferCredit.js',
  'src/mutations/updateApp.js',
  'src/server/authentication.js',
  'src/server/handlers.js',
  'src/server/quick-response.js',
  'src/server/server.js',
  'src/server/static-resources.js',
  'src/util/prompt.js',
  'src/util/safeWriteFile.js',
  'src/util.js'
]

这就是我的答案。希望它能帮助到一些人。

我的重点是使搜索例程可以停在任何地方,对于找到的文件,告诉原始路径的相对深度。

var _fs = require('fs');
var _path = require('path');
var _defer = process.nextTick;

// next() will pop the first element from an array and return it, together with
// the recursive depth and the container array of the element. i.e. If the first
// element is an array, it'll be dug into recursively. But if the first element is
// an empty array, it'll be simply popped and ignored.
// e.g. If the original array is [1,[2],3], next() will return [1,0,[[2],3]], and
// the array becomes [[2],3]. If the array is [[[],[1,2],3],4], next() will return
// [1,2,[2]], and the array becomes [[[2],3],4].
// There is an infinity loop `while(true) {...}`, because I optimized the code to
// make it a non-recursive version.
var next = function(c) {
    var a = c;
    var n = 0;
    while (true) {
        if (a.length == 0) return null;
        var x = a[0];
        if (x.constructor == Array) {
            if (x.length > 0) {
                a = x;
                ++n;
            } else {
                a.shift();
                a = c;
                n = 0;
            }
        } else {
            a.shift();
            return [x, n, a];
        }
    }
}

// cb is the callback function, it have four arguments:
//    1) an error object if any exception happens;
//    2) a path name, may be a directory or a file;
//    3) a flag, `true` means directory, and `false` means file;
//    4) a zero-based number indicates the depth relative to the original path.
// cb should return a state value to tell whether the searching routine should
// continue: `true` means it should continue; `false` means it should stop here;
// but for a directory, there is a third state `null`, means it should do not
// dig into the directory and continue searching the next file.
var ls = function(path, cb) {
    // use `_path.resolve()` to correctly handle '.' and '..'.
    var c = [ _path.resolve(path) ];
    var f = function() {
        var p = next(c);
        p && s(p);
    };
    var s = function(p) {
        _fs.stat(p[0], function(err, ss) {
            if (err) {
                // use `_defer()` to turn a recursive call into a non-recursive call.
                cb(err, p[0], null, p[1]) && _defer(f);
            } else if (ss.isDirectory()) {
                var y = cb(null, p[0], true, p[1]);
                if (y) r(p);
                else if (y == null) _defer(f);
            } else {
                cb(null, p[0], false, p[1]) && _defer(f);
            }
        });
    };
    var r = function(p) {
        _fs.readdir(p[0], function(err, files) {
            if (err) {
                cb(err, p[0], true, p[1]) && _defer(f);
            } else {
                // not use `Array.prototype.map()` because we can make each change on site.
                for (var i = 0; i < files.length; i++) {
                    files[i] = _path.join(p[0], files[i]);
                }
                p[2].unshift(files);
                _defer(f);
            }
        });
    }
    _defer(f);
};

var printfile = function(err, file, isdir, n) {
    if (err) {
        console.log('-->   ' + ('[' + n + '] ') + file + ': ' + err);
        return true;
    } else {
        console.log('... ' + ('[' + n + '] ') + (isdir ? 'D' : 'F') + ' ' + file);
        return true;
    }
};

var path = process.argv[2];
ls(path, printfile);