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

在这种情况下,Klaw和Klaw -sync值得考虑。这些是node-fs-extra的一部分。

其他回答

我修改了老特雷弗的承诺为蓝鸟工作的基础上的答案

var fs = require('fs'),
    path = require('path'),
    Promise = require('bluebird');

var readdirAsync = Promise.promisify(fs.readdir);
var statAsync = Promise.promisify(fs.stat);
function walkFiles (directory) {
    var results = [];
    return readdirAsync(directory).map(function(file) {
        file = path.join(directory, file);
        return statAsync(file).then(function(stat) {
            if (stat.isFile()) {
                return results.push(file);
            }
            return walkFiles(file).then(function(filesInDir) {
                results = results.concat(filesInDir);
            });
        });
    }).then(function() {
        return results;
    });
}

//use
walkDir(__dirname).then(function(files) {
    console.log(files);
}).catch(function(e) {
    console.error(e); {
});

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。

TypeScript中基于承诺的递归解决方案,使用Array.flat()处理嵌套返回。

import { resolve } from 'path'
import { Dirent } from 'fs'
import * as fs from 'fs'

function getFiles(root: string): Promise<string[]> {
 return fs.promises
   .readdir(root, { withFileTypes: true })
   .then(dirents => {
      const mapToPath = (r: string) => (dirent: Dirent): string => resolve(r, dirent.name)
      const directoryPaths = dirents.filter(a => a.isDirectory()).map(mapToPath(root))
      const filePaths = dirents.filter(a => a.isFile()).map(mapToPath(root))

     return Promise.all<string>([
       ...directoryPaths.map(a => getFiles(a, include)).flat(),
       ...filePaths.map(a => Promise.resolve(a))
     ]).then(a => a.flat())
  })
}

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);

qwtel的答案变体,在TypeScript中

import { resolve } from 'path';
import { readdir } from 'fs/promises';

async function* getFiles(dir: string): AsyncGenerator<string> {
    const entries = await readdir(dir, { withFileTypes: true });
    for (const entry of entries) {
        const res = resolve(dir, entry.name);
        if (entry.isDirectory()) {
            yield* getFiles(res);
        } else {
            yield res;
        }
    }
}