独立承诺实现

在这个例子中，我使用的是when.js承诺库。

var fs = require('fs')
, path = require('path')
, when = require('when')
, nodefn = require('when/node/function');

function walk (directory, includeDir) {
    var results = [];
    return when.map(nodefn.call(fs.readdir, directory), function(file) {
        file = path.join(directory, file);
        return nodefn.call(fs.stat, file).then(function(stat) {
            if (stat.isFile()) { return results.push(file); }
            if (includeDir) { results.push(file + path.sep); }
            return walk(file, includeDir).then(function(filesInDir) {
                results = results.concat(filesInDir);
            });
        });
    }).then(function() {
        return results;
    });
};

walk(__dirname).then(function(files) {
    console.log(files);
}).otherwise(function(error) {
    console.error(error.stack || error);
});

我包含了一个可选参数includeDir，如果设置为true，它将在文件列表中包含目录。

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。

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。

使用bluebird promise.coroutine:

let promise = require('bluebird'),
    PC = promise.coroutine,
    fs = promise.promisifyAll(require('fs'));
let getFiles = PC(function*(dir){
    let files = [];
    let contents = yield fs.readdirAsync(dir);
    for (let i = 0, l = contents.length; i < l; i ++) {
        //to remove dot(hidden) files on MAC
        if (/^\..*/.test(contents[i])) contents.splice(i, 1);
    }
    for (let i = 0, l = contents.length; i < l; i ++) {
        let content = path.resolve(dir, contents[i]);
        let contentStat = yield fs.statAsync(content);
        if (contentStat && contentStat.isDirectory()) {
            let subFiles = yield getFiles(content);
            files = files.concat(subFiles);
        } else {
            files.push(content);
        }
    }
    return files;
});
//how to use
//easy error handling in one place
getFiles(your_dir).then(console.log).catch(err => console.log(err));

另一个很好的npm包是glob。

npm公司

它非常强大，应该能满足你所有的递归需求。

编辑:

实际上我对glob不是很满意，所以我创建了readdirp。

我非常有信心，它的API使得递归地查找文件和目录以及应用特定的过滤器非常容易。

阅读它的文档，以更好地了解它的功能和安装方式:

NPM安装readdirp

这是一个简单的同步递归解决方案

const fs = require('fs')

const getFiles = path => {
    const files = []
    for (const file of fs.readdirSync(path)) {
        const fullPath = path + '/' + file
        if(fs.lstatSync(fullPath).isDirectory())
            getFiles(fullPath).forEach(x => files.push(file + '/' + x))
        else files.push(file)
    }
    return files
}

用法:

const files = getFiles(process.cwd())

console.log(files)

您可以异步地编写它，但是没有必要。只需确保输入目录存在并且可以访问。