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

使用承诺(Q)以函数式风格解决此问题:

var fs = require('fs'),
    fsPath = require('path'),
    Q = require('q');

var walk = function (dir) {
  return Q.ninvoke(fs, 'readdir', dir).then(function (files) {

    return Q.all(files.map(function (file) {

      file = fsPath.join(dir, file);
      return Q.ninvoke(fs, 'lstat', file).then(function (stat) {

        if (stat.isDirectory()) {
          return walk(file);
        } else {
          return [file];
        }
      });
    }));
  }).then(function (files) {
    return files.reduce(function (pre, cur) {
      return pre.concat(cur);
    });
  });
};

它返回一个数组的promise,所以你可以这样使用它:

walk('/home/mypath').then(function (files) { console.log(files); });

其他回答

递归-readdir模块具有此功能。

a .看一下文件模块。它有一个叫walk的函数:

文件。步行(开始,回调) 导航文件树,为每个目录调用回调,传入 (null, dirPath, dirs, files)。

这可能是为你准备的!是的,它是异步的。但是,如果需要的话,我认为您必须自己聚合完整的路径。

B.另一种选择,甚至是我的最爱之一:使用unix find来查找。为什么要再做一件已经编程好的事情呢?也许不是你真正需要的,但仍然值得一试:

var execFile = require('child_process').execFile;
execFile('find', [ 'somepath/' ], function(err, stdout, stderr) {
  var file_list = stdout.split('\n');
  /* now you've got a list with full path file names */
});

Find有一个很好的内置缓存机制,使得后续搜索非常快,只要只有少数文件夹被更改。

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)

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("./")
)

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。