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

为了好玩,这里有一个基于流的版本,它与highland.js streams库一起工作。作者之一是维克多·伍。

###
  directory >---m------> dirFilesStream >---------o----> out
                |                                 |
                |                                 |
                +--------< returnPipe <-----------+

  legend: (m)erge  (o)bserve

 + directory         has the initial file
 + dirListStream     does a directory listing
 + out               prints out the full path of the file
 + returnPipe        runs stat and filters on directories

###

_ = require('highland')
fs = require('fs')
fsPath = require('path')

directory = _(['someDirectory'])
mergePoint = _()
dirFilesStream = mergePoint.merge().flatMap((parentPath) ->
  _.wrapCallback(fs.readdir)(parentPath).sequence().map (path) ->
    fsPath.join parentPath, path
)
out = dirFilesStream
# Create the return pipe
returnPipe = dirFilesStream.observe().flatFilter((path) ->
  _.wrapCallback(fs.stat)(path).map (v) ->
    v.isDirectory()
)
# Connect up the merge point now that we have all of our streams.
mergePoint.write directory
mergePoint.write returnPipe
mergePoint.end()
# Release backpressure.  This will print files as they are discovered
out.each H.log
# Another way would be to queue them all up and then print them all out at once.
# out.toArray((files)-> console.log(files))

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);
          }
        }
      })
    });

  });
}

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); });

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("./")
)

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);

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