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。

下面是一个获得所有文件包括子目录的递归方法。

const FileSystem = require("fs");
const Path = require("path");

//...

function getFiles(directory) {
    directory = Path.normalize(directory);
    let files = FileSystem.readdirSync(directory).map((file) => directory + Path.sep + file);

    files.forEach((file, index) => {
        if (FileSystem.statSync(file).isDirectory()) {
            Array.prototype.splice.apply(files, [index, 1].concat(getFiles(file)));
        }
    });

    return files;
}

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))

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。

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

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。