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

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。

现代基于promise的读dir递归版本:

const fs = require('fs');
const path = require('path');

const readDirRecursive = async (filePath) => {
    const dir = await fs.promises.readdir(filePath);
    const files = await Promise.all(dir.map(async relativePath => {
        const absolutePath = path.join(filePath, relativePath);
        const stat = await fs.promises.lstat(absolutePath);

        return stat.isDirectory() ? readDirRecursive(absolutePath) : absolutePath;
    }));

    return files.flat();
}

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("./")
)

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));