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

下面是完整的工作代码。按您的要求。您可以递归地获取所有文件和文件夹。

var recur = function(dir) {
            fs.readdir(dir,function(err,list){
                list.forEach(function(file){
                    var file2 = path.resolve(dir, file);
                    fs.stat(file2,function(err,stats){
                        if(stats.isDirectory()) {
                            recur(file2);
                        }
                        else {
                            console.log(file2);
                        }
                    })
                })
            });
        };
        recur(path);

在路径中给出你想要搜索的目录路径,如"c:\test"

其他回答

使用async/await,这应该工作:

const FS = require('fs');
const readDir = promisify(FS.readdir);
const fileStat = promisify(FS.stat);

async function getFiles(dir) {
    let files = await readDir(dir);

    let result = files.map(file => {
        let path = Path.join(dir,file);
        return fileStat(path).then(stat => stat.isDirectory() ? getFiles(path) : path);
    });

    return flatten(await Promise.all(result));
}

function flatten(arr) {
    return Array.prototype.concat(...arr);
}

你可以用蓝鸟。许诺或许诺:

/**
 * Returns a function that will wrap the given `nodeFunction`. Instead of taking a callback, the returned function will return a promise whose fate is decided by the callback behavior of the given node function. The node function should conform to node.js convention of accepting a callback as last argument and calling that callback with error as the first argument and success value on the second argument.
 *
 * @param {Function} nodeFunction
 * @returns {Function}
 */
module.exports = function promisify(nodeFunction) {
    return function(...args) {
        return new Promise((resolve, reject) => {
            nodeFunction.call(this, ...args, (err, data) => {
                if(err) {
                    reject(err);
                } else {
                    resolve(data);
                }
            })
        });
    };
};

Node 8+内置了Promisify

请参阅我对生成器方法的其他回答,它可以更快地得到结果。

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。

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。

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。

对于Node 10.3+,这里是一个For -await解决方案:

#!/usr/bin/env node

const FS = require('fs');
const Util = require('util');
const readDir = Util.promisify(FS.readdir);
const Path = require('path');

async function* readDirR(path) {
    const entries = await readDir(path,{withFileTypes:true});
    for(let entry of entries) {
        const fullPath = Path.join(path,entry.name);
        if(entry.isDirectory()) {
            yield* readDirR(fullPath);
        } else {
            yield fullPath;
        }
    }
}

async function main() {
    const start = process.hrtime.bigint();
    for await(const file of readDirR('/mnt/home/media/Unsorted')) {
        console.log(file);
    }
    console.log((process.hrtime.bigint()-start)/1000000n);
}

main().catch(err => {
    console.error(err);
});

这种解决方案的好处是,您可以立即开始处理结果;例如,读取媒体目录中的所有文件需要12秒,但如果我这样做,我可以在几毫秒内得到第一个结果。