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

短小、现代、高效:

import {readdir} from 'node:fs/promises'
import {join} from 'node:path'

const deepReadDir = async (dirPath) => await Promise.all(
  (await readdir(dirPath, {withFileTypes: true})).map(async (dirent) => {
    const path = join(dirPath, dirent.name)
    return dirent.isDirectory() ? await deepReadDir(path) : path
  }),
)

特别感谢函数提示使用{withFileTypes: true}。


这将自动将每个嵌套路径折叠成一个新的嵌套数组。例如,如果:

await deepReadDir('src')

返回如下内容:

[
  [
    'src/client/api.js',
    'src/client/http-constants.js',
    'src/client/index.html',
    'src/client/index.js',
    [ 'src/client/res/favicon.ico' ],
    'src/client/storage.js'
  ],
  [ 'src/crypto/keygen.js' ],
  'src/discover.js',
  [
    'src/mutations/createNewMutation.js',
    'src/mutations/newAccount.js',
    'src/mutations/transferCredit.js',
    'src/mutations/updateApp.js'
  ],
  [
    'src/server/authentication.js',
    'src/server/handlers.js',
    'src/server/quick-response.js',
    'src/server/server.js',
    'src/server/static-resources.js'
  ],
  [ 'src/util/prompt.js', 'src/util/safeWriteFile.js' ],
  'src/util.js'
]

但如果你想,你可以很容易地把它压平:

(await deepReadDir('src')).flat(Number.POSITIVE_INFINITY)
[
  'src/client/api.js',
  'src/client/http-constants.js',
  'src/client/index.html',
  'src/client/index.js',
  'src/client/res/favicon.ico',
  'src/client/storage.js',
  'src/crypto/keygen.js',
  'src/discover.js',
  'src/mutations/createNewMutation.js',
  'src/mutations/newAccount.js',
  'src/mutations/transferCredit.js',
  'src/mutations/updateApp.js',
  'src/server/authentication.js',
  'src/server/handlers.js',
  'src/server/quick-response.js',
  'src/server/server.js',
  'src/server/static-resources.js',
  'src/util/prompt.js',
  'src/util/safeWriteFile.js',
  'src/util.js'
]

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。

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))

简单,基于异步承诺


const fs = require('fs/promises');
const getDirRecursive = async (dir) => {
    try {
        const items = await fs.readdir(dir);
        let files = [];
        for (const item of items) {
            if ((await fs.lstat(`${dir}/${item}`)).isDirectory()) files = [...files, ...(await getDirRecursive(`${dir}/${item}`))];
            else files.push({file: item, path: `${dir}/${item}`, parents: dir.split("/")});
        }
        return files;
    } catch (e) {
        return e
    }
};

用法:await getDirRecursive("./public");

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);
          }
        }
      })
    });

  });
}