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

为了以防有人发现它有用,我还整理了一个同步版本。

var walk = function(dir) {
    var results = [];
    var list = fs.readdirSync(dir);
    list.forEach(function(file) {
        file = dir + '/' + file;
        var stat = fs.statSync(file);
        if (stat && stat.isDirectory()) { 
            /* Recurse into a subdirectory */
            results = results.concat(walk(file));
        } else { 
            /* Is a file */
            results.push(file);
        }
    });
    return results;
}

提示:在筛选时使用更少的资源。这个函数本身的过滤器。例如:替换results.push(文件);下面的代码。根据需要调整:

    file_type = file.split(".").pop();
    file_name = file.split(/(\\|\/)/g).pop();
    if (file_type == "json") results.push(file);

其他回答

查看final-fs库。它提供了一个readdirRecursive函数:

ffs.readdirRecursive(dirPath, true, 'my/initial/path')
    .then(function (files) {
        // in the `files` variable you've got all the files
    })
    .otherwise(function (err) {
        // something went wrong
    });

另一个答案,但这次使用的是TypeScript:

/** * Recursively walk a directory asynchronously and obtain all file names (with full path). * * @param dir Folder name you want to recursively process * @param done Callback function, returns all files with full path. * @param filter Optional filter to specify which files to include, * e.g. for json files: (f: string) => /.json$/.test(f) */ const walk = ( dir: string, done: (err: Error | null, results ? : string[]) => void, filter ? : (f: string) => boolean ) => { let results: string[] = []; fs.readdir(dir, (err: Error, list: string[]) => { if (err) { return done(err); } let pending = list.length; if (!pending) { return done(null, results); } list.forEach((file: string) => { file = path.resolve(dir, file); fs.stat(file, (err2, stat) => { if (stat && stat.isDirectory()) { walk(file, (err3, res) => { if (res) { results = results.concat(res); } if (!--pending) { done(null, results); } }, filter); } else { if (typeof filter === 'undefined' || (filter && filter(file))) { results.push(file); } if (!--pending) { done(null, results); } } }); }); }); };

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。

这是我如何使用nodejs的fs。递归搜索目录的Readdir函数。

const fs = require('fs');
const mime = require('mime-types');
const readdirRecursivePromise = path => {
    return new Promise((resolve, reject) => {
        fs.readdir(path, (err, directoriesPaths) => {
            if (err) {
                reject(err);
            } else {
                if (directoriesPaths.indexOf('.DS_Store') != -1) {
                    directoriesPaths.splice(directoriesPaths.indexOf('.DS_Store'), 1);
                }
                directoriesPaths.forEach((e, i) => {
                    directoriesPaths[i] = statPromise(`${path}/${e}`);
                });
                Promise.all(directoriesPaths).then(out => {
                    resolve(out);
                }).catch(err => {
                    reject(err);
                });
            }
        });
    });
};
const statPromise = path => {
    return new Promise((resolve, reject) => {
        fs.stat(path, (err, stats) => {
            if (err) {
                reject(err);
            } else {
                if (stats.isDirectory()) {
                    readdirRecursivePromise(path).then(out => {
                        resolve(out);
                    }).catch(err => {
                        reject(err);
                    });
                } else if (stats.isFile()) {
                    resolve({
                        'path': path,
                        'type': mime.lookup(path)
                    });
                } else {
                    reject(`Error parsing path: ${path}`);
                }
            }
        });
    });
};
const flatten = (arr, result = []) => {
    for (let i = 0, length = arr.length; i < length; i++) {
        const value = arr[i];
        if (Array.isArray(value)) {
            flatten(value, result);
        } else {
            result.push(value);
        }
    }
    return result;
};

假设在节点项目根目录中有一个名为“/database”的路径。一旦这个承诺被解决,它应该吐出'/database'下的每个文件的数组。

readdirRecursivePromise('database').then(out => {
    console.log(flatten(out));
}).catch(err => {
    console.log(err);
});

香草ES6 +异步/等待+小和可读

我没有在这篇文章中找到我想要的答案;在不同的答案中有一些相似的元素,但我只想要一些简单易读的东西。

为了防止它在未来帮助到任何人(比如几个月后的我自己),这就是我最终使用的:

const { readdir } = require('fs/promises');
const { join } = require('path');

const readdirRecursive = async dir => {
  const files = await readdir( dir, { withFileTypes: true } );

  const paths = files.map( async file => {
    const path = join( dir, file.name );

    if ( file.isDirectory() ) return await readdirRecursive( path );

    return path;
  } );

  return ( await Promise.all( paths ) ).flat( Infinity );
}

module.exports = {
  readdirRecursive,
}