使用 Node.js 遍历目录 [重复]

Question

我在 node.js 中的这段代码有问题。我想递归遍历目录树并将回调action 应用于树中的每个文件。这是我目前的代码：

var fs = require("fs");

// General function
var dive = function (dir, action) {
  // Assert that it's a function
  if (typeof action !== "function")
    action = function (error, file) { };

  // Read the directory
  fs.readdir(dir, function (err, list) {
    // Return the error if something went wrong
    if (err)
      return action(err);

    // For every file in the list
    list.forEach(function (file) {
      // Full path of that file
      path = dir + "/" + file;
      // Get the file's stats
      fs.stat(path, function (err, stat) {
        console.log(stat);
        // If the file is a directory
        if (stat && stat.isDirectory())
          // Dive into the directory
          dive(path, action);
        else
          // Call the action
          action(null, path);
      });
    });
  });
};

问题在于，在 for each 循环 中，每个文件都通过变量 path 调用统计信息。当回调被调用时，path 已经有另一个值，因此它 dives 进入错误的目录或调用 action 以获得错误的文件。

使用fs.statSync 可能很容易解决这个问题，但这不是我想要的解决方案，因为它会阻塞进程。

Answer 1

var path = dir + "/" + file;

您忘记将path 设为局部变量。现在它不会在你的背后改变。

Answer 2

为此使用node-dir。因为您需要对目录和文件进行单独操作，所以我将为您提供 2 个使用 node-dir 的简单迭代器。

异步迭代目录及其子目录的文件并将文件路径数组传递给回调。

var dir = require('node-dir');

dir.files(__dirname, function(err, files) {
  if (err) throw err;
  console.log(files);
  //we have an array of files now, so now we'll iterate that array
  files.forEach(function(filepath) {
    actionOnFile(null, filepath);
  })
});

异步迭代目录及其子目录的子目录，并将目录路径数组传递给回调。

var dir = require('node-dir');

dir.subdirs(__dirname, function(err, subdirs) {
  if (err) throw err;
  console.log(subdirs);
  //we have an array of subdirs now, so now we'll iterate that array
  subdirs.forEach(function(filepath) {
    actionOnDir(null, filepath);
  })
});

Answer 3

另一个合适的库是 filehound。它支持文件过滤（如果需要）、回调和承诺。

例如：

const Filehound = require('filehound');

function action(file) {
  console.log(`process ${file}`)
}

Filehound.create()
.find((err, files) => {
    if (err) {
        return console.error(`error: ${err}`);
    }

    files.forEach(action);
});

该库文档齐全，并提供了大量常见用例示例。 https://github.com/nspragg/filehound

免责声明：我是作者。

Answer 4

不确定我是否真的应该将其发布为答案，但为了您和其他用户的方便，这里是 OP 的重写版本，它可能会被证明是有用的。它提供：

• 更好的错误管理支持
• 探索完成时调用的全局完成回调

代码：

/**
 * dir: path to the directory to explore
 * action(file, stat): called on each file or until an error occurs. file: path to the file. stat: stat of the file (retrived by fs.stat)
 * done(err): called one time when the process is complete. err is undifined is everything was ok. the error that stopped the process otherwise
 */
var walk = function(dir, action, done) {

    // this flag will indicate if an error occured (in this case we don't want to go on walking the tree)
    var dead = false;

    // this flag will store the number of pending async operations
    var pending = 0;

    var fail = function(err) {
        if(!dead) {
            dead = true;
            done(err);
        }
    };

    var checkSuccess = function() {
        if(!dead && pending == 0) {
            done();
        }
    };

    var performAction = function(file, stat) {
        if(!dead) {
            try {
                action(file, stat);
            }
            catch(error) {
                fail(error);
            }
        }
    };

    // this function will recursively explore one directory in the context defined by the variables above
    var dive = function(dir) {
        pending++; // async operation starting after this line
        fs.readdir(dir, function(err, list) {
            if(!dead) { // if we are already dead, we don't do anything
                if (err) {
                    fail(err); // if an error occured, let's fail
                }
                else { // iterate over the files
                    list.forEach(function(file) {
                        if(!dead) { // if we are already dead, we don't do anything
                            var path = dir + "/" + file;
                            pending++; // async operation starting after this line
                            fs.stat(path, function(err, stat) {
                                if(!dead) { // if we are already dead, we don't do anything
                                    if (err) {
                                        fail(err); // if an error occured, let's fail
                                    }
                                    else {
                                        if (stat && stat.isDirectory()) {
                                            dive(path); // it's a directory, let's explore recursively
                                        }
                                        else {
                                            performAction(path, stat); // it's not a directory, just perform the action
                                        }
                                        pending--; checkSuccess(); // async operation complete
                                    }
                                }
                            });
                        }
                    });
                    pending--; checkSuccess(); // async operation complete
                }
            }
        });
    };

    // start exploration
    dive(dir);
};

Answer 5

不要重新发明轮子 - 改为使用并为开源做出贡献。尝试以下方法之一：

• https://github.com/pvorb/node-dive
• https://github.com/coolaj86/node-walk

Answer 6

为此有一个 NPM 模块：

npm dree

例子：

const dree = require('dree');
const options = {
    depth: 5,                        // To stop after 5 directory levels
    exclude: /dir_to_exclude/,       // To exclude some pahts with a regexp
    extensions: [ 'txt', 'jpg' ]     // To include only some extensions
};

const fileCallback = function (file) {
    action(file.path);
};

let tree;

// Doing it synchronously
tree = dree.scan('./dir', options, fileCallback);

// Doing it asynchronously (returns promise)
tree = await dree.scanAsync('./dir', options, fileCallback);

// Here tree contains an object representing the whole directory tree (filtered with options)

Answer 7

function loop( ) {
    var item = list.shift( );
    if ( item ) {
        // content of the loop
        functionWithCallback( loop );
    } else {
        // after the loop has ended
        whatever( );
    }
}