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']
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
有一个名为cup-readdir的新模块,可以快速递归地搜索目录。它使用异步承诺,在处理深层目录结构时性能优于许多流行的模块。
它可以返回数组中的所有文件,并根据它们的属性对它们进行排序,但缺乏文件过滤和进入符号链接目录等功能。这对于只想从目录中获取每个文件的大型项目非常有用。这里是他们项目主页的链接。
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。
这就是我的答案。希望它能帮助到一些人。
我的重点是使搜索例程可以停在任何地方,对于找到的文件,告诉原始路径的相对深度。
var _fs = require('fs');
var _path = require('path');
var _defer = process.nextTick;
// next() will pop the first element from an array and return it, together with
// the recursive depth and the container array of the element. i.e. If the first
// element is an array, it'll be dug into recursively. But if the first element is
// an empty array, it'll be simply popped and ignored.
// e.g. If the original array is [1,[2],3], next() will return [1,0,[[2],3]], and
// the array becomes [[2],3]. If the array is [[[],[1,2],3],4], next() will return
// [1,2,[2]], and the array becomes [[[2],3],4].
// There is an infinity loop `while(true) {...}`, because I optimized the code to
// make it a non-recursive version.
var next = function(c) {
var a = c;
var n = 0;
while (true) {
if (a.length == 0) return null;
var x = a[0];
if (x.constructor == Array) {
if (x.length > 0) {
a = x;
++n;
} else {
a.shift();
a = c;
n = 0;
}
} else {
a.shift();
return [x, n, a];
}
}
}
// cb is the callback function, it have four arguments:
// 1) an error object if any exception happens;
// 2) a path name, may be a directory or a file;
// 3) a flag, `true` means directory, and `false` means file;
// 4) a zero-based number indicates the depth relative to the original path.
// cb should return a state value to tell whether the searching routine should
// continue: `true` means it should continue; `false` means it should stop here;
// but for a directory, there is a third state `null`, means it should do not
// dig into the directory and continue searching the next file.
var ls = function(path, cb) {
// use `_path.resolve()` to correctly handle '.' and '..'.
var c = [ _path.resolve(path) ];
var f = function() {
var p = next(c);
p && s(p);
};
var s = function(p) {
_fs.stat(p[0], function(err, ss) {
if (err) {
// use `_defer()` to turn a recursive call into a non-recursive call.
cb(err, p[0], null, p[1]) && _defer(f);
} else if (ss.isDirectory()) {
var y = cb(null, p[0], true, p[1]);
if (y) r(p);
else if (y == null) _defer(f);
} else {
cb(null, p[0], false, p[1]) && _defer(f);
}
});
};
var r = function(p) {
_fs.readdir(p[0], function(err, files) {
if (err) {
cb(err, p[0], true, p[1]) && _defer(f);
} else {
// not use `Array.prototype.map()` because we can make each change on site.
for (var i = 0; i < files.length; i++) {
files[i] = _path.join(p[0], files[i]);
}
p[2].unshift(files);
_defer(f);
}
});
}
_defer(f);
};
var printfile = function(err, file, isdir, n) {
if (err) {
console.log('--> ' + ('[' + n + '] ') + file + ': ' + err);
return true;
} else {
console.log('... ' + ('[' + n + '] ') + (isdir ? 'D' : 'F') + ' ' + file);
return true;
}
};
var path = process.argv[2];
ls(path, printfile);
使用node-dir可以生成您想要的输出
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 can iterate that array
files.forEach(function(path) {
action(null, path);
})
});
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))