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
使用承诺(Q)以函数式风格解决此问题:
var fs = require('fs'),
fsPath = require('path'),
Q = require('q');
var walk = function (dir) {
return Q.ninvoke(fs, 'readdir', dir).then(function (files) {
return Q.all(files.map(function (file) {
file = fsPath.join(dir, file);
return Q.ninvoke(fs, 'lstat', file).then(function (stat) {
if (stat.isDirectory()) {
return walk(file);
} else {
return [file];
}
});
}));
}).then(function (files) {
return files.reduce(function (pre, cur) {
return pre.concat(cur);
});
});
};
它返回一个数组的promise,所以你可以这样使用它:
walk('/home/mypath').then(function (files) { console.log(files); });
其他回答
在这种情况下,Klaw和Klaw -sync值得考虑。这些是node-fs-extra的一部分。
谁想要一个公认答案的同步替代方案(我知道我做过):
var fs = require('fs');
var path = require('path');
var walk = function(dir) {
let results = [], err = null, list;
try {
list = fs.readdirSync(dir)
} catch(e) {
err = e.toString();
}
if (err) return err;
var i = 0;
return (function next() {
var file = list[i++];
if(!file) return results;
file = path.resolve(dir, file);
let stat = fs.statSync(file);
if (stat && stat.isDirectory()) {
let res = walk(file);
results = results.concat(res);
return next();
} else {
results.push(file);
return next();
}
})();
};
console.log(
walk("./")
)
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");
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。