Question

我需要浏览一个目录及其所有子目录。我可以通过同步递归轻松探索目录：

use failure::Error;
use std::fs;
use std::path::Path;

fn main() -> Result<(), Error> {
    visit(Path::new("."))
}

fn visit(path: &Path) -> Result<(), Error> {
    for e in fs::read_dir(path)? {
        let e = e?;
        let path = e.path();
        if path.is_dir() {
            visit(&path)?;
        } else if path.is_file() {
            println!("File: {:?}", path);
        }
    }
    Ok(())
}

当我尝试使用 tokio_fs 以异步方式执行相同操作时：

use failure::Error; // 0.1.6
use futures::Future; // 0.1.29
use std::path::PathBuf;
use tokio::{fs, prelude::*}; // 0.1.22

fn visit(path: PathBuf) -> impl Future<Item = (), Error = Error> {
    let task = fs::read_dir(path)
        .flatten_stream()
        .for_each(|entry| {
            println!("{:?}", entry.path());
            let path = entry.path();
            if path.is_dir() {
                let task = visit(entry.path());
                tokio::spawn(task.map_err(drop));
            }
            future::ok(())
        })
        .map_err(Error::from);

    task
}

Playground

我收到以下错误：

error[E0391]: cycle detected when processing `visit::{{opaque}}#0`
 --> src/lib.rs:6:28
  |
6 | fn visit(path: PathBuf) -> impl Future<Item = (), Error = Error> {
  |                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  |
note: ...which requires processing `visit`...
 --> src/lib.rs:6:1
  |
6 | fn visit(path: PathBuf) -> impl Future<Item = (), Error = Error> {
  | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  = note: ...which requires evaluating trait selection obligation `futures::future::map_err::MapErr<impl futures::future::Future, fn(failure::error::Error) {std::mem::drop::<failure::error::Error>}>: std::marker::Send`...
  = note: ...which again requires processing `visit::{{opaque}}#0`, completing the cycle
note: cycle used when checking item types in top-level module
 --> src/lib.rs:1:1
  |
1 | / use failure::Error; // 0.1.6
2 | | use futures::Future; // 0.1.29
3 | | use std::path::PathBuf;
4 | | use tokio::{fs, prelude::*}; // 0.1.22
... |
20| |     task
21| | }
  | |_^

error[E0391]: cycle detected when processing `visit::{{opaque}}#0`
 --> src/lib.rs:6:28
  |
6 | fn visit(path: PathBuf) -> impl Future<Item = (), Error = Error> {
  |                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  |
note: ...which requires processing `visit`...
 --> src/lib.rs:6:1
  |
6 | fn visit(path: PathBuf) -> impl Future<Item = (), Error = Error> {
  | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  = note: ...which again requires processing `visit::{{opaque}}#0`, completing the cycle
note: cycle used when checking item types in top-level module
 --> src/lib.rs:1:1
  |
1 | / use failure::Error; // 0.1.6
2 | | use futures::Future; // 0.1.29
3 | | use std::path::PathBuf;
4 | | use tokio::{fs, prelude::*}; // 0.1.22
... |
20| |     task
21| | }
  | |_^

在传播所有错误的同时异步探索目录及其子目录的正确方法是什么？

Answer 1

您的代码有两个错误：

首先，函数 returning impl Trait 当前不能递归，因为实际类型 returned 将取决于它自己。

要使您的示例正常工作，您需要 return 大小适中的类型。简单的候选是一个trait对象，即一个Box<dyn Future<...>>:

fn visit(path: PathBuf) -> Box<dyn Future<Item = (), Error = Error>> {
    // ...
            let task = visit(entry.path());
            tokio::spawn(task.map_err(drop));
    // ...

    Box::new(task)
}

还有你的第二个错误：

error[E0277]: `dyn futures::future::Future<Item = (), Error = failure::error::Error>` cannot be sent between threads safely
   --> src/lib.rs:14:30
    |
14  |                 tokio::spawn(task.map_err(drop));
    |                              ^^^^^^^^^^^^^^^^^^ `dyn futures::future::Future<Item = (), Error = failure::error::Error>` cannot be sent between threads safely
    | 
   ::: /root/.cargo/registry/src/github.com-1ecc6299db9ec823/tokio-0.1.22/src/executor/mod.rs:131:52
    |
131 | where F: Future<Item = (), Error = ()> + 'static + Send
    |                                                    ---- required by this bound in `tokio::executor::spawn`
    |
    = help: the trait `std::marker::Send` is not implemented for `dyn futures::future::Future<Item = (), Error = failure::error::Error>`
    = note: required because of the requirements on the impl of `std::marker::Send` for `std::ptr::Unique<dyn futures::future::Future<Item = (), Error = failure::error::Error>>`
    = note: required because it appears within the type `std::boxed::Box<dyn futures::future::Future<Item = (), Error = failure::error::Error>>`
    = note: required because it appears within the type `futures::future::map_err::MapErr<std::boxed::Box<dyn futures::future::Future<Item = (), Error = failure::error::Error>>, fn(failure::error::Error) {std::mem::drop::<failure::error::Error>}>`

这意味着您的特征对象不是 Send，因此无法使用 tokio::spawn() 安排在另一个线程中执行。幸运的是，这很容易解决：只需将 + Send 添加到您的特征对象中：

fn visit(path: PathBuf) -> Box<dyn Future<Item = (), Error = Error> + Send> {
    //...
}

请参阅 Playground 中的完整代码。

Answer 2

我会对做一些修改：

Return 来自函数的 Stream，允许调用者对给定的文件条目执行他们需要的操作。
Return impl Stream 而不是 Box<dyn Stream>。这为实施提供了更大的灵活性。例如，可以创建使用内部堆栈而不是效率较低的递归类型的自定义类型。
Return io::Error 允许用户处理任何错误的功能。
接受 impl Into<PathBuf> 以允许更好的 API。
创建一个在其 API.

期货 0.3 / Tokio 0.2

在这个版本中，我避免了深度递归调用，保留了本地访问路径堆栈 (to_visit)。

use futures::{stream, Stream, StreamExt}; // 0.3.1
use std::{io, path::PathBuf};
use tokio::fs::{self, DirEntry}; // 0.2.4

fn visit(path: impl Into<PathBuf>) -> impl Stream<Item = io::Result<DirEntry>> + Send + 'static {
    async fn one_level(path: PathBuf, to_visit: &mut Vec<PathBuf>) -> io::Result<Vec<DirEntry>> {
        let mut dir = fs::read_dir(path).await?;
        let mut files = Vec::new();

        while let Some(child) = dir.next_entry().await? {
            if child.metadata().await?.is_dir() {
                to_visit.push(child.path());
            } else {
                files.push(child)
            }
        }

        Ok(files)
    }

    stream::unfold(vec![path.into()], |mut to_visit| {
        async {
            let path = to_visit.pop()?;
            let file_stream = match one_level(path, &mut to_visit).await {
                Ok(files) => stream::iter(files).map(Ok).left_stream(),
                Err(e) => stream::once(async { Err(e) }).right_stream(),
            };

            Some((file_stream, to_visit))
        }
    })
    .flatten()
}

#[tokio::main]
async fn main() {
    let root_path = std::env::args().nth(1).expect("One argument required");
    let paths = visit(root_path);

    paths
        .for_each(|entry| {
            async {
                match entry {
                    Ok(entry) => println!("visiting {:?}", entry),
                    Err(e) => eprintln!("encountered an error: {}", e),
                }
            }
        })
        .await;
}

期货 0.1 / Tokio 0.1

use std::path::PathBuf;
use tokio::{fs, prelude::*}; // 0.1.22
use tokio_fs::DirEntry; // 1.0.6

fn visit(
    path: impl Into<PathBuf>,
) -> impl Stream<Item = DirEntry, Error = std::io::Error> + Send + 'static {
    fn visit_inner(
        path: PathBuf,
    ) -> Box<dyn Stream<Item = DirEntry, Error = std::io::Error> + Send + 'static> {
        Box::new({
            fs::read_dir(path)
                .flatten_stream()
                .map(|entry| {
                    let path = entry.path();
                    if path.is_dir() {
                        // Optionally include `entry` if you want to
                        // include directories in the resulting
                        // stream.
                        visit_inner(path)
                    } else {
                        Box::new(stream::once(Ok(entry)))
                    }
                })
                .flatten()
        })
    }

    visit_inner(path.into())
}

fn main() {
    tokio::run({
        let root_path = std::env::args().nth(1).expect("One argument required");
        let paths = visit(root_path);

        paths
            .then(|entry| {
                match entry {
                    Ok(entry) => println!("visiting {:?}", entry),
                    Err(e) => eprintln!("encountered an error: {}", e),
                };

                Ok(())
            })
            .for_each(|_| Ok(()))
    });
}

另请参阅：

如何异步浏览目录及其子目录？

How to asynchronously explore a directory and its sub-directories?

asynchronous

rust

filesystems

rust-tokio

期货 0.3 / Tokio 0.2

期货 0.1 / Tokio 0.1