Merge pull request #12 from rbtcollins/readdir

Readdir support #11

Cargo.toml

@@ -14,13 +14,18 @@ version = "0.0.1"
 
 [dependencies]
 cfg-if = "1.0.0"
+cvt = "0.1.1"
 
 [dev-dependencies]
 tempfile = "3.3.0"
 
 [target.'cfg(not(windows))'.dependencies]
-cvt = "0.1.1"
 libc = "0.2.121"
+# Saves nontrivial unsafe and platform specific code (Darwin vs other Unixes,
+# MAX_PATH and more) : consider it weak and something we can remove if expedient
+# later.
+nix = { version = "0.24.2", default-features = false, features = ["dir"] }
+
 
 [target.'cfg(windows)'.dependencies]
 ntapi = "0.3.7"

README.md

@@ -6,7 +6,7 @@ filesystem code, since otherwise the state of the filesystem path that
 operations are executed against can change silently, leading to TOC-TOU race
 conditions. For Unix these calls are readily available in the libc crate, but
 for Windows some more plumbing is needed. This crate provides a unified
-Rust-y interface to these calls.
+Rust-y and safe interface to these calls.
 
 ## MSRV policy
 

src/lib.rs

@@ -14,6 +14,7 @@
 //! unified Rust-y interface to these calls.
 
 use std::{
+    ffi::OsStr,
     fs::File,
     io::{Error, ErrorKind, Result},
     path::Path,
@@ -23,11 +24,11 @@ cfg_if::cfg_if! {
     if #[cfg(windows)] {
         mod win;
 
-        use win::OpenOptionsImpl;
+        use win::{OpenOptionsImpl, ReadDirImpl, DirEntryImpl};
     } else {
         mod unix;
 
-        use unix::OpenOptionsImpl;
+        use unix::{OpenOptionsImpl, ReadDirImpl, DirEntryImpl};
     }
 }
 
@@ -183,6 +184,11 @@ impl OpenOptions {
     /// This will honour the options set for creation/append etc, but will only
     /// operate relative to d. To open a file with an absolute path, use the
     /// stdlib fs::OpenOptions.
+    ///
+    /// Note: On Windows this uses low level APIs that do not perform path
+    /// separator translation: if passing a path containing a separator, it must
+    /// be a platform native one. e.g. `foo\\bar` on Windows, vs `foo/bar` on
+    /// most other OS's.
     pub fn open_at<P: AsRef<Path>>(&self, d: &mut File, p: P) -> Result<File> {
         self._impl.open_at(d, OpenOptions::ensure_root(p.as_ref())?)
     }
@@ -198,6 +204,66 @@ impl OpenOptions {
     }
 }
 
+/// Iterate over the contents of a directory. Created by calling read_dir() on
+/// an opened directory. Each item yielded by the iterator is an io::Result to
+/// allow communication of io errors as the iterator is advanced.
+///
+/// To the greatest extent possible the underlying OS semantics are preserved.
+/// That means that `.` and `..` entries are exposed, and that no sort order is
+/// guaranteed by the iterator.
+#[derive(Debug)]
+pub struct ReadDir<'a> {
+    _impl: ReadDirImpl<'a>,
+}
+
+impl<'a> ReadDir<'a> {
+    pub fn new(d: &'a mut File) -> Result<Self> {
+        Ok(ReadDir {
+            _impl: ReadDirImpl::new(d)?,
+        })
+    }
+}
+
+impl Iterator for ReadDir<'_> {
+    type Item = Result<DirEntry>;
+
+    fn next(&mut self) -> Option<Result<DirEntry>> {
+        self._impl
+            .next()
+            .map(|entry| entry.map(|_impl| DirEntry { _impl }))
+    }
+}
+
+/// The returned type for each entry found by [`read_dir`].
+///
+/// Each entry represents a single entry inside the directory. Platforms that
+/// provide rich metadata may in future expose this through methods or extension
+/// traits on DirEntry.
+///
+/// For now however, only the [`name()`] is exposed. This does not imply any
+/// additional IO for most workloads: metadata returned from a directory listing
+/// is inherently racy: presuming that what was a dir, or symlink etc when the
+/// directory was listed, will still be the same when opened is fallible.
+/// Instead, use open_at to open the contents, and then process based on the
+/// type of content found.
+#[derive(Debug)]
+pub struct DirEntry {
+    _impl: DirEntryImpl,
+}
+
+impl DirEntry {
+    pub fn name(&self) -> &OsStr {
+        self._impl.name()
+    }
+}
+
+/// Read the children of the directory d.
+///
+/// See [`ReadDir`] and [`DirEntry`] for details.
+pub fn read_dir(d: &mut File) -> Result<ReadDir> {
+    ReadDir::new(d)
+}
+
 pub mod os {
     cfg_if::cfg_if! {
         if #[cfg(windows)] {
@@ -214,14 +280,15 @@ pub mod testsupport;
 #[cfg(test)]
 mod tests {
     use std::{
+        ffi::OsStr,
         fs::{rename, File},
         io::{Error, ErrorKind, Result, Seek, SeekFrom, Write},
         path::PathBuf,
     };
 
     use tempfile::TempDir;
 
-    use crate::{testsupport::open_dir, OpenOptions, OpenOptionsWriteMode};
+    use crate::{read_dir, testsupport::open_dir, DirEntry, OpenOptions, OpenOptionsWriteMode};
 
     /// Create a directory parent, open it, then rename it to renamed-parent and
     /// create another directory in its place. returns the file handle and the
@@ -464,4 +531,46 @@ mod tests {
         }
         Ok(())
     }
+
+    #[test]
+    fn readdir() -> Result<()> {
+        let (_tmp, mut parent_dir, _pathname) = setup()?;
+        assert_eq!(
+            2, // . and ..
+            read_dir(&mut parent_dir)?
+                .collect::<Result<Vec<DirEntry>>>()?
+                .len()
+        );
+        let dir_present =
+            |children: &Vec<DirEntry>, name: &OsStr| children.iter().any(|e| e.name() == name);
+
+        let mut options = OpenOptions::default();
+        options.create_new(true).write(OpenOptionsWriteMode::Write);
+        options.open_at(&mut parent_dir, "1")?;
+        options.open_at(&mut parent_dir, "2")?;
+        options.open_at(&mut options.mkdir_at(&mut parent_dir, "child")?, "3")?;
+        let children = read_dir(&mut parent_dir)?.collect::<Result<Vec<_>>>()?;
+        assert_eq!(
+            5,
+            children.len(),
+            "directory contains 5 entries (., .., 1, 2, child)"
+        );
+        assert!(dir_present(&children, OsStr::new("1")), "{:?}", children);
+        assert!(dir_present(&children, OsStr::new("2")), "{:?}", children);
+        assert!(
+            dir_present(&children, OsStr::new("child")),
+            "{:?}",
+            children
+        );
+
+        {
+            let mut child = OpenOptions::default()
+                .read(true)
+                .open_at(&mut parent_dir, "child")?;
+            let children = read_dir(&mut child)?.collect::<Result<Vec<_>>>()?;
+            assert_eq!(3, children.len(), "{:?}", children);
+            assert!(dir_present(&children, OsStr::new("3")), "{:?}", children);
+        }
+        Ok(())
+    }
 }

src/unix.rs

@@ -1,9 +1,11 @@
 use std::{
-    ffi::CString,
+    ffi::{CString, OsStr, OsString},
     fs::File,
     io::Result,
+    marker::PhantomData,
     os::unix::prelude::{AsRawFd, FromRawFd, OsStrExt},
     path::Path,
+    ptr,
 };
 
 // This will probably take a few iterations to get right. The idea: always use
@@ -180,6 +182,109 @@ impl OpenOptionsExt for OpenOptions {
     }
 }
 
+#[derive(Debug)]
+pub(crate) struct ReadDirImpl<'a> {
+    // Since we clone the FD, the original FD is now separate. In theory.
+    // However for Windows we use the File directly, thus here we need to
+    // pretend.
+    _phantom: PhantomData<&'a File>,
+    // Set to None after we closedir it. Perhaps we should we impl Send and Sync
+    // because the data referenced is owned by libc ?
+    dir: Option<ptr::NonNull<libc::DIR>>,
+}
+
+impl<'a> ReadDirImpl<'a> {
+    pub fn new(dir_file: &'a mut File) -> Result<Self> {
+        // closedir closes the FD; make a new one that we can close when done with.
+        let new_fd =
+            cvt_r(|| unsafe { libc::fcntl(dir_file.as_raw_fd(), libc::F_DUPFD_CLOEXEC, 0) })?;
+        let mut dir = Some(
+            ptr::NonNull::new(unsafe { libc::fdopendir(new_fd) }).ok_or_else(|| {
+                let _droppable = unsafe { File::from_raw_fd(new_fd) };
+                std::io::Error::last_os_error()
+            })?,
+        );
+
+        // If dir_file has had operations on it - such as open_at - its pointer
+        // might not be at the start of the dir, and fdopendir is documented
+        // (e.g. BSD man pages) to not rewind the fd - and our cloned fd
+        // inherits the pointer.
+        if let Some(d) = dir.as_mut() {
+            unsafe { libc::rewinddir(d.as_mut()) };
+        }
+
+        Ok(ReadDirImpl {
+            _phantom: PhantomData,
+            dir,
+        })
+    }
+
+    fn close_dir(&mut self) -> Result<()> {
+        if let Some(ref mut dir) = self.dir {
+            let result = unsafe { libc::closedir(dir.as_mut()) };
+            // call made, clear state
+            self.dir = None;
+            cvt_r(|| result)?;
+        }
+        Ok(())
+    }
+}
+
+impl Drop for ReadDirImpl<'_> {
+    fn drop(&mut self) {
+        // like the stdlib, we eat errors occuring during drop, as there is no
+        // way to get error handling.
+        let _ = self.close_dir();
+    }
+}
+
+impl Iterator for ReadDirImpl<'_> {
+    type Item = Result<DirEntryImpl>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let dir = unsafe { self.dir?.as_mut() };
+        // the readdir result is only guaranteed valid within the same thread
+        // and until other calls are made on the same dir stream. Thus we
+        // perform the required work inside next, allowing the next call to
+        // readdir to be managed by the single mutable borrower rule in Rust.
+        // readdir requires errno set to zero.
+        nix::Error::clear();
+        ptr::NonNull::new(unsafe { libc::readdir(dir) })
+            .map(|e| {
+                Ok(DirEntryImpl {
+                    name: unsafe {
+                        // Step one: C pointer to CStr - referenced data, length not known.
+                        let c_str = std::ffi::CStr::from_ptr(e.as_ref().d_name.as_ptr());
+                        // Step two: OsStr: referenced data, length calcu;ated
+                        let os_str = OsStr::from_bytes(c_str.to_bytes());
+                        // Step three: owned copy
+                        os_str.to_os_string()
+                    },
+                })
+            })
+            .or_else(|| {
+                // NULL result, an error IFF errno has been set.
+                let err = std::io::Error::last_os_error();
+                if err.raw_os_error() == Some(0) {
+                    None
+                } else {
+                    Some(Err(err))
+                }
+            })
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct DirEntryImpl {
+    name: OsString,
+}
+
+impl DirEntryImpl {
+    pub fn name(&self) -> &OsStr {
+        &self.name
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use std::{