rhg: Add support for dirstate-v2

Differential Revision: https://phab.mercurial-scm.org/D10804

rust/hg-core/src/dirstate.rs

@@ -1,141 +1,149 b''
 // dirstate module
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::dirstate_tree::on_disk::DirstateV2ParseError;
 use crate::errors::HgError;
+use crate::revlog::node::NULL_NODE;
 use crate::revlog::Node;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::FastHashMap;
 use bytes_cast::{unaligned, BytesCast};
 use std::convert::TryFrom;
 
 pub mod dirs_multiset;
 pub mod dirstate_map;
 pub mod parsers;
 pub mod status;
 
 #[derive(Debug, PartialEq, Clone, BytesCast)]
 #[repr(C)]
 pub struct DirstateParents {
     pub p1: Node,
     pub p2: Node,
 }
 
+impl DirstateParents {
+    pub const NULL: Self = Self {
+        p1: NULL_NODE,
+        p2: NULL_NODE,
+    };
+}
+
 /// The C implementation uses all signed types. This will be an issue
 /// either when 4GB+ source files are commonplace or in 2038, whichever
 /// comes first.
 #[derive(Debug, PartialEq, Copy, Clone)]
 pub struct DirstateEntry {
     pub state: EntryState,
     pub mode: i32,
     pub mtime: i32,
     pub size: i32,
 }
 
 impl DirstateEntry {
     pub fn is_non_normal(&self) -> bool {
         self.state != EntryState::Normal || self.mtime == MTIME_UNSET
     }
 
     pub fn is_from_other_parent(&self) -> bool {
         self.state == EntryState::Normal && self.size == SIZE_FROM_OTHER_PARENT
     }
 
     // TODO: other platforms
     #[cfg(unix)]
     pub fn mode_changed(
         &self,
         filesystem_metadata: &std::fs::Metadata,
     ) -> bool {
         use std::os::unix::fs::MetadataExt;
         const EXEC_BIT_MASK: u32 = 0o100;
         let dirstate_exec_bit = (self.mode as u32) & EXEC_BIT_MASK;
         let fs_exec_bit = filesystem_metadata.mode() & EXEC_BIT_MASK;
         dirstate_exec_bit != fs_exec_bit
     }
 }
 
 #[derive(BytesCast)]
 #[repr(C)]
 struct RawEntry {
     state: u8,
     mode: unaligned::I32Be,
     size: unaligned::I32Be,
     mtime: unaligned::I32Be,
     length: unaligned::I32Be,
 }
 
 const MTIME_UNSET: i32 = -1;
 
 /// A `DirstateEntry` with a size of `-2` means that it was merged from the
 /// other parent. This allows revert to pick the right status back during a
 /// merge.
 pub const SIZE_FROM_OTHER_PARENT: i32 = -2;
 
 pub type StateMap = FastHashMap<HgPathBuf, DirstateEntry>;
 pub type StateMapIter<'a> = Box<
     dyn Iterator<
             Item = Result<(&'a HgPath, DirstateEntry), DirstateV2ParseError>,
         > + Send
         + 'a,
 >;
 
 pub type CopyMap = FastHashMap<HgPathBuf, HgPathBuf>;
 pub type CopyMapIter<'a> = Box<
     dyn Iterator<Item = Result<(&'a HgPath, &'a HgPath), DirstateV2ParseError>>
         + Send
         + 'a,
 >;
 
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum EntryState {
     Normal,
     Added,
     Removed,
     Merged,
     Unknown,
 }
 
 impl EntryState {
     pub fn is_tracked(self) -> bool {
         use EntryState::*;
         match self {
             Normal | Added | Merged => true,
             Removed | Unknown => false,
         }
     }
 }
 
 impl TryFrom<u8> for EntryState {
     type Error = HgError;
 
     fn try_from(value: u8) -> Result<Self, Self::Error> {
         match value {
             b'n' => Ok(EntryState::Normal),
             b'a' => Ok(EntryState::Added),
             b'r' => Ok(EntryState::Removed),
             b'm' => Ok(EntryState::Merged),
             b'?' => Ok(EntryState::Unknown),
             _ => Err(HgError::CorruptedRepository(format!(
                 "Incorrect dirstate entry state {}",
                 value
             ))),
         }
     }
 }
 
 impl Into<u8> for EntryState {
     fn into(self) -> u8 {
         match self {
             EntryState::Normal => b'n',
             EntryState::Added => b'a',
             EntryState::Removed => b'r',
             EntryState::Merged => b'm',
             EntryState::Unknown => b'?',
         }
     }
 }

rust/hg-core/src/dirstate_tree.rs

@@ -1,5 +1,5 b''
 pub mod dirstate_map;
 pub mod dispatch;
 pub mod on_disk;
 pub mod path_with_basename;
-mod status;
+pub mod status;

rust/hg-core/src/dirstate_tree/on_disk.rs

@@ -1,543 +1,574 b''
 //! The "version 2" disk representation of the dirstate
 //!
 //! # File format
 //!
 //! The file starts with a fixed-sized header, whose layout is defined by the
 //! `Header` struct. Its `root` field contains the slice (offset and length) to
 //! the nodes representing the files and directories at the root of the
 //! repository. Each node is also fixed-size, defined by the `Node` struct.
 //! Nodes in turn contain slices to variable-size paths, and to their own child
 //! nodes (if any) for nested files and directories.
 
 use crate::dirstate_tree::dirstate_map::{self, DirstateMap, NodeRef};
 use crate::dirstate_tree::path_with_basename::WithBasename;
 use crate::errors::HgError;
 use crate::utils::hg_path::HgPath;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateParents;
 use crate::EntryState;
 use bytes_cast::unaligned::{I32Be, I64Be, U32Be, U64Be};
 use bytes_cast::BytesCast;
 use std::borrow::Cow;
 use std::convert::TryFrom;
 use std::time::{Duration, SystemTime, UNIX_EPOCH};
 
 /// Added at the start of `.hg/dirstate` when the "v2" format is used.
 /// This a redundant sanity check more than an actual "magic number" since
 /// `.hg/requires` already governs which format should be used.
 pub const V2_FORMAT_MARKER: &[u8; 12] = b"dirstate-v2\n";
 
 #[derive(BytesCast)]
 #[repr(C)]
 struct Header {
     marker: [u8; V2_FORMAT_MARKER.len()],
 
     /// `dirstatemap.parents()` in `mercurial/dirstate.py` relies on this
     /// `parents` field being at this offset, immediately after `marker`.
     parents: DirstateParents,
 
     root: ChildNodes,
     nodes_with_entry_count: Size,
     nodes_with_copy_source_count: Size,
 }
 
 #[derive(BytesCast)]
 #[repr(C)]
 pub(super) struct Node {
     full_path: PathSlice,
 
     /// In bytes from `self.full_path.start`
     base_name_start: Size,
 
     copy_source: OptPathSlice,
     children: ChildNodes,
     pub(super) tracked_descendants_count: Size,
 
     /// Dependending on the value of `state`:
     ///
     /// * A null byte: `data` is not used.
     ///
     /// * A `n`, `a`, `r`, or `m` ASCII byte: `state` and `data` together
     ///   represent a dirstate entry like in the v1 format.
     ///
     /// * A `d` ASCII byte: the bytes of `data` should instead be interpreted
     ///   as the `Timestamp` for the mtime of a cached directory.
     ///
     ///   The presence of this state means that at some point, this path in
     ///   the working directory was observed:
     ///
     ///   - To be a directory
     ///   - With the modification time as given by `Timestamp`
     ///   - That timestamp was already strictly in the past when observed,
     ///     meaning that later changes cannot happen in the same clock tick
     ///     and must cause a different modification time (unless the system
     ///     clock jumps back and we get unlucky, which is not impossible but
     ///     but deemed unlikely enough).
     ///   - The directory did not contain any child entry that did not have a
     ///     corresponding dirstate node.
     ///
     ///   This means that if `std::fs::symlink_metadata` later reports the
     ///   same modification time, we don’t need to call `std::fs::read_dir`
     ///   again for this directory and can iterate child dirstate nodes
     ///   instead.
     state: u8,
     data: Entry,
 }
 
 #[derive(BytesCast, Copy, Clone)]
 #[repr(C)]
 struct Entry {
     mode: I32Be,
     mtime: I32Be,
     size: I32Be,
 }
 
 /// Duration since the Unix epoch
 #[derive(BytesCast, Copy, Clone, PartialEq)]
 #[repr(C)]
 pub(super) struct Timestamp {
     seconds: I64Be,
 
     /// In `0 .. 1_000_000_000`.
     ///
     /// This timestamp is later or earlier than `(seconds, 0)` by this many
     /// nanoseconds, if `seconds` is non-negative or negative, respectively.
     nanoseconds: U32Be,
 }
 
 /// Counted in bytes from the start of the file
 ///
 /// NOTE: If we decide to never support `.hg/dirstate` files larger than 4 GiB
 /// we could save space by using `U32Be` instead.
 type Offset = U64Be;
 
 /// Counted in number of items
 ///
 /// NOTE: not supporting directories with more than 4 billion direct children,
 /// or filenames more than 4 GiB.
 type Size = U32Be;
 
 /// Location of consecutive, fixed-size items.
 ///
 /// An item can be a single byte for paths, or a struct with
 /// `derive(BytesCast)`.
 #[derive(BytesCast, Copy, Clone)]
 #[repr(C)]
 struct Slice {
     start: Offset,
     len: Size,
 }
 
 /// A contiguous sequence of `len` times `Node`, representing the child nodes
 /// of either some other node or of the repository root.
 ///
 /// Always sorted by ascending `full_path`, to allow binary search.
 /// Since nodes with the same parent nodes also have the same parent path,
 /// only the `base_name`s need to be compared during binary search.
 type ChildNodes = Slice;
 
 /// A `HgPath` of `len` bytes
 type PathSlice = Slice;
 
 /// Either nothing if `start == 0`, or a `HgPath` of `len` bytes
 type OptPathSlice = Slice;
 
 /// Make sure that size-affecting changes are made knowingly
 fn _static_assert_size_of() {
     let _ = std::mem::transmute::<Header, [u8; 72]>;
     let _ = std::mem::transmute::<Node, [u8; 57]>;
 }
 
 /// Unexpected file format found in `.hg/dirstate` with the "v2" format.
 ///
 /// This should only happen if Mercurial is buggy or a repository is corrupted.
 #[derive(Debug)]
 pub struct DirstateV2ParseError;
 
 impl From<DirstateV2ParseError> for HgError {
     fn from(_: DirstateV2ParseError) -> Self {
         HgError::corrupted("dirstate-v2 parse error")
     }
 }
 
 impl From<DirstateV2ParseError> for crate::DirstateError {
     fn from(error: DirstateV2ParseError) -> Self {
         HgError::from(error).into()
     }
 }
 
+fn read_header(on_disk: &[u8]) -> Result<&Header, DirstateV2ParseError> {
+    let (header, _) =
+        Header::from_bytes(on_disk).map_err(|_| DirstateV2ParseError)?;
+    if header.marker == *V2_FORMAT_MARKER {
+        Ok(header)
+    } else {
+        Err(DirstateV2ParseError)
+    }
+}
+
 pub(super) fn read<'on_disk>(
     on_disk: &'on_disk [u8],
 ) -> Result<
     (DirstateMap<'on_disk>, Option<DirstateParents>),
     DirstateV2ParseError,
 > {
     if on_disk.is_empty() {
         return Ok((DirstateMap::empty(on_disk), None));
     }
-    let (header, _) =
-        Header::from_bytes(on_disk).map_err(|_| DirstateV2ParseError)?;
-    let Header {
-        marker,
-        parents,
-        root,
-        nodes_with_entry_count,
-        nodes_with_copy_source_count,
-    } = header;
-    if marker != V2_FORMAT_MARKER {
-        return Err(DirstateV2ParseError);
-    }
+    let header = read_header(on_disk)?;
     let dirstate_map = DirstateMap {
         on_disk,
         root: dirstate_map::ChildNodes::OnDisk(read_slice::<Node>(
-            on_disk, *root,
+            on_disk,
+            header.root,
         )?),
-        nodes_with_entry_count: nodes_with_entry_count.get(),
-        nodes_with_copy_source_count: nodes_with_copy_source_count.get(),
+        nodes_with_entry_count: header.nodes_with_entry_count.get(),
+        nodes_with_copy_source_count: header
+            .nodes_with_copy_source_count
+            .get(),
     };
-    let parents = Some(parents.clone());
+    let parents = Some(header.parents.clone());
     Ok((dirstate_map, parents))
 }
 
 impl Node {
     pub(super) fn full_path<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'on_disk HgPath, DirstateV2ParseError> {
         read_hg_path(on_disk, self.full_path)
     }
 
     pub(super) fn base_name_start<'on_disk>(
         &self,
     ) -> Result<usize, DirstateV2ParseError> {
         let start = self.base_name_start.get();
         if start < self.full_path.len.get() {
             let start = usize::try_from(start)
                 // u32 -> usize, could only panic on a 16-bit CPU
                 .expect("dirstate-v2 base_name_start out of bounds");
             Ok(start)
         } else {
             Err(DirstateV2ParseError)
         }
     }
 
     pub(super) fn base_name<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'on_disk HgPath, DirstateV2ParseError> {
         let full_path = self.full_path(on_disk)?;
         let base_name_start = self.base_name_start()?;
         Ok(HgPath::new(&full_path.as_bytes()[base_name_start..]))
     }
 
     pub(super) fn path<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<dirstate_map::NodeKey<'on_disk>, DirstateV2ParseError> {
         Ok(WithBasename::from_raw_parts(
             Cow::Borrowed(self.full_path(on_disk)?),
             self.base_name_start()?,
         ))
     }
 
     pub(super) fn has_copy_source<'on_disk>(&self) -> bool {
         self.copy_source.start.get() != 0
     }
 
     pub(super) fn copy_source<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<&'on_disk HgPath>, DirstateV2ParseError> {
         Ok(if self.has_copy_source() {
             Some(read_hg_path(on_disk, self.copy_source)?)
         } else {
             None
         })
     }
 
     pub(super) fn node_data(
         &self,
     ) -> Result<dirstate_map::NodeData, DirstateV2ParseError> {
         let entry = |state| {
             dirstate_map::NodeData::Entry(self.entry_with_given_state(state))
         };
 
         match self.state {
             b'\0' => Ok(dirstate_map::NodeData::None),
             b'd' => Ok(dirstate_map::NodeData::CachedDirectory {
                 mtime: *self.data.as_timestamp(),
             }),
             b'n' => Ok(entry(EntryState::Normal)),
             b'a' => Ok(entry(EntryState::Added)),
             b'r' => Ok(entry(EntryState::Removed)),
             b'm' => Ok(entry(EntryState::Merged)),
             _ => Err(DirstateV2ParseError),
         }
     }
 
     pub(super) fn cached_directory_mtime(&self) -> Option<&Timestamp> {
         if self.state == b'd' {
             Some(self.data.as_timestamp())
         } else {
             None
         }
     }
 
     pub(super) fn state(
         &self,
     ) -> Result<Option<EntryState>, DirstateV2ParseError> {
         match self.state {
             b'\0' | b'd' => Ok(None),
             b'n' => Ok(Some(EntryState::Normal)),
             b'a' => Ok(Some(EntryState::Added)),
             b'r' => Ok(Some(EntryState::Removed)),
             b'm' => Ok(Some(EntryState::Merged)),
             _ => Err(DirstateV2ParseError),
         }
     }
 
     fn entry_with_given_state(&self, state: EntryState) -> DirstateEntry {
         DirstateEntry {
             state,
             mode: self.data.mode.get(),
             mtime: self.data.mtime.get(),
             size: self.data.size.get(),
         }
     }
 
     pub(super) fn entry(
         &self,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         Ok(self
             .state()?
             .map(|state| self.entry_with_given_state(state)))
     }
 
     pub(super) fn children<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'on_disk [Node], DirstateV2ParseError> {
         read_slice::<Node>(on_disk, self.children)
     }
 
     pub(super) fn to_in_memory_node<'on_disk>(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<dirstate_map::Node<'on_disk>, DirstateV2ParseError> {
         Ok(dirstate_map::Node {
             children: dirstate_map::ChildNodes::OnDisk(
                 self.children(on_disk)?,
             ),
             copy_source: self.copy_source(on_disk)?.map(Cow::Borrowed),
             data: self.node_data()?,
             tracked_descendants_count: self.tracked_descendants_count.get(),
         })
     }
 }
 
 impl Entry {
     fn from_timestamp(timestamp: Timestamp) -> Self {
         // Safety: both types implement the `ByteCast` trait, so we could
         // safely use `as_bytes` and `from_bytes` to do this conversion. Using
         // `transmute` instead makes the compiler check that the two types
         // have the same size, which eliminates the error case of
         // `from_bytes`.
         unsafe { std::mem::transmute::<Timestamp, Entry>(timestamp) }
     }
 
     fn as_timestamp(&self) -> &Timestamp {
         // Safety: same as above in `from_timestamp`
         unsafe { &*(self as *const Entry as *const Timestamp) }
     }
 }
 
 impl Timestamp {
     pub fn seconds(&self) -> i64 {
         self.seconds.get()
     }
 }
 
 impl From<SystemTime> for Timestamp {
     fn from(system_time: SystemTime) -> Self {
         let (secs, nanos) = match system_time.duration_since(UNIX_EPOCH) {
             Ok(duration) => {
                 (duration.as_secs() as i64, duration.subsec_nanos())
             }
             Err(error) => {
                 let negative = error.duration();
                 (-(negative.as_secs() as i64), negative.subsec_nanos())
             }
         };
         Timestamp {
             seconds: secs.into(),
             nanoseconds: nanos.into(),
         }
     }
 }
 
 impl From<&'_ Timestamp> for SystemTime {
     fn from(timestamp: &'_ Timestamp) -> Self {
         let secs = timestamp.seconds.get();
         let nanos = timestamp.nanoseconds.get();
         if secs >= 0 {
             UNIX_EPOCH + Duration::new(secs as u64, nanos)
         } else {
             UNIX_EPOCH - Duration::new((-secs) as u64, nanos)
         }
     }
 }
 
 fn read_hg_path(
     on_disk: &[u8],
     slice: Slice,
 ) -> Result<&HgPath, DirstateV2ParseError> {
     let bytes = read_slice::<u8>(on_disk, slice)?;
     Ok(HgPath::new(bytes))
 }
 
 fn read_slice<T>(
     on_disk: &[u8],
     slice: Slice,
 ) -> Result<&[T], DirstateV2ParseError>
 where
     T: BytesCast,
 {
     // Either `usize::MAX` would result in "out of bounds" error since a single
     // `&[u8]` cannot occupy the entire addess space.
     let start = usize::try_from(slice.start.get()).unwrap_or(std::usize::MAX);
     let len = usize::try_from(slice.len.get()).unwrap_or(std::usize::MAX);
     on_disk
         .get(start..)
         .and_then(|bytes| T::slice_from_bytes(bytes, len).ok())
         .map(|(slice, _rest)| slice)
         .ok_or_else(|| DirstateV2ParseError)
 }
 
+pub(crate) fn parse_dirstate_parents(
+    on_disk: &[u8],
+) -> Result<&DirstateParents, HgError> {
+    Ok(&read_header(on_disk)?.parents)
+}
+
+pub(crate) fn for_each_tracked_path<'on_disk>(
+    on_disk: &'on_disk [u8],
+    mut f: impl FnMut(&'on_disk HgPath),
+) -> Result<(), DirstateV2ParseError> {
+    let header = read_header(on_disk)?;
+    fn recur<'on_disk>(
+        on_disk: &'on_disk [u8],
+        nodes: Slice,
+        f: &mut impl FnMut(&'on_disk HgPath),
+    ) -> Result<(), DirstateV2ParseError> {
+        for node in read_slice::<Node>(on_disk, nodes)? {
+            if let Some(state) = node.state()? {
+                if state.is_tracked() {
+                    f(node.full_path(on_disk)?)
+                }
+            }
+            recur(on_disk, node.children, f)?
+        }
+        Ok(())
+    }
+    recur(on_disk, header.root, &mut f)
+}
+
 pub(super) fn write(
     dirstate_map: &mut DirstateMap,
     parents: DirstateParents,
 ) -> Result<Vec<u8>, DirstateError> {
     let header_len = std::mem::size_of::<Header>();
 
     // This ignores the space for paths, and for nodes without an entry.
     // TODO: better estimate? Skip the `Vec` and write to a file directly?
     let size_guess = header_len
         + std::mem::size_of::<Node>()
             * dirstate_map.nodes_with_entry_count as usize;
     let mut out = Vec::with_capacity(size_guess);
 
     // Keep space for the header. We’ll fill it out at the end when we know the
     // actual offset for the root nodes.
     out.resize(header_len, 0_u8);
 
     let root =
         write_nodes(dirstate_map, dirstate_map.root.as_ref(), &mut out)?;
 
     let header = Header {
         marker: *V2_FORMAT_MARKER,
         parents: parents,
         root,
         nodes_with_entry_count: dirstate_map.nodes_with_entry_count.into(),
         nodes_with_copy_source_count: dirstate_map
             .nodes_with_copy_source_count
             .into(),
     };
     out[..header_len].copy_from_slice(header.as_bytes());
     Ok(out)
 }
 
 fn write_nodes(
     dirstate_map: &DirstateMap,
     nodes: dirstate_map::ChildNodesRef,
     out: &mut Vec<u8>,
 ) -> Result<ChildNodes, DirstateError> {
     // `dirstate_map::ChildNodes` is a `HashMap` with undefined iteration
     // order. Sort to enable binary search in the written file.
     let nodes = nodes.sorted();
 
     // First accumulate serialized nodes in a `Vec`
     let mut on_disk_nodes = Vec::with_capacity(nodes.len());
     for node in nodes {
         let children = write_nodes(
             dirstate_map,
             node.children(dirstate_map.on_disk)?,
             out,
         )?;
         let full_path = node.full_path(dirstate_map.on_disk)?;
         let full_path = write_slice::<u8>(full_path.as_bytes(), out);
         let copy_source =
             if let Some(source) = node.copy_source(dirstate_map.on_disk)? {
                 write_slice::<u8>(source.as_bytes(), out)
             } else {
                 Slice {
                     start: 0.into(),
                     len: 0.into(),
                 }
             };
         on_disk_nodes.push(match node {
             NodeRef::InMemory(path, node) => {
                 let (state, data) = match &node.data {
                     dirstate_map::NodeData::Entry(entry) => (
                         entry.state.into(),
                         Entry {
                             mode: entry.mode.into(),
                             mtime: entry.mtime.into(),
                             size: entry.size.into(),
                         },
                     ),
                     dirstate_map::NodeData::CachedDirectory { mtime } => {
                         (b'd', Entry::from_timestamp(*mtime))
                     }
                     dirstate_map::NodeData::None => (
                         b'\0',
                         Entry {
                             mode: 0.into(),
                             mtime: 0.into(),
                             size: 0.into(),
                         },
                     ),
                 };
                 Node {
                     children,
                     copy_source,
                     full_path,
                     base_name_start: u32::try_from(path.base_name_start())
                         // Could only panic for paths over 4 GiB
                         .expect("dirstate-v2 offset overflow")
                         .into(),
                     tracked_descendants_count: node
                         .tracked_descendants_count
                         .into(),
                     state,
                     data,
                 }
             }
             NodeRef::OnDisk(node) => Node {
                 children,
                 copy_source,
                 full_path,
                 ..*node
             },
         })
     }
     // … so we can write them contiguously
     Ok(write_slice::<Node>(&on_disk_nodes, out))
 }
 
 fn write_slice<T>(slice: &[T], out: &mut Vec<u8>) -> Slice
 where
     T: BytesCast,
 {
     let start = u64::try_from(out.len())
         // Could only panic on a 128-bit CPU with a dirstate over 16 EiB
         .expect("dirstate-v2 offset overflow")
         .into();
     let len = u32::try_from(slice.len())
         // Could only panic for paths over 4 GiB or nodes with over 4 billions
         // child nodes
         .expect("dirstate-v2 offset overflow")
         .into();
     out.extend(slice.as_bytes());
     Slice { start, len }
 }

rust/hg-core/src/operations/list_tracked_files.rs

@@ -1,68 +1,79 b''
 // list_tracked_files.rs
 //
 // Copyright 2020 Antoine Cezar <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::dirstate::parsers::parse_dirstate_entries;
+use crate::dirstate_tree::on_disk::for_each_tracked_path;
 use crate::errors::HgError;
 use crate::repo::Repo;
 use crate::revlog::changelog::Changelog;
 use crate::revlog::manifest::{Manifest, ManifestEntry};
 use crate::revlog::node::Node;
 use crate::revlog::revlog::RevlogError;
 use crate::utils::hg_path::HgPath;
+use crate::DirstateError;
 use rayon::prelude::*;
 
 /// List files under Mercurial control in the working directory
 /// by reading the dirstate
 pub struct Dirstate {
     /// The `dirstate` content.
     content: Vec<u8>,
+    dirstate_v2: bool,
 }
 
 impl Dirstate {
     pub fn new(repo: &Repo) -> Result<Self, HgError> {
-        let content = repo.hg_vfs().read("dirstate")?;
-        Ok(Self { content })
+        Ok(Self {
+            content: repo.hg_vfs().read("dirstate")?,
+            dirstate_v2: repo.has_dirstate_v2(),
+        })
     }
 
-    pub fn tracked_files(&self) -> Result<Vec<&HgPath>, HgError> {
+    pub fn tracked_files(&self) -> Result<Vec<&HgPath>, DirstateError> {
         let mut files = Vec::new();
-        let _parents = parse_dirstate_entries(
-            &self.content,
-            |path, entry, _copy_source| {
-                if entry.state.is_tracked() {
-                    files.push(path)
-                }
-                Ok(())
-            },
-        )?;
+        if !self.content.is_empty() {
+            if self.dirstate_v2 {
+                for_each_tracked_path(&self.content, |path| files.push(path))?
+            } else {
+                let _parents = parse_dirstate_entries(
+                    &self.content,
+                    |path, entry, _copy_source| {
+                        if entry.state.is_tracked() {
+                            files.push(path)
+                        }
+                        Ok(())
+                    },
+                )?;
+            }
+        }
         files.par_sort_unstable();
         Ok(files)
     }
 }
 
 /// List files under Mercurial control at a given revision.
 pub fn list_rev_tracked_files(
     repo: &Repo,
     revset: &str,
 ) -> Result<FilesForRev, RevlogError> {
     let rev = crate::revset::resolve_single(revset, repo)?;
     let changelog = Changelog::open(repo)?;
     let manifest = Manifest::open(repo)?;
     let changelog_entry = changelog.get_rev(rev)?;
     let manifest_node =
         Node::from_hex_for_repo(&changelog_entry.manifest_node()?)?;
     let manifest_entry = manifest.get_node(manifest_node.into())?;
     Ok(FilesForRev(manifest_entry))
 }
 
 pub struct FilesForRev(ManifestEntry);
 
 impl FilesForRev {
     pub fn iter(&self) -> impl Iterator<Item = &HgPath> {
         self.0.files()
     }
 }

rust/hg-core/src/repo.rs

@@ -1,266 +1,277 b''
 use crate::config::{Config, ConfigError, ConfigParseError};
 use crate::errors::{HgError, IoErrorContext, IoResultExt};
 use crate::requirements;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::SliceExt;
 use memmap::{Mmap, MmapOptions};
 use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 
 /// A repository on disk
 pub struct Repo {
     working_directory: PathBuf,
     dot_hg: PathBuf,
     store: PathBuf,
     requirements: HashSet<String>,
     config: Config,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum RepoError {
     NotFound {
         at: PathBuf,
     },
     #[from]
     ConfigParseError(ConfigParseError),
     #[from]
     Other(HgError),
 }
 
 impl From<ConfigError> for RepoError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 /// Filesystem access abstraction for the contents of a given "base" diretory
 #[derive(Clone, Copy)]
 pub struct Vfs<'a> {
     pub(crate) base: &'a Path,
 }
 
 impl Repo {
     /// Find a repository, either at the given path (which must contain a `.hg`
     /// sub-directory) or by searching the current directory and its
     /// ancestors.
     ///
     /// A method with two very different "modes" like this usually a code smell
     /// to make two methods instead, but in this case an `Option` is what rhg
     /// sub-commands get from Clap for the `-R` / `--repository` CLI argument.
     /// Having two methods would just move that `if` to almost all callers.
     pub fn find(
         config: &Config,
         explicit_path: Option<&Path>,
     ) -> Result<Self, RepoError> {
         if let Some(root) = explicit_path {
             if root.join(".hg").is_dir() {
                 Self::new_at_path(root.to_owned(), config)
             } else if root.is_file() {
                 Err(HgError::unsupported("bundle repository").into())
             } else {
                 Err(RepoError::NotFound {
                     at: root.to_owned(),
                 })
             }
         } else {
             let current_directory = crate::utils::current_dir()?;
             // ancestors() is inclusive: it first yields `current_directory`
             // as-is.
             for ancestor in current_directory.ancestors() {
                 if ancestor.join(".hg").is_dir() {
                     return Self::new_at_path(ancestor.to_owned(), config);
                 }
             }
             Err(RepoError::NotFound {
                 at: current_directory,
             })
         }
     }
 
     /// To be called after checking that `.hg` is a sub-directory
     fn new_at_path(
         working_directory: PathBuf,
         config: &Config,
     ) -> Result<Self, RepoError> {
         let dot_hg = working_directory.join(".hg");
 
         let mut repo_config_files = Vec::new();
         repo_config_files.push(dot_hg.join("hgrc"));
         repo_config_files.push(dot_hg.join("hgrc-not-shared"));
 
         let hg_vfs = Vfs { base: &dot_hg };
         let mut reqs = requirements::load_if_exists(hg_vfs)?;
         let relative =
             reqs.contains(requirements::RELATIVE_SHARED_REQUIREMENT);
         let shared =
             reqs.contains(requirements::SHARED_REQUIREMENT) || relative;
 
         // From `mercurial/localrepo.py`:
         //
         // if .hg/requires contains the sharesafe requirement, it means
         // there exists a `.hg/store/requires` too and we should read it
         // NOTE: presence of SHARESAFE_REQUIREMENT imply that store requirement
         // is present. We never write SHARESAFE_REQUIREMENT for a repo if store
         // is not present, refer checkrequirementscompat() for that
         //
         // However, if SHARESAFE_REQUIREMENT is not present, it means that the
         // repository was shared the old way. We check the share source
         // .hg/requires for SHARESAFE_REQUIREMENT to detect whether the
         // current repository needs to be reshared
         let share_safe = reqs.contains(requirements::SHARESAFE_REQUIREMENT);
 
         let store_path;
         if !shared {
             store_path = dot_hg.join("store");
         } else {
             let bytes = hg_vfs.read("sharedpath")?;
             let mut shared_path =
                 get_path_from_bytes(bytes.trim_end_newlines()).to_owned();
             if relative {
                 shared_path = dot_hg.join(shared_path)
             }
             if !shared_path.is_dir() {
                 return Err(HgError::corrupted(format!(
                     ".hg/sharedpath points to nonexistent directory {}",
                     shared_path.display()
                 ))
                 .into());
             }
 
             store_path = shared_path.join("store");
 
             let source_is_share_safe =
                 requirements::load(Vfs { base: &shared_path })?
                     .contains(requirements::SHARESAFE_REQUIREMENT);
 
             if share_safe && !source_is_share_safe {
                 return Err(match config
                     .get(b"share", b"safe-mismatch.source-not-safe")
                 {
                     Some(b"abort") | None => HgError::abort(
                         "abort: share source does not support share-safe requirement\n\
                         (see `hg help config.format.use-share-safe` for more information)",
                     ),
                     _ => HgError::unsupported("share-safe downgrade"),
                 }
                 .into());
             } else if source_is_share_safe && !share_safe {
                 return Err(
                     match config.get(b"share", b"safe-mismatch.source-safe") {
                         Some(b"abort") | None => HgError::abort(
                             "abort: version mismatch: source uses share-safe \
                             functionality while the current share does not\n\
                             (see `hg help config.format.use-share-safe` for more information)",
                         ),
                         _ => HgError::unsupported("share-safe upgrade"),
                     }
                     .into(),
                 );
             }
 
             if share_safe {
                 repo_config_files.insert(0, shared_path.join("hgrc"))
             }
         }
         if share_safe {
             reqs.extend(requirements::load(Vfs { base: &store_path })?);
         }
 
         let repo_config = if std::env::var_os("HGRCSKIPREPO").is_none() {
             config.combine_with_repo(&repo_config_files)?
         } else {
             config.clone()
         };
 
         let repo = Self {
             requirements: reqs,
             working_directory,
             store: store_path,
             dot_hg,
             config: repo_config,
         };
 
         requirements::check(&repo)?;
 
         Ok(repo)
     }
 
     pub fn working_directory_path(&self) -> &Path {
         &self.working_directory
     }
 
     pub fn requirements(&self) -> &HashSet<String> {
         &self.requirements
     }
 
     pub fn config(&self) -> &Config {
         &self.config
     }
 
     /// For accessing repository files (in `.hg`), except for the store
     /// (`.hg/store`).
     pub fn hg_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.dot_hg }
     }
 
     /// For accessing repository store files (in `.hg/store`)
     pub fn store_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.store }
     }
 
     /// For accessing the working copy
     pub fn working_directory_vfs(&self) -> Vfs<'_> {
         Vfs {
             base: &self.working_directory,
         }
     }
 
+    pub fn has_dirstate_v2(&self) -> bool {
+        self.requirements
+            .contains(requirements::DIRSTATE_V2_REQUIREMENT)
+    }
+
     pub fn dirstate_parents(
         &self,
     ) -> Result<crate::dirstate::DirstateParents, HgError> {
         let dirstate = self.hg_vfs().mmap_open("dirstate")?;
-        let parents =
-            crate::dirstate::parsers::parse_dirstate_parents(&dirstate)?;
+        if dirstate.is_empty() {
+            return Ok(crate::dirstate::DirstateParents::NULL);
+        }
+        let parents = if self.has_dirstate_v2() {
+            crate::dirstate_tree::on_disk::parse_dirstate_parents(&dirstate)?
+        } else {
+            crate::dirstate::parsers::parse_dirstate_parents(&dirstate)?
+        };
         Ok(parents.clone())
     }
 }
 
 impl Vfs<'_> {
     pub fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
         self.base.join(relative_path)
     }
 
     pub fn read(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Vec<u8>, HgError> {
         let path = self.join(relative_path);
         std::fs::read(&path).when_reading_file(&path)
     }
 
     pub fn mmap_open(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Mmap, HgError> {
         let path = self.base.join(relative_path);
         let file = std::fs::File::open(&path).when_reading_file(&path)?;
         // TODO: what are the safety requirements here?
         let mmap = unsafe { MmapOptions::new().map(&file) }
             .when_reading_file(&path)?;
         Ok(mmap)
     }
 
     pub fn rename(
         &self,
         relative_from: impl AsRef<Path>,
         relative_to: impl AsRef<Path>,
     ) -> Result<(), HgError> {
         let from = self.join(relative_from);
         let to = self.join(relative_to);
         std::fs::rename(&from, &to)
             .with_context(|| IoErrorContext::RenamingFile { from, to })
     }
 }

rust/hg-core/src/requirements.rs

@@ -1,153 +1,156 b''
 use crate::errors::{HgError, HgResultExt};
 use crate::repo::{Repo, Vfs};
 use crate::utils::join_display;
 use std::collections::HashSet;
 
 fn parse(bytes: &[u8]) -> Result<HashSet<String>, HgError> {
     // The Python code reading this file uses `str.splitlines`
     // which looks for a number of line separators (even including a couple of
     // non-ASCII ones), but Python code writing it always uses `\n`.
     let lines = bytes.split(|&byte| byte == b'\n');
 
     lines
         .filter(|line| !line.is_empty())
         .map(|line| {
             // Python uses Unicode `str.isalnum` but feature names are all
             // ASCII
             if line[0].is_ascii_alphanumeric() && line.is_ascii() {
                 Ok(String::from_utf8(line.into()).unwrap())
             } else {
                 Err(HgError::corrupted("parse error in 'requires' file"))
             }
         })
         .collect()
 }
 
 pub(crate) fn load(hg_vfs: Vfs) -> Result<HashSet<String>, HgError> {
     parse(&hg_vfs.read("requires")?)
 }
 
 pub(crate) fn load_if_exists(hg_vfs: Vfs) -> Result<HashSet<String>, HgError> {
     if let Some(bytes) = hg_vfs.read("requires").io_not_found_as_none()? {
         parse(&bytes)
     } else {
         // Treat a missing file the same as an empty file.
         // From `mercurial/localrepo.py`:
         // > requires file contains a newline-delimited list of
         // > features/capabilities the opener (us) must have in order to use
         // > the repository. This file was introduced in Mercurial 0.9.2,
         // > which means very old repositories may not have one. We assume
         // > a missing file translates to no requirements.
         Ok(HashSet::new())
     }
 }
 
 pub(crate) fn check(repo: &Repo) -> Result<(), HgError> {
     let unknown: Vec<_> = repo
         .requirements()
         .iter()
         .map(String::as_str)
         // .filter(|feature| !ALL_SUPPORTED.contains(feature.as_str()))
         .filter(|feature| {
             !REQUIRED.contains(feature) && !SUPPORTED.contains(feature)
         })
         .collect();
     if !unknown.is_empty() {
         return Err(HgError::unsupported(format!(
             "repository requires feature unknown to this Mercurial: {}",
             join_display(&unknown, ", ")
         )));
     }
     let missing: Vec<_> = REQUIRED
         .iter()
         .filter(|&&feature| !repo.requirements().contains(feature))
         .collect();
     if !missing.is_empty() {
         return Err(HgError::unsupported(format!(
             "repository is missing feature required by this Mercurial: {}",
             join_display(&missing, ", ")
         )));
     }
     Ok(())
 }
 
 /// rhg does not support repositories that are *missing* any of these features
 const REQUIRED: &[&str] = &["revlogv1", "store", "fncache", "dotencode"];
 
 /// rhg supports repository with or without these
 const SUPPORTED: &[&str] = &[
     "generaldelta",
     SHARED_REQUIREMENT,
     SHARESAFE_REQUIREMENT,
     SPARSEREVLOG_REQUIREMENT,
     RELATIVE_SHARED_REQUIREMENT,
     REVLOG_COMPRESSION_ZSTD,
+    DIRSTATE_V2_REQUIREMENT,
     // As of this writing everything rhg does is read-only.
     // When it starts writing to the repository, it’ll need to either keep the
     // persistent nodemap up to date or remove this entry:
     NODEMAP_REQUIREMENT,
 ];
 
 // Copied from mercurial/requirements.py:
 
+pub(crate) const DIRSTATE_V2_REQUIREMENT: &str = "exp-dirstate-v2";
+
 /// When narrowing is finalized and no longer subject to format changes,
 /// we should move this to just "narrow" or similar.
 #[allow(unused)]
 pub(crate) const NARROW_REQUIREMENT: &str = "narrowhg-experimental";
 
 /// Enables sparse working directory usage
 #[allow(unused)]
 pub(crate) const SPARSE_REQUIREMENT: &str = "exp-sparse";
 
 /// Enables the internal phase which is used to hide changesets instead
 /// of stripping them
 #[allow(unused)]
 pub(crate) const INTERNAL_PHASE_REQUIREMENT: &str = "internal-phase";
 
 /// Stores manifest in Tree structure
 #[allow(unused)]
 pub(crate) const TREEMANIFEST_REQUIREMENT: &str = "treemanifest";
 
 /// Increment the sub-version when the revlog v2 format changes to lock out old
 /// clients.
 #[allow(unused)]
 pub(crate) const REVLOGV2_REQUIREMENT: &str = "exp-revlogv2.1";
 
 /// A repository with the sparserevlog feature will have delta chains that
 /// can spread over a larger span. Sparse reading cuts these large spans into
 /// pieces, so that each piece isn't too big.
 /// Without the sparserevlog capability, reading from the repository could use
 /// huge amounts of memory, because the whole span would be read at once,
 /// including all the intermediate revisions that aren't pertinent for the
 /// chain. This is why once a repository has enabled sparse-read, it becomes
 /// required.
 #[allow(unused)]
 pub(crate) const SPARSEREVLOG_REQUIREMENT: &str = "sparserevlog";
 
 /// A repository with the the copies-sidedata-changeset requirement will store
 /// copies related information in changeset's sidedata.
 #[allow(unused)]
 pub(crate) const COPIESSDC_REQUIREMENT: &str = "exp-copies-sidedata-changeset";
 
 /// The repository use persistent nodemap for the changelog and the manifest.
 #[allow(unused)]
 pub(crate) const NODEMAP_REQUIREMENT: &str = "persistent-nodemap";
 
 /// Denotes that the current repository is a share
 #[allow(unused)]
 pub(crate) const SHARED_REQUIREMENT: &str = "shared";
 
 /// Denotes that current repository is a share and the shared source path is
 /// relative to the current repository root path
 #[allow(unused)]
 pub(crate) const RELATIVE_SHARED_REQUIREMENT: &str = "relshared";
 
 /// A repository with share implemented safely. The repository has different
 /// store and working copy requirements i.e. both `.hg/requires` and
 /// `.hg/store/requires` are present.
 #[allow(unused)]
 pub(crate) const SHARESAFE_REQUIREMENT: &str = "share-safe";
 
 /// A repository that use zstd compression inside its revlog
 #[allow(unused)]
 pub(crate) const REVLOG_COMPRESSION_ZSTD: &str = "revlog-compression-zstd";

rust/rhg/src/commands/status.rs

@@ -1,318 +1,322 b''
 // status.rs
 //
 // Copyright 2020, Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::error::CommandError;
 use crate::ui::Ui;
 use clap::{Arg, SubCommand};
 use hg;
+use hg::dirstate_tree::dirstate_map::DirstateMap;
 use hg::errors::HgResultExt;
 use hg::errors::IoResultExt;
 use hg::matchers::AlwaysMatcher;
 use hg::operations::cat;
 use hg::repo::Repo;
 use hg::revlog::node::Node;
 use hg::utils::hg_path::{hg_path_to_os_string, HgPath};
-use hg::{DirstateMap, StatusError};
+use hg::StatusError;
 use hg::{HgPathCow, StatusOptions};
 use log::{info, warn};
 use std::convert::TryInto;
 use std::fs;
 use std::io::BufReader;
 use std::io::Read;
 
 pub const HELP_TEXT: &str = "
 Show changed files in the working directory
 
 This is a pure Rust version of `hg status`.
 
 Some options might be missing, check the list below.
 ";
 
 pub fn args() -> clap::App<'static, 'static> {
     SubCommand::with_name("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::with_name("all")
                 .help("show status of all files")
                 .short("-A")
                 .long("--all"),
         )
         .arg(
             Arg::with_name("modified")
                 .help("show only modified files")
                 .short("-m")
                 .long("--modified"),
         )
         .arg(
             Arg::with_name("added")
                 .help("show only added files")
                 .short("-a")
                 .long("--added"),
         )
         .arg(
             Arg::with_name("removed")
                 .help("show only removed files")
                 .short("-r")
                 .long("--removed"),
         )
         .arg(
             Arg::with_name("clean")
                 .help("show only clean files")
                 .short("-c")
                 .long("--clean"),
         )
         .arg(
             Arg::with_name("deleted")
                 .help("show only deleted files")
                 .short("-d")
                 .long("--deleted"),
         )
         .arg(
             Arg::with_name("unknown")
                 .help("show only unknown (not tracked) files")
                 .short("-u")
                 .long("--unknown"),
         )
         .arg(
             Arg::with_name("ignored")
                 .help("show only ignored files")
                 .short("-i")
                 .long("--ignored"),
         )
 }
 
 /// Pure data type allowing the caller to specify file states to display
 #[derive(Copy, Clone, Debug)]
 pub struct DisplayStates {
     pub modified: bool,
     pub added: bool,
     pub removed: bool,
     pub clean: bool,
     pub deleted: bool,
     pub unknown: bool,
     pub ignored: bool,
 }
 
 pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: false,
     deleted: true,
     unknown: true,
     ignored: false,
 };
 
 pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: true,
     deleted: true,
     unknown: true,
     ignored: true,
 };
 
 impl DisplayStates {
     pub fn is_empty(&self) -> bool {
         !(self.modified
             || self.added
             || self.removed
             || self.clean
             || self.deleted
             || self.unknown
             || self.ignored)
     }
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     let status_enabled_default = false;
     let status_enabled = invocation.config.get_option(b"rhg", b"status")?;
     if !status_enabled.unwrap_or(status_enabled_default) {
         return Err(CommandError::unsupported(
             "status is experimental in rhg (enable it with 'rhg.status = true' \
             or enable fallback with 'rhg.on-unsupported = fallback')"
         ));
     }
 
     let ui = invocation.ui;
     let args = invocation.subcommand_args;
     let display_states = if args.is_present("all") {
         // TODO when implementing `--quiet`: it excludes clean files
         // from `--all`
         ALL_DISPLAY_STATES
     } else {
         let requested = DisplayStates {
             modified: args.is_present("modified"),
             added: args.is_present("added"),
             removed: args.is_present("removed"),
             clean: args.is_present("clean"),
             deleted: args.is_present("deleted"),
             unknown: args.is_present("unknown"),
             ignored: args.is_present("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
 
     let repo = invocation.repo?;
-    let mut dmap = DirstateMap::new();
     let dirstate_data =
         repo.hg_vfs().mmap_open("dirstate").io_not_found_as_none()?;
     let dirstate_data = match &dirstate_data {
         Some(mmap) => &**mmap,
         None => b"",
     };
-    let parents = dmap.read(dirstate_data)?;
+    let (mut dmap, parents) = if repo.has_dirstate_v2() {
+        DirstateMap::new_v2(dirstate_data)?
+    } else {
+        DirstateMap::new_v1(dirstate_data)?
+    };
     let options = StatusOptions {
         // TODO should be provided by the dirstate parsing and
         // hence be stored on dmap. Using a value that assumes we aren't
         // below the time resolution granularity of the FS and the
         // dirstate.
         last_normal_time: 0,
         // we're currently supporting file systems with exec flags only
         // anyway
         check_exec: true,
         list_clean: display_states.clean,
         list_unknown: display_states.unknown,
         list_ignored: display_states.ignored,
         collect_traversed_dirs: false,
     };
     let ignore_file = repo.working_directory_vfs().join(".hgignore"); // TODO hardcoded
-    let (mut ds_status, pattern_warnings) = hg::status(
-        &dmap,
+    let (mut ds_status, pattern_warnings) = hg::dirstate_tree::status::status(
+        &mut dmap,
         &AlwaysMatcher,
         repo.working_directory_path().to_owned(),
         vec![ignore_file],
         options,
     )?;
     if !pattern_warnings.is_empty() {
         warn!("Pattern warnings: {:?}", &pattern_warnings);
     }
 
     if !ds_status.bad.is_empty() {
         warn!("Bad matches {:?}", &(ds_status.bad))
     }
     if !ds_status.unsure.is_empty() {
         info!(
             "Files to be rechecked by retrieval from filelog: {:?}",
             &ds_status.unsure
         );
     }
     if !ds_status.unsure.is_empty()
         && (display_states.modified || display_states.clean)
     {
         let p1: Node = parents
             .expect(
                 "Dirstate with no parents should not list any file to
             be rechecked for modifications",
             )
             .p1
             .into();
         let p1_hex = format!("{:x}", p1);
         for to_check in ds_status.unsure {
             if cat_file_is_modified(repo, &to_check, &p1_hex)? {
                 if display_states.modified {
                     ds_status.modified.push(to_check);
                 }
             } else {
                 if display_states.clean {
                     ds_status.clean.push(to_check);
                 }
             }
         }
     }
     if display_states.modified {
         display_status_paths(ui, &mut ds_status.modified, b"M")?;
     }
     if display_states.added {
         display_status_paths(ui, &mut ds_status.added, b"A")?;
     }
     if display_states.removed {
         display_status_paths(ui, &mut ds_status.removed, b"R")?;
     }
     if display_states.deleted {
         display_status_paths(ui, &mut ds_status.deleted, b"!")?;
     }
     if display_states.unknown {
         display_status_paths(ui, &mut ds_status.unknown, b"?")?;
     }
     if display_states.ignored {
         display_status_paths(ui, &mut ds_status.ignored, b"I")?;
     }
     if display_states.clean {
         display_status_paths(ui, &mut ds_status.clean, b"C")?;
     }
     Ok(())
 }
 
 // Probably more elegant to use a Deref or Borrow trait rather than
 // harcode HgPathBuf, but probably not really useful at this point
 fn display_status_paths(
     ui: &Ui,
     paths: &mut [HgPathCow],
     status_prefix: &[u8],
 ) -> Result<(), CommandError> {
     paths.sort_unstable();
     for path in paths {
         // Same TODO as in commands::root
         let bytes: &[u8] = path.as_bytes();
         // TODO optim, probably lots of unneeded copies here, especially
         // if out stream is buffered
         ui.write_stdout(&[status_prefix, b" ", bytes, b"\n"].concat())?;
     }
     Ok(())
 }
 
 /// Check if a file is modified by comparing actual repo store and file system.
 ///
 /// This meant to be used for those that the dirstate cannot resolve, due
 /// to time resolution limits.
 ///
 /// TODO: detect permission bits and similar metadata modifications
 fn cat_file_is_modified(
     repo: &Repo,
     hg_path: &HgPath,
     rev: &str,
 ) -> Result<bool, CommandError> {
     // TODO CatRev expects &[HgPathBuf], something like
     // &[impl Deref<HgPath>] would be nicer and should avoid the copy
     let path_bufs = [hg_path.into()];
     // TODO IIUC CatRev returns a simple Vec<u8> for all files
     //      being able to tell them apart as (path, bytes) would be nicer
     //      and OPTIM would allow manifest resolution just once.
     let output = cat(repo, rev, &path_bufs).map_err(|e| (e, rev))?;
 
     let fs_path = repo
         .working_directory_vfs()
         .join(hg_path_to_os_string(hg_path).expect("HgPath conversion"));
     let hg_data_len: u64 = match output.concatenated.len().try_into() {
         Ok(v) => v,
         Err(_) => {
             // conversion of data length to u64 failed,
             // good luck for any file to have this content
             return Ok(true);
         }
     };
     let fobj = fs::File::open(&fs_path).when_reading_file(&fs_path)?;
     if fobj.metadata().map_err(|e| StatusError::from(e))?.len() != hg_data_len
     {
         return Ok(true);
     }
     for (fs_byte, hg_byte) in
         BufReader::new(fobj).bytes().zip(output.concatenated)
     {
         if fs_byte.map_err(|e| StatusError::from(e))? != hg_byte {
             return Ok(true);
         }
     }
     Ok(false)
 }