dirstate-tree: Refactor DirstateMap::drop_file to be recursive

It should behave the same as before. This will enable the next changeset
to run code on the way "down" (in order to removing newly-empty nodes).

Differential Revision: https://phab.mercurial-scm.org/D10705

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

@@ -1,623 +1,622 b''
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::convert::TryInto;
 use std::path::PathBuf;
 
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::clear_ambiguous_mtime;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateMapError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::FastHashMap;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     nodes_with_entry_count: usize,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     nodes_with_copy_source_count: usize,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `BTreeMap` would waste time always re-comparing the same
 /// string prefix.
 pub(super) type ChildNodes<'on_disk> =
     FastHashMap<WithBasename<Cow<'on_disk, HgPath>>, Node<'on_disk>>;
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     /// `None` for directories
     pub(super) entry: Option<DirstateEntry>,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node are tracked files
     tracked_descendants_count: usize,
 }
 
 impl Node<'_> {
     pub(super) fn state(&self) -> Option<EntryState> {
         self.entry.as_ref().map(|entry| entry.state)
     }
 }
 
 /// `(full_path, entry, copy_source)`
 type NodeDataMut<'tree, 'on_disk> = (
     &'tree HgPath,
     &'tree mut Option<DirstateEntry>,
     &'tree mut Option<Cow<'on_disk, HgPath>>,
 );
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub fn new(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
         };
         let parents = map.read()?;
         Ok((map, parents))
     }
 
     /// Should only be called in `new`
     #[timed]
     fn read(&mut self) -> Result<Option<DirstateParents>, DirstateError> {
         if self.on_disk.is_empty() {
             return Ok(None);
         }
 
         let parents = parse_dirstate_entries(
             self.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state.is_tracked();
                 let node = Self::get_or_insert_node(
                     &mut self.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                     },
                 );
                 assert!(
                     node.entry.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.entry = Some(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 self.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     self.nodes_with_copy_source_count += 1
                 }
             },
         )?;
 
         Ok(Some(parents.clone()))
     }
 
     fn get_node(&self, path: &HgPath) -> Option<&Node> {
         let mut children = &self.root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get(component)?;
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Option<&'tree mut Node<'on_disk>> {
-        Self::get_node_mut_tracing_ancestors(root, path, |_| {})
-    }
-
-    /// Same as `get_node_mut`, and calls `each_ancestor` for each ancestor of
-    /// the node.
-    ///
-    /// Note that `each_ancestor` may be called (with what would be ancestors)
-    /// even if it turns out there is no node at `path`.
-    fn get_node_mut_tracing_ancestors<'tree>(
-        root: &'tree mut ChildNodes<'on_disk>,
-        path: &HgPath,
-        mut each_ancestor: impl FnMut(&mut Node),
-    ) -> Option<&'tree mut Node<'on_disk>> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get_mut(component)?;
             if let Some(next_component) = components.next() {
-                each_ancestor(child);
                 component = next_component;
                 children = &mut child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     fn get_or_insert_node<'tree, 'path>(
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> &'tree mut Node<'on_disk> {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
             // TODO: can we avoid allocating an owned key in cases where the
             // map already contains that key, without introducing double
             // lookup?
             let child_node =
                 child_nodes.entry(to_cow(ancestor_path)).or_default();
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return child_node;
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
         old_state: EntryState,
         new_entry: DirstateEntry,
     ) {
         let tracked_count_increment =
             match (old_state.is_tracked(), new_entry.state.is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         );
         if node.entry.is_none() {
             self.nodes_with_entry_count += 1
         }
         node.entry = Some(new_entry)
     }
 
     fn iter_nodes<'a>(
         &'a self,
     ) -> impl Iterator<Item = (&'a HgPath, &'a Node)> + 'a {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.iter();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let new_iter = child_node.children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 let key = &**key.full_path();
                 stack.push((key, child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((key, child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some((key, child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     /// Mutable iterator for the `(entry, copy source)` of each node.
     ///
     /// It would not be safe to yield mutable references to nodes themeselves
     /// with `-> impl Iterator<Item = &mut Node>` since child nodes are
     /// reachable from their ancestor nodes, potentially creating multiple
     /// `&mut` references to a given node.
     fn iter_node_data_mut<'tree>(
         &'tree mut self,
     ) -> impl Iterator<Item = NodeDataMut<'tree, 'on_disk>> + 'tree {
         // Explict stack for pseudo-recursion, see `iter_nodes` above.
         let mut stack = Vec::new();
         let mut iter = self.root.iter_mut();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let data = (
                     &**key.full_path(),
                     &mut child_node.entry,
                     &mut child_node.copy_source,
                 );
                 let new_iter = child_node.children.iter_mut();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((data, old_iter));
             }
             // Found the end of a `children.values_mut()` iterator.
             if let Some((data, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(data)
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 }
 
 impl<'on_disk> super::dispatch::DirstateMapMethods for DirstateMap<'on_disk> {
     fn clear(&mut self) {
         self.root.clear();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         self.add_or_remove_file(filename, old_state, entry);
         Ok(())
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         let entry = DirstateEntry {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         };
         self.add_or_remove_file(filename, old_state, entry);
         Ok(())
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
-        let was_tracked = old_state.is_tracked();
-        if let Some(node) = Self::get_node_mut_tracing_ancestors(
-            &mut self.root,
-            filename,
-            |ancestor| {
-                if was_tracked {
-                    ancestor.tracked_descendants_count -= 1
+        struct Dropped {
+            was_tracked: bool,
+            had_entry: bool,
+            had_copy_source: bool,
                 }
-            },
-        ) {
-            let had_entry = node.entry.is_some();
-            let had_copy_source = node.copy_source.is_some();
-
+        fn recur(nodes: &mut ChildNodes, path: &HgPath) -> Option<Dropped> {
+            let (first_path_component, rest_of_path) =
+                path.split_first_component();
+            let node = nodes.get_mut(first_path_component)?;
+            let dropped;
+            if let Some(rest) = rest_of_path {
+                dropped = recur(&mut node.children, rest)?;
+                if dropped.was_tracked {
+                    node.tracked_descendants_count -= 1;
+                }
+            } else {
+                dropped = Dropped {
+                    was_tracked: node
+                        .entry
+                        .as_ref()
+                        .map_or(false, |entry| entry.state.is_tracked()),
+                    had_entry: node.entry.take().is_some(),
+                    had_copy_source: node.copy_source.take().is_some(),
+                };
             // TODO: this leaves in the tree a "non-file" node. Should we
             // remove the node instead, together with ancestor nodes for
             // directories that become empty?
-            node.entry = None;
-            node.copy_source = None;
+            }
+            Some(dropped)
+        }
 
-            if had_entry {
+        if let Some(dropped) = recur(&mut self.root, filename) {
+            if dropped.had_entry {
                 self.nodes_with_entry_count -= 1
             }
-            if had_copy_source {
+            if dropped.had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
-            Ok(had_entry)
+            Ok(dropped.had_entry)
         } else {
-            assert!(!was_tracked);
+            debug_assert!(!old_state.is_tracked());
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32) {
         for filename in filenames {
             if let Some(node) = Self::get_node_mut(&mut self.root, &filename) {
                 if let Some(entry) = node.entry.as_mut() {
                     clear_ambiguous_mtime(entry, now);
                 }
             }
         }
     }
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool {
         self.get_node(key)
             .and_then(|node| node.entry.as_ref())
             .map_or(false, DirstateEntry::is_non_normal)
     }
 
     fn non_normal_entries_remove(&mut self, _key: &HgPath) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| {
                     entry.is_non_normal() || entry.is_from_other_parent()
                 })
                 .map(|_| path)
         }))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, _force: bool) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" and "from other parent" sets that need to be recomputed
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_non_normal())
                 .map(|_| path)
         }))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_from_other_parent())
                 .map(|_| path)
         }))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none() && node.tracked_descendants_count > 0)
         } else {
             Ok(false)
         }
     }
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none())
         } else {
             Ok(false)
         }
     }
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for (path, node) in self.iter_nodes() {
             if node.entry.is_some() {
                 size += packed_entry_size(
                     path,
                     node.copy_source.as_ref().map(|p| &**p),
                 )
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         let now: i32 = now.0.try_into().expect("time overflow");
         for (path, opt_entry, copy_source) in self.iter_node_data_mut() {
             if let Some(entry) = opt_entry {
                 clear_ambiguous_mtime(entry, now);
                 pack_entry(
                     path,
                     entry,
                     copy_source.as_ref().map(|p| &**p),
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `all_dirs` that
         // needs to be recomputed
         Ok(())
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `dirs` that needs
         // to be recomputed
         Ok(())
     }
 
     fn status<'a>(
         &'a mut self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
     {
         super::status::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.copy_source
                 .as_ref()
                 .map(|copy_source| (path, &**copy_source))
         }))
     }
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool {
         if let Some(node) = self.get_node(key) {
             node.copy_source.is_some()
         } else {
             false
         }
     }
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPath> {
         self.get_node(key)?.copy_source.as_ref().map(|p| &**p)
     }
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf> {
         let count = &mut self.nodes_with_copy_source_count;
         Self::get_node_mut(&mut self.root, key).and_then(|node| {
             if node.copy_source.is_some() {
                 *count -= 1
             }
             node.copy_source.take().map(Cow::into_owned)
         })
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf> {
         let node = Self::get_or_insert_node(
             &mut self.root,
             &key,
             WithBasename::to_cow_owned,
             |_ancestor| {},
         );
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         node.copy_source.replace(value.into()).map(Cow::into_owned)
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count
     }
 
     fn contains_key(&self, key: &HgPath) -> bool {
         self.get(key).is_some()
     }
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry> {
         self.get_node(key)?.entry.as_ref()
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry.as_ref().map(|entry| (path, entry))
         }))
     }
 }

rust/hg-core/src/utils/hg_path.rs

@@ -1,804 +1,814 b''
 // hg_path.rs
 //
 // 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::utils::SliceExt;
 use std::borrow::Borrow;
 use std::borrow::Cow;
 use std::convert::TryFrom;
 use std::ffi::{OsStr, OsString};
 use std::fmt;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 #[derive(Debug, Eq, PartialEq)]
 pub enum HgPathError {
     /// Bytes from the invalid `HgPath`
     LeadingSlash(Vec<u8>),
     ConsecutiveSlashes {
         bytes: Vec<u8>,
         second_slash_index: usize,
     },
     ContainsNullByte {
         bytes: Vec<u8>,
         null_byte_index: usize,
     },
     /// Bytes
     DecodeError(Vec<u8>),
     /// The rest come from audit errors
     EndsWithSlash(HgPathBuf),
     ContainsIllegalComponent(HgPathBuf),
     /// Path is inside the `.hg` folder
     InsideDotHg(HgPathBuf),
     IsInsideNestedRepo {
         path: HgPathBuf,
         nested_repo: HgPathBuf,
     },
     TraversesSymbolicLink {
         path: HgPathBuf,
         symlink: HgPathBuf,
     },
     NotFsCompliant(HgPathBuf),
     /// `path` is the smallest invalid path
     NotUnderRoot {
         path: PathBuf,
         root: PathBuf,
     },
 }
 
 impl fmt::Display for HgPathError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             HgPathError::LeadingSlash(bytes) => {
                 write!(f, "Invalid HgPath '{:?}': has a leading slash.", bytes)
             }
             HgPathError::ConsecutiveSlashes {
                 bytes,
                 second_slash_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': consecutive slashes at pos {}.",
                 bytes, pos
             ),
             HgPathError::ContainsNullByte {
                 bytes,
                 null_byte_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': contains null byte at pos {}.",
                 bytes, pos
             ),
             HgPathError::DecodeError(bytes) => write!(
                 f,
                 "Invalid HgPath '{:?}': could not be decoded.",
                 bytes
             ),
             HgPathError::EndsWithSlash(path) => {
                 write!(f, "Audit failed for '{}': ends with a slash.", path)
             }
             HgPathError::ContainsIllegalComponent(path) => write!(
                 f,
                 "Audit failed for '{}': contains an illegal component.",
                 path
             ),
             HgPathError::InsideDotHg(path) => write!(
                 f,
                 "Audit failed for '{}': is inside the '.hg' folder.",
                 path
             ),
             HgPathError::IsInsideNestedRepo {
                 path,
                 nested_repo: nested,
             } => {
                 write!(f,
                 "Audit failed for '{}': is inside a nested repository '{}'.",
                 path, nested
             )
             }
             HgPathError::TraversesSymbolicLink { path, symlink } => write!(
                 f,
                 "Audit failed for '{}': traverses symbolic link '{}'.",
                 path, symlink
             ),
             HgPathError::NotFsCompliant(path) => write!(
                 f,
                 "Audit failed for '{}': cannot be turned into a \
                  filesystem path.",
                 path
             ),
             HgPathError::NotUnderRoot { path, root } => write!(
                 f,
                 "Audit failed for '{}': not under root {}.",
                 path.display(),
                 root.display()
             ),
         }
     }
 }
 
 impl From<HgPathError> for std::io::Error {
     fn from(e: HgPathError) -> Self {
         std::io::Error::new(std::io::ErrorKind::InvalidData, e.to_string())
     }
 }
 
 /// This is a repository-relative path (or canonical path):
 ///     - no null characters
 ///     - `/` separates directories
 ///     - no consecutive slashes
 ///     - no leading slash,
 ///     - no `.` nor `..` of special meaning
 ///     - stored in repository and shared across platforms
 ///
 /// Note: there is no guarantee of any `HgPath` being well-formed at any point
 /// in its lifetime for performance reasons and to ease ergonomics. It is
 /// however checked using the `check_state` method before any file-system
 /// operation.
 ///
 /// This allows us to be encoding-transparent as much as possible, until really
 /// needed; `HgPath` can be transformed into a platform-specific path (`OsStr`
 /// or `Path`) whenever more complex operations are needed:
 /// On Unix, it's just byte-to-byte conversion. On Windows, it has to be
 /// decoded from MBCS to WTF-8. If WindowsUTF8Plan is implemented, the source
 /// character encoding will be determined on a per-repository basis.
 //
 // FIXME: (adapted from a comment in the stdlib)
 // `HgPath::new()` current implementation relies on `Slice` being
 // layout-compatible with `[u8]`.
 // When attribute privacy is implemented, `Slice` should be annotated as
 // `#[repr(transparent)]`.
 // Anyway, `Slice` representation and layout are considered implementation
 // detail, are not documented and must not be relied upon.
 #[derive(Eq, Ord, PartialEq, PartialOrd, Hash)]
 pub struct HgPath {
     inner: [u8],
 }
 
 impl HgPath {
     pub fn new<S: AsRef<[u8]> + ?Sized>(s: &S) -> &Self {
         unsafe { &*(s.as_ref() as *const [u8] as *const Self) }
     }
     pub fn is_empty(&self) -> bool {
         self.inner.is_empty()
     }
     pub fn len(&self) -> usize {
         self.inner.len()
     }
     fn to_hg_path_buf(&self) -> HgPathBuf {
         HgPathBuf {
             inner: self.inner.to_owned(),
         }
     }
     pub fn bytes(&self) -> std::slice::Iter<u8> {
         self.inner.iter()
     }
     pub fn to_ascii_uppercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_uppercase())
     }
     pub fn to_ascii_lowercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_lowercase())
     }
     pub fn as_bytes(&self) -> &[u8] {
         &self.inner
     }
     pub fn contains(&self, other: u8) -> bool {
         self.inner.contains(&other)
     }
     pub fn starts_with(&self, needle: impl AsRef<Self>) -> bool {
         self.inner.starts_with(needle.as_ref().as_bytes())
     }
     pub fn trim_trailing_slash(&self) -> &Self {
         Self::new(if self.inner.last() == Some(&b'/') {
             &self.inner[..self.inner.len() - 1]
         } else {
             &self.inner[..]
         })
     }
     /// Returns a tuple of slices `(base, filename)` resulting from the split
     /// at the rightmost `/`, if any.
     ///
     /// # Examples:
     ///
     /// ```
     /// use hg::utils::hg_path::HgPath;
     ///
     /// let path = HgPath::new(b"cool/hg/path").split_filename();
     /// assert_eq!(path, (HgPath::new(b"cool/hg"), HgPath::new(b"path")));
     ///
     /// let path = HgPath::new(b"pathwithoutsep").split_filename();
     /// assert_eq!(path, (HgPath::new(b""), HgPath::new(b"pathwithoutsep")));
     /// ```
     pub fn split_filename(&self) -> (&Self, &Self) {
         match &self.inner.iter().rposition(|c| *c == b'/') {
             None => (HgPath::new(""), &self),
             Some(size) => (
                 HgPath::new(&self.inner[..*size]),
                 HgPath::new(&self.inner[*size + 1..]),
             ),
         }
     }
     pub fn join<T: ?Sized + AsRef<Self>>(&self, other: &T) -> HgPathBuf {
         let mut inner = self.inner.to_owned();
         if !inner.is_empty() && inner.last() != Some(&b'/') {
             inner.push(b'/');
         }
         inner.extend(other.as_ref().bytes());
         HgPathBuf::from_bytes(&inner)
     }
 
     pub fn components(&self) -> impl Iterator<Item = &HgPath> {
         self.inner.split(|&byte| byte == b'/').map(HgPath::new)
     }
 
+    /// Returns the first (that is "root-most") slash-separated component of
+    /// the path, and the rest after the first slash if there is one.
+    pub fn split_first_component(&self) -> (&HgPath, Option<&HgPath>) {
+        match self.inner.split_2(b'/') {
+            Some((a, b)) => (HgPath::new(a), Some(HgPath::new(b))),
+            None => (self, None),
+        }
+    }
+
     pub fn parent(&self) -> &Self {
         let inner = self.as_bytes();
         HgPath::new(match inner.iter().rposition(|b| *b == b'/') {
             Some(pos) => &inner[..pos],
             None => &[],
         })
     }
     /// Given a base directory, returns the slice of `self` relative to the
     /// base directory. If `base` is not a directory (does not end with a
     /// `b'/'`), returns `None`.
     pub fn relative_to(&self, base: impl AsRef<Self>) -> Option<&Self> {
         let base = base.as_ref();
         if base.is_empty() {
             return Some(self);
         }
         let is_dir = base.as_bytes().ends_with(b"/");
         if is_dir && self.starts_with(base) {
             Some(Self::new(&self.inner[base.len()..]))
         } else {
             None
         }
     }
 
     #[cfg(windows)]
     /// Copied from the Python stdlib's `os.path.splitdrive` implementation.
     ///
     /// Split a pathname into drive/UNC sharepoint and relative path
     /// specifiers. Returns a 2-tuple (drive_or_unc, path); either part may
     /// be empty.
     ///
     /// If you assign
     ///  result = split_drive(p)
     /// It is always true that:
     ///  result[0] + result[1] == p
     ///
     /// If the path contained a drive letter, drive_or_unc will contain
     /// everything up to and including the colon.
     /// e.g. split_drive("c:/dir") returns ("c:", "/dir")
     ///
     /// If the path contained a UNC path, the drive_or_unc will contain the
     /// host name and share up to but not including the fourth directory
     /// separator character.
     /// e.g. split_drive("//host/computer/dir") returns ("//host/computer",
     /// "/dir")
     ///
     /// Paths cannot contain both a drive letter and a UNC path.
     pub fn split_drive<'a>(&self) -> (&HgPath, &HgPath) {
         let bytes = self.as_bytes();
         let is_sep = |b| std::path::is_separator(b as char);
 
         if self.len() < 2 {
             (HgPath::new(b""), &self)
         } else if is_sep(bytes[0])
             && is_sep(bytes[1])
             && (self.len() == 2 || !is_sep(bytes[2]))
         {
             // Is a UNC path:
             // vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
             // \\machine\mountpoint\directory\etc\...
             //           directory ^^^^^^^^^^^^^^^
 
             let machine_end_index = bytes[2..].iter().position(|b| is_sep(*b));
             let mountpoint_start_index = if let Some(i) = machine_end_index {
                 i + 2
             } else {
                 return (HgPath::new(b""), &self);
             };
 
             match bytes[mountpoint_start_index + 1..]
                 .iter()
                 .position(|b| is_sep(*b))
             {
                 // A UNC path can't have two slashes in a row
                 // (after the initial two)
                 Some(0) => (HgPath::new(b""), &self),
                 Some(i) => {
                     let (a, b) =
                         bytes.split_at(mountpoint_start_index + 1 + i);
                     (HgPath::new(a), HgPath::new(b))
                 }
                 None => (&self, HgPath::new(b"")),
             }
         } else if bytes[1] == b':' {
             // Drive path c:\directory
             let (a, b) = bytes.split_at(2);
             (HgPath::new(a), HgPath::new(b))
         } else {
             (HgPath::new(b""), &self)
         }
     }
 
     #[cfg(unix)]
     /// Split a pathname into drive and path. On Posix, drive is always empty.
     pub fn split_drive(&self) -> (&HgPath, &HgPath) {
         (HgPath::new(b""), &self)
     }
 
     /// Checks for errors in the path, short-circuiting at the first one.
     /// This generates fine-grained errors useful for debugging.
     /// To simply check if the path is valid during tests, use `is_valid`.
     pub fn check_state(&self) -> Result<(), HgPathError> {
         if self.is_empty() {
             return Ok(());
         }
         let bytes = self.as_bytes();
         let mut previous_byte = None;
 
         if bytes[0] == b'/' {
             return Err(HgPathError::LeadingSlash(bytes.to_vec()));
         }
         for (index, byte) in bytes.iter().enumerate() {
             match byte {
                 0 => {
                     return Err(HgPathError::ContainsNullByte {
                         bytes: bytes.to_vec(),
                         null_byte_index: index,
                     })
                 }
                 b'/' => {
                     if previous_byte.is_some() && previous_byte == Some(b'/') {
                         return Err(HgPathError::ConsecutiveSlashes {
                             bytes: bytes.to_vec(),
                             second_slash_index: index,
                         });
                     }
                 }
                 _ => (),
             };
             previous_byte = Some(*byte);
         }
         Ok(())
     }
 
     #[cfg(test)]
     /// Only usable during tests to force developers to handle invalid states
     fn is_valid(&self) -> bool {
         self.check_state().is_ok()
     }
 }
 
 impl fmt::Debug for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPath({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 #[derive(
     Default, Eq, Ord, Clone, PartialEq, PartialOrd, Hash, derive_more::From,
 )]
 pub struct HgPathBuf {
     inner: Vec<u8>,
 }
 
 impl HgPathBuf {
     pub fn new() -> Self {
         Default::default()
     }
     pub fn push(&mut self, byte: u8) {
         self.inner.push(byte);
     }
     pub fn from_bytes(s: &[u8]) -> HgPathBuf {
         HgPath::new(s).to_owned()
     }
     pub fn into_vec(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl fmt::Debug for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPathBuf({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl Deref for HgPathBuf {
     type Target = HgPath;
 
     #[inline]
     fn deref(&self) -> &HgPath {
         &HgPath::new(&self.inner)
     }
 }
 
 impl<T: ?Sized + AsRef<HgPath>> From<&T> for HgPathBuf {
     fn from(s: &T) -> HgPathBuf {
         s.as_ref().to_owned()
     }
 }
 
 impl Into<Vec<u8>> for HgPathBuf {
     fn into(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl Borrow<HgPath> for HgPathBuf {
     fn borrow(&self) -> &HgPath {
         &HgPath::new(self.as_bytes())
     }
 }
 
 impl ToOwned for HgPath {
     type Owned = HgPathBuf;
 
     fn to_owned(&self) -> HgPathBuf {
         self.to_hg_path_buf()
     }
 }
 
 impl AsRef<HgPath> for HgPath {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl AsRef<HgPath> for HgPathBuf {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl Extend<u8> for HgPathBuf {
     fn extend<T: IntoIterator<Item = u8>>(&mut self, iter: T) {
         self.inner.extend(iter);
     }
 }
 
 /// TODO: Once https://www.mercurial-scm.org/wiki/WindowsUTF8Plan is
 /// implemented, these conversion utils will have to work differently depending
 /// on the repository encoding: either `UTF-8` or `MBCS`.
 
 pub fn hg_path_to_os_string<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<OsString, HgPathError> {
     hg_path.as_ref().check_state()?;
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(&hg_path.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     Ok(os_str.to_os_string())
 }
 
 pub fn hg_path_to_path_buf<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<PathBuf, HgPathError> {
     Ok(Path::new(&hg_path_to_os_string(hg_path)?).to_path_buf())
 }
 
 pub fn os_string_to_hg_path_buf<S: AsRef<OsStr>>(
     os_string: S,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_string.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 pub fn path_to_hg_path_buf<P: AsRef<Path>>(
     path: P,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     let os_str = path.as_ref().as_os_str();
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_str.as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 impl TryFrom<PathBuf> for HgPathBuf {
     type Error = HgPathError;
     fn try_from(path: PathBuf) -> Result<Self, Self::Error> {
         path_to_hg_path_buf(path)
     }
 }
 
 impl From<HgPathBuf> for Cow<'_, HgPath> {
     fn from(path: HgPathBuf) -> Self {
         Cow::Owned(path)
     }
 }
 
 impl<'a> From<&'a HgPath> for Cow<'a, HgPath> {
     fn from(path: &'a HgPath) -> Self {
         Cow::Borrowed(path)
     }
 }
 
 impl<'a> From<&'a HgPathBuf> for Cow<'a, HgPath> {
     fn from(path: &'a HgPathBuf) -> Self {
         Cow::Borrowed(&**path)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn test_path_states() {
         assert_eq!(
             Err(HgPathError::LeadingSlash(b"/".to_vec())),
             HgPath::new(b"/").check_state()
         );
         assert_eq!(
             Err(HgPathError::ConsecutiveSlashes {
                 bytes: b"a/b//c".to_vec(),
                 second_slash_index: 4
             }),
             HgPath::new(b"a/b//c").check_state()
         );
         assert_eq!(
             Err(HgPathError::ContainsNullByte {
                 bytes: b"a/b/\0c".to_vec(),
                 null_byte_index: 4
             }),
             HgPath::new(b"a/b/\0c").check_state()
         );
         // TODO test HgPathError::DecodeError for the Windows implementation.
         assert_eq!(true, HgPath::new(b"").is_valid());
         assert_eq!(true, HgPath::new(b"a/b/c").is_valid());
         // Backslashes in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(br"a\b/c").is_valid());
         // Dots in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(b"a/b/../c/").is_valid());
         assert_eq!(true, HgPath::new(b"./a/b/../c/").is_valid());
     }
 
     #[test]
     fn test_iter() {
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'c'), iter.next_back());
         assert_eq!(Some(&b'b'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'b'), iter.next());
         assert_eq!(Some(&b'c'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let iter = path.bytes();
         let mut vec = Vec::new();
         vec.extend(iter);
         assert_eq!(vec![b'a', b'b', b'c'], vec);
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(2), iter.rposition(|c| *c == b'c'));
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(None, iter.rposition(|c| *c == b'd'));
     }
 
     #[test]
     fn test_join() {
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"b"));
         assert_eq!(b"a/b", path.as_bytes());
 
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"b/c"));
         assert_eq!(b"a/b/c", path.as_bytes());
 
         // No leading slash if empty before join
         let path = HgPathBuf::new().join(HgPath::new(b"b/c"));
         assert_eq!(b"b/c", path.as_bytes());
 
         // The leading slash is an invalid representation of an `HgPath`, but
         // it can happen. This creates another invalid representation of
         // consecutive bytes.
         // TODO What should be done in this case? Should we silently remove
         // the extra slash? Should we change the signature to a problematic
         // `Result<HgPathBuf, HgPathError>`, or should we just keep it so and
         // let the error happen upon filesystem interaction?
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
     }
 
     #[test]
     fn test_relative_to() {
         let path = HgPath::new(b"");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"path");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"a");
         let base = HgPath::new(b"b");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a/");
         assert_eq!(Some(HgPath::new(b"b")), path.relative_to(base));
 
         let path = HgPath::new(b"nested/path/to/b");
         let base = HgPath::new(b"nested/path/");
         assert_eq!(Some(HgPath::new(b"to/b")), path.relative_to(base));
 
         let path = HgPath::new(b"ends/with/dir/");
         let base = HgPath::new(b"ends/");
         assert_eq!(Some(HgPath::new(b"with/dir/")), path.relative_to(base));
     }
 
     #[test]
     #[cfg(unix)]
     fn test_split_drive() {
         // Taken from the Python stdlib's tests
         assert_eq!(
             HgPath::new(br"/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"foo:bar"))
         );
         assert_eq!(
             HgPath::new(br":foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br":foo:bar"))
         );
         // Also try NT paths; should not split them
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(b""),
                 HgPath::new(br"\\conky\mountpoint\foo\bar")
             )
         );
     }
 
     #[test]
     #[cfg(windows)]
     fn test_split_drive() {
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br"\\conky\mountpoint"),
                 HgPath::new(br"\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br"//conky/mountpoint"),
                 HgPath::new(br"/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\\conky\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"///conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"///conky/mountpoint/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\conky\\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\conky\\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky//mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"//conky//mountpoint/foo/bar")
             )
         );
         // UNC part containing U+0130
         assert_eq!(
             HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT/foo/bar").split_drive(),
             (
                 HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT"),
                 HgPath::new(br"/foo/bar")
             )
         );
     }
 
     #[test]
     fn test_parent() {
         let path = HgPath::new(b"");
         assert_eq!(path.parent(), path);
 
         let path = HgPath::new(b"a");
         assert_eq!(path.parent(), HgPath::new(b""));
 
         let path = HgPath::new(b"a/b");
         assert_eq!(path.parent(), HgPath::new(b"a"));
 
         let path = HgPath::new(b"a/other/b");
         assert_eq!(path.parent(), HgPath::new(b"a/other"));
     }
 }