rust: Add a Filelog struct that wraps Revlog

Some filelog-specific logic is moved from code `rhg cat` into this struct
where it can better be reused.

Additionally, a missing end delimiter for metadata causes an error
to be returned instead of being silently ignored.

Differential Revision: https://phab.mercurial-scm.org/D11408

rust/hg-core/src/revlog/filelog.rs

@@ -0,0 +1,79 b''
+use crate::errors::HgError;
+use crate::repo::Repo;
+use crate::revlog::path_encode::path_encode;
+use crate::revlog::revlog::{Revlog, RevlogError};
+use crate::revlog::NodePrefix;
+use crate::revlog::Revision;
+use crate::utils::files::get_path_from_bytes;
+use crate::utils::hg_path::HgPath;
+use crate::utils::SliceExt;
+use std::borrow::Cow;
+use std::path::PathBuf;
+
+/// A specialized `Revlog` to work with file data logs.
+pub struct Filelog {
+    /// The generic `revlog` format.
+    revlog: Revlog,
+}
+
+impl Filelog {
+    pub fn open(repo: &Repo, file_path: &HgPath) -> Result<Self, RevlogError> {
+        let index_path = store_path(file_path, b".i");
+        let data_path = store_path(file_path, b".d");
+        let revlog = Revlog::open(repo, index_path, Some(&data_path))?;
+        Ok(Self { revlog })
+    }
+
+    /// The given node ID is that of the file as found in a manifest, not of a
+    /// changeset.
+    pub fn get_node(
+        &self,
+        file_node: impl Into<NodePrefix>,
+    ) -> Result<FilelogEntry, RevlogError> {
+        let file_rev = self.revlog.get_node_rev(file_node.into())?;
+        self.get_rev(file_rev)
+    }
+
+    /// The given revision is that of the file as found in a manifest, not of a
+    /// changeset.
+    pub fn get_rev(
+        &self,
+        file_rev: Revision,
+    ) -> Result<FilelogEntry, RevlogError> {
+        let data = self.revlog.get_rev_data(file_rev)?;
+        Ok(FilelogEntry(data.into()))
+    }
+}
+
+fn store_path(hg_path: &HgPath, suffix: &[u8]) -> PathBuf {
+    let encoded_bytes =
+        path_encode(&[b"data/", hg_path.as_bytes(), suffix].concat());
+    get_path_from_bytes(&encoded_bytes).into()
+}
+
+pub struct FilelogEntry<'filelog>(Cow<'filelog, [u8]>);
+
+impl<'filelog> FilelogEntry<'filelog> {
+    /// Split into metadata and data
+    pub fn split(&self) -> Result<(Option<&[u8]>, &[u8]), HgError> {
+        const DELIMITER: &[u8; 2] = &[b'\x01', b'\n'];
+
+        if let Some(rest) = self.0.drop_prefix(DELIMITER) {
+            if let Some((metadata, data)) = rest.split_2_by_slice(DELIMITER) {
+                Ok((Some(metadata), data))
+            } else {
+                Err(HgError::corrupted(
+                    "Missing metadata end delimiter in filelog entry",
+                ))
+            }
+        } else {
+            Ok((None, &self.0))
+        }
+    }
+
+    /// Returns the file contents at this revision, stripped of any metadata
+    pub fn data(&self) -> Result<&[u8], HgError> {
+        let (_metadata, data) = self.split()?;
+        Ok(data)
+    }
+}

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

@@ -1,99 +1,71 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 std::path::PathBuf;
-
 use crate::repo::Repo;
-use crate::revlog::path_encode::path_encode;
-use crate::revlog::revlog::Revlog;
 use crate::revlog::revlog::RevlogError;
 use crate::revlog::Node;
-use crate::utils::files::get_path_from_bytes;
-use crate::utils::hg_path::{HgPath, HgPathBuf};
+
+use crate::utils::hg_path::HgPathBuf;
 
 pub struct CatOutput {
     /// Whether any file in the manifest matched the paths given as CLI
     /// arguments
     pub found_any: bool,
     /// The contents of matching files, in manifest order
     pub concatenated: Vec<u8>,
     /// Which of the CLI arguments did not match any manifest file
     pub missing: Vec<HgPathBuf>,
     /// The node ID that the given revset was resolved to
     pub node: Node,
 }
 
-const METADATA_DELIMITER: [u8; 2] = [b'\x01', b'\n'];
-
 /// Output the given revision of files
 ///
 /// * `root`: Repository root
 /// * `rev`: The revision to cat the files from.
 /// * `files`: The files to output.
 pub fn cat<'a>(
     repo: &Repo,
     revset: &str,
     files: &'a [HgPathBuf],
 ) -> Result<CatOutput, RevlogError> {
     let rev = crate::revset::resolve_single(revset, repo)?;
     let manifest = repo.manifest(rev)?;
     let node = *repo
         .changelog()?
         .node_from_rev(rev)
         .expect("should succeed when repo.manifest did");
     let mut bytes = vec![];
     let mut matched = vec![false; files.len()];
     let mut found_any = false;
 
     for (manifest_file, node_bytes) in manifest.files_with_nodes() {
         for (cat_file, is_matched) in files.iter().zip(&mut matched) {
             if cat_file.as_bytes() == manifest_file.as_bytes() {
                 *is_matched = true;
                 found_any = true;
-                let index_path = store_path(manifest_file, b".i");
-                let data_path = store_path(manifest_file, b".d");
-
-                let file_log =
-                    Revlog::open(repo, &index_path, Some(&data_path))?;
+                let file_log = repo.filelog(manifest_file)?;
                 let file_node = Node::from_hex_for_repo(node_bytes)?;
-                let file_rev = file_log.get_node_rev(file_node.into())?;
-                let data = file_log.get_rev_data(file_rev)?;
-                if data.starts_with(&METADATA_DELIMITER) {
-                    let end_delimiter_position = data
-                        [METADATA_DELIMITER.len()..]
-                        .windows(METADATA_DELIMITER.len())
-                        .position(|bytes| bytes == METADATA_DELIMITER);
-                    if let Some(position) = end_delimiter_position {
-                        let offset = METADATA_DELIMITER.len() * 2;
-                        bytes.extend(data[position + offset..].iter());
-                    }
-                } else {
-                    bytes.extend(data);
-                }
+                let entry = file_log.get_node(file_node)?;
+                bytes.extend(entry.data()?)
             }
         }
     }
 
     let missing: Vec<_> = files
         .iter()
         .zip(&matched)
         .filter(|pair| !*pair.1)
         .map(|pair| pair.0.clone())
         .collect();
     Ok(CatOutput {
         found_any,
         concatenated: bytes,
         missing,
         node,
     })
 }
-
-fn store_path(hg_path: &HgPath, suffix: &[u8]) -> PathBuf {
-    let encoded_bytes =
-        path_encode(&[b"data/", hg_path.as_bytes(), suffix].concat());
-    get_path_from_bytes(&encoded_bytes).into()
-}

rust/hg-core/src/repo.rs

@@ -1,403 +1,409 b''
 use crate::changelog::Changelog;
 use crate::config::{Config, ConfigError, ConfigParseError};
 use crate::dirstate::DirstateParents;
 use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::owning::OwningDirstateMap;
 use crate::errors::HgError;
 use crate::errors::HgResultExt;
 use crate::manifest::{Manifest, Manifestlog};
 use crate::requirements;
+use crate::revlog::filelog::Filelog;
 use crate::revlog::revlog::RevlogError;
 use crate::utils::files::get_path_from_bytes;
+use crate::utils::hg_path::HgPath;
 use crate::utils::SliceExt;
 use crate::vfs::{is_dir, is_file, Vfs};
 use crate::{exit_codes, Node};
 use crate::{DirstateError, Revision};
 use std::cell::{Cell, Ref, RefCell, RefMut};
 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,
     // None means not known/initialized yet
     dirstate_parents: Cell<Option<DirstateParents>>,
     dirstate_map: LazyCell<OwningDirstateMap, DirstateError>,
     changelog: LazyCell<Changelog, RevlogError>,
     manifestlog: LazyCell<Manifestlog, RevlogError>,
 }
 
 #[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(),
         }
     }
 }
 
 impl Repo {
     /// tries to find nearest repository root in current working directory or
     /// its ancestors
     pub fn find_repo_root() -> Result<PathBuf, RepoError> {
         let current_directory = crate::utils::current_dir()?;
         // ancestors() is inclusive: it first yields `current_directory`
         // as-is.
         for ancestor in current_directory.ancestors() {
             if is_dir(ancestor.join(".hg"))? {
                 return Ok(ancestor.to_path_buf());
             }
         }
         return Err(RepoError::NotFound {
             at: current_directory,
         });
     }
 
     /// 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<PathBuf>,
     ) -> Result<Self, RepoError> {
         if let Some(root) = explicit_path {
             if is_dir(root.join(".hg"))? {
                 Self::new_at_path(root.to_owned(), config)
             } else if is_file(&root)? {
                 Err(HgError::unsupported("bundle repository").into())
             } else {
                 Err(RepoError::NotFound {
                     at: root.to_owned(),
                 })
             }
         } else {
             let root = Self::find_repo_root()?;
             Self::new_at_path(root, config)
         }
     }
 
     /// 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_matches(|b| b == b'\n'))
                     .to_owned();
             if relative {
                 shared_path = dot_hg.join(shared_path)
             }
             if !is_dir(&shared_path)? {
                 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)",
                         exit_codes::ABORT,
                     ),
                     _ => 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)",
                         exit_codes::ABORT,
                         ),
                         _ => 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,
             dirstate_parents: Cell::new(None),
             dirstate_map: LazyCell::new(Self::new_dirstate_map),
             changelog: LazyCell::new(Changelog::open),
             manifestlog: LazyCell::new(Manifestlog::open),
         };
 
         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)
     }
 
     fn dirstate_file_contents(&self) -> Result<Vec<u8>, HgError> {
         Ok(self
             .hg_vfs()
             .read("dirstate")
             .io_not_found_as_none()?
             .unwrap_or(Vec::new()))
     }
 
     pub fn dirstate_parents(&self) -> Result<DirstateParents, HgError> {
         if let Some(parents) = self.dirstate_parents.get() {
             return Ok(parents);
         }
         let dirstate = self.dirstate_file_contents()?;
         let parents = if dirstate.is_empty() {
             DirstateParents::NULL
         } else if self.has_dirstate_v2() {
             crate::dirstate_tree::on_disk::read_docket(&dirstate)?.parents()
         } else {
             crate::dirstate::parsers::parse_dirstate_parents(&dirstate)?
                 .clone()
         };
         self.dirstate_parents.set(Some(parents));
         Ok(parents)
     }
 
     fn new_dirstate_map(&self) -> Result<OwningDirstateMap, DirstateError> {
         let dirstate_file_contents = self.dirstate_file_contents()?;
         if dirstate_file_contents.is_empty() {
             self.dirstate_parents.set(Some(DirstateParents::NULL));
             Ok(OwningDirstateMap::new_empty(Vec::new()))
         } else if self.has_dirstate_v2() {
             let docket = crate::dirstate_tree::on_disk::read_docket(
                 &dirstate_file_contents,
             )?;
             self.dirstate_parents.set(Some(docket.parents()));
             let data_size = docket.data_size();
             let metadata = docket.tree_metadata();
             let mut map = if let Some(data_mmap) = self
                 .hg_vfs()
                 .mmap_open(docket.data_filename())
                 .io_not_found_as_none()?
             {
                 OwningDirstateMap::new_empty(MmapWrapper(data_mmap))
             } else {
                 OwningDirstateMap::new_empty(Vec::new())
             };
             let (on_disk, placeholder) = map.get_mut_pair();
             *placeholder = DirstateMap::new_v2(on_disk, data_size, metadata)?;
             Ok(map)
         } else {
             let mut map = OwningDirstateMap::new_empty(dirstate_file_contents);
             let (on_disk, placeholder) = map.get_mut_pair();
             let (inner, parents) = DirstateMap::new_v1(on_disk)?;
             self.dirstate_parents
                 .set(Some(parents.unwrap_or(DirstateParents::NULL)));
             *placeholder = inner;
             Ok(map)
         }
     }
 
     pub fn dirstate_map(
         &self,
     ) -> Result<Ref<OwningDirstateMap>, DirstateError> {
         self.dirstate_map.get_or_init(self)
     }
 
     pub fn dirstate_map_mut(
         &self,
     ) -> Result<RefMut<OwningDirstateMap>, DirstateError> {
         self.dirstate_map.get_mut_or_init(self)
     }
 
     pub fn changelog(&self) -> Result<Ref<Changelog>, RevlogError> {
         self.changelog.get_or_init(self)
     }
 
     pub fn changelog_mut(&self) -> Result<RefMut<Changelog>, RevlogError> {
         self.changelog.get_mut_or_init(self)
     }
 
     pub fn manifestlog(&self) -> Result<Ref<Manifestlog>, RevlogError> {
         self.manifestlog.get_or_init(self)
     }
 
     pub fn manifestlog_mut(&self) -> Result<RefMut<Manifestlog>, RevlogError> {
         self.manifestlog.get_mut_or_init(self)
     }
 
     /// Returns the manifest of the given revision
     pub fn manifest(
         &self,
         revision: Revision,
     ) -> Result<Manifest, RevlogError> {
         let changelog = self.changelog()?;
         let manifest = self.manifestlog()?;
         let changelog_entry = changelog.get_rev(revision)?;
         let manifest_node =
             Node::from_hex_for_repo(&changelog_entry.manifest_node()?)?;
         manifest.get_node(manifest_node.into())
     }
+
+    pub fn filelog(&self, path: &HgPath) -> Result<Filelog, RevlogError> {
+        Filelog::open(self, path)
+    }
 }
 
 /// Lazily-initialized component of `Repo` with interior mutability
 ///
 /// This differs from `OnceCell` in that the value can still be "deinitialized"
 /// later by setting its inner `Option` to `None`.
 struct LazyCell<T, E> {
     value: RefCell<Option<T>>,
     // `Fn`s that don’t capture environment are zero-size, so this box does
     // not allocate:
     init: Box<dyn Fn(&Repo) -> Result<T, E>>,
 }
 
 impl<T, E> LazyCell<T, E> {
     fn new(init: impl Fn(&Repo) -> Result<T, E> + 'static) -> Self {
         Self {
             value: RefCell::new(None),
             init: Box::new(init),
         }
     }
 
     fn get_or_init(&self, repo: &Repo) -> Result<Ref<T>, E> {
         let mut borrowed = self.value.borrow();
         if borrowed.is_none() {
             drop(borrowed);
             // Only use `borrow_mut` if it is really needed to avoid panic in
             // case there is another outstanding borrow but mutation is not
             // needed.
             *self.value.borrow_mut() = Some((self.init)(repo)?);
             borrowed = self.value.borrow()
         }
         Ok(Ref::map(borrowed, |option| option.as_ref().unwrap()))
     }
 
     pub fn get_mut_or_init(&self, repo: &Repo) -> Result<RefMut<T>, E> {
         let mut borrowed = self.value.borrow_mut();
         if borrowed.is_none() {
             *borrowed = Some((self.init)(repo)?);
         }
         Ok(RefMut::map(borrowed, |option| option.as_mut().unwrap()))
     }
 }
 
 // TODO: remove this when https://github.com/RazrFalcon/memmap2-rs/pull/22 is on crates.io
 struct MmapWrapper(memmap2::Mmap);
 
 impl std::ops::Deref for MmapWrapper {
     type Target = [u8];
 
     fn deref(&self) -> &[u8] {
         self.0.deref()
     }
 }
 
 unsafe impl stable_deref_trait::StableDeref for MmapWrapper {}

rust/hg-core/src/revlog.rs

@@ -1,71 +1,72 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 //! Mercurial concepts for handling revision history
 
 pub mod node;
 pub mod nodemap;
 mod nodemap_docket;
 pub mod path_encode;
 pub use node::{FromHexError, Node, NodePrefix};
 pub mod changelog;
+pub mod filelog;
 pub mod index;
 pub mod manifest;
 pub mod patch;
 pub mod revlog;
 
 /// Mercurial revision numbers
 ///
 /// As noted in revlog.c, revision numbers are actually encoded in
 /// 4 bytes, and are liberally converted to ints, whence the i32
 pub type Revision = i32;
 
 /// Marker expressing the absence of a parent
 ///
 /// Independently of the actual representation, `NULL_REVISION` is guaranteed
 /// to be smaller than all existing revisions.
 pub const NULL_REVISION: Revision = -1;
 
 /// Same as `mercurial.node.wdirrev`
 ///
 /// This is also equal to `i32::max_value()`, but it's better to spell
 /// it out explicitely, same as in `mercurial.node`
 #[allow(clippy::unreadable_literal)]
 pub const WORKING_DIRECTORY_REVISION: Revision = 0x7fffffff;
 
 pub const WORKING_DIRECTORY_HEX: &str =
     "ffffffffffffffffffffffffffffffffffffffff";
 
 /// The simplest expression of what we need of Mercurial DAGs.
 pub trait Graph {
     /// Return the two parents of the given `Revision`.
     ///
     /// Each of the parents can be independently `NULL_REVISION`
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError>;
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
     WorkingDirectoryUnsupported,
 }
 
 /// The Mercurial Revlog Index
 ///
 /// This is currently limited to the minimal interface that is needed for
 /// the [`nodemap`](nodemap/index.html) module
 pub trait RevlogIndex {
     /// Total number of Revisions referenced in this index
     fn len(&self) -> usize;
 
     fn is_empty(&self) -> bool {
         self.len() == 0
     }
 
     /// Return a reference to the Node or `None` if rev is out of bounds
     ///
     /// `NULL_REVISION` is not considered to be out of bounds.
     fn node(&self, rev: Revision) -> Option<&Node>;
 }

rust/hg-core/src/utils.rs

@@ -1,481 +1,490 b''
 // utils 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.
 
 //! Contains useful functions, traits, structs, etc. for use in core.
 
 use crate::errors::{HgError, IoErrorContext};
 use crate::utils::hg_path::HgPath;
 use im_rc::ordmap::DiffItem;
 use im_rc::ordmap::OrdMap;
 use std::cell::Cell;
 use std::fmt;
 use std::{io::Write, ops::Deref};
 
 pub mod files;
 pub mod hg_path;
 pub mod path_auditor;
 
 /// Useful until rust/issues/56345 is stable
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::find_slice_in_slice;
 ///
 /// let haystack = b"This is the haystack".to_vec();
 /// assert_eq!(find_slice_in_slice(&haystack, b"the"), Some(8));
 /// assert_eq!(find_slice_in_slice(&haystack, b"not here"), None);
 /// ```
 pub fn find_slice_in_slice<T>(slice: &[T], needle: &[T]) -> Option<usize>
 where
     for<'a> &'a [T]: PartialEq,
 {
     slice
         .windows(needle.len())
         .position(|window| window == needle)
 }
 
 /// Replaces the `from` slice with the `to` slice inside the `buf` slice.
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::replace_slice;
 /// let mut line = b"I hate writing tests!".to_vec();
 /// replace_slice(&mut line, b"hate", b"love");
 /// assert_eq!(
 ///     line,
 ///     b"I love writing tests!".to_vec()
 /// );
 /// ```
 pub fn replace_slice<T>(buf: &mut [T], from: &[T], to: &[T])
 where
     T: Clone + PartialEq,
 {
     if buf.len() < from.len() || from.len() != to.len() {
         return;
     }
     for i in 0..=buf.len() - from.len() {
         if buf[i..].starts_with(from) {
             buf[i..(i + from.len())].clone_from_slice(to);
         }
     }
 }
 
 pub trait SliceExt {
     fn trim_end(&self) -> &Self;
     fn trim_start(&self) -> &Self;
     fn trim_end_matches(&self, f: impl FnMut(u8) -> bool) -> &Self;
     fn trim_start_matches(&self, f: impl FnMut(u8) -> bool) -> &Self;
     fn trim(&self) -> &Self;
     fn drop_prefix(&self, needle: &Self) -> Option<&Self>;
     fn split_2(&self, separator: u8) -> Option<(&[u8], &[u8])>;
+    fn split_2_by_slice(&self, separator: &[u8]) -> Option<(&[u8], &[u8])>;
 }
 
 impl SliceExt for [u8] {
     fn trim_end(&self) -> &[u8] {
         self.trim_end_matches(|byte| byte.is_ascii_whitespace())
     }
 
     fn trim_start(&self) -> &[u8] {
         self.trim_start_matches(|byte| byte.is_ascii_whitespace())
     }
 
     fn trim_end_matches(&self, mut f: impl FnMut(u8) -> bool) -> &Self {
         if let Some(last) = self.iter().rposition(|&byte| !f(byte)) {
             &self[..=last]
         } else {
             &[]
         }
     }
 
     fn trim_start_matches(&self, mut f: impl FnMut(u8) -> bool) -> &Self {
         if let Some(first) = self.iter().position(|&byte| !f(byte)) {
             &self[first..]
         } else {
             &[]
         }
     }
 
     /// ```
     /// use hg::utils::SliceExt;
     /// assert_eq!(
     ///     b"  to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"  to trim".trim(),
     ///     b"to trim"
     /// );
     /// ```
     fn trim(&self) -> &[u8] {
         self.trim_start().trim_end()
     }
 
     fn drop_prefix(&self, needle: &Self) -> Option<&Self> {
         if self.starts_with(needle) {
             Some(&self[needle.len()..])
         } else {
             None
         }
     }
 
     fn split_2(&self, separator: u8) -> Option<(&[u8], &[u8])> {
         let mut iter = self.splitn(2, |&byte| byte == separator);
         let a = iter.next()?;
         let b = iter.next()?;
         Some((a, b))
     }
+
+    fn split_2_by_slice(&self, separator: &[u8]) -> Option<(&[u8], &[u8])> {
+        if let Some(pos) = find_slice_in_slice(self, separator) {
+            Some((&self[..pos], &self[pos + separator.len()..]))
+        } else {
+            None
+        }
+    }
 }
 
 pub trait Escaped {
     /// Return bytes escaped for display to the user
     fn escaped_bytes(&self) -> Vec<u8>;
 }
 
 impl Escaped for u8 {
     fn escaped_bytes(&self) -> Vec<u8> {
         let mut acc = vec![];
         match self {
             c @ b'\'' | c @ b'\\' => {
                 acc.push(b'\\');
                 acc.push(*c);
             }
             b'\t' => {
                 acc.extend(br"\\t");
             }
             b'\n' => {
                 acc.extend(br"\\n");
             }
             b'\r' => {
                 acc.extend(br"\\r");
             }
             c if (*c < b' ' || *c >= 127) => {
                 write!(acc, "\\x{:x}", self).unwrap();
             }
             c => {
                 acc.push(*c);
             }
         }
         acc
     }
 }
 
 impl<'a, T: Escaped> Escaped for &'a [T] {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.iter().flat_map(Escaped::escaped_bytes).collect()
     }
 }
 
 impl<T: Escaped> Escaped for Vec<T> {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.deref().escaped_bytes()
     }
 }
 
 impl<'a> Escaped for &'a HgPath {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.as_bytes().escaped_bytes()
     }
 }
 
 // TODO: use the str method when we require Rust 1.45
 pub(crate) fn strip_suffix<'a>(s: &'a str, suffix: &str) -> Option<&'a str> {
     if s.ends_with(suffix) {
         Some(&s[..s.len() - suffix.len()])
     } else {
         None
     }
 }
 
 #[cfg(unix)]
 pub fn shell_quote(value: &[u8]) -> Vec<u8> {
     // TODO: Use the `matches!` macro when we require Rust 1.42+
     if value.iter().all(|&byte| match byte {
         b'a'..=b'z'
         | b'A'..=b'Z'
         | b'0'..=b'9'
         | b'.'
         | b'_'
         | b'/'
         | b'+'
         | b'-' => true,
         _ => false,
     }) {
         value.to_owned()
     } else {
         let mut quoted = Vec::with_capacity(value.len() + 2);
         quoted.push(b'\'');
         for &byte in value {
             if byte == b'\'' {
                 quoted.push(b'\\');
             }
             quoted.push(byte);
         }
         quoted.push(b'\'');
         quoted
     }
 }
 
 pub fn current_dir() -> Result<std::path::PathBuf, HgError> {
     std::env::current_dir().map_err(|error| HgError::IoError {
         error,
         context: IoErrorContext::CurrentDir,
     })
 }
 
 pub fn current_exe() -> Result<std::path::PathBuf, HgError> {
     std::env::current_exe().map_err(|error| HgError::IoError {
         error,
         context: IoErrorContext::CurrentExe,
     })
 }
 
 /// Expand `$FOO` and `${FOO}` environment variables in the given byte string
 pub fn expand_vars(s: &[u8]) -> std::borrow::Cow<[u8]> {
     lazy_static::lazy_static! {
         /// https://github.com/python/cpython/blob/3.9/Lib/posixpath.py#L301
         /// The `x` makes whitespace ignored.
         /// `-u` disables the Unicode flag, which makes `\w` like Python with the ASCII flag.
         static ref VAR_RE: regex::bytes::Regex =
             regex::bytes::Regex::new(r"(?x-u)
                 \$
                 (?:
                     (\w+)
                     |
                     \{
                         ([^}]*)
                     \}
                 )
             ").unwrap();
     }
     VAR_RE.replace_all(s, |captures: &regex::bytes::Captures| {
         let var_name = files::get_os_str_from_bytes(
             captures
                 .get(1)
                 .or_else(|| captures.get(2))
                 .expect("either side of `|` must participate in match")
                 .as_bytes(),
         );
         std::env::var_os(var_name)
             .map(files::get_bytes_from_os_str)
             .unwrap_or_else(|| {
                 // Referencing an environment variable that does not exist.
                 // Leave the $FOO reference as-is.
                 captures[0].to_owned()
             })
     })
 }
 
 #[test]
 fn test_expand_vars() {
     // Modifying process-global state in a test isn’t great,
     // but hopefully this won’t collide with anything.
     std::env::set_var("TEST_EXPAND_VAR", "1");
     assert_eq!(
         expand_vars(b"before/$TEST_EXPAND_VAR/after"),
         &b"before/1/after"[..]
     );
     assert_eq!(
         expand_vars(b"before${TEST_EXPAND_VAR}${TEST_EXPAND_VAR}${TEST_EXPAND_VAR}after"),
         &b"before111after"[..]
     );
     let s = b"before $SOME_LONG_NAME_THAT_WE_ASSUME_IS_NOT_AN_ACTUAL_ENV_VAR after";
     assert_eq!(expand_vars(s), &s[..]);
 }
 
 pub(crate) enum MergeResult<V> {
     UseLeftValue,
     UseRightValue,
     UseNewValue(V),
 }
 
 /// Return the union of the two given maps,
 /// calling `merge(key, left_value, right_value)` to resolve keys that exist in
 /// both.
 ///
 /// CC https://github.com/bodil/im-rs/issues/166
 pub(crate) fn ordmap_union_with_merge<K, V>(
     left: OrdMap<K, V>,
     right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone + PartialEq,
 {
     if left.ptr_eq(&right) {
         // One of the two maps is an unmodified clone of the other
         left
     } else if left.len() / 2 > right.len() {
         // When two maps have different sizes,
         // their size difference is a lower bound on
         // how many keys of the larger map are not also in the smaller map.
         // This in turn is a lower bound on the number of differences in
         // `OrdMap::diff` and the "amount of work" that would be done
         // by `ordmap_union_with_merge_by_diff`.
         //
         // Here `left` is more than twice the size of `right`,
         // so the number of differences is more than the total size of
         // `right`. Therefore an algorithm based on iterating `right`
         // is more efficient.
         //
         // This helps a lot when a tiny (or empty) map is merged
         // with a large one.
         ordmap_union_with_merge_by_iter(left, right, merge)
     } else if left.len() < right.len() / 2 {
         // Same as above but with `left` and `right` swapped
         ordmap_union_with_merge_by_iter(right, left, |key, a, b| {
             // Also swapped in `merge` arguments:
             match merge(key, b, a) {
                 MergeResult::UseNewValue(v) => MergeResult::UseNewValue(v),
                 // … and swap back in `merge` result:
                 MergeResult::UseLeftValue => MergeResult::UseRightValue,
                 MergeResult::UseRightValue => MergeResult::UseLeftValue,
             }
         })
     } else {
         // For maps of similar size, use the algorithm based on `OrdMap::diff`
         ordmap_union_with_merge_by_diff(left, right, merge)
     }
 }
 
 /// Efficient if `right` is much smaller than `left`
 fn ordmap_union_with_merge_by_iter<K, V>(
     mut left: OrdMap<K, V>,
     right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone,
 {
     for (key, right_value) in right {
         match left.get(&key) {
             None => {
                 left.insert(key, right_value);
             }
             Some(left_value) => match merge(&key, left_value, &right_value) {
                 MergeResult::UseLeftValue => {}
                 MergeResult::UseRightValue => {
                     left.insert(key, right_value);
                 }
                 MergeResult::UseNewValue(new_value) => {
                     left.insert(key, new_value);
                 }
             },
         }
     }
     left
 }
 
 /// Fallback when both maps are of similar size
 fn ordmap_union_with_merge_by_diff<K, V>(
     mut left: OrdMap<K, V>,
     mut right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone + PartialEq,
 {
     // (key, value) pairs that would need to be inserted in either map
     // in order to turn it into the union.
     //
     // TODO: if/when https://github.com/bodil/im-rs/pull/168 is accepted,
     // change these from `Vec<(K, V)>` to `Vec<(&K, Cow<V>)>`
     // with `left_updates` only borrowing from `right` and `right_updates` from
     // `left`, and with `Cow::Owned` used for `MergeResult::UseNewValue`.
     //
     // This would allow moving all `.clone()` calls to after we’ve decided
     // which of `right_updates` or `left_updates` to use
     // (value ones becoming `Cow::into_owned`),
     // and avoid making clones we don’t end up using.
     let mut left_updates = Vec::new();
     let mut right_updates = Vec::new();
 
     for difference in left.diff(&right) {
         match difference {
             DiffItem::Add(key, value) => {
                 left_updates.push((key.clone(), value.clone()))
             }
             DiffItem::Remove(key, value) => {
                 right_updates.push((key.clone(), value.clone()))
             }
             DiffItem::Update {
                 old: (key, left_value),
                 new: (_, right_value),
             } => match merge(key, left_value, right_value) {
                 MergeResult::UseLeftValue => {
                     right_updates.push((key.clone(), left_value.clone()))
                 }
                 MergeResult::UseRightValue => {
                     left_updates.push((key.clone(), right_value.clone()))
                 }
                 MergeResult::UseNewValue(new_value) => {
                     left_updates.push((key.clone(), new_value.clone()));
                     right_updates.push((key.clone(), new_value))
                 }
             },
         }
     }
     if left_updates.len() < right_updates.len() {
         for (key, value) in left_updates {
             left.insert(key, value);
         }
         left
     } else {
         for (key, value) in right_updates {
             right.insert(key, value);
         }
         right
     }
 }
 
 /// Join items of the iterable with the given separator, similar to Python’s
 /// `separator.join(iter)`.
 ///
 /// Formatting the return value consumes the iterator.
 /// Formatting it again will produce an empty string.
 pub fn join_display(
     iter: impl IntoIterator<Item = impl fmt::Display>,
     separator: impl fmt::Display,
 ) -> impl fmt::Display {
     JoinDisplay {
         iter: Cell::new(Some(iter.into_iter())),
         separator,
     }
 }
 
 struct JoinDisplay<I, S> {
     iter: Cell<Option<I>>,
     separator: S,
 }
 
 impl<I, T, S> fmt::Display for JoinDisplay<I, S>
 where
     I: Iterator<Item = T>,
     T: fmt::Display,
     S: fmt::Display,
 {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         if let Some(mut iter) = self.iter.take() {
             if let Some(first) = iter.next() {
                 first.fmt(f)?;
             }
             for value in iter {
                 self.separator.fmt(f)?;
                 value.fmt(f)?;
             }
         }
         Ok(())
     }
 }