rhg: Initial repository locking

Initial Rust implementation of locking based on the `.hg/wlock` symlink (or file),
with lock breaking when the recorded pid and hostname show that a lock was
left by a local process that is not running anymore (as it might have been
killed).

Differential Revision: https://phab.mercurial-scm.org/D11835

rust/hg-core/src/lock.rs

@@ -0,0 +1,187 b''
+//! Filesystem-based locks for local repositories
+
+use crate::errors::HgError;
+use crate::errors::HgResultExt;
+use crate::utils::StrExt;
+use crate::vfs::Vfs;
+use std::io;
+use std::io::ErrorKind;
+
+#[derive(derive_more::From)]
+pub enum LockError {
+    AlreadyHeld,
+    #[from]
+    Other(HgError),
+}
+
+/// Try to call `f` with the lock acquired, without waiting.
+///
+/// If the lock is aready held, `f` is not called and `LockError::AlreadyHeld`
+/// is returned. `LockError::Io` is returned for any unexpected I/O error
+/// accessing the lock file, including for removing it after `f` was called.
+/// The return value of `f` is dropped in that case. If all is successful, the
+/// return value of `f` is forwarded.
+pub fn try_with_lock_no_wait<R>(
+    hg_vfs: Vfs,
+    lock_filename: &str,
+    f: impl FnOnce() -> R,
+) -> Result<R, LockError> {
+    let our_lock_data = &*OUR_LOCK_DATA;
+    for _retry in 0..5 {
+        match make_lock(hg_vfs, lock_filename, our_lock_data) {
+            Ok(()) => {
+                let result = f();
+                unlock(hg_vfs, lock_filename)?;
+                return Ok(result);
+            }
+            Err(HgError::IoError { error, .. })
+                if error.kind() == ErrorKind::AlreadyExists =>
+            {
+                let lock_data = read_lock(hg_vfs, lock_filename)?;
+                if lock_data.is_none() {
+                    // Lock was apparently just released, retry acquiring it
+                    continue;
+                }
+                if !lock_should_be_broken(&lock_data) {
+                    return Err(LockError::AlreadyHeld);
+                }
+                // The lock file is left over from a process not running
+                // anymore. Break it, but with another lock to
+                // avoid a race.
+                break_lock(hg_vfs, lock_filename)?;
+
+                // Retry acquiring
+            }
+            Err(error) => Err(error)?,
+        }
+    }
+    Err(LockError::AlreadyHeld)
+}
+
+fn break_lock(hg_vfs: Vfs, lock_filename: &str) -> Result<(), LockError> {
+    try_with_lock_no_wait(hg_vfs, &format!("{}.break", lock_filename), || {
+        // Check again in case some other process broke and
+        // acquired the lock in the meantime
+        let lock_data = read_lock(hg_vfs, lock_filename)?;
+        if !lock_should_be_broken(&lock_data) {
+            return Err(LockError::AlreadyHeld);
+        }
+        Ok(hg_vfs.remove_file(lock_filename)?)
+    })?
+}
+
+#[cfg(unix)]
+fn make_lock(
+    hg_vfs: Vfs,
+    lock_filename: &str,
+    data: &str,
+) -> Result<(), HgError> {
+    // Use a symbolic link because creating it is atomic.
+    // The link’s "target" contains data not representing any path.
+    let fake_symlink_target = data;
+    hg_vfs.create_symlink(lock_filename, fake_symlink_target)
+}
+
+fn read_lock(
+    hg_vfs: Vfs,
+    lock_filename: &str,
+) -> Result<Option<String>, HgError> {
+    let link_target =
+        hg_vfs.read_link(lock_filename).io_not_found_as_none()?;
+    if let Some(target) = link_target {
+        let data = target
+            .into_os_string()
+            .into_string()
+            .map_err(|_| HgError::corrupted("non-UTF-8 lock data"))?;
+        Ok(Some(data))
+    } else {
+        Ok(None)
+    }
+}
+
+fn unlock(hg_vfs: Vfs, lock_filename: &str) -> Result<(), HgError> {
+    hg_vfs.remove_file(lock_filename)
+}
+
+/// Return whether the process that is/was holding the lock is known not to be
+/// running anymore.
+fn lock_should_be_broken(data: &Option<String>) -> bool {
+    (|| -> Option<bool> {
+        let (prefix, pid) = data.as_ref()?.split_2(':')?;
+        if prefix != &*LOCK_PREFIX {
+            return Some(false);
+        }
+        let process_is_running;
+
+        #[cfg(unix)]
+        {
+            let pid: libc::pid_t = pid.parse().ok()?;
+            unsafe {
+                let signal = 0; // Test if we could send a signal, without sending
+                let result = libc::kill(pid, signal);
+                if result == 0 {
+                    process_is_running = true
+                } else {
+                    let errno =
+                        io::Error::last_os_error().raw_os_error().unwrap();
+                    process_is_running = errno != libc::ESRCH
+                }
+            }
+        }
+
+        Some(!process_is_running)
+    })()
+    .unwrap_or(false)
+}
+
+lazy_static::lazy_static! {
+    /// A string which is used to differentiate pid namespaces
+    ///
+    /// It's useful to detect "dead" processes and remove stale locks with
+    /// confidence. Typically it's just hostname. On modern linux, we include an
+    /// extra Linux-specific pid namespace identifier.
+    static ref LOCK_PREFIX: String = {
+        // Note: this must match the behavior of `_getlockprefix` in `mercurial/lock.py`
+
+        /// Same as https://github.com/python/cpython/blob/v3.10.0/Modules/socketmodule.c#L5414
+        const BUFFER_SIZE: usize = 1024;
+        let mut buffer = [0_i8; BUFFER_SIZE];
+        let hostname_bytes = unsafe {
+            let result = libc::gethostname(buffer.as_mut_ptr(), BUFFER_SIZE);
+            if result != 0 {
+                panic!("gethostname: {}", io::Error::last_os_error())
+            }
+            std::ffi::CStr::from_ptr(buffer.as_mut_ptr()).to_bytes()
+        };
+        let hostname =
+            std::str::from_utf8(hostname_bytes).expect("non-UTF-8 hostname");
+
+        #[cfg(target_os = "linux")]
+        {
+            use std::os::linux::fs::MetadataExt;
+            match std::fs::metadata("/proc/self/ns/pid") {
+                Ok(meta) => {
+                    return format!("{}/{:x}", hostname, meta.st_ino())
+                }
+                Err(error) => {
+                    // TODO: match on `error.kind()` when `NotADirectory`
+                    // is available on all supported Rust versions:
+                    // https://github.com/rust-lang/rust/issues/86442
+                    use libc::{
+                        ENOENT, // ErrorKind::NotFound
+                        ENOTDIR, // ErrorKind::NotADirectory
+                        EACCES, // ErrorKind::PermissionDenied
+                    };
+                    match error.raw_os_error() {
+                        Some(ENOENT) | Some(ENOTDIR) | Some(EACCES) => {}
+                        _ => panic!("stat /proc/self/ns/pid: {}", error),
+                    }
+                }
+            }
+        }
+
+        hostname.to_owned()
+    };
+
+    static ref OUR_LOCK_DATA: String = format!("{}:{}", &*LOCK_PREFIX, std::process::id());
+}

rust/hg-core/src/lib.rs

@@ -1,131 +1,132 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.
 
 mod ancestors;
 pub mod dagops;
 pub mod errors;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 pub mod dirstate;
 pub mod dirstate_tree;
 pub mod discovery;
 pub mod exit_codes;
 pub mod requirements;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     status::{
         BadMatch, BadType, DirstateStatus, HgPathCow, StatusError,
         StatusOptions,
     },
     DirstateEntry, DirstateParents, EntryState,
 };
 pub mod copy_tracing;
 mod filepatterns;
 pub mod matchers;
 pub mod repo;
 pub mod revlog;
 pub use revlog::*;
 pub mod config;
+pub mod lock;
 pub mod logging;
 pub mod operations;
 pub mod revset;
 pub mod utils;
 pub mod vfs;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
     parse_pattern_syntax, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use std::fmt;
 use twox_hash::RandomXxHashBuilder64;
 
 /// This is a contract between the `micro-timer` crate and us, to expose
 /// the `log` crate as `crate::log`.
 use log;
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     InvalidPath(HgPathError),
 }
 
 impl fmt::Display for DirstateMapError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 f.write_str("expected a value, found none")
             }
             DirstateMapError::EmptyPath => {
                 f.write_str("Overflow in dirstate.")
             }
             DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum DirstateError {
     Map(DirstateMapError),
     Common(errors::HgError),
 }
 
 impl fmt::Display for DirstateError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateError::Map(error) => error.fmt(f),
             DirstateError::Common(error) => error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum PatternError {
     #[from]
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     #[from]
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
 }
 
 impl fmt::Display for PatternError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 write!(f, "Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 write!(
                     f,
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 write!(f, "matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(error) => error.fmt(f),
             PatternError::Path(error) => error.fmt(f),
             PatternError::NonRegexPattern(pattern) => {
                 write!(f, "'{:?}' cannot be turned into a regex", pattern)
             }
         }
     }
 }

rust/hg-core/src/repo.rs

@@ -1,417 +1,425 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::exit_codes;
+use crate::lock::{try_with_lock_no_wait, LockError};
 use crate::manifest::{Manifest, Manifestlog};
 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::{requirements, NodePrefix};
 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, HgError>,
     manifestlog: LazyCell<Manifestlog, HgError>,
 }
 
 #[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 try_with_wlock_no_wait<R>(
+        &self,
+        f: impl FnOnce() -> R,
+    ) -> Result<R, LockError> {
+        try_with_lock_no_wait(self.hg_vfs(), "wlock", f)
+    }
+
     pub fn has_dirstate_v2(&self) -> bool {
         self.requirements
             .contains(requirements::DIRSTATE_V2_REQUIREMENT)
     }
 
     pub fn has_sparse(&self) -> bool {
         self.requirements.contains(requirements::SPARSE_REQUIREMENT)
     }
 
     pub fn has_narrow(&self) -> bool {
         self.requirements.contains(requirements::NARROW_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(data_mmap)
             } else {
                 OwningDirstateMap::new_empty(Vec::new())
             };
             let (on_disk, placeholder) = map.get_pair_mut();
             *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_pair_mut();
             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>, HgError> {
         self.changelog.get_or_init(self)
     }
 
     pub fn changelog_mut(&self) -> Result<RefMut<Changelog>, HgError> {
         self.changelog.get_mut_or_init(self)
     }
 
     pub fn manifestlog(&self) -> Result<Ref<Manifestlog>, HgError> {
         self.manifestlog.get_or_init(self)
     }
 
     pub fn manifestlog_mut(&self) -> Result<RefMut<Manifestlog>, HgError> {
         self.manifestlog.get_mut_or_init(self)
     }
 
     /// Returns the manifest of the *changeset* with the given node ID
     pub fn manifest_for_node(
         &self,
         node: impl Into<NodePrefix>,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_node(node.into())?
                 .manifest_node()?
                 .into(),
         )
     }
 
     /// Returns the manifest of the *changeset* with the given revision number
     pub fn manifest_for_rev(
         &self,
         revision: Revision,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_rev(revision)?
                 .manifest_node()?
                 .into(),
         )
     }
 
     pub fn filelog(&self, path: &HgPath) -> Result<Filelog, HgError> {
         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()))
     }
 }

rust/hg-core/src/utils.rs

@@ -1,490 +1,505 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 StrExt {
+    // TODO: Use https://doc.rust-lang.org/nightly/std/primitive.str.html#method.split_once
+    // once we require Rust 1.52+
+    fn split_2(&self, separator: char) -> Option<(&str, &str)>;
+}
+
+impl StrExt for str {
+    fn split_2(&self, separator: char) -> Option<(&str, &str)> {
+        let mut iter = self.splitn(2, separator);
+        let a = iter.next()?;
+        let b = iter.next()?;
+        Some((a, b))
+    }
+}
+
 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(())
     }
 }

rust/hg-core/src/vfs.rs

@@ -1,116 +1,136 b''
 use crate::errors::{HgError, IoErrorContext, IoResultExt};
 use memmap2::{Mmap, MmapOptions};
 use std::io::ErrorKind;
 use std::path::{Path, PathBuf};
 
 /// Filesystem access abstraction for the contents of a given "base" diretory
 #[derive(Clone, Copy)]
 pub struct Vfs<'a> {
     pub(crate) base: &'a Path,
 }
 
 struct FileNotFound(std::io::Error, PathBuf);
 
 impl Vfs<'_> {
     pub fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
         self.base.join(relative_path)
     }
 
     pub fn symlink_metadata(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<std::fs::Metadata, HgError> {
         let path = self.join(relative_path);
         std::fs::symlink_metadata(&path).when_reading_file(&path)
     }
 
     pub fn read_link(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<PathBuf, HgError> {
         let path = self.join(relative_path);
         std::fs::read_link(&path).when_reading_file(&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)
     }
 
     fn mmap_open_gen(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Result<Mmap, FileNotFound>, HgError> {
         let path = self.join(relative_path);
         let file = match std::fs::File::open(&path) {
             Err(err) => {
                 if let ErrorKind::NotFound = err.kind() {
                     return Ok(Err(FileNotFound(err, path)));
                 };
                 return (Err(err)).when_reading_file(&path);
             }
             Ok(file) => file,
         };
         // TODO: what are the safety requirements here?
         let mmap = unsafe { MmapOptions::new().map(&file) }
             .when_reading_file(&path)?;
         Ok(Ok(mmap))
     }
 
     pub fn mmap_open_opt(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Option<Mmap>, HgError> {
         self.mmap_open_gen(relative_path).map(|res| res.ok())
     }
 
     pub fn mmap_open(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Mmap, HgError> {
         match self.mmap_open_gen(relative_path)? {
             Err(FileNotFound(err, path)) => Err(err).when_reading_file(&path),
             Ok(res) => Ok(res),
         }
     }
 
     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 })
     }
+
+    pub fn remove_file(
+        &self,
+        relative_path: impl AsRef<Path>,
+    ) -> Result<(), HgError> {
+        let path = self.join(relative_path);
+        std::fs::remove_file(&path)
+            .with_context(|| IoErrorContext::RemovingFile(path))
+    }
+
+    #[cfg(unix)]
+    pub fn create_symlink(
+        &self,
+        relative_link_path: impl AsRef<Path>,
+        target_path: impl AsRef<Path>,
+    ) -> Result<(), HgError> {
+        let link_path = self.join(relative_link_path);
+        std::os::unix::fs::symlink(target_path, &link_path)
+            .with_context(|| IoErrorContext::WritingFile(link_path))
+    }
 }
 
 fn fs_metadata(
     path: impl AsRef<Path>,
 ) -> Result<Option<std::fs::Metadata>, HgError> {
     let path = path.as_ref();
     match std::fs::metadata(path) {
         Ok(meta) => Ok(Some(meta)),
         Err(error) => match error.kind() {
             // TODO: when we require a Rust version where `NotADirectory` is
             // stable, invert this logic and return None for it and `NotFound`
             // and propagate any other error.
             ErrorKind::PermissionDenied => Err(error).with_context(|| {
                 IoErrorContext::ReadingMetadata(path.to_owned())
             }),
             _ => Ok(None),
         },
     }
 }
 
 pub(crate) fn is_dir(path: impl AsRef<Path>) -> Result<bool, HgError> {
     Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_dir()))
 }
 
 pub(crate) fn is_file(path: impl AsRef<Path>) -> Result<bool, HgError> {
     Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_file()))
 }