rhg: initial support for shared repositories

Differential Revision: https://phab.mercurial-scm.org/D9941

rust/hg-core/src/errors.rs

@@ -1,114 +1,118 b''
 use std::fmt;
 
 /// Common error cases that can happen in many different APIs
 #[derive(Debug)]
 pub enum HgError {
     IoError {
         error: std::io::Error,
         context: IoErrorContext,
     },
 
     /// A file under `.hg/` normally only written by Mercurial
     ///
     /// The given string is a short explanation for users, not intended to be
     /// machine-readable.
     CorruptedRepository(String),
 
     /// The respository or requested operation involves a feature not
     /// supported by the Rust implementation. Falling back to the Python
     /// implementation may or may not work.
     ///
     /// The given string is a short explanation for users, not intended to be
     /// machine-readable.
     UnsupportedFeature(String),
 }
 
 /// Details about where an I/O error happened
 #[derive(Debug, derive_more::From)]
 pub enum IoErrorContext {
     /// A filesystem operation returned `std::io::Error`
     #[from]
     File(std::path::PathBuf),
     /// `std::env::current_dir` returned `std::io::Error`
     CurrentDir,
 }
 
 impl HgError {
     pub fn corrupted(explanation: impl Into<String>) -> Self {
         // TODO: capture a backtrace here and keep it in the error value
         // to aid debugging?
         // https://doc.rust-lang.org/std/backtrace/struct.Backtrace.html
         HgError::CorruptedRepository(explanation.into())
     }
+
+    pub fn unsupported(explanation: impl Into<String>) -> Self {
+        HgError::UnsupportedFeature(explanation.into())
+    }
 }
 
 // TODO: use `DisplayBytes` instead to show non-Unicode filenames losslessly?
 impl fmt::Display for HgError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             HgError::IoError { error, context } => {
                 write!(f, "{}: {}", error, context)
             }
             HgError::CorruptedRepository(explanation) => {
                 write!(f, "corrupted repository: {}", explanation)
             }
             HgError::UnsupportedFeature(explanation) => {
                 write!(f, "unsupported feature: {}", explanation)
             }
         }
     }
 }
 
 // TODO: use `DisplayBytes` instead to show non-Unicode filenames losslessly?
 impl fmt::Display for IoErrorContext {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             IoErrorContext::File(path) => path.display().fmt(f),
             IoErrorContext::CurrentDir => f.write_str("current directory"),
         }
     }
 }
 
 pub trait IoResultExt<T> {
     /// Annotate a possible I/O error as related to a file at the given path.
     ///
     /// This allows printing something like “File not found: example.txt”
     /// instead of just “File not found”.
     ///
     /// Converts a `Result` with `std::io::Error` into one with `HgError`.
     fn for_file(self, path: &std::path::Path) -> Result<T, HgError>;
 }
 
 impl<T> IoResultExt<T> for std::io::Result<T> {
     fn for_file(self, path: &std::path::Path) -> Result<T, HgError> {
         self.map_err(|error| HgError::IoError {
             error,
             context: IoErrorContext::File(path.to_owned()),
         })
     }
 }
 
 pub trait HgResultExt<T> {
     /// Handle missing files separately from other I/O error cases.
     ///
     /// Wraps the `Ok` type in an `Option`:
     ///
     /// * `Ok(x)` becomes `Ok(Some(x))`
     /// * An I/O "not found" error becomes `Ok(None)`
     /// * Other errors are unchanged
     fn io_not_found_as_none(self) -> Result<Option<T>, HgError>;
 }
 
 impl<T> HgResultExt<T> for Result<T, HgError> {
     fn io_not_found_as_none(self) -> Result<Option<T>, HgError> {
         match self {
             Ok(x) => Ok(Some(x)),
             Err(HgError::IoError { error, .. })
                 if error.kind() == std::io::ErrorKind::NotFound =>
             {
                 Ok(None)
             }
             Err(other_error) => Err(other_error),
         }
     }
 }

rust/hg-core/src/repo.rs

@@ -1,100 +1,140 b''
 use crate::errors::{HgError, IoResultExt};
 use crate::requirements;
+use crate::utils::files::get_path_from_bytes;
 use memmap::{Mmap, MmapOptions};
+use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 
 /// A repository on disk
 pub struct Repo {
     working_directory: PathBuf,
     dot_hg: PathBuf,
     store: PathBuf,
+    requirements: HashSet<String>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum RepoFindError {
     NotFoundInCurrentDirectoryOrAncestors {
         current_directory: PathBuf,
     },
     #[from]
     Other(HgError),
 }
 
 /// Filesystem access abstraction for the contents of a given "base" diretory
 #[derive(Clone, Copy)]
 pub(crate) struct Vfs<'a> {
     base: &'a Path,
 }
 
 impl Repo {
     /// Search the current directory and its ancestores for a repository:
     /// a working directory that contains a `.hg` sub-directory.
     pub fn find() -> Result<Self, RepoFindError> {
         let current_directory = crate::utils::current_dir()?;
         // ancestors() is inclusive: it first yields `current_directory` as-is.
         for ancestor in current_directory.ancestors() {
-            let dot_hg = ancestor.join(".hg");
-            if dot_hg.is_dir() {
-                let repo = Self {
-                    store: dot_hg.join("store"),
-                    dot_hg,
-                    working_directory: ancestor.to_owned(),
-                };
-                requirements::check(&repo)?;
-                return Ok(repo);
+            if ancestor.join(".hg").is_dir() {
+                return Ok(Self::new_at_path(ancestor.to_owned())?);
             }
         }
         Err(RepoFindError::NotFoundInCurrentDirectoryOrAncestors {
             current_directory,
         })
     }
 
+    /// To be called after checking that `.hg` is a sub-directory
+    fn new_at_path(working_directory: PathBuf) -> Result<Self, HgError> {
+        let dot_hg = working_directory.join(".hg");
+        let hg_vfs = Vfs { base: &dot_hg };
+        let reqs = requirements::load_if_exists(hg_vfs)?;
+        let relative =
+            reqs.contains(requirements::RELATIVE_SHARED_REQUIREMENT);
+        let shared =
+            reqs.contains(requirements::SHARED_REQUIREMENT) || relative;
+        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).to_owned();
+            if relative {
+                shared_path = dot_hg.join(shared_path)
+            }
+            if !shared_path.is_dir() {
+                return Err(HgError::corrupted(format!(
+                    ".hg/sharedpath points to nonexistent directory {}",
+                    shared_path.display()
+                )));
+            }
+
+            store_path = shared_path.join("store");
+        }
+
+        let repo = Self {
+            requirements: reqs,
+            working_directory,
+            store: store_path,
+            dot_hg,
+        };
+
+        requirements::check(&repo)?;
+
+        Ok(repo)
+    }
+
     pub fn working_directory_path(&self) -> &Path {
         &self.working_directory
     }
 
+    pub fn requirements(&self) -> &HashSet<String> {
+        &self.requirements
+    }
+
     /// For accessing repository files (in `.hg`), except for the store
     /// (`.hg/store`).
     pub(crate) fn hg_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.dot_hg }
     }
 
     /// For accessing repository store files (in `.hg/store`)
     pub(crate) fn store_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.store }
     }
 
     /// For accessing the working copy
 
     // The undescore prefix silences the "never used" warning. Remove before
     // using.
     pub(crate) fn _working_directory_vfs(&self) -> Vfs<'_> {
         Vfs {
             base: &self.working_directory,
         }
     }
 }
 
 impl Vfs<'_> {
     pub(crate) fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
         self.base.join(relative_path)
     }
 
     pub(crate) fn read(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Vec<u8>, HgError> {
         let path = self.join(relative_path);
         std::fs::read(&path).for_file(&path)
     }
 
     pub(crate) fn mmap_open(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Mmap, HgError> {
         let path = self.base.join(relative_path);
         let file = std::fs::File::open(&path).for_file(&path)?;
         // TODO: what are the safety requirements here?
         let mmap = unsafe { MmapOptions::new().map(&file) }.for_file(&path)?;
         Ok(mmap)
     }
 }

rust/hg-core/src/requirements.rs

@@ -1,67 +1,133 b''
 use crate::errors::{HgError, HgResultExt};
-use crate::repo::Repo;
+use crate::repo::{Repo, Vfs};
+use std::collections::HashSet;
 
-fn parse(bytes: &[u8]) -> Result<Vec<String>, HgError> {
+fn parse(bytes: &[u8]) -> Result<HashSet<String>, HgError> {
     // The Python code reading this file uses `str.splitlines`
     // which looks for a number of line separators (even including a couple of
     // non-ASCII ones), but Python code writing it always uses `\n`.
     let lines = bytes.split(|&byte| byte == b'\n');
 
     lines
         .filter(|line| !line.is_empty())
         .map(|line| {
             // Python uses Unicode `str.isalnum` but feature names are all
             // ASCII
             if line[0].is_ascii_alphanumeric() && line.is_ascii() {
                 Ok(String::from_utf8(line.into()).unwrap())
             } else {
                 Err(HgError::corrupted("parse error in 'requires' file"))
             }
         })
         .collect()
 }
 
-pub fn load(repo: &Repo) -> Result<Vec<String>, HgError> {
-    if let Some(bytes) =
-        repo.hg_vfs().read("requires").io_not_found_as_none()?
-    {
+pub(crate) fn load_if_exists(hg_vfs: Vfs) -> Result<HashSet<String>, HgError> {
+    if let Some(bytes) = hg_vfs.read("requires").io_not_found_as_none()? {
         parse(&bytes)
     } else {
         // Treat a missing file the same as an empty file.
         // From `mercurial/localrepo.py`:
         // > requires file contains a newline-delimited list of
         // > features/capabilities the opener (us) must have in order to use
         // > the repository. This file was introduced in Mercurial 0.9.2,
         // > which means very old repositories may not have one. We assume
         // > a missing file translates to no requirements.
-        Ok(Vec::new())
+        Ok(HashSet::new())
     }
 }
 
-pub fn check(repo: &Repo) -> Result<(), HgError> {
-    for feature in load(repo)? {
-        if !SUPPORTED.contains(&&*feature) {
+pub(crate) fn check(repo: &Repo) -> Result<(), HgError> {
+    for feature in repo.requirements() {
+        if !SUPPORTED.contains(&feature.as_str()) {
             // TODO: collect and all unknown features and include them in the
             // error message?
             return Err(HgError::UnsupportedFeature(format!(
                 "repository requires feature unknown to this Mercurial: {}",
                 feature
             )));
         }
     }
     Ok(())
 }
 
 // TODO: set this to actually-supported features
 const SUPPORTED: &[&str] = &[
     "dotencode",
     "fncache",
     "generaldelta",
     "revlogv1",
-    "sparserevlog",
+    SHARED_REQUIREMENT,
+    SPARSEREVLOG_REQUIREMENT,
+    RELATIVE_SHARED_REQUIREMENT,
     "store",
     // As of this writing everything rhg does is read-only.
     // When it starts writing to the repository, it’ll need to either keep the
     // persistent nodemap up to date or remove this entry:
     "persistent-nodemap",
 ];
+
+// Copied from mercurial/requirements.py:
+
+/// When narrowing is finalized and no longer subject to format changes,
+/// we should move this to just "narrow" or similar.
+#[allow(unused)]
+pub(crate) const NARROW_REQUIREMENT: &str = "narrowhg-experimental";
+
+/// Enables sparse working directory usage
+#[allow(unused)]
+pub(crate) const SPARSE_REQUIREMENT: &str = "exp-sparse";
+
+/// Enables the internal phase which is used to hide changesets instead
+/// of stripping them
+#[allow(unused)]
+pub(crate) const INTERNAL_PHASE_REQUIREMENT: &str = "internal-phase";
+
+/// Stores manifest in Tree structure
+#[allow(unused)]
+pub(crate) const TREEMANIFEST_REQUIREMENT: &str = "treemanifest";
+
+/// Increment the sub-version when the revlog v2 format changes to lock out old
+/// clients.
+#[allow(unused)]
+pub(crate) const REVLOGV2_REQUIREMENT: &str = "exp-revlogv2.1";
+
+/// A repository with the sparserevlog feature will have delta chains that
+/// can spread over a larger span. Sparse reading cuts these large spans into
+/// pieces, so that each piece isn't too big.
+/// Without the sparserevlog capability, reading from the repository could use
+/// huge amounts of memory, because the whole span would be read at once,
+/// including all the intermediate revisions that aren't pertinent for the
+/// chain. This is why once a repository has enabled sparse-read, it becomes
+/// required.
+#[allow(unused)]
+pub(crate) const SPARSEREVLOG_REQUIREMENT: &str = "sparserevlog";
+
+/// A repository with the sidedataflag requirement will allow to store extra
+/// information for revision without altering their original hashes.
+#[allow(unused)]
+pub(crate) const SIDEDATA_REQUIREMENT: &str = "exp-sidedata-flag";
+
+/// A repository with the the copies-sidedata-changeset requirement will store
+/// copies related information in changeset's sidedata.
+#[allow(unused)]
+pub(crate) const COPIESSDC_REQUIREMENT: &str = "exp-copies-sidedata-changeset";
+
+/// The repository use persistent nodemap for the changelog and the manifest.
+#[allow(unused)]
+pub(crate) const NODEMAP_REQUIREMENT: &str = "persistent-nodemap";
+
+/// Denotes that the current repository is a share
+#[allow(unused)]
+pub(crate) const SHARED_REQUIREMENT: &str = "shared";
+
+/// Denotes that current repository is a share and the shared source path is
+/// relative to the current repository root path
+#[allow(unused)]
+pub(crate) const RELATIVE_SHARED_REQUIREMENT: &str = "relshared";
+
+/// A repository with share implemented safely. The repository has different
+/// store and working copy requirements i.e. both `.hg/requires` and
+/// `.hg/store/requires` are present.
+#[allow(unused)]
+pub(crate) const SHARESAFE_REQUIREMENT: &str = "exp-sharesafe";

rust/rhg/src/commands/debugrequirements.rs

@@ -1,30 +1,31 b''
 use crate::commands::Command;
 use crate::error::CommandError;
 use crate::ui::Ui;
 use hg::repo::Repo;
-use hg::requirements;
 
 pub const HELP_TEXT: &str = "
 Print the current repo requirements.
 ";
 
 pub struct DebugRequirementsCommand {}
 
 impl DebugRequirementsCommand {
     pub fn new() -> Self {
         DebugRequirementsCommand {}
     }
 }
 
 impl Command for DebugRequirementsCommand {
     fn run(&self, ui: &Ui) -> Result<(), CommandError> {
         let repo = Repo::find()?;
         let mut output = String::new();
-        for req in requirements::load(&repo)? {
-            output.push_str(&req);
+        let mut requirements: Vec<_> = repo.requirements().iter().collect();
+        requirements.sort();
+        for req in requirements {
+            output.push_str(req);
             output.push('\n');
         }
         ui.write_stdout(output.as_bytes())?;
         Ok(())
     }
 }

tests/test-rhg.t

@@ -1,262 +1,262 b''
 #require rust
 
 Define an rhg function that will only run if rhg exists
   $ rhg() {
   > if [ -f "$RUNTESTDIR/../rust/target/release/rhg" ]; then
   >   "$RUNTESTDIR/../rust/target/release/rhg" "$@"
   > else
   >   echo "skipped: Cannot find rhg. Try to run cargo build in rust/rhg."
   >   exit 80
   > fi
   > }
 
 Unimplemented command
   $ rhg unimplemented-command
   error: Found argument 'unimplemented-command' which wasn't expected, or isn't valid in this context
   
   USAGE:
       rhg <SUBCOMMAND>
   
   For more information try --help
   [252]
 
 Finding root
   $ rhg root
   abort: no repository found in '$TESTTMP' (.hg not found)!
   [255]
 
   $ hg init repository
   $ cd repository
   $ rhg root
   $TESTTMP/repository
 
 Unwritable file descriptor
   $ rhg root > /dev/full
   abort: No space left on device (os error 28)
   [255]
 
 Deleted repository
   $ rm -rf `pwd`
   $ rhg root
   abort: $ENOENT$: current directory
   [255]
 
 Listing tracked files
   $ cd $TESTTMP
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3; do
   >   echo $i >> file$i
   >   hg add file$i
   > done
   > hg commit -m "commit $i" -q
 
 Listing tracked files from root
   $ rhg files
   file1
   file2
   file3
 
 Listing tracked files from subdirectory
   $ mkdir -p path/to/directory
   $ cd path/to/directory
   $ rhg files
   ../../../file1
   ../../../file2
   ../../../file3
 
 Listing tracked files through broken pipe
   $ rhg files | head -n 1
   ../../../file1
 
 Debuging data in inline index
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3 4 5 6; do
   >   echo $i >> file-$i
   >   hg add file-$i
   >   hg commit -m "Commit $i" -q
   > done
   $ rhg debugdata -c 2
   8d0267cb034247ebfa5ee58ce59e22e57a492297
   test
   0 0
   file-3
   
   Commit 3 (no-eol)
   $ rhg debugdata -m 2
   file-1\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   file-2\x005d9299349fc01ddd25d0070d149b124d8f10411e (esc)
   file-3\x002661d26c649684b482d10f91960cc3db683c38b4 (esc)
 
 Debuging with full node id
   $ rhg debugdata -c `hg log -r 0 -T '{node}'`
   d1d1c679d3053e8926061b6f45ca52009f011e3f
   test
   0 0
   file-1
   
   Commit 1 (no-eol)
 
 Specifying revisions by changeset ID
   $ hg log -T '{node}\n'
   c6ad58c44207b6ff8a4fbbca7045a5edaa7e908b
   d654274993d0149eecc3cc03214f598320211900
   f646af7e96481d3a5470b695cf30ad8e3ab6c575
   cf8b83f14ead62b374b6e91a0e9303b85dfd9ed7
   91c6f6e73e39318534dc415ea4e8a09c99cd74d6
   6ae9681c6d30389694d8701faf24b583cf3ccafe
   $ rhg files -r cf8b83
   file-1
   file-2
   file-3
   $ rhg cat -r cf8b83 file-2
   2
   $ rhg cat -r c file-2
   abort: ambiguous revision identifier c
   [255]
   $ rhg cat -r d file-2
   2
 
 Cat files
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ echo "original content" > original
   $ hg add original
   $ hg commit -m "add original" original
   $ rhg cat -r 0 original
   original content
 Cat copied file should not display copy metadata
   $ hg copy original copy_of_original
   $ hg commit -m "add copy of original"
   $ rhg cat -r 1 copy_of_original
   original content
 
 Requirements
   $ rhg debugrequirements
   dotencode
   fncache
   generaldelta
   revlogv1
   sparserevlog
   store
 
   $ echo indoor-pool >> .hg/requires
   $ rhg files
   [252]
 
   $ rhg cat -r 1 copy_of_original
   [252]
 
   $ rhg debugrequirements
   [252]
 
   $ echo -e '\xFF' >> .hg/requires
   $ rhg debugrequirements
   abort: corrupted repository: parse error in 'requires' file
   [255]
 
 Persistent nodemap
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ rhg debugrequirements | grep nodemap
   [1]
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   $ rhg files -r c3ae8dec9fad
   of
 
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg --config format.use-persistent-nodemap=True init repository
   $ cd repository
   $ rhg debugrequirements | grep nodemap
   persistent-nodemap
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog-*.nd (glob)
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   .hg/store/00changelog.n
 
 Specifying revisions by changeset ID
   $ rhg files -r c3ae8dec9fad
   of
   $ rhg cat -r c3ae8dec9fad of
   r5000
 
 Crate a shared repository
 
   $ echo "[extensions]"      >> $HGRCPATH
   $ echo "share = "          >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo1
   $ cd repo1
   $ echo a > a
   $ hg commit -A -m'init'
   adding a
 
   $ cd ..
   $ hg share repo1 repo2
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ cd repo2
   $ rhg files
-  [252]
+  a
   $ rhg cat -r 0 a
-  [252]
+  a
 
 Same with relative sharing
 
   $ cd ..
   $ hg share repo2 repo3 --relative
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ cd repo3
   $ rhg files
-  [252]
+  a
   $ rhg cat -r 0 a
-  [252]
+  a
 
 Same with share-safe
 
   $ echo "[format]"         >> $HGRCPATH
   $ echo "use-share-safe = True" >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo4
   $ cd repo4
   $ echo a > a
   $ hg commit -A -m'init'
   adding a
 
   $ cd ..
   $ hg share repo4 repo5
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ cd repo5
   $ rhg files
   [252]
   $ rhg cat -r 0 a
   [252]