rhg: support rhg status --rev --rev

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

@@ -0,0 +1,89 b''
+use crate::errors::HgError;
+use crate::matchers::Matcher;
+use crate::repo::Repo;
+use crate::revlog::manifest::Manifest;
+use crate::utils::filter_map_results;
+use crate::utils::hg_path::HgPath;
+use crate::utils::merge_join_results_by;
+
+use crate::Revision;
+
+use itertools::EitherOrBoth;
+
+#[derive(Debug, Copy, Clone)]
+pub enum DiffStatus {
+    Removed,
+    Added,
+    Matching,
+    Modified,
+}
+
+pub struct StatusRevRev {
+    manifest1: Manifest,
+    manifest2: Manifest,
+    narrow_matcher: Box<dyn Matcher>,
+}
+
+fn manifest_for_rev(repo: &Repo, rev: Revision) -> Result<Manifest, HgError> {
+    repo.manifest_for_rev(rev.into()).map_err(|e| {
+        HgError::corrupted(format!(
+            "manifest lookup failed for revision {}: {}",
+            rev, e
+        ))
+    })
+}
+
+pub fn status_rev_rev_no_copies(
+    repo: &Repo,
+    rev1: Revision,
+    rev2: Revision,
+    narrow_matcher: Box<dyn Matcher>,
+) -> Result<StatusRevRev, HgError> {
+    let manifest1 = manifest_for_rev(repo, rev1)?;
+    let manifest2 = manifest_for_rev(repo, rev2)?;
+    Ok(StatusRevRev {
+        manifest1,
+        manifest2,
+        narrow_matcher,
+    })
+}
+
+impl StatusRevRev {
+    pub fn iter(
+        &self,
+    ) -> impl Iterator<Item = Result<(&HgPath, DiffStatus), HgError>> {
+        let iter1 = self.manifest1.iter();
+        let iter2 = self.manifest2.iter();
+
+        let merged =
+            merge_join_results_by(iter1, iter2, |i1, i2| i1.path.cmp(i2.path));
+
+        filter_map_results(merged, |entry| {
+            let (path, status) = match entry {
+                EitherOrBoth::Left(entry) => {
+                    let path = entry.path;
+                    (path, DiffStatus::Removed)
+                }
+                EitherOrBoth::Right(entry) => {
+                    let path = entry.path;
+                    (path, DiffStatus::Added)
+                }
+                EitherOrBoth::Both(entry1, entry2) => {
+                    let path = entry1.path;
+                    if entry1.node_id().unwrap() == entry2.node_id().unwrap()
+                        && entry1.flags == entry2.flags
+                    {
+                        (path, DiffStatus::Matching)
+                    } else {
+                        (path, DiffStatus::Modified)
+                    }
+                }
+            };
+            Ok(if self.narrow_matcher.matches(path) {
+                Some((path, status))
+            } else {
+                None
+            })
+        })
+    }
+}

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

@@ -1,10 +1,12 b''
 //! A distinction is made between operations and commands.
 //! An operation is what can be done whereas a command is what is exposed by
 //! the cli. A single command can use several operations to achieve its goal.
 
 mod cat;
 mod debugdata;
 mod list_tracked_files;
+mod status_rev_rev;
 pub use cat::{cat, CatOutput};
 pub use debugdata::{debug_data, DebugDataKind};
 pub use list_tracked_files::{list_rev_tracked_files, FilesForRev};
+pub use status_rev_rev::{status_rev_rev_no_copies, DiffStatus, StatusRevRev};

rust/rhg/src/commands/status.rs

@@ -1,728 +1,815 b''
 // status.rs
 //
 // Copyright 2020, Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::error::CommandError;
 use crate::ui::{
     format_pattern_file_warning, print_narrow_sparse_warnings, relative_paths,
     RelativePaths, Ui,
 };
 use crate::utils::path_utils::RelativizePaths;
 use clap::Arg;
 use format_bytes::format_bytes;
 use hg::config::Config;
 use hg::dirstate::has_exec_bit;
 use hg::dirstate::status::StatusPath;
 use hg::dirstate::TruncatedTimestamp;
 use hg::errors::{HgError, IoResultExt};
 use hg::filepatterns::parse_pattern_args;
 use hg::lock::LockError;
 use hg::manifest::Manifest;
 use hg::matchers::{AlwaysMatcher, IntersectionMatcher};
 use hg::repo::Repo;
 use hg::utils::debug::debug_wait_for_file;
 use hg::utils::files::{
     get_bytes_from_os_str, get_bytes_from_os_string, get_path_from_bytes,
 };
 use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
 use hg::DirstateStatus;
 use hg::PatternFileWarning;
+use hg::Revision;
 use hg::StatusError;
 use hg::StatusOptions;
 use hg::{self, narrow, sparse};
 use log::info;
 use rayon::prelude::*;
+use std::borrow::Cow;
 use std::io;
 use std::mem::take;
 use std::path::PathBuf;
 
 pub const HELP_TEXT: &str = "
 Show changed files in the working directory
 
 This is a pure Rust version of `hg status`.
 
 Some options might be missing, check the list below.
 ";
 
 pub fn args() -> clap::Command {
     clap::command!("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::new("file")
                 .value_parser(clap::value_parser!(std::ffi::OsString))
                 .help("show only these files")
                 .action(clap::ArgAction::Append),
         )
         .arg(
             Arg::new("all")
                 .help("show status of all files")
                 .short('A')
                 .action(clap::ArgAction::SetTrue)
                 .long("all"),
         )
         .arg(
             Arg::new("modified")
                 .help("show only modified files")
                 .short('m')
                 .action(clap::ArgAction::SetTrue)
                 .long("modified"),
         )
         .arg(
             Arg::new("added")
                 .help("show only added files")
                 .short('a')
                 .action(clap::ArgAction::SetTrue)
                 .long("added"),
         )
         .arg(
             Arg::new("removed")
                 .help("show only removed files")
                 .short('r')
                 .action(clap::ArgAction::SetTrue)
                 .long("removed"),
         )
         .arg(
             Arg::new("clean")
                 .help("show only clean files")
                 .short('c')
                 .action(clap::ArgAction::SetTrue)
                 .long("clean"),
         )
         .arg(
             Arg::new("deleted")
                 .help("show only deleted files")
                 .short('d')
                 .action(clap::ArgAction::SetTrue)
                 .long("deleted"),
         )
         .arg(
             Arg::new("unknown")
                 .help("show only unknown (not tracked) files")
                 .short('u')
                 .action(clap::ArgAction::SetTrue)
                 .long("unknown"),
         )
         .arg(
             Arg::new("ignored")
                 .help("show only ignored files")
                 .short('i')
                 .action(clap::ArgAction::SetTrue)
                 .long("ignored"),
         )
         .arg(
             Arg::new("copies")
                 .help("show source of copied files (DEFAULT: ui.statuscopies)")
                 .short('C')
                 .action(clap::ArgAction::SetTrue)
                 .long("copies"),
         )
         .arg(
             Arg::new("print0")
                 .help("end filenames with NUL, for use with xargs")
                 .short('0')
                 .action(clap::ArgAction::SetTrue)
                 .long("print0"),
         )
         .arg(
             Arg::new("no-status")
                 .help("hide status prefix")
                 .short('n')
                 .action(clap::ArgAction::SetTrue)
                 .long("no-status"),
         )
         .arg(
             Arg::new("verbose")
                 .help("enable additional output")
                 .short('v')
                 .action(clap::ArgAction::SetTrue)
                 .long("verbose"),
         )
+        .arg(
+            Arg::new("rev")
+                .help("show difference from/to revision")
+                .long("rev")
+                .num_args(1)
+                .action(clap::ArgAction::Append)
+                .value_name("REV"),
+        )
+}
+
+fn parse_revpair(
+    repo: &Repo,
+    revs: Option<Vec<String>>,
+) -> Result<Option<(Revision, Revision)>, CommandError> {
+    let revs = match revs {
+        None => return Ok(None),
+        Some(revs) => revs,
+    };
+    if revs.is_empty() {
+        return Ok(None);
+    }
+    if revs.len() != 2 {
+        return Err(CommandError::unsupported("expected 0 or 2 --rev flags"));
+    }
+
+    let rev1 = &revs[0];
+    let rev2 = &revs[1];
+    let rev1 = hg::revset::resolve_single(rev1, repo)
+        .map_err(|e| (e, rev1.as_str()))?;
+    let rev2 = hg::revset::resolve_single(rev2, repo)
+        .map_err(|e| (e, rev2.as_str()))?;
+    Ok(Some((rev1, rev2)))
 }
 
 /// Pure data type allowing the caller to specify file states to display
 #[derive(Copy, Clone, Debug)]
 pub struct DisplayStates {
     pub modified: bool,
     pub added: bool,
     pub removed: bool,
     pub clean: bool,
     pub deleted: bool,
     pub unknown: bool,
     pub ignored: bool,
 }
 
 pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: false,
     deleted: true,
     unknown: true,
     ignored: false,
 };
 
 pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: true,
     deleted: true,
     unknown: true,
     ignored: true,
 };
 
 impl DisplayStates {
     pub fn is_empty(&self) -> bool {
         !(self.modified
             || self.added
             || self.removed
             || self.clean
             || self.deleted
             || self.unknown
             || self.ignored)
     }
 }
 
 fn has_unfinished_merge(repo: &Repo) -> Result<bool, CommandError> {
     Ok(repo.dirstate_parents()?.is_merge())
 }
 
 fn has_unfinished_state(repo: &Repo) -> Result<bool, CommandError> {
     // These are all the known values for the [fname] argument of
     // [addunfinished] function in [state.py]
     let known_state_files: &[&str] = &[
         "bisect.state",
         "graftstate",
         "histedit-state",
         "rebasestate",
         "shelvedstate",
         "transplant/journal",
         "updatestate",
     ];
     if has_unfinished_merge(repo)? {
         return Ok(true);
     };
     for f in known_state_files {
         if repo.hg_vfs().join(f).exists() {
             return Ok(true);
         }
     }
     Ok(false)
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     // TODO: lift these limitations
     if invocation
         .config
         .get(b"commands", b"status.terse")
         .is_some()
     {
         return Err(CommandError::unsupported(
             "status.terse is not yet supported with rhg status",
         ));
     }
 
     let ui = invocation.ui;
     let config = invocation.config;
     let args = invocation.subcommand_args;
 
+    let revs = args.get_many::<String>("rev");
     let print0 = args.get_flag("print0");
     let verbose = args.get_flag("verbose")
         || config.get_bool(b"ui", b"verbose")?
         || config.get_bool(b"commands", b"status.verbose")?;
     let verbose = verbose && !print0;
 
     let all = args.get_flag("all");
     let display_states = if all {
         // TODO when implementing `--quiet`: it excludes clean files
         // from `--all`
         ALL_DISPLAY_STATES
     } else {
         let requested = DisplayStates {
             modified: args.get_flag("modified"),
             added: args.get_flag("added"),
             removed: args.get_flag("removed"),
             clean: args.get_flag("clean"),
             deleted: args.get_flag("deleted"),
             unknown: args.get_flag("unknown"),
             ignored: args.get_flag("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
     let no_status = args.get_flag("no-status");
     let list_copies = all
         || args.get_flag("copies")
         || config.get_bool(b"ui", b"statuscopies")?;
 
     let repo = invocation.repo?;
+    let revpair = parse_revpair(repo, revs.map(|i| i.cloned().collect()))?;
 
     if verbose && has_unfinished_state(repo)? {
         return Err(CommandError::unsupported(
             "verbose status output is not supported by rhg (and is needed because we're in an unfinished operation)",
         ));
     }
 
     let mut dmap = repo.dirstate_map_mut()?;
 
     let check_exec = hg::checkexec::check_exec(repo.working_directory_path());
 
     let options = StatusOptions {
         check_exec,
         list_clean: display_states.clean,
         list_unknown: display_states.unknown,
         list_ignored: display_states.ignored,
         list_copies,
         collect_traversed_dirs: false,
     };
 
     type StatusResult<'a> =
         Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>;
 
     let relative_status = config
         .get_option(b"commands", b"status.relative")?
         .expect("commands.status.relative should have a default value");
 
     let relativize_paths = relative_status || {
         // See in Python code with `getuipathfn` usage in `commands.py`.
         let legacy_relative_behavior = args.contains_id("file");
         match relative_paths(invocation.config)? {
             RelativePaths::Legacy => legacy_relative_behavior,
             RelativePaths::Bool(v) => v,
         }
     };
 
     let mut output = DisplayStatusPaths {
         ui,
         no_status,
         relativize: if relativize_paths {
             Some(RelativizePaths::new(repo)?)
         } else {
             None
         },
         print0,
     };
 
     let after_status = |res: StatusResult| -> Result<_, CommandError> {
         let (mut ds_status, pattern_warnings) = res?;
         for warning in pattern_warnings {
             ui.write_stderr(&format_pattern_file_warning(&warning, repo))?;
         }
 
         for (path, error) in take(&mut ds_status.bad) {
             let error = match error {
                 hg::BadMatch::OsError(code) => {
                     std::io::Error::from_raw_os_error(code).to_string()
                 }
                 hg::BadMatch::BadType(ty) => {
                     format!("unsupported file type (type is {})", ty)
                 }
             };
             ui.write_stderr(&format_bytes!(
                 b"{}: {}\n",
                 path.as_bytes(),
                 error.as_bytes()
             ))?
         }
         if !ds_status.unsure.is_empty() {
             info!(
                 "Files to be rechecked by retrieval from filelog: {:?}",
                 ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
             );
         }
         let mut fixup = Vec::new();
         if !ds_status.unsure.is_empty()
             && (display_states.modified || display_states.clean)
         {
             let p1 = repo.dirstate_parents()?.p1;
             let manifest = repo.manifest_for_node(p1).map_err(|e| {
                 CommandError::from((e, &*format!("{:x}", p1.short())))
             })?;
             let working_directory_vfs = repo.working_directory_vfs();
             let store_vfs = repo.store_vfs();
             let res: Vec<_> = take(&mut ds_status.unsure)
                 .into_par_iter()
                 .map(|to_check| {
                     // The compiler seems to get a bit confused with complex
                     // inference when using a parallel iterator + map
                     // + map_err + collect, so let's just inline some of the
                     // logic.
                     match unsure_is_modified(
                         working_directory_vfs,
                         store_vfs,
                         check_exec,
                         &manifest,
                         &to_check.path,
                     ) {
                         Err(HgError::IoError { .. }) => {
                             // IO errors most likely stem from the file being
                             // deleted even though we know it's in the
                             // dirstate.
                             Ok((to_check, UnsureOutcome::Deleted))
                         }
                         Ok(outcome) => Ok((to_check, outcome)),
                         Err(e) => Err(e),
                     }
                 })
                 .collect::<Result<_, _>>()?;
             for (status_path, outcome) in res.into_iter() {
                 match outcome {
                     UnsureOutcome::Clean => {
                         if display_states.clean {
                             ds_status.clean.push(status_path.clone());
                         }
                         fixup.push(status_path.path.into_owned())
                     }
                     UnsureOutcome::Modified => {
                         if display_states.modified {
                             ds_status.modified.push(status_path);
                         }
                     }
                     UnsureOutcome::Deleted => {
                         if display_states.deleted {
                             ds_status.deleted.push(status_path);
                         }
                     }
                 }
             }
         }
 
         let dirstate_write_needed = ds_status.dirty;
         let filesystem_time_at_status_start =
             ds_status.filesystem_time_at_status_start;
 
         output.output(display_states, ds_status)?;
 
         Ok((
             fixup,
             dirstate_write_needed,
             filesystem_time_at_status_start,
         ))
     };
     let (narrow_matcher, narrow_warnings) = narrow::matcher(repo)?;
+
+    match revpair {
+        Some((rev1, rev2)) => {
+            let mut ds_status = DirstateStatus::default();
+            if list_copies {
+                return Err(CommandError::unsupported(
+                    "status --rev --rev with copy information is not implemented yet",
+                ));
+            }
+
+            let stat = hg::operations::status_rev_rev_no_copies(
+                repo,
+                rev1,
+                rev2,
+                narrow_matcher,
+            )?;
+            for entry in stat.iter() {
+                let (path, status) = entry?;
+                let path = StatusPath {
+                    path: Cow::Borrowed(path),
+                    copy_source: None,
+                };
+                match status {
+                    hg::operations::DiffStatus::Removed => {
+                        if display_states.removed {
+                            ds_status.removed.push(path)
+                        }
+                    }
+                    hg::operations::DiffStatus::Added => {
+                        if display_states.added {
+                            ds_status.added.push(path)
+                        }
+                    }
+                    hg::operations::DiffStatus::Modified => {
+                        if display_states.modified {
+                            ds_status.modified.push(path)
+                        }
+                    }
+                    hg::operations::DiffStatus::Matching => {
+                        if display_states.clean {
+                            ds_status.clean.push(path)
+                        }
+                    }
+                }
+            }
+            output.output(display_states, ds_status)?;
+            return Ok(());
+        }
+        None => (),
+    }
+
     let (sparse_matcher, sparse_warnings) = sparse::matcher(repo)?;
     let matcher = match (repo.has_narrow(), repo.has_sparse()) {
         (true, true) => {
             Box::new(IntersectionMatcher::new(narrow_matcher, sparse_matcher))
         }
         (true, false) => narrow_matcher,
         (false, true) => sparse_matcher,
         (false, false) => Box::new(AlwaysMatcher),
     };
     let matcher = match args.get_many::<std::ffi::OsString>("file") {
         None => matcher,
         Some(files) => {
             let patterns: Vec<Vec<u8>> = files
                 .filter(|s| !s.is_empty())
                 .map(get_bytes_from_os_str)
                 .collect();
             for file in &patterns {
                 if file.starts_with(b"set:") {
                     return Err(CommandError::unsupported("fileset"));
                 }
             }
             let cwd = hg::utils::current_dir()?;
             let root = repo.working_directory_path();
             let ignore_patterns = parse_pattern_args(patterns, &cwd, root)?;
             let files_matcher =
                 hg::matchers::PatternMatcher::new(ignore_patterns)?;
             Box::new(IntersectionMatcher::new(
                 Box::new(files_matcher),
                 matcher,
             ))
         }
     };
 
     print_narrow_sparse_warnings(
         &narrow_warnings,
         &sparse_warnings,
         ui,
         repo,
     )?;
     let (fixup, mut dirstate_write_needed, filesystem_time_at_status_start) =
         dmap.with_status(
             matcher.as_ref(),
             repo.working_directory_path().to_owned(),
             ignore_files(repo, config),
             options,
             after_status,
         )?;
 
     // Development config option to test write races
     if let Err(e) =
         debug_wait_for_file(config, "status.pre-dirstate-write-file")
     {
         ui.write_stderr(e.as_bytes()).ok();
     }
 
     if (fixup.is_empty() || filesystem_time_at_status_start.is_none())
         && !dirstate_write_needed
     {
         // Nothing to update
         return Ok(());
     }
 
     // Update the dirstate on disk if we can
     let with_lock_result =
         repo.try_with_wlock_no_wait(|| -> Result<(), CommandError> {
             if let Some(mtime_boundary) = filesystem_time_at_status_start {
                 for hg_path in fixup {
                     use std::os::unix::fs::MetadataExt;
                     let fs_path = hg_path_to_path_buf(&hg_path)
                         .expect("HgPath conversion");
                     // Specifically do not reuse `fs_metadata` from
                     // `unsure_is_clean` which was needed before reading
                     // contents. Here we access metadata again after reading
                     // content, in case it changed in the meantime.
                     let metadata_res = repo
                         .working_directory_vfs()
                         .symlink_metadata(&fs_path);
                     let fs_metadata = match metadata_res {
                         Ok(meta) => meta,
                         Err(err) => match err {
                             HgError::IoError { .. } => {
                                 // The file has probably been deleted. In any
                                 // case, it was in the dirstate before, so
                                 // let's ignore the error.
                                 continue;
                             }
                             _ => return Err(err.into()),
                         },
                     };
                     if let Some(mtime) =
                         TruncatedTimestamp::for_reliable_mtime_of(
                             &fs_metadata,
                             &mtime_boundary,
                         )
                         .when_reading_file(&fs_path)?
                     {
                         let mode = fs_metadata.mode();
                         let size = fs_metadata.len();
                         dmap.set_clean(&hg_path, mode, size as u32, mtime)?;
                         dirstate_write_needed = true
                     }
                 }
             }
             drop(dmap); // Avoid "already mutably borrowed" RefCell panics
             if dirstate_write_needed {
                 repo.write_dirstate()?
             }
             Ok(())
         });
     match with_lock_result {
         Ok(closure_result) => closure_result?,
         Err(LockError::AlreadyHeld) => {
             // Not updating the dirstate is not ideal but not critical:
             // don’t keep our caller waiting until some other Mercurial
             // process releases the lock.
             log::info!("not writing dirstate from `status`: lock is held")
         }
         Err(LockError::Other(HgError::IoError { error, .. }))
             if error.kind() == io::ErrorKind::PermissionDenied =>
         {
             // `hg status` on a read-only repository is fine
         }
         Err(LockError::Other(error)) => {
             // Report other I/O errors
             Err(error)?
         }
     }
     Ok(())
 }
 
 fn ignore_files(repo: &Repo, config: &Config) -> Vec<PathBuf> {
     let mut ignore_files = Vec::new();
     let repo_ignore = repo.working_directory_vfs().join(".hgignore");
     if repo_ignore.exists() {
         ignore_files.push(repo_ignore)
     }
     for (key, value) in config.iter_section(b"ui") {
         if key == b"ignore" || key.starts_with(b"ignore.") {
             let path = get_path_from_bytes(value);
             // TODO: expand "~/" and environment variable here, like Python
             // does with `os.path.expanduser` and `os.path.expandvars`
 
             let joined = repo.working_directory_path().join(path);
             ignore_files.push(joined);
         }
     }
     ignore_files
 }
 
 struct DisplayStatusPaths<'a> {
     ui: &'a Ui,
     no_status: bool,
     relativize: Option<RelativizePaths>,
     print0: bool,
 }
 
 impl DisplayStatusPaths<'_> {
     // Probably more elegant to use a Deref or Borrow trait rather than
     // harcode HgPathBuf, but probably not really useful at this point
     fn display(
         &self,
         status_prefix: &[u8],
         label: &'static str,
         mut paths: Vec<StatusPath<'_>>,
     ) -> Result<(), CommandError> {
         paths.sort_unstable();
         // TODO: get the stdout lock once for the whole loop
         // instead of in each write
         for StatusPath { path, copy_source } in paths {
             let relative_path;
             let relative_source;
             let (path, copy_source) = if let Some(relativize) =
                 &self.relativize
             {
                 relative_path = relativize.relativize(&path);
                 relative_source =
                     copy_source.as_ref().map(|s| relativize.relativize(s));
                 (&*relative_path, relative_source.as_deref())
             } else {
                 (path.as_bytes(), copy_source.as_ref().map(|s| s.as_bytes()))
             };
             // TODO: Add a way to use `write_bytes!` instead of `format_bytes!`
             // in order to stream to stdout instead of allocating an
             // itermediate `Vec<u8>`.
             if !self.no_status {
                 self.ui.write_stdout_labelled(status_prefix, label)?
             }
             let linebreak = if self.print0 { b"\x00" } else { b"\n" };
             self.ui.write_stdout_labelled(
                 &format_bytes!(b"{}{}", path, linebreak),
                 label,
             )?;
             if let Some(source) = copy_source.filter(|_| !self.no_status) {
                 let label = "status.copied";
                 self.ui.write_stdout_labelled(
                     &format_bytes!(b"  {}{}", source, linebreak),
                     label,
                 )?
             }
         }
         Ok(())
     }
 
     fn output(
         &mut self,
         display_states: DisplayStates,
         ds_status: DirstateStatus,
     ) -> Result<(), CommandError> {
         if display_states.modified {
             self.display(b"M ", "status.modified", ds_status.modified)?;
         }
         if display_states.added {
             self.display(b"A ", "status.added", ds_status.added)?;
         }
         if display_states.removed {
             self.display(b"R ", "status.removed", ds_status.removed)?;
         }
         if display_states.deleted {
             self.display(b"! ", "status.deleted", ds_status.deleted)?;
         }
         if display_states.unknown {
             self.display(b"? ", "status.unknown", ds_status.unknown)?;
         }
         if display_states.ignored {
             self.display(b"I ", "status.ignored", ds_status.ignored)?;
         }
         if display_states.clean {
             self.display(b"C ", "status.clean", ds_status.clean)?;
         }
         Ok(())
     }
 }
 
 /// Outcome of the additional check for an ambiguous tracked file
 enum UnsureOutcome {
     /// The file is actually clean
     Clean,
     /// The file has been modified
     Modified,
     /// The file was deleted on disk (or became another type of fs entry)
     Deleted,
 }
 
 /// Check if a file is modified by comparing actual repo store and file system.
 ///
 /// This meant to be used for those that the dirstate cannot resolve, due
 /// to time resolution limits.
 fn unsure_is_modified(
     working_directory_vfs: hg::vfs::Vfs,
     store_vfs: hg::vfs::Vfs,
     check_exec: bool,
     manifest: &Manifest,
     hg_path: &HgPath,
 ) -> Result<UnsureOutcome, HgError> {
     let vfs = working_directory_vfs;
     let fs_path = hg_path_to_path_buf(hg_path).expect("HgPath conversion");
     let fs_metadata = vfs.symlink_metadata(&fs_path)?;
     let is_symlink = fs_metadata.file_type().is_symlink();
 
     let entry = manifest
         .find_by_path(hg_path)?
         .expect("ambgious file not in p1");
 
     // TODO: Also account for `FALLBACK_SYMLINK` and `FALLBACK_EXEC` from the
     // dirstate
     let fs_flags = if is_symlink {
         Some(b'l')
     } else if check_exec && has_exec_bit(&fs_metadata) {
         Some(b'x')
     } else {
         None
     };
 
     let entry_flags = if check_exec {
         entry.flags
     } else if entry.flags == Some(b'x') {
         None
     } else {
         entry.flags
     };
 
     if entry_flags != fs_flags {
         return Ok(UnsureOutcome::Modified);
     }
     let filelog = hg::filelog::Filelog::open_vfs(&store_vfs, hg_path)?;
     let fs_len = fs_metadata.len();
     let file_node = entry.node_id()?;
     let filelog_entry = filelog.entry_for_node(file_node).map_err(|_| {
         HgError::corrupted(format!(
             "filelog {:?} missing node {:?} from manifest",
             hg_path, file_node
         ))
     })?;
     if filelog_entry.file_data_len_not_equal_to(fs_len) {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(UnsureOutcome::Modified);
     }
 
     let p1_filelog_data = filelog_entry.data()?;
     let p1_contents = p1_filelog_data.file_data()?;
     if p1_contents.len() as u64 != fs_len {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(UnsureOutcome::Modified);
     }
 
     let fs_contents = if is_symlink {
         get_bytes_from_os_string(vfs.read_link(fs_path)?.into_os_string())
     } else {
         vfs.read(fs_path)?
     };
 
     Ok(if p1_contents != &*fs_contents {
         UnsureOutcome::Modified
     } else {
         UnsureOutcome::Clean
     })
 }

rust/rhg/src/main.rs

@@ -1,842 +1,849 b''
 extern crate log;
 use crate::error::CommandError;
 use crate::ui::{local_to_utf8, Ui};
 use clap::{command, Arg, ArgMatches};
 use format_bytes::{format_bytes, join};
 use hg::config::{Config, ConfigSource, PlainInfo};
 use hg::repo::{Repo, RepoError};
 use hg::utils::files::{get_bytes_from_os_str, get_path_from_bytes};
 use hg::utils::SliceExt;
 use hg::{exit_codes, requirements};
 use std::borrow::Cow;
 use std::collections::HashSet;
 use std::ffi::OsString;
 use std::os::unix::prelude::CommandExt;
 use std::path::PathBuf;
 use std::process::Command;
 
 mod blackbox;
 mod color;
 mod error;
 mod ui;
 pub mod utils {
     pub mod path_utils;
 }
 
 fn main_with_result(
     argv: Vec<OsString>,
     process_start_time: &blackbox::ProcessStartTime,
     ui: &ui::Ui,
     repo: Result<&Repo, &NoRepoInCwdError>,
     config: &Config,
 ) -> Result<(), CommandError> {
     check_unsupported(config, repo)?;
 
     let app = command!()
         .subcommand_required(true)
         .arg(
             Arg::new("repository")
                 .help("repository root directory")
                 .short('R')
                 .value_name("REPO")
                 // Both ok: `hg -R ./foo log` or `hg log -R ./foo`
                 .global(true),
         )
         .arg(
             Arg::new("config")
                 .help("set/override config option (use 'section.name=value')")
                 .value_name("CONFIG")
                 .global(true)
                 .long("config")
                 // Ok: `--config section.key1=val --config section.key2=val2`
                 // Not ok: `--config section.key1=val section.key2=val2`
                 .action(clap::ArgAction::Append),
         )
         .arg(
             Arg::new("cwd")
                 .help("change working directory")
                 .value_name("DIR")
                 .long("cwd")
                 .global(true),
         )
         .arg(
             Arg::new("color")
                 .help("when to colorize (boolean, always, auto, never, or debug)")
                 .value_name("TYPE")
                 .long("color")
                 .global(true),
         )
         .version("0.0.1");
     let app = add_subcommand_args(app);
 
     let matches = app.try_get_matches_from(argv.iter())?;
 
     let (subcommand_name, subcommand_args) =
         matches.subcommand().expect("subcommand required");
 
     // Mercurial allows users to define "defaults" for commands, fallback
     // if a default is detected for the current command
     let defaults = config.get_str(b"defaults", subcommand_name.as_bytes())?;
     match defaults {
         // Programmatic usage might set defaults to an empty string to unset
         // it; allow that
         None | Some("") => {}
         Some(_) => {
             let msg = "`defaults` config set";
             return Err(CommandError::unsupported(msg));
         }
     }
 
     for prefix in ["pre", "post", "fail"].iter() {
         // Mercurial allows users to define generic hooks for commands,
         // fallback if any are detected
         let item = format!("{}-{}", prefix, subcommand_name);
         let hook_for_command =
             config.get_str_no_default(b"hooks", item.as_bytes())?;
         if hook_for_command.is_some() {
             let msg = format!("{}-{} hook defined", prefix, subcommand_name);
             return Err(CommandError::unsupported(msg));
         }
     }
     let run = subcommand_run_fn(subcommand_name)
         .expect("unknown subcommand name from clap despite Command::subcommand_required");
 
     let invocation = CliInvocation {
         ui,
         subcommand_args,
         config,
         repo,
     };
 
     if let Ok(repo) = repo {
         // We don't support subrepos, fallback if the subrepos file is present
         if repo.working_directory_vfs().join(".hgsub").exists() {
             let msg = "subrepos (.hgsub is present)";
             return Err(CommandError::unsupported(msg));
         }
     }
 
     if config.is_extension_enabled(b"blackbox") {
         let blackbox =
             blackbox::Blackbox::new(&invocation, process_start_time)?;
         blackbox.log_command_start(argv.iter());
         let result = run(&invocation);
         blackbox.log_command_end(
             argv.iter(),
             exit_code(
                 &result,
                 // TODO: show a warning or combine with original error if
                 // `get_bool` returns an error
                 config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             ),
         );
         result
     } else {
         run(&invocation)
     }
 }
 
 fn rhg_main(argv: Vec<OsString>) -> ! {
     // Run this first, before we find out if the blackbox extension is even
     // enabled, in order to include everything in-between in the duration
     // measurements. Reading config files can be slow if they’re on NFS.
     let process_start_time = blackbox::ProcessStartTime::now();
 
     env_logger::init();
 
     // Make sure nothing in a future version of `rhg` sets the global
     // threadpool before we can cap default threads. (This is also called
     // in core because Python uses the same code path, we're adding a
     // redundant check.)
     hg::utils::cap_default_rayon_threads()
         .expect("Rayon threadpool already initialized");
 
     let early_args = EarlyArgs::parse(&argv);
 
     let initial_current_dir = early_args.cwd.map(|cwd| {
         let cwd = get_path_from_bytes(&cwd);
         std::env::current_dir()
             .and_then(|initial| {
                 std::env::set_current_dir(cwd)?;
                 Ok(initial)
             })
             .unwrap_or_else(|error| {
                 exit(
                     &argv,
                     &None,
                     &Ui::new_infallible(&Config::empty()),
                     OnUnsupported::Abort,
                     Err(CommandError::abort(format!(
                         "abort: {}: '{}'",
                         error,
                         cwd.display()
                     ))),
                     false,
                 )
             })
     });
 
     let mut non_repo_config =
         Config::load_non_repo().unwrap_or_else(|error| {
             // Normally this is decided based on config, but we don’t have that
             // available. As of this writing config loading never returns an
             // "unsupported" error but that is not enforced by the type system.
             let on_unsupported = OnUnsupported::Abort;
 
             exit(
                 &argv,
                 &initial_current_dir,
                 &Ui::new_infallible(&Config::empty()),
                 on_unsupported,
                 Err(error.into()),
                 false,
             )
         });
 
     non_repo_config
         .load_cli_args(early_args.config, early_args.color)
         .unwrap_or_else(|error| {
             exit(
                 &argv,
                 &initial_current_dir,
                 &Ui::new_infallible(&non_repo_config),
                 OnUnsupported::from_config(&non_repo_config),
                 Err(error.into()),
                 non_repo_config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             )
         });
 
     if let Some(repo_path_bytes) = &early_args.repo {
         lazy_static::lazy_static! {
             static ref SCHEME_RE: regex::bytes::Regex =
                 // Same as `_matchscheme` in `mercurial/util.py`
                 regex::bytes::Regex::new("^[a-zA-Z0-9+.\\-]+:").unwrap();
         }
         if SCHEME_RE.is_match(repo_path_bytes) {
             exit(
                 &argv,
                 &initial_current_dir,
                 &Ui::new_infallible(&non_repo_config),
                 OnUnsupported::from_config(&non_repo_config),
                 Err(CommandError::UnsupportedFeature {
                     message: format_bytes!(
                         b"URL-like --repository {}",
                         repo_path_bytes
                     ),
                 }),
                 // TODO: show a warning or combine with original error if
                 // `get_bool` returns an error
                 non_repo_config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             )
         }
     }
     let repo_arg = early_args.repo.unwrap_or_default();
     let repo_path: Option<PathBuf> = {
         if repo_arg.is_empty() {
             None
         } else {
             let local_config = {
                 if std::env::var_os("HGRCSKIPREPO").is_none() {
                     // TODO: handle errors from find_repo_root
                     if let Ok(current_dir_path) = Repo::find_repo_root() {
                         let config_files = vec![
                             ConfigSource::AbsPath(
                                 current_dir_path.join(".hg/hgrc"),
                             ),
                             ConfigSource::AbsPath(
                                 current_dir_path.join(".hg/hgrc-not-shared"),
                             ),
                         ];
                         // TODO: handle errors from
                         // `load_from_explicit_sources`
                         Config::load_from_explicit_sources(config_files).ok()
                     } else {
                         None
                     }
                 } else {
                     None
                 }
             };
 
             let non_repo_config_val = {
                 let non_repo_val = non_repo_config.get(b"paths", &repo_arg);
                 match &non_repo_val {
                     Some(val) if !val.is_empty() => home::home_dir()
                         .unwrap_or_else(|| PathBuf::from("~"))
                         .join(get_path_from_bytes(val))
                         .canonicalize()
                         // TODO: handle error and make it similar to python
                         // implementation maybe?
                         .ok(),
                     _ => None,
                 }
             };
 
             let config_val = match &local_config {
                 None => non_repo_config_val,
                 Some(val) => {
                     let local_config_val = val.get(b"paths", &repo_arg);
                     match &local_config_val {
                         Some(val) if !val.is_empty() => {
                             // presence of a local_config assures that
                             // current_dir
                             // wont result in an Error
                             let canpath = hg::utils::current_dir()
                                 .unwrap()
                                 .join(get_path_from_bytes(val))
                                 .canonicalize();
                             canpath.ok().or(non_repo_config_val)
                         }
                         _ => non_repo_config_val,
                     }
                 }
             };
             config_val
                 .or_else(|| Some(get_path_from_bytes(&repo_arg).to_path_buf()))
         }
     };
 
     let simple_exit =
         |ui: &Ui, config: &Config, result: Result<(), CommandError>| -> ! {
             exit(
                 &argv,
                 &initial_current_dir,
                 ui,
                 OnUnsupported::from_config(config),
                 result,
                 // TODO: show a warning or combine with original error if
                 // `get_bool` returns an error
                 non_repo_config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             )
         };
     let early_exit = |config: &Config, error: CommandError| -> ! {
         simple_exit(&Ui::new_infallible(config), config, Err(error))
     };
     let repo_result = match Repo::find(&non_repo_config, repo_path.to_owned())
     {
         Ok(repo) => Ok(repo),
         Err(RepoError::NotFound { at }) if repo_path.is_none() => {
             // Not finding a repo is not fatal yet, if `-R` was not given
             Err(NoRepoInCwdError { cwd: at })
         }
         Err(error) => early_exit(&non_repo_config, error.into()),
     };
 
     let config = if let Ok(repo) = &repo_result {
         repo.config()
     } else {
         &non_repo_config
     };
 
     let mut config_cow = Cow::Borrowed(config);
     config_cow.to_mut().apply_plain(PlainInfo::from_env());
     if !ui::plain(Some("tweakdefaults"))
         && config_cow
             .as_ref()
             .get_bool(b"ui", b"tweakdefaults")
             .unwrap_or_else(|error| early_exit(config, error.into()))
     {
         config_cow.to_mut().tweakdefaults()
     };
     let config = config_cow.as_ref();
     let ui = Ui::new(config)
         .unwrap_or_else(|error| early_exit(config, error.into()));
 
     if let Ok(true) = config.get_bool(b"rhg", b"fallback-immediately") {
         exit(
             &argv,
             &initial_current_dir,
             &ui,
             OnUnsupported::fallback(config),
             Err(CommandError::unsupported(
                 "`rhg.fallback-immediately is true`",
             )),
             false,
         )
     }
 
     let result = main_with_result(
         argv.iter().map(|s| s.to_owned()).collect(),
         &process_start_time,
         &ui,
         repo_result.as_ref(),
         config,
     );
     simple_exit(&ui, config, result)
 }
 
 fn main() -> ! {
     rhg_main(std::env::args_os().collect())
 }
 
 fn exit_code(
     result: &Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> i32 {
     match result {
         Ok(()) => exit_codes::OK,
         Err(CommandError::Abort {
             detailed_exit_code, ..
         }) => {
             if use_detailed_exit_code {
                 *detailed_exit_code
             } else {
                 exit_codes::ABORT
             }
         }
         Err(CommandError::Unsuccessful) => exit_codes::UNSUCCESSFUL,
         // Exit with a specific code and no error message to let a potential
         // wrapper script fallback to Python-based Mercurial.
         Err(CommandError::UnsupportedFeature { .. }) => {
             exit_codes::UNIMPLEMENTED
         }
         Err(CommandError::InvalidFallback { .. }) => {
             exit_codes::INVALID_FALLBACK
         }
     }
 }
 
 fn exit(
     original_args: &[OsString],
     initial_current_dir: &Option<PathBuf>,
     ui: &Ui,
     mut on_unsupported: OnUnsupported,
     result: Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> ! {
     if let (
         OnUnsupported::Fallback { executable },
         Err(CommandError::UnsupportedFeature { message }),
     ) = (&on_unsupported, &result)
     {
         let mut args = original_args.iter();
         let executable = match executable {
             None => {
                 exit_no_fallback(
                     ui,
                     OnUnsupported::Abort,
                     Err(CommandError::abort(
                         "abort: 'rhg.on-unsupported=fallback' without \
                                 'rhg.fallback-executable' set.",
                     )),
                     false,
                 );
             }
             Some(executable) => executable,
         };
         let executable_path = get_path_from_bytes(executable);
         let this_executable = args.next().expect("exepcted argv[0] to exist");
         if executable_path == *this_executable {
             // Avoid spawning infinitely many processes until resource
             // exhaustion.
             let _ = ui.write_stderr(&format_bytes!(
                 b"Blocking recursive fallback. The 'rhg.fallback-executable = {}' config \
                 points to `rhg` itself.\n",
                 executable
             ));
             on_unsupported = OnUnsupported::Abort
         } else {
             log::debug!("falling back (see trace-level log)");
             log::trace!("{}", local_to_utf8(message));
             if let Err(err) = which::which(executable_path) {
                 exit_no_fallback(
                     ui,
                     OnUnsupported::Abort,
                     Err(CommandError::InvalidFallback {
                         path: executable.to_owned(),
                         err: err.to_string(),
                     }),
                     use_detailed_exit_code,
                 )
             }
             // `args` is now `argv[1..]` since we’ve already consumed
             // `argv[0]`
             let mut command = Command::new(executable_path);
             command.args(args);
             if let Some(initial) = initial_current_dir {
                 command.current_dir(initial);
             }
             // We don't use subprocess because proper signal handling is harder
             // and we don't want to keep `rhg` around after a fallback anyway.
             // For example, if `rhg` is run in the background and falls back to
             // `hg` which, in turn, waits for a signal, we'll get stuck if
             // we're doing plain subprocess.
             //
             // If `exec` returns, we can only assume our process is very broken
             // (see its documentation), so only try to forward the error code
             // when exiting.
             let err = command.exec();
             std::process::exit(
                 err.raw_os_error().unwrap_or(exit_codes::ABORT),
             );
         }
     }
     exit_no_fallback(ui, on_unsupported, result, use_detailed_exit_code)
 }
 
 fn exit_no_fallback(
     ui: &Ui,
     on_unsupported: OnUnsupported,
     result: Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> ! {
     match &result {
         Ok(_) => {}
         Err(CommandError::Unsuccessful) => {}
         Err(CommandError::Abort { message, hint, .. }) => {
             // Ignore errors when writing to stderr, we’re already exiting
             // with failure code so there’s not much more we can do.
             if !message.is_empty() {
                 let _ = ui.write_stderr(&format_bytes!(b"{}\n", message));
             }
             if let Some(hint) = hint {
                 let _ = ui.write_stderr(&format_bytes!(b"({})\n", hint));
             }
         }
         Err(CommandError::UnsupportedFeature { message }) => {
             match on_unsupported {
                 OnUnsupported::Abort => {
                     let _ = ui.write_stderr(&format_bytes!(
                         b"unsupported feature: {}\n",
                         message
                     ));
                 }
                 OnUnsupported::AbortSilent => {}
                 OnUnsupported::Fallback { .. } => unreachable!(),
             }
         }
         Err(CommandError::InvalidFallback { path, err }) => {
             let _ = ui.write_stderr(&format_bytes!(
                 b"abort: invalid fallback '{}': {}\n",
                 path,
                 err.as_bytes(),
             ));
         }
     }
     std::process::exit(exit_code(&result, use_detailed_exit_code))
 }
 
+mod commands {
+    pub mod cat;
+    pub mod config;
+    pub mod debugdata;
+    pub mod debugignorerhg;
+    pub mod debugrequirements;
+    pub mod debugrhgsparse;
+    pub mod files;
+    pub mod root;
+    pub mod status;
+}
+
 macro_rules! subcommands {
     ($( $command: ident )+) => {
-        mod commands {
-            $(
-                pub mod $command;
-            )+
-        }
 
         fn add_subcommand_args(app: clap::Command) -> clap::Command {
             app
             $(
                 .subcommand(commands::$command::args())
             )+
         }
 
         pub type RunFn = fn(&CliInvocation) -> Result<(), CommandError>;
 
         fn subcommand_run_fn(name: &str) -> Option<RunFn> {
             match name {
                 $(
                     stringify!($command) => Some(commands::$command::run),
                 )+
                 _ => None,
             }
         }
     };
 }
 
 subcommands! {
     cat
     debugdata
     debugrequirements
     debugignorerhg
     debugrhgsparse
     files
     root
     config
     status
 }
 
 pub struct CliInvocation<'a> {
     ui: &'a Ui,
     subcommand_args: &'a ArgMatches,
     config: &'a Config,
     /// References inside `Result` is a bit peculiar but allow
     /// `invocation.repo?` to work out with `&CliInvocation` since this
     /// `Result` type is `Copy`.
     repo: Result<&'a Repo, &'a NoRepoInCwdError>,
 }
 
 struct NoRepoInCwdError {
     cwd: PathBuf,
 }
 
 /// CLI arguments to be parsed "early" in order to be able to read
 /// configuration before using Clap. Ideally we would also use Clap for this,
 /// see <https://github.com/clap-rs/clap/discussions/2366>.
 ///
 /// These arguments are still declared when we do use Clap later, so that Clap
 /// does not return an error for their presence.
 struct EarlyArgs {
     /// Values of all `--config` arguments. (Possibly none)
     config: Vec<Vec<u8>>,
     /// Value of all the `--color` argument, if any.
     color: Option<Vec<u8>>,
     /// Value of the `-R` or `--repository` argument, if any.
     repo: Option<Vec<u8>>,
     /// Value of the `--cwd` argument, if any.
     cwd: Option<Vec<u8>>,
 }
 
 impl EarlyArgs {
     fn parse<'a>(args: impl IntoIterator<Item = &'a OsString>) -> Self {
         let mut args = args.into_iter().map(get_bytes_from_os_str);
         let mut config = Vec::new();
         let mut color = None;
         let mut repo = None;
         let mut cwd = None;
         // Use `while let` instead of `for` so that we can also call
         // `args.next()` inside the loop.
         while let Some(arg) = args.next() {
             if arg == b"--config" {
                 if let Some(value) = args.next() {
                     config.push(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--config=") {
                 config.push(value.to_owned())
             }
 
             if arg == b"--color" {
                 if let Some(value) = args.next() {
                     color = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--color=") {
                 color = Some(value.to_owned())
             }
 
             if arg == b"--cwd" {
                 if let Some(value) = args.next() {
                     cwd = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--cwd=") {
                 cwd = Some(value.to_owned())
             }
 
             if arg == b"--repository" || arg == b"-R" {
                 if let Some(value) = args.next() {
                     repo = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--repository=") {
                 repo = Some(value.to_owned())
             } else if let Some(value) = arg.drop_prefix(b"-R") {
                 repo = Some(value.to_owned())
             }
         }
         Self {
             config,
             color,
             repo,
             cwd,
         }
     }
 }
 
 /// What to do when encountering some unsupported feature.
 ///
 /// See `HgError::UnsupportedFeature` and `CommandError::UnsupportedFeature`.
 enum OnUnsupported {
     /// Print an error message describing what feature is not supported,
     /// and exit with code 252.
     Abort,
     /// Silently exit with code 252.
     AbortSilent,
     /// Try running a Python implementation
     Fallback { executable: Option<Vec<u8>> },
 }
 
 impl OnUnsupported {
     const DEFAULT: Self = OnUnsupported::Abort;
 
     fn fallback_executable(config: &Config) -> Option<Vec<u8>> {
         config
             .get(b"rhg", b"fallback-executable")
             .map(|x| x.to_owned())
     }
 
     fn fallback(config: &Config) -> Self {
         OnUnsupported::Fallback {
             executable: Self::fallback_executable(config),
         }
     }
 
     fn from_config(config: &Config) -> Self {
         match config
             .get(b"rhg", b"on-unsupported")
             .map(|value| value.to_ascii_lowercase())
             .as_deref()
         {
             Some(b"abort") => OnUnsupported::Abort,
             Some(b"abort-silent") => OnUnsupported::AbortSilent,
             Some(b"fallback") => Self::fallback(config),
             None => Self::DEFAULT,
             Some(_) => {
                 // TODO: warn about unknown config value
                 Self::DEFAULT
             }
         }
     }
 }
 
 /// The `*` extension is an edge-case for config sub-options that apply to all
 /// extensions. For now, only `:required` exists, but that may change in the
 /// future.
 const SUPPORTED_EXTENSIONS: &[&[u8]] = &[
     b"blackbox",
     b"share",
     b"sparse",
     b"narrow",
     b"*",
     b"strip",
     b"rebase",
 ];
 
 fn check_extensions(config: &Config) -> Result<(), CommandError> {
     if let Some(b"*") = config.get(b"rhg", b"ignored-extensions") {
         // All extensions are to be ignored, nothing to do here
         return Ok(());
     }
 
     let enabled: HashSet<&[u8]> = config
         .iter_section(b"extensions")
         .filter_map(|(extension, value)| {
             if value == b"!" {
                 // Filter out disabled extensions
                 return None;
             }
             // Ignore extension suboptions. Only `required` exists for now.
             // `rhg` either supports an extension or doesn't, so it doesn't
             // make sense to consider the loading of an extension.
             let actual_extension =
                 extension.split_2(b':').unwrap_or((extension, b"")).0;
             Some(actual_extension)
         })
         .collect();
 
     let mut unsupported = enabled;
     for supported in SUPPORTED_EXTENSIONS {
         unsupported.remove(supported);
     }
 
     if let Some(ignored_list) = config.get_list(b"rhg", b"ignored-extensions")
     {
         for ignored in ignored_list {
             unsupported.remove(ignored.as_slice());
         }
     }
 
     if unsupported.is_empty() {
         Ok(())
     } else {
         let mut unsupported: Vec<_> = unsupported.into_iter().collect();
         // Sort the extensions to get a stable output
         unsupported.sort();
         Err(CommandError::UnsupportedFeature {
             message: format_bytes!(
                 b"extensions: {} (consider adding them to 'rhg.ignored-extensions' config)",
                 join(unsupported, b", ")
             ),
         })
     }
 }
 
 /// Array of tuples of (auto upgrade conf, feature conf, local requirement)
 #[allow(clippy::type_complexity)]
 const AUTO_UPGRADES: &[((&str, &str), (&str, &str), &str)] = &[
     (
         ("format", "use-share-safe.automatic-upgrade-of-mismatching-repositories"),
         ("format", "use-share-safe"),
         requirements::SHARESAFE_REQUIREMENT,
     ),
     (
         ("format", "use-dirstate-tracked-hint.automatic-upgrade-of-mismatching-repositories"),
         ("format", "use-dirstate-tracked-hint"),
         requirements::DIRSTATE_TRACKED_HINT_V1,
     ),
     (
         ("format", "use-dirstate-v2.automatic-upgrade-of-mismatching-repositories"),
         ("format", "use-dirstate-v2"),
         requirements::DIRSTATE_V2_REQUIREMENT,
     ),
 ];
 
 /// Mercurial allows users to automatically upgrade their repository.
 /// `rhg` does not have the ability to upgrade yet, so fallback if an upgrade
 /// is needed.
 fn check_auto_upgrade(
     config: &Config,
     reqs: &HashSet<String>,
 ) -> Result<(), CommandError> {
     for (upgrade_conf, feature_conf, local_req) in AUTO_UPGRADES.iter() {
         let auto_upgrade = config
             .get_bool(upgrade_conf.0.as_bytes(), upgrade_conf.1.as_bytes())?;
 
         if auto_upgrade {
             let want_it = config.get_bool(
                 feature_conf.0.as_bytes(),
                 feature_conf.1.as_bytes(),
             )?;
             let have_it = reqs.contains(*local_req);
 
             let action = match (want_it, have_it) {
                 (true, false) => Some("upgrade"),
                 (false, true) => Some("downgrade"),
                 _ => None,
             };
             if let Some(action) = action {
                 let message = format!(
                     "automatic {} {}.{}",
                     action, upgrade_conf.0, upgrade_conf.1
                 );
                 return Err(CommandError::unsupported(message));
             }
         }
     }
     Ok(())
 }
 
 fn check_unsupported(
     config: &Config,
     repo: Result<&Repo, &NoRepoInCwdError>,
 ) -> Result<(), CommandError> {
     check_extensions(config)?;
 
     if std::env::var_os("HG_PENDING").is_some() {
         // TODO: only if the value is `== repo.working_directory`?
         // What about relative v.s. absolute paths?
         Err(CommandError::unsupported("$HG_PENDING"))?
     }
 
     if let Ok(repo) = repo {
         if repo.has_subrepos()? {
             Err(CommandError::unsupported("sub-repositories"))?
         }
         check_auto_upgrade(config, repo.requirements())?;
     }
 
     if config.has_non_empty_section(b"encode") {
         Err(CommandError::unsupported("[encode] config"))?
     }
 
     if config.has_non_empty_section(b"decode") {
         Err(CommandError::unsupported("[decode] config"))?
     }
 
     Ok(())
 }

tests/test-status-rev.t

@@ -1,159 +1,186 b''
 Tests of 'hg status --rev <rev>' to make sure status between <rev> and '.' get
 combined correctly with the dirstate status.
 
   $ hg init repo
   $ cd repo
 
 First commit
 
   $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 1
   $ hg addremove --similarity 0
   adding content1_content1_content1-tracked
   adding content1_content1_content1-untracked
   adding content1_content1_content3-tracked
   adding content1_content1_content3-untracked
   adding content1_content1_missing-tracked
   adding content1_content1_missing-untracked
   adding content1_content2_content1-tracked
   adding content1_content2_content1-untracked
   adding content1_content2_content2-tracked
   adding content1_content2_content2-untracked
   adding content1_content2_content3-tracked
   adding content1_content2_content3-untracked
   adding content1_content2_missing-tracked
   adding content1_content2_missing-untracked
   adding content1_missing_content1-tracked
   adding content1_missing_content1-untracked
   adding content1_missing_content3-tracked
   adding content1_missing_content3-untracked
   adding content1_missing_missing-tracked
   adding content1_missing_missing-untracked
   $ hg commit -m first
 
 Second commit
 
   $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 2
   $ hg addremove --similarity 0
   removing content1_missing_content1-tracked
   removing content1_missing_content1-untracked
   removing content1_missing_content3-tracked
   removing content1_missing_content3-untracked
   removing content1_missing_missing-tracked
   removing content1_missing_missing-untracked
   adding missing_content2_content2-tracked
   adding missing_content2_content2-untracked
   adding missing_content2_content3-tracked
   adding missing_content2_content3-untracked
   adding missing_content2_missing-tracked
   adding missing_content2_missing-untracked
   $ hg commit -m second
 
 Working copy
 
   $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 wc
   $ hg addremove --similarity 0
   adding content1_missing_content1-tracked
   adding content1_missing_content1-untracked
   adding content1_missing_content3-tracked
   adding content1_missing_content3-untracked
   adding content1_missing_missing-tracked
   adding content1_missing_missing-untracked
   adding missing_missing_content3-tracked
   adding missing_missing_content3-untracked
   adding missing_missing_missing-tracked
   adding missing_missing_missing-untracked
   $ hg forget *_*_*-untracked
   $ rm *_*_missing-*
 
 Status compared to parent of the working copy, i.e. the dirstate status
 
   $ hg status -A --rev 1 'glob:missing_content2_content3-tracked'
   M missing_content2_content3-tracked
   $ hg status -A --rev 1 'glob:missing_content2_content2-tracked'
   C missing_content2_content2-tracked
   $ hg status -A --rev 1 'glob:missing_missing_content3-tracked'
   A missing_missing_content3-tracked
   $ hg status -A --rev 1 'glob:missing_missing_content3-untracked'
   ? missing_missing_content3-untracked
   $ hg status -A --rev 1 'glob:missing_content2_*-untracked'
   R missing_content2_content2-untracked
   R missing_content2_content3-untracked
   R missing_content2_missing-untracked
   $ hg status -A --rev 1 'glob:missing_*_missing-tracked'
   ! missing_content2_missing-tracked
   ! missing_missing_missing-tracked
 
   $ hg status -A --rev 1 'glob:missing_missing_missing-untracked'
   missing_missing_missing-untracked: $ENOENT$
 
 Status between first and second commit. Should ignore dirstate status.
 
+  $ hg status -marc --rev 0 --rev 1 --config rhg.on-unsupported=abort
+  M content1_content2_content1-tracked
+  M content1_content2_content1-untracked
+  M content1_content2_content2-tracked
+  M content1_content2_content2-untracked
+  M content1_content2_content3-tracked
+  M content1_content2_content3-untracked
+  M content1_content2_missing-tracked
+  M content1_content2_missing-untracked
+  A missing_content2_content2-tracked
+  A missing_content2_content2-untracked
+  A missing_content2_content3-tracked
+  A missing_content2_content3-untracked
+  A missing_content2_missing-tracked
+  A missing_content2_missing-untracked
+  R content1_missing_content1-tracked
+  R content1_missing_content1-untracked
+  R content1_missing_content3-tracked
+  R content1_missing_content3-untracked
+  R content1_missing_missing-tracked
+  R content1_missing_missing-untracked
+  C content1_content1_content1-tracked
+  C content1_content1_content1-untracked
+  C content1_content1_content3-tracked
+  C content1_content1_content3-untracked
+  C content1_content1_missing-tracked
+  C content1_content1_missing-untracked
   $ hg status -A --rev 0:1 'glob:content1_content2_*'
   M content1_content2_content1-tracked
   M content1_content2_content1-untracked
   M content1_content2_content2-tracked
   M content1_content2_content2-untracked
   M content1_content2_content3-tracked
   M content1_content2_content3-untracked
   M content1_content2_missing-tracked
   M content1_content2_missing-untracked
   $ hg status -A --rev 0:1 'glob:content1_content1_*'
   C content1_content1_content1-tracked
   C content1_content1_content1-untracked
   C content1_content1_content3-tracked
   C content1_content1_content3-untracked
   C content1_content1_missing-tracked
   C content1_content1_missing-untracked
   $ hg status -A --rev 0:1 'glob:missing_content2_*'
   A missing_content2_content2-tracked
   A missing_content2_content2-untracked
   A missing_content2_content3-tracked
   A missing_content2_content3-untracked
   A missing_content2_missing-tracked
   A missing_content2_missing-untracked
   $ hg status -A --rev 0:1 'glob:content1_missing_*'
   R content1_missing_content1-tracked
   R content1_missing_content1-untracked
   R content1_missing_content3-tracked
   R content1_missing_content3-untracked
   R content1_missing_missing-tracked
   R content1_missing_missing-untracked
   $ hg status -A --rev 0:1 'glob:missing_missing_*'
 
 Status compared to one revision back, checking that the dirstate status
 is correctly combined with the inter-revision status
 
   $ hg status -A --rev 0 'glob:content1_*_content[23]-tracked'
   M content1_content1_content3-tracked
   M content1_content2_content2-tracked
   M content1_content2_content3-tracked
   M content1_missing_content3-tracked
   $ hg status -A --rev 0 'glob:content1_*_content1-tracked'
   C content1_content1_content1-tracked
   C content1_content2_content1-tracked
   C content1_missing_content1-tracked
   $ hg status -A --rev 0 'glob:missing_*_content?-tracked'
   A missing_content2_content2-tracked
   A missing_content2_content3-tracked
   A missing_missing_content3-tracked
 BROKEN: missing_content2_content[23]-untracked exist, so should be listed
   $ hg status -A --rev 0 'glob:missing_*_content?-untracked'
   ? missing_missing_content3-untracked
   $ hg status -A --rev 0 'glob:content1_*_*-untracked'
   R content1_content1_content1-untracked
   R content1_content1_content3-untracked
   R content1_content1_missing-untracked
   R content1_content2_content1-untracked
   R content1_content2_content2-untracked
   R content1_content2_content3-untracked
   R content1_content2_missing-untracked
   R content1_missing_content1-untracked
   R content1_missing_content3-untracked
   R content1_missing_missing-untracked
   $ hg status -A --rev 0 'glob:*_*_missing-tracked'
   ! content1_content1_missing-tracked
   ! content1_content2_missing-tracked
   ! content1_missing_missing-tracked
   ! missing_content2_missing-tracked
   ! missing_missing_missing-tracked
   $ hg status -A --rev 0 'glob:missing_*_missing-untracked'