rhg: support `status --print0`

This seems very easy to support, and useful because it makes it possible
to parse the [hg status] output even if the user creates files
with '\n' characters by accident.

rust/rhg/src/commands/status.rs

@@ -1,657 +1,670 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, 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::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_string;
 use hg::utils::files::get_path_from_bytes;
 use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
 use hg::DirstateStatus;
 use hg::PatternFileWarning;
 use hg::StatusError;
 use hg::StatusOptions;
 use hg::{self, narrow, sparse};
 use log::info;
 use rayon::prelude::*;
 use std::io;
 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("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"),
         )
 }
 
 /// 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;
 
-    // TODO add `!args.get_flag("print0") &&` when we support `print0`
+    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?;
 
     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 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 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<_> = 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 relative_paths = config
             .get_option(b"commands", b"status.relative")?
             .unwrap_or(config.get_bool(b"ui", b"relative-paths")?);
         let output = DisplayStatusPaths {
             ui,
             no_status,
             relativize: if relative_paths {
                 Some(RelativizePaths::new(repo)?)
             } else {
                 None
             },
+            print0,
         };
         if display_states.modified {
             output.display(b"M ", "status.modified", ds_status.modified)?;
         }
         if display_states.added {
             output.display(b"A ", "status.added", ds_status.added)?;
         }
         if display_states.removed {
             output.display(b"R ", "status.removed", ds_status.removed)?;
         }
         if display_states.deleted {
             output.display(b"! ", "status.deleted", ds_status.deleted)?;
         }
         if display_states.unknown {
             output.display(b"? ", "status.unknown", ds_status.unknown)?;
         }
         if display_states.ignored {
             output.display(b"I ", "status.ignored", ds_status.ignored)?;
         }
         if display_states.clean {
             output.display(b"C ", "status.clean", ds_status.clean)?;
         }
 
         let dirstate_write_needed = ds_status.dirty;
         let filesystem_time_at_status_start =
             ds_status.filesystem_time_at_status_start;
 
         Ok((
             fixup,
             dirstate_write_needed,
             filesystem_time_at_status_start,
         ))
     };
     let (narrow_matcher, narrow_warnings) = narrow::matcher(repo)?;
     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),
     };
 
     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;
             let path = if let Some(relativize) = &self.relativize {
                 relative = relativize.relativize(&path);
                 &*relative
             } else {
                 path.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)?
             }
-            self.ui
-                .write_stdout_labelled(&format_bytes!(b"{}\n", path), 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 {
                 let label = "status.copied";
                 self.ui.write_stdout_labelled(
-                    &format_bytes!(b"  {}\n", source.as_bytes()),
+                    &format_bytes!(b"  {}{}", source.as_bytes(), linebreak),
                     label,
                 )?
             }
         }
         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
     })
 }

tests/test-status.t

@@ -1,1002 +1,1007 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
   $ cat >> $HGRCPATH << EOF
   > [format]
   > use-dirstate-v2=1
   > [storage]
   > dirstate-v2.slow-path=allow
   > EOF
 #endif
 
   $ hg init repo1
   $ cd repo1
   $ mkdir a b a/1 b/1 b/2
   $ touch in_root a/in_a b/in_b a/1/in_a_1 b/1/in_b_1 b/2/in_b_2
 
 hg status in repo root:
 
   $ hg status
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
 hg status . in repo root:
 
   $ hg status .
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ hg status --cwd a
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a .
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a ..
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd b
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b .
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   $ hg status --cwd b ..
   ? ../a/1/in_a_1
   ? ../a/in_a
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   ? ../in_root
 
   $ hg status --cwd a/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a/1 .
   ? in_a_1
   $ hg status --cwd a/1 ..
   ? in_a_1
   ? ../in_a
 
   $ hg status --cwd b/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/1 .
   ? in_b_1
   $ hg status --cwd b/1 ..
   ? in_b_1
   ? ../2/in_b_2
   ? ../in_b
 
   $ hg status --cwd b/2
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/2 .
   ? in_b_2
   $ hg status --cwd b/2 ..
   ? ../1/in_b_1
   ? in_b_2
   ? ../in_b
 
 combining patterns with root and patterns without a root works
 
   $ hg st a/in_a re:.*b$
   ? a/in_a
   ? b/in_b
 
 tweaking defaults works
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
   $ HGPLAINEXCEPT=tweakdefaults hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root (glob)
 
 relative paths can be requested
 
   $ hg status --cwd a --config ui.relative-paths=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd a . --config ui.relative-paths=legacy
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a . --config ui.relative-paths=no
   ? a/1/in_a_1
   ? a/in_a
 
 commands.status.relative overrides ui.relative-paths
 
   $ cat >> $HGRCPATH <<EOF
   > [ui]
   > relative-paths = False
   > [commands]
   > status.relative = True
   > EOF
   $ hg status --cwd a
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
 
 if relative paths are explicitly off, tweakdefaults doesn't change it
   $ cat >> $HGRCPATH <<EOF
   > [commands]
   > status.relative = False
   > EOF
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ cd ..
 
   $ hg init repo2
   $ cd repo2
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg ci -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch modified added unknown ignored
   $ hg add added
   $ hg remove removed
   $ rm deleted
 
 hg status:
 
   $ hg status
   A added
   R removed
   ! deleted
   ? unknown
 
 hg status -n:
   $ env RHG_ON_UNSUPPORTED=abort hg status -n
   added
   removed
   deleted
   unknown
 
 hg status modified added removed deleted unknown never-existed ignored:
 
   $ hg status modified added removed deleted unknown never-existed ignored
   never-existed: * (glob)
   A added
   R removed
   ! deleted
   ? unknown
 
   $ hg copy modified copied
 
 hg status -C:
 
   $ hg status -C
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
 
+hg status -0:
+
+  $ hg status -0 --config rhg.on-unsupported=abort
+  A added\x00A copied\x00R removed\x00! deleted\x00? unknown\x00 (no-eol) (esc)
+
 hg status -A:
 
   $ hg status -A
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
   I ignored
   C .hgignore
   C modified
 
   $ hg status -A -T '{status} {path} {node|shortest}\n'
   A added ffff
   A copied ffff
   R removed ffff
   ! deleted ffff
   ? unknown ffff
   I ignored ffff
   C .hgignore ffff
   C modified ffff
 
   $ hg status -A -Tjson
   [
    {
     "itemtype": "file",
     "path": "added",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "copied",
     "source": "modified",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "removed",
     "status": "R"
    },
    {
     "itemtype": "file",
     "path": "deleted",
     "status": "!"
    },
    {
     "itemtype": "file",
     "path": "unknown",
     "status": "?"
    },
    {
     "itemtype": "file",
     "path": "ignored",
     "status": "I"
    },
    {
     "itemtype": "file",
     "path": ".hgignore",
     "status": "C"
    },
    {
     "itemtype": "file",
     "path": "modified",
     "status": "C"
    }
   ]
 
   $ hg status -A -Tpickle > pickle
   >>> import pickle
   >>> from mercurial import util
   >>> data = sorted((x[b'status'].decode(), x[b'path'].decode()) for x in pickle.load(open("pickle", r"rb")))
   >>> for s, p in data: print("%s %s" % (s, p))
   ! deleted
   ? pickle
   ? unknown
   A added
   A copied
   C .hgignore
   C modified
   I ignored
   R removed
   $ rm pickle
 
   $ echo "^ignoreddir$" > .hgignore
   $ mkdir ignoreddir
   $ touch ignoreddir/file
 
 Test templater support:
 
   $ hg status -AT "[{status}]\t{if(source, '{source} -> ')}{path}\n"
   [M]	.hgignore
   [A]	added
   [A]	modified -> copied
   [R]	removed
   [!]	deleted
   [?]	ignored
   [?]	unknown
   [I]	ignoreddir/file
   [C]	modified
   $ hg status -AT default
   M .hgignore
   A added
   A copied
     modified
   R removed
   ! deleted
   ? ignored
   ? unknown
   I ignoreddir/file
   C modified
   $ hg status -T compact
   abort: "status" not in template map
   [255]
 
 hg status ignoreddir/file:
 
   $ hg status ignoreddir/file
 
 hg status -i ignoreddir/file:
 
   $ hg status -i ignoreddir/file
   I ignoreddir/file
   $ cd ..
 
 Check 'status -q' and some combinations
 
   $ hg init repo3
   $ cd repo3
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg commit -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch added unknown ignored
   $ hg add added
   $ echo "test" >> modified
   $ hg remove removed
   $ rm deleted
   $ hg copy modified copied
 
 Specify working directory revision explicitly, that should be the same as
 "hg status"
 
   $ hg status --change "wdir()"
   M modified
   A added
   A copied
   R removed
   ! deleted
   ? unknown
 
 Run status with 2 different flags.
 Check if result is the same or different.
 If result is not as expected, raise error
 
   $ assert() {
   >     hg status $1 > ../a
   >     hg status $2 > ../b
   >     if diff ../a ../b > /dev/null; then
   >         out=0
   >     else
   >         out=1
   >     fi
   >     if [ $3 -eq 0 ]; then
   >         df="same"
   >     else
   >         df="different"
   >     fi
   >     if [ $out -ne $3 ]; then
   >         echo "Error on $1 and $2, should be $df."
   >     fi
   > }
 
 Assert flag1 flag2 [0-same | 1-different]
 
   $ assert "-q" "-mard"      0
   $ assert "-A" "-marduicC"  0
   $ assert "-qA" "-mardcC"   0
   $ assert "-qAui" "-A"      0
   $ assert "-qAu" "-marducC" 0
   $ assert "-qAi" "-mardicC" 0
   $ assert "-qu" "-u"        0
   $ assert "-q" "-u"         1
   $ assert "-m" "-a"         1
   $ assert "-r" "-d"         1
   $ cd ..
 
   $ hg init repo4
   $ cd repo4
   $ touch modified removed deleted
   $ hg ci -q -A -m 'initial checkin'
   $ touch added unknown
   $ hg add added
   $ hg remove removed
   $ rm deleted
   $ echo x > modified
   $ hg copy modified copied
   $ hg ci -m 'test checkin' -d "1000001 0"
   $ rm *
   $ touch unrelated
   $ hg ci -q -A -m 'unrelated checkin' -d "1000002 0"
 
 hg status --change 1:
 
   $ hg status --change 1
   M modified
   A added
   A copied
   R removed
 
 hg status --change 1 unrelated:
 
   $ hg status --change 1 unrelated
 
 hg status -C --change 1 added modified copied removed deleted:
 
   $ hg status -C --change 1 added modified copied removed deleted
   M modified
   A added
   A copied
     modified
   R removed
 
 hg status -A --change 1 and revset:
 
   $ hg status -A --change '1|1'
   M modified
   A added
   A copied
     modified
   R removed
   C deleted
 
   $ cd ..
 
 hg status with --rev and reverted changes:
 
   $ hg init reverted-changes-repo
   $ cd reverted-changes-repo
   $ echo a > file
   $ hg add file
   $ hg ci -m a
   $ echo b > file
   $ hg ci -m b
 
 reverted file should appear clean
 
   $ hg revert -r 0 .
   reverting file
   $ hg status -A --rev 0
   C file
 
 #if execbit
 reverted file with changed flag should appear modified
 
   $ chmod +x file
   $ hg status -A --rev 0
   M file
 
   $ hg revert -r 0 .
   reverting file
 
 reverted and committed file with changed flag should appear modified
 
   $ hg co -C .
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ chmod +x file
   $ hg ci -m 'change flag'
   $ hg status -A --rev 1 --rev 2
   M file
   $ hg diff -r 1 -r 2
 
 #endif
 
   $ cd ..
 
 hg status of binary file starting with '\1\n', a separator for metadata:
 
   $ hg init repo5
   $ cd repo5
   >>> open("010a", r"wb").write(b"\1\nfoo") and None
   $ hg ci -q -A -m 'initial checkin'
   $ hg status -A
   C 010a
 
   >>> open("010a", r"wb").write(b"\1\nbar") and None
   $ hg status -A
   M 010a
   $ hg ci -q -m 'modify 010a'
   $ hg status -A --rev 0:1
   M 010a
 
   $ touch empty
   $ hg ci -q -A -m 'add another file'
   $ hg status -A --rev 1:2 010a
   C 010a
 
   $ cd ..
 
 test "hg status" with "directory pattern" which matches against files
 only known on target revision.
 
   $ hg init repo6
   $ cd repo6
 
   $ echo a > a.txt
   $ hg add a.txt
   $ hg commit -m '#0'
   $ mkdir -p 1/2/3/4/5
   $ echo b > 1/2/3/4/5/b.txt
   $ hg add 1/2/3/4/5/b.txt
   $ hg commit -m '#1'
 
   $ hg update -C 0 > /dev/null
   $ hg status -A
   C a.txt
 
 the directory matching against specified pattern should be removed,
 because directory existence prevents 'dirstate.walk()' from showing
 warning message about such pattern.
 
   $ test ! -d 1
   $ hg status -A --rev 1 1/2/3/4/5/b.txt
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3/4/5
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1
   R 1/2/3/4/5/b.txt
 
   $ hg status --config ui.formatdebug=True --rev 1 1
   status = [
       {
           'itemtype': 'file',
           'path': '1/2/3/4/5/b.txt',
           'status': 'R'
       },
   ]
 
 #if windows
   $ hg --config ui.slash=false status -A --rev 1 1
   R 1\2\3\4\5\b.txt
 #endif
 
   $ cd ..
 
 Status after move overwriting a file (issue4458)
 =================================================
 
 
   $ hg init issue4458
   $ cd issue4458
   $ echo a > a
   $ echo b > b
   $ hg commit -Am base
   adding a
   adding b
 
 
 with --force
 
   $ hg mv b --force a
   $ hg st --copies
   M a
     b
   R b
   $ hg revert --all
   reverting a
   undeleting b
   $ rm *.orig
 
 without force
 
   $ hg rm a
   $ hg st --copies
   R a
   $ hg mv b a
   $ hg st --copies
   M a
     b
   R b
 
 using ui.statuscopies setting
   $ hg st --config ui.statuscopies=true
   M a
     b
   R b
   $ hg st --config ui.statuscopies=true --no-copies
   M a
   R b
   $ hg st --config ui.statuscopies=false
   M a
   R b
   $ hg st --config ui.statuscopies=false --copies
   M a
     b
   R b
   $ hg st --config ui.tweakdefaults=yes
   M a
     b
   R b
 
 using log status template (issue5155)
   $ hg log -Tstatus -r 'wdir()' -C
   changeset:   2147483647:ffffffffffff
   parent:      0:8c55c58b4c0e
   user:        test
   date:        * (glob)
   files:
   M a
     b
   R b
   
   $ hg log -GTstatus -r 'wdir()' -C
   o  changeset:   2147483647:ffffffffffff
   |  parent:      0:8c55c58b4c0e
   ~  user:        test
      date:        * (glob)
      files:
      M a
        b
      R b
   
 
 Other "bug" highlight, the revision status does not report the copy information.
 This is buggy behavior.
 
   $ hg commit -m 'blah'
   $ hg st --copies --change .
   M a
   R b
 
 using log status template, the copy information is displayed correctly.
   $ hg log -Tstatus -r. -C
   changeset:   1:6685fde43d21
   tag:         tip
   user:        test
   date:        * (glob)
   summary:     blah
   files:
   M a
     b
   R b
   
 
   $ cd ..
 
 Make sure .hg doesn't show up even as a symlink
 
   $ hg init repo0
   $ mkdir symlink-repo0
   $ cd symlink-repo0
   $ ln -s ../repo0/.hg
   $ hg status
 
 If the size hasn’t changed but mtime has, status needs to read the contents
 of the file to check whether it has changed
 
   $ echo 1 > a
   $ echo 1 > b
   $ touch -t 200102030000 a b
   $ hg commit -Aqm '#0'
   $ echo 2 > a
   $ touch -t 200102040000 a b
   $ hg status
   M a
 
 Asking specifically for the status of a deleted/removed file
 
   $ rm a
   $ rm b
   $ hg status a
   ! a
   $ hg rm a
   $ hg rm b
   $ hg status a
   R a
   $ hg commit -qm '#1'
   $ hg status a
   a: $ENOENT$
 
 Check using include flag with pattern when status does not need to traverse
 the working directory (issue6483)
 
   $ cd ..
   $ hg init issue6483
   $ cd issue6483
   $ touch a.py b.rs
   $ hg add a.py b.rs
   $ hg st -aI "*.py"
   A a.py
 
 Also check exclude pattern
 
   $ hg st -aX "*.rs"
   A a.py
 
 issue6335
 When a directory containing a tracked file gets symlinked, as of 5.8
 `hg st` only gives the correct answer about clean (or deleted) files
 if also listing unknowns.
 The tree-based dirstate and status algorithm fix this:
 
 #if symlink no-dirstate-v1 rust
 
   $ cd ..
   $ hg init issue6335
   $ cd issue6335
   $ mkdir foo
   $ touch foo/a
   $ hg ci -Ama
   adding foo/a
   $ mv foo bar
   $ ln -s bar foo
   $ hg status
   ! foo/a
   ? bar/a
   ? foo
 
   $ hg status -c  # incorrect output without the Rust implementation
   $ hg status -cu
   ? bar/a
   ? foo
   $ hg status -d  # incorrect output without the Rust implementation
   ! foo/a
   $ hg status -du
   ! foo/a
   ? bar/a
   ? foo
 
 #endif
 
 
 Create a repo with files in each possible status
 
   $ cd ..
   $ hg init repo7
   $ cd repo7
   $ mkdir subdir
   $ touch clean modified deleted removed
   $ touch subdir/clean subdir/modified subdir/deleted subdir/removed
   $ echo ignored > .hgignore
   $ hg ci -Aqm '#0'
   $ echo 1 > modified
   $ echo 1 > subdir/modified
   $ rm deleted
   $ rm subdir/deleted
   $ hg rm removed
   $ hg rm subdir/removed
   $ touch unknown ignored
   $ touch subdir/unknown subdir/ignored
 
 Check the output
 
   $ hg status
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
 
   $ hg status -mard
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
 
   $ hg status -A
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
   I ignored
   I subdir/ignored
   C .hgignore
   C clean
   C subdir/clean
 
 Note: `hg status some-name` creates a patternmatcher which is not supported
 yet by the Rust implementation of status, but includematcher is supported.
 --include is used below for that reason
 
 #if unix-permissions
 
 Not having permission to read a directory that contains tracked files makes
 status emit a warning then behave as if the directory was empty or removed
 entirely:
 
   $ chmod 0 subdir
   $ hg status --include subdir
   subdir: $EACCES$
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   $ chmod 755 subdir
 
 #endif
 
 Remove a directory that contains tracked files
 
   $ rm -r subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
 
 … and replace it by a file
 
   $ touch subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   ? subdir
 
 Replaced a deleted or removed file with a directory
 
   $ mkdir deleted removed
   $ touch deleted/1 removed/1
   $ hg status --include deleted --include removed
   R removed
   ! deleted
   ? deleted/1
   ? removed/1
   $ hg add removed/1
   $ hg status --include deleted --include removed
   A removed/1
   R removed
   ! deleted
   ? deleted/1
 
 Deeply nested files in an ignored directory are still listed on request
 
   $ echo ignored-dir >> .hgignore
   $ mkdir ignored-dir
   $ mkdir ignored-dir/subdir
   $ touch ignored-dir/subdir/1
   $ hg status --ignored
   I ignored
   I ignored-dir/subdir/1
 
 Check using include flag while listing ignored composes correctly (issue6514)
 
   $ cd ..
   $ hg init issue6514
   $ cd issue6514
   $ mkdir ignored-folder
   $ touch A.hs B.hs C.hs ignored-folder/other.txt ignored-folder/ctest.hs
   $ cat >.hgignore <<EOF
   > A.hs
   > B.hs
   > ignored-folder/
   > EOF
   $ hg st -i -I 're:.*\.hs$'
   I A.hs
   I B.hs
   I ignored-folder/ctest.hs
 
 #if rust dirstate-v2
 
 Check read_dir caching
 
   $ cd ..
   $ hg init repo8
   $ cd repo8
   $ mkdir subdir
   $ touch subdir/a subdir/b
   $ hg ci -Aqm '#0'
 
 The cached mtime is initially unset
 
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 It is still not set when there are unknown files
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 Now the directory is eligible for caching, so its mtime is saved in the dirstate
 
   $ rm subdir/unknown
   $ sleep 0.1 # ensure the kernel’s internal clock for mtimes has ticked
   $ hg status
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
 This time the command should be ever so slightly faster since it does not need `read_dir("subdir")`
 
   $ hg status
 
 Creating a new file changes the directory’s mtime, invalidating the cache
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
 
   $ rm subdir/unknown
   $ hg status
 
 Removing a node from the dirstate resets the cache for its parent directory
 
   $ hg forget subdir/a
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
   $ hg ci -qm '#1'
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
   $ hg status
   ? subdir/a
 
 Changing the hgignore rules makes us recompute the status (and rewrite the dirstate).
 
   $ rm subdir/a
   $ mkdir another-subdir
   $ touch another-subdir/something-else
 
   $ cat > "$TESTTMP"/extra-hgignore <<EOF
   > something-else
   > EOF
 
   $ hg status --config ui.ignore.global="$TESTTMP"/extra-hgignore
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
   $ hg status
   ? another-subdir/something-else
 
 One invocation of status is enough to populate the cache even if it's invalidated
 in the same run.
 
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
 #endif