rhg-status: add support for narrow clones

rust/hg-core/src/narrow.rs

@@ -0,0 +1,111 b''
+use std::path::Path;
+
+use crate::{
+    errors::HgError,
+    exit_codes,
+    filepatterns::parse_pattern_file_contents,
+    matchers::{
+        AlwaysMatcher, DifferenceMatcher, IncludeMatcher, Matcher,
+        NeverMatcher,
+    },
+    repo::Repo,
+    requirements::NARROW_REQUIREMENT,
+    sparse::{self, SparseConfigError, SparseWarning},
+};
+
+/// The file in .hg/store/ that indicates which paths exit in the store
+const FILENAME: &str = "narrowspec";
+/// The file in .hg/ that indicates which paths exit in the dirstate
+const DIRSTATE_FILENAME: &str = "narrowspec.dirstate";
+
+/// Pattern prefixes that are allowed in narrow patterns. This list MUST
+/// only contain patterns that are fast and safe to evaluate. Keep in mind
+/// that patterns are supplied by clients and executed on remote servers
+/// as part of wire protocol commands. That means that changes to this
+/// data structure influence the wire protocol and should not be taken
+/// lightly - especially removals.
+const VALID_PREFIXES: [&str; 2] = ["path:", "rootfilesin:"];
+
+/// Return the matcher for the current narrow spec, and all configuration
+/// warnings to display.
+pub fn matcher(
+    repo: &Repo,
+) -> Result<(Box<dyn Matcher + Sync>, Vec<SparseWarning>), SparseConfigError> {
+    let mut warnings = vec![];
+    if !repo.requirements().contains(NARROW_REQUIREMENT) {
+        return Ok((Box::new(AlwaysMatcher), warnings));
+    }
+    // Treat "narrowspec does not exist" the same as "narrowspec file exists
+    // and is empty".
+    let store_spec = repo.store_vfs().try_read(FILENAME)?.unwrap_or(vec![]);
+    let working_copy_spec =
+        repo.hg_vfs().try_read(DIRSTATE_FILENAME)?.unwrap_or(vec![]);
+    if store_spec != working_copy_spec {
+        return Err(HgError::abort(
+            "working copy's narrowspec is stale",
+            exit_codes::STATE_ERROR,
+            Some("run 'hg tracked --update-working-copy'".into()),
+        )
+        .into());
+    }
+
+    let config = sparse::parse_config(
+        &store_spec,
+        sparse::SparseConfigContext::Narrow,
+    )?;
+
+    warnings.extend(config.warnings);
+
+    if !config.profiles.is_empty() {
+        // TODO (from Python impl) maybe do something with profiles?
+        return Err(SparseConfigError::IncludesInNarrow);
+    }
+    validate_patterns(&config.includes)?;
+    validate_patterns(&config.excludes)?;
+
+    if config.includes.is_empty() {
+        return Ok((Box::new(NeverMatcher), warnings));
+    }
+
+    let (patterns, subwarnings) = parse_pattern_file_contents(
+        &config.includes,
+        Path::new(""),
+        None,
+        false,
+    )?;
+    warnings.extend(subwarnings.into_iter().map(From::from));
+
+    let mut m: Box<dyn Matcher + Sync> =
+        Box::new(IncludeMatcher::new(patterns)?);
+
+    let (patterns, subwarnings) = parse_pattern_file_contents(
+        &config.excludes,
+        Path::new(""),
+        None,
+        false,
+    )?;
+    if !patterns.is_empty() {
+        warnings.extend(subwarnings.into_iter().map(From::from));
+        let exclude_matcher = Box::new(IncludeMatcher::new(patterns)?);
+        m = Box::new(DifferenceMatcher::new(m, exclude_matcher));
+    }
+
+    Ok((m, warnings))
+}
+
+fn validate_patterns(patterns: &[u8]) -> Result<(), SparseConfigError> {
+    for pattern in patterns.split(|c| *c == b'\n') {
+        if pattern.is_empty() {
+            continue;
+        }
+        for prefix in VALID_PREFIXES.iter() {
+            if pattern.starts_with(prefix.as_bytes()) {
+                break;
+            }
+            return Err(SparseConfigError::InvalidNarrowPrefix(
+                pattern.to_owned(),
+            ));
+        }
+    }
+    Ok(())
+}

rust/hg-core/src/exit_codes.rs

@@ -1,22 +1,26 b''
 pub type ExitCode = i32;
 
 /// Successful exit
 pub const OK: ExitCode = 0;
 
 /// Generic abort
 pub const ABORT: ExitCode = 255;
 
 // Abort when there is a config related error
 pub const CONFIG_ERROR_ABORT: ExitCode = 30;
 
+/// Indicates that the operation might work if retried in a different state.
+/// Examples: Unresolved merge conflicts, unfinished operations
+pub const STATE_ERROR: ExitCode = 20;
+
 // Abort when there is an error while parsing config
 pub const CONFIG_PARSE_ERROR_ABORT: ExitCode = 10;
 
 /// Generic something completed but did not succeed
 pub const UNSUCCESSFUL: ExitCode = 1;
 
 /// Command or feature not implemented by rhg
 pub const UNIMPLEMENTED: ExitCode = 252;
 
 /// The fallback path is not valid
 pub const INVALID_FALLBACK: ExitCode = 253;

rust/hg-core/src/filepatterns.rs

@@ -1,704 +1,706 b''
 // filepatterns.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Handling of Mercurial-specific patterns.
 
 use crate::{
     utils::{
         files::{canonical_path, get_bytes_from_path, get_path_from_bytes},
         hg_path::{path_to_hg_path_buf, HgPathBuf, HgPathError},
         SliceExt,
     },
     FastHashMap, PatternError,
 };
 use lazy_static::lazy_static;
 use regex::bytes::{NoExpand, Regex};
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 use std::vec::Vec;
 
 lazy_static! {
     static ref RE_ESCAPE: Vec<Vec<u8>> = {
         let mut v: Vec<Vec<u8>> = (0..=255).map(|byte| vec![byte]).collect();
         let to_escape = b"()[]{}?*+-|^$\\.&~# \t\n\r\x0b\x0c";
         for byte in to_escape {
             v[*byte as usize].insert(0, b'\\');
         }
         v
     };
 }
 
 /// These are matched in order
 const GLOB_REPLACEMENTS: &[(&[u8], &[u8])] =
     &[(b"*/", b"(?:.*/)?"), (b"*", b".*"), (b"", b"[^/]*")];
 
 /// Appended to the regexp of globs
 const GLOB_SUFFIX: &[u8; 7] = b"(?:/|$)";
 
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum PatternSyntax {
     /// A regular expression
     Regexp,
     /// Glob that matches at the front of the path
     RootGlob,
     /// Glob that matches at any suffix of the path (still anchored at
     /// slashes)
     Glob,
     /// a path relative to repository root, which is matched recursively
     Path,
     /// A path relative to cwd
     RelPath,
     /// an unrooted glob (*.rs matches Rust files in all dirs)
     RelGlob,
     /// A regexp that needn't match the start of a name
     RelRegexp,
     /// A path relative to repository root, which is matched non-recursively
     /// (will not match subdirectories)
     RootFiles,
     /// A file of patterns to read and include
     Include,
     /// A file of patterns to match against files under the same directory
     SubInclude,
     /// SubInclude with the result of parsing the included file
     ///
     /// Note: there is no ExpandedInclude because that expansion can be done
     /// in place by replacing the Include pattern by the included patterns.
     /// SubInclude requires more handling.
     ///
     /// Note: `Box` is used to minimize size impact on other enum variants
     ExpandedSubInclude(Box<SubInclude>),
 }
 
 /// Transforms a glob pattern into a regex
 fn glob_to_re(pat: &[u8]) -> Vec<u8> {
     let mut input = pat;
     let mut res: Vec<u8> = vec![];
     let mut group_depth = 0;
 
     while let Some((c, rest)) = input.split_first() {
         input = rest;
 
         match c {
             b'*' => {
                 for (source, repl) in GLOB_REPLACEMENTS {
                     if let Some(rest) = input.drop_prefix(source) {
                         input = rest;
                         res.extend(*repl);
                         break;
                     }
                 }
             }
             b'?' => res.extend(b"."),
             b'[' => {
                 match input.iter().skip(1).position(|b| *b == b']') {
                     None => res.extend(b"\\["),
                     Some(end) => {
                         // Account for the one we skipped
                         let end = end + 1;
 
                         res.extend(b"[");
 
                         for (i, b) in input[..end].iter().enumerate() {
                             if *b == b'!' && i == 0 {
                                 res.extend(b"^")
                             } else if *b == b'^' && i == 0 {
                                 res.extend(b"\\^")
                             } else if *b == b'\\' {
                                 res.extend(b"\\\\")
                             } else {
                                 res.push(*b)
                             }
                         }
                         res.extend(b"]");
                         input = &input[end + 1..];
                     }
                 }
             }
             b'{' => {
                 group_depth += 1;
                 res.extend(b"(?:")
             }
             b'}' if group_depth > 0 => {
                 group_depth -= 1;
                 res.extend(b")");
             }
             b',' if group_depth > 0 => res.extend(b"|"),
             b'\\' => {
                 let c = {
                     if let Some((c, rest)) = input.split_first() {
                         input = rest;
                         c
                     } else {
                         c
                     }
                 };
                 res.extend(&RE_ESCAPE[*c as usize])
             }
             _ => res.extend(&RE_ESCAPE[*c as usize]),
         }
     }
     res
 }
 
 fn escape_pattern(pattern: &[u8]) -> Vec<u8> {
     pattern
         .iter()
         .flat_map(|c| RE_ESCAPE[*c as usize].clone())
         .collect()
 }
 
 pub fn parse_pattern_syntax(
     kind: &[u8],
 ) -> Result<PatternSyntax, PatternError> {
     match kind {
         b"re:" => Ok(PatternSyntax::Regexp),
         b"path:" => Ok(PatternSyntax::Path),
         b"relpath:" => Ok(PatternSyntax::RelPath),
         b"rootfilesin:" => Ok(PatternSyntax::RootFiles),
         b"relglob:" => Ok(PatternSyntax::RelGlob),
         b"relre:" => Ok(PatternSyntax::RelRegexp),
         b"glob:" => Ok(PatternSyntax::Glob),
         b"rootglob:" => Ok(PatternSyntax::RootGlob),
         b"include:" => Ok(PatternSyntax::Include),
         b"subinclude:" => Ok(PatternSyntax::SubInclude),
         _ => Err(PatternError::UnsupportedSyntax(
             String::from_utf8_lossy(kind).to_string(),
         )),
     }
 }
 
 /// Builds the regex that corresponds to the given pattern.
 /// If within a `syntax: regexp` context, returns the pattern,
 /// otherwise, returns the corresponding regex.
 fn _build_single_regex(entry: &IgnorePattern) -> Vec<u8> {
     let IgnorePattern {
         syntax, pattern, ..
     } = entry;
     if pattern.is_empty() {
         return vec![];
     }
     match syntax {
         PatternSyntax::Regexp => pattern.to_owned(),
         PatternSyntax::RelRegexp => {
             // The `regex` crate accepts `**` while `re2` and Python's `re`
             // do not. Checking for `*` correctly triggers the same error all
             // engines.
             if pattern[0] == b'^'
                 || pattern[0] == b'*'
                 || pattern.starts_with(b".*")
             {
                 return pattern.to_owned();
             }
             [&b".*"[..], pattern].concat()
         }
         PatternSyntax::Path | PatternSyntax::RelPath => {
             if pattern == b"." {
                 return vec![];
             }
             [escape_pattern(pattern).as_slice(), b"(?:/|$)"].concat()
         }
         PatternSyntax::RootFiles => {
             let mut res = if pattern == b"." {
                 vec![]
             } else {
                 // Pattern is a directory name.
                 [escape_pattern(pattern).as_slice(), b"/"].concat()
             };
 
             // Anything after the pattern must be a non-directory.
             res.extend(b"[^/]+$");
             res
         }
         PatternSyntax::RelGlob => {
             let glob_re = glob_to_re(pattern);
             if let Some(rest) = glob_re.drop_prefix(b"[^/]*") {
                 [b".*", rest, GLOB_SUFFIX].concat()
             } else {
                 [b"(?:.*/)?", glob_re.as_slice(), GLOB_SUFFIX].concat()
             }
         }
         PatternSyntax::Glob | PatternSyntax::RootGlob => {
             [glob_to_re(pattern).as_slice(), GLOB_SUFFIX].concat()
         }
         PatternSyntax::Include
         | PatternSyntax::SubInclude
         | PatternSyntax::ExpandedSubInclude(_) => unreachable!(),
     }
 }
 
 const GLOB_SPECIAL_CHARACTERS: [u8; 7] =
     [b'*', b'?', b'[', b']', b'{', b'}', b'\\'];
 
 /// TODO support other platforms
 #[cfg(unix)]
 pub fn normalize_path_bytes(bytes: &[u8]) -> Vec<u8> {
     if bytes.is_empty() {
         return b".".to_vec();
     }
     let sep = b'/';
 
     let mut initial_slashes = bytes.iter().take_while(|b| **b == sep).count();
     if initial_slashes > 2 {
         // POSIX allows one or two initial slashes, but treats three or more
         // as single slash.
         initial_slashes = 1;
     }
     let components = bytes
         .split(|b| *b == sep)
         .filter(|c| !(c.is_empty() || c == b"."))
         .fold(vec![], |mut acc, component| {
             if component != b".."
                 || (initial_slashes == 0 && acc.is_empty())
                 || (!acc.is_empty() && acc[acc.len() - 1] == b"..")
             {
                 acc.push(component)
             } else if !acc.is_empty() {
                 acc.pop();
             }
             acc
         });
     let mut new_bytes = components.join(&sep);
 
     if initial_slashes > 0 {
         let mut buf: Vec<_> = (0..initial_slashes).map(|_| sep).collect();
         buf.extend(new_bytes);
         new_bytes = buf;
     }
     if new_bytes.is_empty() {
         b".".to_vec()
     } else {
         new_bytes
     }
 }
 
 /// Wrapper function to `_build_single_regex` that short-circuits 'exact' globs
 /// that don't need to be transformed into a regex.
 pub fn build_single_regex(
     entry: &IgnorePattern,
 ) -> Result<Option<Vec<u8>>, PatternError> {
     let IgnorePattern {
         pattern, syntax, ..
     } = entry;
     let pattern = match syntax {
         PatternSyntax::RootGlob
         | PatternSyntax::Path
         | PatternSyntax::RelGlob
         | PatternSyntax::RootFiles => normalize_path_bytes(&pattern),
         PatternSyntax::Include | PatternSyntax::SubInclude => {
             return Err(PatternError::NonRegexPattern(entry.clone()))
         }
         _ => pattern.to_owned(),
     };
     if *syntax == PatternSyntax::RootGlob
         && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
     {
         Ok(None)
     } else {
         let mut entry = entry.clone();
         entry.pattern = pattern;
         Ok(Some(_build_single_regex(&entry)))
     }
 }
 
 lazy_static! {
     static ref SYNTAXES: FastHashMap<&'static [u8], &'static [u8]> = {
         let mut m = FastHashMap::default();
 
         m.insert(b"re".as_ref(), b"relre:".as_ref());
         m.insert(b"regexp".as_ref(), b"relre:".as_ref());
         m.insert(b"glob".as_ref(), b"relglob:".as_ref());
         m.insert(b"rootglob".as_ref(), b"rootglob:".as_ref());
         m.insert(b"include".as_ref(), b"include:".as_ref());
         m.insert(b"subinclude".as_ref(), b"subinclude:".as_ref());
+        m.insert(b"path".as_ref(), b"path:".as_ref());
+        m.insert(b"rootfilesin".as_ref(), b"rootfilesin:".as_ref());
         m
     };
 }
 
 #[derive(Debug)]
 pub enum PatternFileWarning {
     /// (file path, syntax bytes)
     InvalidSyntax(PathBuf, Vec<u8>),
     /// File path
     NoSuchFile(PathBuf),
 }
 
 pub fn parse_pattern_file_contents(
     lines: &[u8],
     file_path: &Path,
     default_syntax_override: Option<&[u8]>,
     warn: bool,
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     let comment_regex = Regex::new(r"((?:^|[^\\])(?:\\\\)*)#.*").unwrap();
 
     #[allow(clippy::trivial_regex)]
     let comment_escape_regex = Regex::new(r"\\#").unwrap();
     let mut inputs: Vec<IgnorePattern> = vec![];
     let mut warnings: Vec<PatternFileWarning> = vec![];
 
     let mut current_syntax =
         default_syntax_override.unwrap_or(b"relre:".as_ref());
 
     for (line_number, mut line) in lines.split(|c| *c == b'\n').enumerate() {
         let line_number = line_number + 1;
 
         let line_buf;
         if line.contains(&b'#') {
             if let Some(cap) = comment_regex.captures(line) {
                 line = &line[..cap.get(1).unwrap().end()]
             }
             line_buf = comment_escape_regex.replace_all(line, NoExpand(b"#"));
             line = &line_buf;
         }
 
         let mut line = line.trim_end();
 
         if line.is_empty() {
             continue;
         }
 
         if let Some(syntax) = line.drop_prefix(b"syntax:") {
             let syntax = syntax.trim();
 
             if let Some(rel_syntax) = SYNTAXES.get(syntax) {
                 current_syntax = rel_syntax;
             } else if warn {
                 warnings.push(PatternFileWarning::InvalidSyntax(
                     file_path.to_owned(),
                     syntax.to_owned(),
                 ));
             }
             continue;
         }
 
         let mut line_syntax: &[u8] = &current_syntax;
 
         for (s, rels) in SYNTAXES.iter() {
             if let Some(rest) = line.drop_prefix(rels) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
             if let Some(rest) = line.drop_prefix(&[s, &b":"[..]].concat()) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
         }
 
         inputs.push(IgnorePattern::new(
             parse_pattern_syntax(&line_syntax).map_err(|e| match e {
                 PatternError::UnsupportedSyntax(syntax) => {
                     PatternError::UnsupportedSyntaxInFile(
                         syntax,
                         file_path.to_string_lossy().into(),
                         line_number,
                     )
                 }
                 _ => e,
             })?,
             &line,
             file_path,
         ));
     }
     Ok((inputs, warnings))
 }
 
 pub fn read_pattern_file(
     file_path: &Path,
     warn: bool,
     inspect_pattern_bytes: &mut impl FnMut(&[u8]),
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     match std::fs::read(file_path) {
         Ok(contents) => {
             inspect_pattern_bytes(&contents);
             parse_pattern_file_contents(&contents, file_path, None, warn)
         }
         Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok((
             vec![],
             vec![PatternFileWarning::NoSuchFile(file_path.to_owned())],
         )),
         Err(e) => Err(e.into()),
     }
 }
 
 /// Represents an entry in an "ignore" file.
 #[derive(Debug, Eq, PartialEq, Clone)]
 pub struct IgnorePattern {
     pub syntax: PatternSyntax,
     pub pattern: Vec<u8>,
     pub source: PathBuf,
 }
 
 impl IgnorePattern {
     pub fn new(syntax: PatternSyntax, pattern: &[u8], source: &Path) -> Self {
         Self {
             syntax,
             pattern: pattern.to_owned(),
             source: source.to_owned(),
         }
     }
 }
 
 pub type PatternResult<T> = Result<T, PatternError>;
 
 /// Wrapper for `read_pattern_file` that also recursively expands `include:`
 /// and `subinclude:` patterns.
 ///
 /// The former are expanded in place, while `PatternSyntax::ExpandedSubInclude`
 /// is used for the latter to form a tree of patterns.
 pub fn get_patterns_from_file(
     pattern_file: &Path,
     root_dir: &Path,
     inspect_pattern_bytes: &mut impl FnMut(&[u8]),
 ) -> PatternResult<(Vec<IgnorePattern>, Vec<PatternFileWarning>)> {
     let (patterns, mut warnings) =
         read_pattern_file(pattern_file, true, inspect_pattern_bytes)?;
     let patterns = patterns
         .into_iter()
         .flat_map(|entry| -> PatternResult<_> {
             Ok(match &entry.syntax {
                 PatternSyntax::Include => {
                     let inner_include =
                         root_dir.join(get_path_from_bytes(&entry.pattern));
                     let (inner_pats, inner_warnings) = get_patterns_from_file(
                         &inner_include,
                         root_dir,
                         inspect_pattern_bytes,
                     )?;
                     warnings.extend(inner_warnings);
                     inner_pats
                 }
                 PatternSyntax::SubInclude => {
                     let mut sub_include = SubInclude::new(
                         &root_dir,
                         &entry.pattern,
                         &entry.source,
                     )?;
                     let (inner_patterns, inner_warnings) =
                         get_patterns_from_file(
                             &sub_include.path,
                             &sub_include.root,
                             inspect_pattern_bytes,
                         )?;
                     sub_include.included_patterns = inner_patterns;
                     warnings.extend(inner_warnings);
                     vec![IgnorePattern {
                         syntax: PatternSyntax::ExpandedSubInclude(Box::new(
                             sub_include,
                         )),
                         ..entry
                     }]
                 }
                 _ => vec![entry],
             })
         })
         .flatten()
         .collect();
 
     Ok((patterns, warnings))
 }
 
 /// Holds all the information needed to handle a `subinclude:` pattern.
 #[derive(Debug, PartialEq, Eq, Clone)]
 pub struct SubInclude {
     /// Will be used for repository (hg) paths that start with this prefix.
     /// It is relative to the current working directory, so comparing against
     /// repository paths is painless.
     pub prefix: HgPathBuf,
     /// The file itself, containing the patterns
     pub path: PathBuf,
     /// Folder in the filesystem where this it applies
     pub root: PathBuf,
 
     pub included_patterns: Vec<IgnorePattern>,
 }
 
 impl SubInclude {
     pub fn new(
         root_dir: &Path,
         pattern: &[u8],
         source: &Path,
     ) -> Result<SubInclude, HgPathError> {
         let normalized_source =
             normalize_path_bytes(&get_bytes_from_path(source));
 
         let source_root = get_path_from_bytes(&normalized_source);
         let source_root =
             source_root.parent().unwrap_or_else(|| source_root.deref());
 
         let path = source_root.join(get_path_from_bytes(pattern));
         let new_root = path.parent().unwrap_or_else(|| path.deref());
 
         let prefix = canonical_path(root_dir, root_dir, new_root)?;
 
         Ok(Self {
             prefix: path_to_hg_path_buf(prefix).and_then(|mut p| {
                 if !p.is_empty() {
                     p.push_byte(b'/');
                 }
                 Ok(p)
             })?,
             path: path.to_owned(),
             root: new_root.to_owned(),
             included_patterns: Vec::new(),
         })
     }
 }
 
 /// Separate and pre-process subincludes from other patterns for the "ignore"
 /// phase.
 pub fn filter_subincludes(
     ignore_patterns: Vec<IgnorePattern>,
 ) -> Result<(Vec<Box<SubInclude>>, Vec<IgnorePattern>), HgPathError> {
     let mut subincludes = vec![];
     let mut others = vec![];
 
     for pattern in ignore_patterns {
         if let PatternSyntax::ExpandedSubInclude(sub_include) = pattern.syntax
         {
             subincludes.push(sub_include);
         } else {
             others.push(pattern)
         }
     }
     Ok((subincludes, others))
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn escape_pattern_test() {
         let untouched =
             br#"!"%',/0123456789:;<=>@ABCDEFGHIJKLMNOPQRSTUVWXYZ_`abcdefghijklmnopqrstuvwxyz"#;
         assert_eq!(escape_pattern(untouched), untouched.to_vec());
         // All escape codes
         assert_eq!(
             escape_pattern(br#"()[]{}?*+-|^$\\.&~# \t\n\r\v\f"#),
             br#"\(\)\[\]\{\}\?\*\+\-\|\^\$\\\\\.\&\~\#\ \\t\\n\\r\\v\\f"#
                 .to_vec()
         );
     }
 
     #[test]
     fn glob_test() {
         assert_eq!(glob_to_re(br#"?"#), br#"."#);
         assert_eq!(glob_to_re(br#"*"#), br#"[^/]*"#);
         assert_eq!(glob_to_re(br#"**"#), br#".*"#);
         assert_eq!(glob_to_re(br#"**/a"#), br#"(?:.*/)?a"#);
         assert_eq!(glob_to_re(br#"a/**/b"#), br#"a/(?:.*/)?b"#);
         assert_eq!(glob_to_re(br#"[a*?!^][^b][!c]"#), br#"[a*?!^][\^b][^c]"#);
         assert_eq!(glob_to_re(br#"{a,b}"#), br#"(?:a|b)"#);
         assert_eq!(glob_to_re(br#".\*\?"#), br#"\.\*\?"#);
     }
 
     #[test]
     fn test_parse_pattern_file_contents() {
         let lines = b"syntax: glob\n*.elc";
 
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"*.elc",
                 Path::new("file_path")
             )],
         );
 
         let lines = b"syntax: include\nsyntax: glob";
 
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![]
         );
         let lines = b"glob:**.o";
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"**.o",
                 Path::new("file_path")
             )]
         );
     }
 
     #[test]
     fn test_build_single_regex() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"rust/target/",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()),
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::Regexp,
                 br"rust/target/\d+",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"rust/target/\d+".to_vec()),
         );
     }
 
     #[test]
     fn test_build_single_regex_shortcut() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"whatever",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"*.o",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"[^/]*\.o(?:/|$)".to_vec()),
         );
     }
 }

rust/hg-core/src/lib.rs

@@ -1,138 +1,139 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 mod ancestors;
 pub mod dagops;
 pub mod errors;
+pub mod narrow;
 pub mod sparse;
 pub use ancestors::{AncestorsIterator, MissingAncestors};
 pub mod dirstate;
 pub mod dirstate_tree;
 pub mod discovery;
 pub mod exit_codes;
 pub mod requirements;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     status::{
         BadMatch, BadType, DirstateStatus, HgPathCow, StatusError,
         StatusOptions,
     },
     DirstateEntry, DirstateParents, EntryState,
 };
 pub mod copy_tracing;
 mod filepatterns;
 pub mod matchers;
 pub mod repo;
 pub mod revlog;
 pub use revlog::*;
 pub mod config;
 pub mod lock;
 pub mod logging;
 pub mod operations;
 pub mod revset;
 pub mod utils;
 pub mod vfs;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
     parse_pattern_syntax, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use std::fmt;
 use twox_hash::RandomXxHashBuilder64;
 
 /// This is a contract between the `micro-timer` crate and us, to expose
 /// the `log` crate as `crate::log`.
 use log;
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
 // TODO: should this be the default `FastHashMap` for all of hg-core, not just
 // dirstate_tree? How does XxHash compare with AHash, hashbrown’s default?
 pub type FastHashbrownMap<K, V> =
     hashbrown::HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     InvalidPath(HgPathError),
 }
 
 impl fmt::Display for DirstateMapError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 f.write_str("expected a value, found none")
             }
             DirstateMapError::EmptyPath => {
                 f.write_str("Overflow in dirstate.")
             }
             DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum DirstateError {
     Map(DirstateMapError),
     Common(errors::HgError),
 }
 
 impl fmt::Display for DirstateError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateError::Map(error) => error.fmt(f),
             DirstateError::Common(error) => error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum PatternError {
     #[from]
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     #[from]
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
 }
 
 impl fmt::Display for PatternError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 write!(f, "Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 write!(
                     f,
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 write!(f, "matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(error) => error.fmt(f),
             PatternError::Path(error) => error.fmt(f),
             PatternError::NonRegexPattern(pattern) => {
                 write!(f, "'{:?}' cannot be turned into a regex", pattern)
             }
         }
     }
 }

rust/hg-core/src/sparse.rs

@@ -1,333 +1,338 b''
 use std::{collections::HashSet, path::Path};
 
 use format_bytes::{write_bytes, DisplayBytes};
 
 use crate::{
     errors::HgError,
     filepatterns::parse_pattern_file_contents,
     matchers::{
         AlwaysMatcher, DifferenceMatcher, IncludeMatcher, Matcher,
         UnionMatcher,
     },
     operations::cat,
     repo::Repo,
     requirements::SPARSE_REQUIREMENT,
     utils::{hg_path::HgPath, SliceExt},
     IgnorePattern, PatternError, PatternFileWarning, PatternSyntax, Revision,
     NULL_REVISION,
 };
 
 /// Command which is triggering the config read
 #[derive(Copy, Clone, Debug)]
 pub enum SparseConfigContext {
     Sparse,
     Narrow,
 }
 
 impl DisplayBytes for SparseConfigContext {
     fn display_bytes(
         &self,
         output: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         match self {
             SparseConfigContext::Sparse => write_bytes!(output, b"sparse"),
             SparseConfigContext::Narrow => write_bytes!(output, b"narrow"),
         }
     }
 }
 
 /// Possible warnings when reading sparse configuration
 #[derive(Debug, derive_more::From)]
 pub enum SparseWarning {
     /// Warns about improper paths that start with "/"
     RootWarning {
         context: SparseConfigContext,
         line: Vec<u8>,
     },
     /// Warns about a profile missing from the given changelog revision
     ProfileNotFound { profile: Vec<u8>, rev: Revision },
     #[from]
     Pattern(PatternFileWarning),
 }
 
 /// Parsed sparse config
 #[derive(Debug, Default)]
 pub struct SparseConfig {
     // Line-separated
-    includes: Vec<u8>,
+    pub(crate) includes: Vec<u8>,
     // Line-separated
-    excludes: Vec<u8>,
-    profiles: HashSet<Vec<u8>>,
-    warnings: Vec<SparseWarning>,
+    pub(crate) excludes: Vec<u8>,
+    pub(crate) profiles: HashSet<Vec<u8>>,
+    pub(crate) warnings: Vec<SparseWarning>,
 }
 
-/// All possible errors when reading sparse config
+/// All possible errors when reading sparse/narrow config
 #[derive(Debug, derive_more::From)]
 pub enum SparseConfigError {
     IncludesAfterExcludes {
         context: SparseConfigContext,
     },
     EntryOutsideSection {
         context: SparseConfigContext,
         line: Vec<u8>,
     },
+    /// Narrow config does not support '%include' directives
+    IncludesInNarrow,
+    /// An invalid pattern prefix was given to the narrow spec. Includes the
+    /// entire pattern for context.
+    InvalidNarrowPrefix(Vec<u8>),
     #[from]
     HgError(HgError),
     #[from]
     PatternError(PatternError),
 }
 
 /// Parse sparse config file content.
-fn parse_config(
+pub(crate) fn parse_config(
     raw: &[u8],
     context: SparseConfigContext,
 ) -> Result<SparseConfig, SparseConfigError> {
     let mut includes = vec![];
     let mut excludes = vec![];
     let mut profiles = HashSet::new();
     let mut warnings = vec![];
 
     #[derive(PartialEq, Eq)]
     enum Current {
         Includes,
         Excludes,
         None,
     };
 
     let mut current = Current::None;
     let mut in_section = false;
 
     for line in raw.split(|c| *c == b'\n') {
         let line = line.trim();
         if line.is_empty() || line[0] == b'#' {
             // empty or comment line, skip
             continue;
         }
         if line.starts_with(b"%include ") {
             let profile = line[b"%include ".len()..].trim();
             if !profile.is_empty() {
                 profiles.insert(profile.into());
             }
         } else if line == b"[include]" {
             if in_section && current == Current::Includes {
                 return Err(SparseConfigError::IncludesAfterExcludes {
                     context,
                 });
             }
             in_section = true;
             current = Current::Includes;
             continue;
         } else if line == b"[exclude]" {
             in_section = true;
             current = Current::Excludes;
         } else {
             if current == Current::None {
                 return Err(SparseConfigError::EntryOutsideSection {
                     context,
                     line: line.into(),
                 });
             }
             if line.trim().starts_with(b"/") {
                 warnings.push(SparseWarning::RootWarning {
                     context,
                     line: line.into(),
                 });
                 continue;
             }
             match current {
                 Current::Includes => {
                     includes.push(b'\n');
                     includes.extend(line.iter());
                 }
                 Current::Excludes => {
                     excludes.push(b'\n');
                     excludes.extend(line.iter());
                 }
                 Current::None => unreachable!(),
             }
         }
     }
 
     Ok(SparseConfig {
         includes,
         excludes,
         profiles,
         warnings,
     })
 }
 
 fn read_temporary_includes(
     repo: &Repo,
 ) -> Result<Vec<Vec<u8>>, SparseConfigError> {
     let raw = repo.hg_vfs().try_read("tempsparse")?.unwrap_or(vec![]);
     if raw.is_empty() {
         return Ok(vec![]);
     }
     Ok(raw.split(|c| *c == b'\n').map(ToOwned::to_owned).collect())
 }
 
 /// Obtain sparse checkout patterns for the given revision
 fn patterns_for_rev(
     repo: &Repo,
     rev: Revision,
 ) -> Result<Option<SparseConfig>, SparseConfigError> {
     if !repo.has_sparse() {
         return Ok(None);
     }
     let raw = repo.hg_vfs().try_read("sparse")?.unwrap_or(vec![]);
 
     if raw.is_empty() {
         return Ok(None);
     }
 
     let mut config = parse_config(&raw, SparseConfigContext::Sparse)?;
 
     if !config.profiles.is_empty() {
         let mut profiles: Vec<Vec<u8>> = config.profiles.into_iter().collect();
         let mut visited = HashSet::new();
 
         while let Some(profile) = profiles.pop() {
             if visited.contains(&profile) {
                 continue;
             }
             visited.insert(profile.to_owned());
 
             let output =
                 cat(repo, &rev.to_string(), vec![HgPath::new(&profile)])
                     .map_err(|_| {
                         HgError::corrupted(format!(
                             "dirstate points to non-existent parent node"
                         ))
                     })?;
             if output.results.is_empty() {
                 config.warnings.push(SparseWarning::ProfileNotFound {
                     profile: profile.to_owned(),
                     rev,
                 })
             }
 
             let subconfig = parse_config(
                 &output.results[0].1,
                 SparseConfigContext::Sparse,
             )?;
             if !subconfig.includes.is_empty() {
                 config.includes.push(b'\n');
                 config.includes.extend(&subconfig.includes);
             }
             if !subconfig.includes.is_empty() {
                 config.includes.push(b'\n');
                 config.excludes.extend(&subconfig.excludes);
             }
             config.warnings.extend(subconfig.warnings.into_iter());
             profiles.extend(subconfig.profiles.into_iter());
         }
 
         config.profiles = visited;
     }
 
     if !config.includes.is_empty() {
         config.includes.extend(b"\n.hg*");
     }
 
     Ok(Some(config))
 }
 
 /// Obtain a matcher for sparse working directories.
 pub fn matcher(
     repo: &Repo,
 ) -> Result<(Box<dyn Matcher + Sync>, Vec<SparseWarning>), SparseConfigError> {
     let mut warnings = vec![];
     if !repo.requirements().contains(SPARSE_REQUIREMENT) {
         return Ok((Box::new(AlwaysMatcher), warnings));
     }
 
     let parents = repo.dirstate_parents()?;
     let mut revs = vec![];
     let p1_rev =
         repo.changelog()?
             .rev_from_node(parents.p1.into())
             .map_err(|_| {
                 HgError::corrupted(format!(
                     "dirstate points to non-existent parent node"
                 ))
             })?;
     if p1_rev != NULL_REVISION {
         revs.push(p1_rev)
     }
     let p2_rev =
         repo.changelog()?
             .rev_from_node(parents.p2.into())
             .map_err(|_| {
                 HgError::corrupted(format!(
                     "dirstate points to non-existent parent node"
                 ))
             })?;
     if p2_rev != NULL_REVISION {
         revs.push(p2_rev)
     }
     let mut matchers = vec![];
 
     for rev in revs.iter() {
         let config = patterns_for_rev(repo, *rev);
         if let Ok(Some(config)) = config {
             warnings.extend(config.warnings);
             let mut m: Box<dyn Matcher + Sync> = Box::new(AlwaysMatcher);
             if !config.includes.is_empty() {
                 let (patterns, subwarnings) = parse_pattern_file_contents(
                     &config.includes,
                     Path::new(""),
                     Some(b"relglob:".as_ref()),
                     false,
                 )?;
                 warnings.extend(subwarnings.into_iter().map(From::from));
                 m = Box::new(IncludeMatcher::new(patterns)?);
             }
             if !config.excludes.is_empty() {
                 let (patterns, subwarnings) = parse_pattern_file_contents(
                     &config.excludes,
                     Path::new(""),
                     Some(b"relglob:".as_ref()),
                     false,
                 )?;
                 warnings.extend(subwarnings.into_iter().map(From::from));
                 m = Box::new(DifferenceMatcher::new(
                     m,
                     Box::new(IncludeMatcher::new(patterns)?),
                 ));
             }
             matchers.push(m);
         }
     }
     let result: Box<dyn Matcher + Sync> = match matchers.len() {
         0 => Box::new(AlwaysMatcher),
         1 => matchers.pop().expect("1 is equal to 0"),
         _ => Box::new(UnionMatcher::new(matchers)),
     };
 
     let matcher =
         force_include_matcher(result, &read_temporary_includes(repo)?)?;
     Ok((matcher, warnings))
 }
 
 /// Returns a matcher that returns true for any of the forced includes before
 /// testing against the actual matcher
 fn force_include_matcher(
     result: Box<dyn Matcher + Sync>,
     temp_includes: &[Vec<u8>],
 ) -> Result<Box<dyn Matcher + Sync>, PatternError> {
     if temp_includes.is_empty() {
         return Ok(result);
     }
     let forced_include_matcher = IncludeMatcher::new(
         temp_includes
             .into_iter()
             .map(|include| {
                 IgnorePattern::new(PatternSyntax::Path, include, Path::new(""))
             })
             .collect(),
     )?;
     Ok(Box::new(UnionMatcher::new(vec![
         Box::new(forced_include_matcher),
         result,
     ])))
 }

rust/rhg/src/commands/status.rs

@@ -1,617 +1,620 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::Ui;
 use crate::utils::path_utils::RelativizePaths;
 use clap::{Arg, SubCommand};
 use format_bytes::format_bytes;
-use hg;
 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::sparse::{matcher, SparseWarning};
 use hg::utils::files::get_bytes_from_os_string;
 use hg::utils::files::get_bytes_from_path;
 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 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::App<'static, 'static> {
     SubCommand::with_name("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::with_name("all")
                 .help("show status of all files")
                 .short("-A")
                 .long("--all"),
         )
         .arg(
             Arg::with_name("modified")
                 .help("show only modified files")
                 .short("-m")
                 .long("--modified"),
         )
         .arg(
             Arg::with_name("added")
                 .help("show only added files")
                 .short("-a")
                 .long("--added"),
         )
         .arg(
             Arg::with_name("removed")
                 .help("show only removed files")
                 .short("-r")
                 .long("--removed"),
         )
         .arg(
             Arg::with_name("clean")
                 .help("show only clean files")
                 .short("-c")
                 .long("--clean"),
         )
         .arg(
             Arg::with_name("deleted")
                 .help("show only deleted files")
                 .short("-d")
                 .long("--deleted"),
         )
         .arg(
             Arg::with_name("unknown")
                 .help("show only unknown (not tracked) files")
                 .short("-u")
                 .long("--unknown"),
         )
         .arg(
             Arg::with_name("ignored")
                 .help("show only ignored files")
                 .short("-i")
                 .long("--ignored"),
         )
         .arg(
             Arg::with_name("copies")
                 .help("show source of copied files (DEFAULT: ui.statuscopies)")
                 .short("-C")
                 .long("--copies"),
         )
         .arg(
             Arg::with_name("no-status")
                 .help("hide status prefix")
                 .short("-n")
                 .long("--no-status"),
         )
         .arg(
             Arg::with_name("verbose")
                 .help("enable additional output")
                 .short("-v")
                 .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> {
     return 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);
         }
     }
     return Ok(false);
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     // TODO: lift these limitations
     if invocation.config.get_bool(b"ui", b"tweakdefaults")? {
         return Err(CommandError::unsupported(
             "ui.tweakdefaults is not yet supported with rhg status",
         ));
     }
     if invocation.config.get_bool(b"ui", b"statuscopies")? {
         return Err(CommandError::unsupported(
             "ui.statuscopies is not yet supported with rhg status",
         ));
     }
     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 verbose = !ui.plain(None)
         && !args.is_present("print0")
         && (args.is_present("verbose")
             || config.get_bool(b"ui", b"verbose")?
             || config.get_bool(b"commands", b"status.verbose")?);
 
     let all = args.is_present("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.is_present("modified"),
             added: args.is_present("added"),
             removed: args.is_present("removed"),
             clean: args.is_present("clean"),
             deleted: args.is_present("deleted"),
             unknown: args.is_present("unknown"),
             ignored: args.is_present("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
     let no_status = args.is_present("no-status");
     let list_copies = all
         || args.is_present("copies")
         || config.get_bool(b"ui", b"statuscopies")?;
 
     let repo = invocation.repo?;
 
     if verbose {
         if 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)",
             ));
         };
     }
 
-    if repo.has_narrow() {
-        return Err(CommandError::unsupported(
-            "rhg status is not supported for narrow clones yet",
-        ));
-    }
-
     let mut dmap = repo.dirstate_map_mut()?;
 
     let options = StatusOptions {
         // we're currently supporting file systems with exec flags only
         // anyway
         check_exec: true,
         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(&print_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())))
             })?;
             for to_check in ds_status.unsure {
                 if unsure_is_modified(repo, &manifest, &to_check.path)? {
                     if display_states.modified {
                         ds_status.modified.push(to_check);
                     }
                 } else {
                     if display_states.clean {
                         ds_status.clean.push(to_check.clone());
                     }
                     fixup.push(to_check.path.into_owned())
                 }
             }
         }
         let relative_paths = (!ui.plain(None))
             && 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
             },
         };
         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 (matcher, sparse_warnings) = matcher(repo)?;
+    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),
+    };
 
-    for warning in sparse_warnings {
+    for warning in narrow_warnings.into_iter().chain(sparse_warnings) {
         match &warning {
-            SparseWarning::RootWarning { context, line } => {
+            sparse::SparseWarning::RootWarning { context, line } => {
                 let msg = format_bytes!(
                     b"warning: {} profile cannot use paths \"
                     starting with /, ignoring {}\n",
                     context,
                     line
                 );
                 ui.write_stderr(&msg)?;
             }
-            SparseWarning::ProfileNotFound { profile, rev } => {
+            sparse::SparseWarning::ProfileNotFound { profile, rev } => {
                 let msg = format_bytes!(
                     b"warning: sparse profile '{}' not found \"
                     in rev {} - ignoring it\n",
                     profile,
                     rev
                 );
                 ui.write_stderr(&msg)?;
             }
-            SparseWarning::Pattern(e) => {
+            sparse::SparseWarning::Pattern(e) => {
                 ui.write_stderr(&print_pattern_file_warning(e, &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,
         )?;
 
     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 fs_metadata = repo
                         .working_directory_vfs()
                         .symlink_metadata(&fs_path)?;
                     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.
         }
         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>,
 }
 
 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)?;
             if let Some(source) = copy_source {
                 let label = "status.copied";
                 self.ui.write_stdout_labelled(
                     &format_bytes!(b"  {}\n", source.as_bytes()),
                     label,
                 )?
             }
         }
         Ok(())
     }
 }
 
 /// 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(
     repo: &Repo,
     manifest: &Manifest,
     hg_path: &HgPath,
 ) -> Result<bool, HgError> {
     let vfs = repo.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();
     // TODO: Also account for `FALLBACK_SYMLINK` and `FALLBACK_EXEC` from the
     // dirstate
     let fs_flags = if is_symlink {
         Some(b'l')
     } else if has_exec_bit(&fs_metadata) {
         Some(b'x')
     } else {
         None
     };
 
     let entry = manifest
         .find_by_path(hg_path)?
         .expect("ambgious file not in p1");
     if entry.flags != fs_flags {
         return Ok(true);
     }
     let filelog = repo.filelog(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",
             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(true);
     }
 
     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(true);
     }
 
     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(p1_contents != &*fs_contents)
 }
 
 fn print_pattern_file_warning(
     warning: &PatternFileWarning,
     repo: &Repo,
 ) -> Vec<u8> {
     match warning {
         PatternFileWarning::InvalidSyntax(path, syntax) => format_bytes!(
             b"{}: ignoring invalid syntax '{}'\n",
             get_bytes_from_path(path),
             &*syntax
         ),
         PatternFileWarning::NoSuchFile(path) => {
             let path = if let Ok(relative) =
                 path.strip_prefix(repo.working_directory_path())
             {
                 relative
             } else {
                 &*path
             };
             format_bytes!(
                 b"skipping unreadable pattern file '{}': \
                     No such file or directory\n",
                 get_bytes_from_path(path),
             )
         }
     }
 }

rust/rhg/src/error.rs

@@ -1,277 +1,290 b''
 use crate::ui::utf8_to_local;
 use crate::ui::UiError;
 use crate::NoRepoInCwdError;
 use format_bytes::format_bytes;
 use hg::config::{ConfigError, ConfigParseError, ConfigValueParseError};
 use hg::dirstate_tree::on_disk::DirstateV2ParseError;
 use hg::errors::HgError;
 use hg::exit_codes;
 use hg::repo::RepoError;
 use hg::revlog::revlog::RevlogError;
 use hg::sparse::SparseConfigError;
 use hg::utils::files::get_bytes_from_path;
 use hg::{DirstateError, DirstateMapError, StatusError};
 use std::convert::From;
 
 /// The kind of command error
 #[derive(Debug)]
 pub enum CommandError {
     /// Exit with an error message and "standard" failure exit code.
     Abort {
         message: Vec<u8>,
         detailed_exit_code: exit_codes::ExitCode,
         hint: Option<Vec<u8>>,
     },
 
     /// Exit with a failure exit code but no message.
     Unsuccessful,
 
     /// Encountered something (such as a CLI argument, repository layout, …)
     /// not supported by this version of `rhg`. Depending on configuration
     /// `rhg` may attempt to silently fall back to Python-based `hg`, which
     /// may or may not support this feature.
     UnsupportedFeature { message: Vec<u8> },
     /// The fallback executable does not exist (or has some other problem if
     /// we end up being more precise about broken fallbacks).
     InvalidFallback { path: Vec<u8>, err: String },
 }
 
 impl CommandError {
     pub fn abort(message: impl AsRef<str>) -> Self {
         CommandError::abort_with_exit_code(message, exit_codes::ABORT)
     }
 
     pub fn abort_with_exit_code(
         message: impl AsRef<str>,
         detailed_exit_code: exit_codes::ExitCode,
     ) -> Self {
         CommandError::Abort {
             // TODO: bytes-based (instead of Unicode-based) formatting
             // of error messages to handle non-UTF-8 filenames etc:
             // https://www.mercurial-scm.org/wiki/EncodingStrategy#Mixing_output
             message: utf8_to_local(message.as_ref()).into(),
             detailed_exit_code: detailed_exit_code,
             hint: None,
         }
     }
 
     pub fn abort_with_exit_code_and_hint(
         message: impl AsRef<str>,
         detailed_exit_code: exit_codes::ExitCode,
         hint: Option<impl AsRef<str>>,
     ) -> Self {
         CommandError::Abort {
             message: utf8_to_local(message.as_ref()).into(),
             detailed_exit_code,
             hint: hint.map(|h| utf8_to_local(h.as_ref()).into()),
         }
     }
 
     pub fn abort_with_exit_code_bytes(
         message: impl AsRef<[u8]>,
         detailed_exit_code: exit_codes::ExitCode,
     ) -> Self {
         // TODO: use this everywhere it makes sense instead of the string
         // version.
         CommandError::Abort {
             message: message.as_ref().into(),
             detailed_exit_code,
             hint: None,
         }
     }
 
     pub fn unsupported(message: impl AsRef<str>) -> Self {
         CommandError::UnsupportedFeature {
             message: utf8_to_local(message.as_ref()).into(),
         }
     }
 }
 
 /// For now we don’t differenciate between invalid CLI args and valid for `hg`
 /// but not supported yet by `rhg`.
 impl From<clap::Error> for CommandError {
     fn from(error: clap::Error) -> Self {
         CommandError::unsupported(error.to_string())
     }
 }
 
 impl From<HgError> for CommandError {
     fn from(error: HgError) -> Self {
         match error {
             HgError::UnsupportedFeature(message) => {
                 CommandError::unsupported(message)
             }
             HgError::CensoredNodeError => {
                 CommandError::unsupported("Encountered a censored node")
             }
             HgError::Abort {
                 message,
                 detailed_exit_code,
                 hint,
             } => CommandError::abort_with_exit_code_and_hint(
                 message,
                 detailed_exit_code,
                 hint,
             ),
             _ => CommandError::abort(error.to_string()),
         }
     }
 }
 
 impl From<ConfigValueParseError> for CommandError {
     fn from(error: ConfigValueParseError) -> Self {
         CommandError::abort_with_exit_code(
             error.to_string(),
             exit_codes::CONFIG_ERROR_ABORT,
         )
     }
 }
 
 impl From<UiError> for CommandError {
     fn from(_error: UiError) -> Self {
         // If we already failed writing to stdout or stderr,
         // writing an error message to stderr about it would be likely to fail
         // too.
         CommandError::abort("")
     }
 }
 
 impl From<RepoError> for CommandError {
     fn from(error: RepoError) -> Self {
         match error {
             RepoError::NotFound { at } => {
                 CommandError::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"abort: repository {} not found",
                         get_bytes_from_path(at)
                     ),
                     exit_codes::ABORT,
                 )
             }
             RepoError::ConfigParseError(error) => error.into(),
             RepoError::Other(error) => error.into(),
         }
     }
 }
 
 impl<'a> From<&'a NoRepoInCwdError> for CommandError {
     fn from(error: &'a NoRepoInCwdError) -> Self {
         let NoRepoInCwdError { cwd } = error;
         CommandError::abort_with_exit_code_bytes(
             format_bytes!(
                 b"abort: no repository found in '{}' (.hg not found)!",
                 get_bytes_from_path(cwd)
             ),
             exit_codes::ABORT,
         )
     }
 }
 
 impl From<ConfigError> for CommandError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 impl From<ConfigParseError> for CommandError {
     fn from(error: ConfigParseError) -> Self {
         let ConfigParseError {
             origin,
             line,
             message,
         } = error;
         let line_message = if let Some(line_number) = line {
             format_bytes!(b":{}", line_number.to_string().into_bytes())
         } else {
             Vec::new()
         };
         CommandError::abort_with_exit_code_bytes(
             format_bytes!(
                 b"config error at {}{}: {}",
                 origin,
                 line_message,
                 message
             ),
             exit_codes::CONFIG_ERROR_ABORT,
         )
     }
 }
 
 impl From<(RevlogError, &str)> for CommandError {
     fn from((err, rev): (RevlogError, &str)) -> CommandError {
         match err {
             RevlogError::WDirUnsupported => CommandError::abort(
                 "abort: working directory revision cannot be specified",
             ),
             RevlogError::InvalidRevision => CommandError::abort(format!(
                 "abort: invalid revision identifier: {}",
                 rev
             )),
             RevlogError::AmbiguousPrefix => CommandError::abort(format!(
                 "abort: ambiguous revision identifier: {}",
                 rev
             )),
             RevlogError::Other(error) => error.into(),
         }
     }
 }
 
 impl From<StatusError> for CommandError {
     fn from(error: StatusError) -> Self {
         CommandError::abort(format!("{}", error))
     }
 }
 
 impl From<DirstateMapError> for CommandError {
     fn from(error: DirstateMapError) -> Self {
         CommandError::abort(format!("{}", error))
     }
 }
 
 impl From<DirstateError> for CommandError {
     fn from(error: DirstateError) -> Self {
         match error {
             DirstateError::Common(error) => error.into(),
             DirstateError::Map(error) => error.into(),
         }
     }
 }
 
 impl From<DirstateV2ParseError> for CommandError {
     fn from(error: DirstateV2ParseError) -> Self {
         HgError::from(error).into()
     }
 }
 
 impl From<SparseConfigError> for CommandError {
     fn from(e: SparseConfigError) -> Self {
         match e {
             SparseConfigError::IncludesAfterExcludes { context } => {
                 Self::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"{} config cannot have includes after excludes",
                         context
                     ),
                     exit_codes::CONFIG_PARSE_ERROR_ABORT,
                 )
             }
             SparseConfigError::EntryOutsideSection { context, line } => {
                 Self::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"{} config entry outside of section: {}",
                         context,
                         &line,
                     ),
                     exit_codes::CONFIG_PARSE_ERROR_ABORT,
                 )
             }
+            SparseConfigError::InvalidNarrowPrefix(prefix) => {
+                Self::abort_with_exit_code_bytes(
+                    format_bytes!(
+                        b"invalid prefix on narrow pattern: {}",
+                        &prefix
+                    ),
+                    exit_codes::ABORT,
+                )
+            }
+            SparseConfigError::IncludesInNarrow => Self::abort(
+                "including other spec files using '%include' \
+                    is not supported in narrowspec",
+            ),
             SparseConfigError::HgError(e) => Self::from(e),
             SparseConfigError::PatternError(e) => {
                 Self::unsupported(format!("{}", e))
             }
         }
     }
 }

tests/test-rhg-sparse-narrow.t

@@ -1,120 +1,117 b''
 #require rhg
 
   $ NO_FALLBACK="env RHG_ON_UNSUPPORTED=abort"
 
 Rhg works well when sparse working copy is enabled.
 
   $ cd "$TESTTMP"
   $ hg init repo-sparse
   $ cd repo-sparse
   $ cat > .hg/hgrc <<EOF
   > [extensions]
   > sparse=
   > EOF
 
   $ echo a > show
   $ echo x > hide
   $ mkdir dir1 dir2
   $ echo x > dir1/x
   $ echo y > dir1/y
   $ echo z > dir2/z
 
   $ hg ci -Aqm 'initial'
   $ hg debugsparse --include 'show'
   $ ls -A
   .hg
   show
 
   $ tip=$(hg log -r . --template '{node}')
   $ $NO_FALLBACK rhg files -r "$tip"
   dir1/x
   dir1/y
   dir2/z
   hide
   show
   $ $NO_FALLBACK rhg files
   show
 
   $ $NO_FALLBACK rhg cat -r "$tip" hide
   x
 
   $ cd ..
 
 We support most things when narrow is enabled, too, with a couple of caveats.
 
   $ . "$TESTDIR/narrow-library.sh"
   $ real_hg=$RHG_FALLBACK_EXECUTABLE
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > narrow=
   > EOF
 
   $ hg clone --narrow  ./repo-sparse repo-narrow --include dir1
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 2 changes to 2 files
   new changesets 6d714a4a2998
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ cd repo-narrow
 
   $ $NO_FALLBACK rhg cat -r "$tip" dir1/x
   x
   $ "$real_hg" cat -r "$tip" dir1/x
   x
 
 TODO: bad error message
 
   $ $NO_FALLBACK rhg cat -r "$tip" hide
   abort: invalid revision identifier: 6d714a4a2998cbfd0620db44da58b749f6565d63
   [255]
   $ "$real_hg" cat -r "$tip" hide
   [1]
 
 A naive implementation of [rhg files] leaks the paths that are supposed to be
 hidden by narrow, so we just fall back to hg.
 
   $ $NO_FALLBACK rhg files -r "$tip"
   unsupported feature: rhg files -r <rev> is not supported in narrow clones
   [252]
   $ "$real_hg" files -r "$tip"
   dir1/x
   dir1/y
 
-Hg status needs to do some filtering based on narrow spec, so we don't
-support it in rhg for narrow clones yet.
+Hg status needs to do some filtering based on narrow spec
 
   $ mkdir dir2
   $ touch dir2/q
   $ "$real_hg" status
   $ $NO_FALLBACK rhg --config rhg.status=true status
-  unsupported feature: rhg status is not supported for narrow clones yet
-  [252]
 
 Adding "orphaned" index files:
 
   $ (cd ..; cp repo-sparse/.hg/store/data/hide.i repo-narrow/.hg/store/data/hide.i)
   $ (cd ..; mkdir repo-narrow/.hg/store/data/dir2; cp repo-sparse/.hg/store/data/dir2/z.i repo-narrow/.hg/store/data/dir2/z.i)
   $ "$real_hg" verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 2 changes to 2 files
 
   $ "$real_hg" files -r "$tip"
   dir1/x
   dir1/y
 
 # TODO: even though [hg files] hides the orphaned dir2/z, [hg cat] still shows it.
 # rhg has the same issue, but at least it's not specific to rhg.
 # This is despite [hg verify] succeeding above.
 
   $ $NO_FALLBACK rhg cat -r "$tip" dir2/z
   z
   $ "$real_hg" cat -r "$tip" dir2/z
   z