rhg: Align config file parse error formatting with Python

Differences can cause tests to fail

Differential Revision: https://phab.mercurial-scm.org/D10110

rust/hg-core/src/config/layer.rs

@@ -1,292 +1,297 b''
 // layer.rs
 //
 // Copyright 2020
 //      Valentin Gatien-Baron,
 //      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.
 
 use crate::errors::{HgError, IoResultExt};
 use crate::utils::files::{get_bytes_from_path, get_path_from_bytes};
-use format_bytes::{write_bytes, DisplayBytes};
+use format_bytes::{format_bytes, write_bytes, DisplayBytes};
 use lazy_static::lazy_static;
 use regex::bytes::Regex;
 use std::collections::HashMap;
 use std::path::{Path, PathBuf};
 
 lazy_static! {
     static ref SECTION_RE: Regex = make_regex(r"^\[([^\[]+)\]");
     static ref ITEM_RE: Regex = make_regex(r"^([^=\s][^=]*?)\s*=\s*((.*\S)?)");
     /// Continuation whitespace
     static ref CONT_RE: Regex = make_regex(r"^\s+(\S|\S.*\S)\s*$");
     static ref EMPTY_RE: Regex = make_regex(r"^(;|#|\s*$)");
     static ref COMMENT_RE: Regex = make_regex(r"^(;|#)");
     /// A directive that allows for removing previous entries
     static ref UNSET_RE: Regex = make_regex(r"^%unset\s+(\S+)");
     /// A directive that allows for including other config files
     static ref INCLUDE_RE: Regex = make_regex(r"^%include\s+(\S|\S.*\S)\s*$");
 }
 
 /// All config values separated by layers of precedence.
 /// Each config source may be split in multiple layers if `%include` directives
 /// are used.
 /// TODO detail the general precedence
 #[derive(Clone)]
 pub struct ConfigLayer {
     /// Mapping of the sections to their items
     sections: HashMap<Vec<u8>, ConfigItem>,
     /// All sections (and their items/values) in a layer share the same origin
     pub origin: ConfigOrigin,
     /// Whether this layer comes from a trusted user or group
     pub trusted: bool,
 }
 
 impl ConfigLayer {
     pub fn new(origin: ConfigOrigin) -> Self {
         ConfigLayer {
             sections: HashMap::new(),
             trusted: true, // TODO check
             origin,
         }
     }
 
     /// Parse `--config` CLI arguments and return a layer if there’s any
     pub(crate) fn parse_cli_args(
         cli_config_args: impl IntoIterator<Item = impl AsRef<[u8]>>,
     ) -> Result<Option<Self>, ConfigError> {
         fn parse_one(arg: &[u8]) -> Option<(Vec<u8>, Vec<u8>, Vec<u8>)> {
             use crate::utils::SliceExt;
 
             let (section_and_item, value) = arg.split_2(b'=')?;
             let (section, item) = section_and_item.trim().split_2(b'.')?;
             Some((
                 section.to_owned(),
                 item.to_owned(),
                 value.trim().to_owned(),
             ))
         }
 
         let mut layer = Self::new(ConfigOrigin::CommandLine);
         for arg in cli_config_args {
             let arg = arg.as_ref();
             if let Some((section, item, value)) = parse_one(arg) {
                 layer.add(section, item, value, None);
             } else {
                 Err(HgError::abort(format!(
                     "malformed --config option: '{}' \
                     (use --config section.name=value)",
                     String::from_utf8_lossy(arg),
                 )))?
             }
         }
         if layer.sections.is_empty() {
             Ok(None)
         } else {
             Ok(Some(layer))
         }
     }
 
     /// Returns whether this layer comes from `--config` CLI arguments
     pub(crate) fn is_from_command_line(&self) -> bool {
         if let ConfigOrigin::CommandLine = self.origin {
             true
         } else {
             false
         }
     }
 
     /// Add an entry to the config, overwriting the old one if already present.
     pub fn add(
         &mut self,
         section: Vec<u8>,
         item: Vec<u8>,
         value: Vec<u8>,
         line: Option<usize>,
     ) {
         self.sections
             .entry(section)
             .or_insert_with(|| HashMap::new())
             .insert(item, ConfigValue { bytes: value, line });
     }
 
     /// Returns the config value in `<section>.<item>` if it exists
     pub fn get(&self, section: &[u8], item: &[u8]) -> Option<&ConfigValue> {
         Some(self.sections.get(section)?.get(item)?)
     }
 
     pub fn is_empty(&self) -> bool {
         self.sections.is_empty()
     }
 
     /// Returns a `Vec` of layers in order of precedence (so, in read order),
     /// recursively parsing the `%include` directives if any.
     pub fn parse(src: &Path, data: &[u8]) -> Result<Vec<Self>, ConfigError> {
         let mut layers = vec![];
 
         // Discard byte order mark if any
         let data = if data.starts_with(b"\xef\xbb\xbf") {
             &data[3..]
         } else {
             data
         };
 
         // TODO check if it's trusted
         let mut current_layer = Self::new(ConfigOrigin::File(src.to_owned()));
 
         let mut lines_iter =
             data.split(|b| *b == b'\n').enumerate().peekable();
         let mut section = b"".to_vec();
 
         while let Some((index, bytes)) = lines_iter.next() {
             if let Some(m) = INCLUDE_RE.captures(&bytes) {
                 let filename_bytes = &m[1];
                 // `Path::parent` only fails for the root directory,
                 // which `src` can’t be since we’ve managed to open it as a
                 // file.
                 let dir = src
                     .parent()
                     .expect("Path::parent fail on a file we’ve read");
                 // `Path::join` with an absolute argument correctly ignores the
                 // base path
                 let filename = dir.join(&get_path_from_bytes(&filename_bytes));
                 let data =
                     std::fs::read(&filename).when_reading_file(&filename)?;
                 layers.push(current_layer);
                 layers.extend(Self::parse(&filename, &data)?);
                 current_layer = Self::new(ConfigOrigin::File(src.to_owned()));
             } else if let Some(_) = EMPTY_RE.captures(&bytes) {
             } else if let Some(m) = SECTION_RE.captures(&bytes) {
                 section = m[1].to_vec();
             } else if let Some(m) = ITEM_RE.captures(&bytes) {
                 let item = m[1].to_vec();
                 let mut value = m[2].to_vec();
                 loop {
                     match lines_iter.peek() {
                         None => break,
                         Some((_, v)) => {
                             if let Some(_) = COMMENT_RE.captures(&v) {
                             } else if let Some(_) = CONT_RE.captures(&v) {
                                 value.extend(b"\n");
                                 value.extend(&m[1]);
                             } else {
                                 break;
                             }
                         }
                     };
                     lines_iter.next();
                 }
                 current_layer.add(
                     section.clone(),
                     item,
                     value,
                     Some(index + 1),
                 );
             } else if let Some(m) = UNSET_RE.captures(&bytes) {
                 if let Some(map) = current_layer.sections.get_mut(&section) {
                     map.remove(&m[1]);
                 }
             } else {
+                let message = if bytes.starts_with(b" ") {
+                    format_bytes!(b"unexpected leading whitespace: {}", bytes)
+                } else {
+                    bytes.to_owned()
+                };
                 return Err(ConfigParseError {
                     origin: ConfigOrigin::File(src.to_owned()),
                     line: Some(index + 1),
-                    bytes: bytes.to_owned(),
+                    message,
                 }
                 .into());
             }
         }
         if !current_layer.is_empty() {
             layers.push(current_layer);
         }
         Ok(layers)
     }
 }
 
 impl DisplayBytes for ConfigLayer {
     fn display_bytes(
         &self,
         out: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         let mut sections: Vec<_> = self.sections.iter().collect();
         sections.sort_by(|e0, e1| e0.0.cmp(e1.0));
 
         for (section, items) in sections.into_iter() {
             let mut items: Vec<_> = items.into_iter().collect();
             items.sort_by(|e0, e1| e0.0.cmp(e1.0));
 
             for (item, config_entry) in items {
                 write_bytes!(
                     out,
                     b"{}.{}={} # {}\n",
                     section,
                     item,
                     &config_entry.bytes,
                     &self.origin,
                 )?
             }
         }
         Ok(())
     }
 }
 
 /// Mapping of section item to value.
 /// In the following:
 /// ```text
 /// [ui]
 /// paginate=no
 /// ```
 /// "paginate" is the section item and "no" the value.
 pub type ConfigItem = HashMap<Vec<u8>, ConfigValue>;
 
 #[derive(Clone, Debug, PartialEq)]
 pub struct ConfigValue {
     /// The raw bytes of the value (be it from the CLI, env or from a file)
     pub bytes: Vec<u8>,
     /// Only present if the value comes from a file, 1-indexed.
     pub line: Option<usize>,
 }
 
 #[derive(Clone, Debug)]
 pub enum ConfigOrigin {
     /// From a configuration file
     File(PathBuf),
     /// From a `--config` CLI argument
     CommandLine,
     /// From environment variables like `$PAGER` or `$EDITOR`
     Environment(Vec<u8>),
     /* TODO cli
      * TODO defaults (configitems.py)
      * TODO extensions
      * TODO Python resources?
      * Others? */
 }
 
 impl DisplayBytes for ConfigOrigin {
     fn display_bytes(
         &self,
         out: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         match self {
             ConfigOrigin::File(p) => out.write_all(&get_bytes_from_path(p)),
             ConfigOrigin::CommandLine => out.write_all(b"--config"),
             ConfigOrigin::Environment(e) => write_bytes!(out, b"${}", e),
         }
     }
 }
 
 #[derive(Debug)]
 pub struct ConfigParseError {
     pub origin: ConfigOrigin,
     pub line: Option<usize>,
-    pub bytes: Vec<u8>,
+    pub message: Vec<u8>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum ConfigError {
     Parse(ConfigParseError),
     Other(HgError),
 }
 
 fn make_regex(pattern: &'static str) -> Regex {
     Regex::new(pattern).expect("expected a valid regex")
 }

rust/hg-core/src/errors.rs

@@ -1,192 +1,196 b''
 use crate::config::ConfigValueParseError;
 use std::fmt;
 
 /// Common error cases that can happen in many different APIs
 #[derive(Debug, derive_more::From)]
 pub enum HgError {
     IoError {
         error: std::io::Error,
         context: IoErrorContext,
     },
 
     /// A file under `.hg/` normally only written by Mercurial is not in the
     /// expected format. This indicates a bug in Mercurial, filesystem
     /// corruption, or hardware failure.
     ///
     /// The given string is a short explanation for users, not intended to be
     /// machine-readable.
     CorruptedRepository(String),
 
     /// The respository or requested operation involves a feature not
     /// supported by the Rust implementation. Falling back to the Python
     /// implementation may or may not work.
     ///
     /// The given string is a short explanation for users, not intended to be
     /// machine-readable.
     UnsupportedFeature(String),
 
     /// Operation cannot proceed for some other reason.
     ///
     /// The given string is a short explanation for users, not intended to be
     /// machine-readable.
     Abort(String),
 
     /// A configuration value is not in the expected syntax.
     ///
     /// These errors can happen in many places in the code because values are
     /// parsed lazily as the file-level parser does not know the expected type
     /// and syntax of each value.
     #[from]
     ConfigValueParseError(ConfigValueParseError),
 }
 
 /// Details about where an I/O error happened
 #[derive(Debug)]
 pub enum IoErrorContext {
     ReadingFile(std::path::PathBuf),
     WritingFile(std::path::PathBuf),
     RemovingFile(std::path::PathBuf),
     RenamingFile {
         from: std::path::PathBuf,
         to: std::path::PathBuf,
     },
     /// `std::env::current_dir`
     CurrentDir,
     /// `std::env::current_exe`
     CurrentExe,
 }
 
 impl HgError {
     pub fn corrupted(explanation: impl Into<String>) -> Self {
         // TODO: capture a backtrace here and keep it in the error value
         // to aid debugging?
         // https://doc.rust-lang.org/std/backtrace/struct.Backtrace.html
         HgError::CorruptedRepository(explanation.into())
     }
 
     pub fn unsupported(explanation: impl Into<String>) -> Self {
         HgError::UnsupportedFeature(explanation.into())
     }
     pub fn abort(explanation: impl Into<String>) -> Self {
         HgError::Abort(explanation.into())
     }
 }
 
 // TODO: use `DisplayBytes` instead to show non-Unicode filenames losslessly?
 impl fmt::Display for HgError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             HgError::Abort(explanation) => write!(f, "{}", explanation),
             HgError::IoError { error, context } => {
-                write!(f, "{}: {}", error, context)
+                write!(f, "abort: {}: {}", context, error)
             }
             HgError::CorruptedRepository(explanation) => {
-                write!(f, "corrupted repository: {}", explanation)
+                write!(f, "abort: corrupted repository: {}", explanation)
             }
             HgError::UnsupportedFeature(explanation) => {
                 write!(f, "unsupported feature: {}", explanation)
             }
             HgError::ConfigValueParseError(ConfigValueParseError {
                 origin: _,
                 line: _,
                 section,
                 item,
                 value,
                 expected_type,
             }) => {
                 // TODO: add origin and line number information, here and in
                 // corresponding python code
                 write!(
                     f,
                     "config error: {}.{} is not a {} ('{}')",
                     String::from_utf8_lossy(section),
                     String::from_utf8_lossy(item),
                     expected_type,
                     String::from_utf8_lossy(value)
                 )
             }
         }
     }
 }
 
 // TODO: use `DisplayBytes` instead to show non-Unicode filenames losslessly?
 impl fmt::Display for IoErrorContext {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             IoErrorContext::ReadingFile(path) => {
                 write!(f, "when reading {}", path.display())
             }
             IoErrorContext::WritingFile(path) => {
                 write!(f, "when writing {}", path.display())
             }
             IoErrorContext::RemovingFile(path) => {
                 write!(f, "when removing {}", path.display())
             }
             IoErrorContext::RenamingFile { from, to } => write!(
                 f,
                 "when renaming {} to {}",
                 from.display(),
                 to.display()
             ),
-            IoErrorContext::CurrentDir => write!(f, "current directory"),
-            IoErrorContext::CurrentExe => write!(f, "current executable"),
+            IoErrorContext::CurrentDir => {
+                write!(f, "error getting current working directory")
+            }
+            IoErrorContext::CurrentExe => {
+                write!(f, "error getting current executable")
+            }
         }
     }
 }
 
 pub trait IoResultExt<T> {
     /// Annotate a possible I/O error as related to a reading a file at the
     /// given path.
     ///
     /// This allows printing something like “File not found when reading
     /// example.txt” instead of just “File not found”.
     ///
     /// Converts a `Result` with `std::io::Error` into one with `HgError`.
     fn when_reading_file(self, path: &std::path::Path) -> Result<T, HgError>;
 
     fn with_context(
         self,
         context: impl FnOnce() -> IoErrorContext,
     ) -> Result<T, HgError>;
 }
 
 impl<T> IoResultExt<T> for std::io::Result<T> {
     fn when_reading_file(self, path: &std::path::Path) -> Result<T, HgError> {
         self.with_context(|| IoErrorContext::ReadingFile(path.to_owned()))
     }
 
     fn with_context(
         self,
         context: impl FnOnce() -> IoErrorContext,
     ) -> Result<T, HgError> {
         self.map_err(|error| HgError::IoError {
             error,
             context: context(),
         })
     }
 }
 
 pub trait HgResultExt<T> {
     /// Handle missing files separately from other I/O error cases.
     ///
     /// Wraps the `Ok` type in an `Option`:
     ///
     /// * `Ok(x)` becomes `Ok(Some(x))`
     /// * An I/O "not found" error becomes `Ok(None)`
     /// * Other errors are unchanged
     fn io_not_found_as_none(self) -> Result<Option<T>, HgError>;
 }
 
 impl<T> HgResultExt<T> for Result<T, HgError> {
     fn io_not_found_as_none(self) -> Result<Option<T>, HgError> {
         match self {
             Ok(x) => Ok(Some(x)),
             Err(HgError::IoError { error, .. })
                 if error.kind() == std::io::ErrorKind::NotFound =>
             {
                 Ok(None)
             }
             Err(other_error) => Err(other_error),
         }
     }
 }

rust/rhg/src/error.rs

@@ -1,143 +1,143 b''
 use crate::ui::utf8_to_local;
 use crate::ui::UiError;
 use crate::NoRepoInCwdError;
 use format_bytes::format_bytes;
 use hg::config::{ConfigError, ConfigParseError};
 use hg::errors::HgError;
 use hg::repo::RepoError;
 use hg::revlog::revlog::RevlogError;
 use hg::utils::files::get_bytes_from_path;
 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> },
 
     /// 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> },
 }
 
 impl CommandError {
     pub fn abort(message: impl AsRef<str>) -> 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(),
         }
     }
 
     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)
             }
             _ => CommandError::abort(error.to_string()),
         }
     }
 }
 
 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 {
                 message: format_bytes!(
                     b"repository {} not found",
                     get_bytes_from_path(at)
                 ),
             },
             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 {
             message: format_bytes!(
-                b"no repository found in '{}' (.hg not found)!",
+                b"abort: no repository found in '{}' (.hg not found)!",
                 get_bytes_from_path(cwd)
             ),
         }
     }
 }
 
 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,
-            bytes,
+            message,
         } = error;
         let line_message = if let Some(line_number) = line {
-            format_bytes!(b" at line {}", line_number.to_string().into_bytes())
+            format_bytes!(b":{}", line_number.to_string().into_bytes())
         } else {
             Vec::new()
         };
         CommandError::Abort {
             message: format_bytes!(
-                b"config parse error in {}{}: '{}'",
+                b"config error at {}{}: {}",
                 origin,
                 line_message,
-                bytes
+                message
             ),
         }
     }
 }
 
 impl From<(RevlogError, &str)> for CommandError {
     fn from((err, rev): (RevlogError, &str)) -> CommandError {
         match err {
             RevlogError::InvalidRevision => CommandError::abort(format!(
-                "invalid revision identifier {}",
+                "abort: invalid revision identifier: {}",
                 rev
             )),
             RevlogError::AmbiguousPrefix => CommandError::abort(format!(
-                "ambiguous revision identifier {}",
+                "abort: ambiguous revision identifier: {}",
                 rev
             )),
             RevlogError::Other(error) => error.into(),
         }
     }
 }

rust/rhg/src/main.rs

@@ -1,355 +1,354 b''
 extern crate log;
 use crate::ui::Ui;
 use clap::App;
 use clap::AppSettings;
 use clap::Arg;
 use clap::ArgMatches;
 use format_bytes::format_bytes;
 use hg::config::Config;
 use hg::repo::{Repo, RepoError};
 use hg::utils::files::{get_bytes_from_os_str, get_path_from_bytes};
 use hg::utils::SliceExt;
 use std::ffi::OsString;
 use std::path::PathBuf;
 use std::process::Command;
 
 mod blackbox;
 mod error;
 mod exitcode;
 mod ui;
 use error::CommandError;
 
 fn main_with_result(
     process_start_time: &blackbox::ProcessStartTime,
     ui: &ui::Ui,
     repo: Result<&Repo, &NoRepoInCwdError>,
     config: &Config,
 ) -> Result<(), CommandError> {
     let app = App::new("rhg")
         .global_setting(AppSettings::AllowInvalidUtf8)
         .setting(AppSettings::SubcommandRequired)
         .setting(AppSettings::VersionlessSubcommands)
         .arg(
             Arg::with_name("repository")
                 .help("repository root directory")
                 .short("-R")
                 .long("--repository")
                 .value_name("REPO")
                 .takes_value(true)
                 // Both ok: `hg -R ./foo log` or `hg log -R ./foo`
                 .global(true),
         )
         .arg(
             Arg::with_name("config")
                 .help("set/override config option (use 'section.name=value')")
                 .long("--config")
                 .value_name("CONFIG")
                 .takes_value(true)
                 .global(true)
                 // Ok: `--config section.key1=val --config section.key2=val2`
                 .multiple(true)
                 // Not ok: `--config section.key1=val section.key2=val2`
                 .number_of_values(1),
         )
         .version("0.0.1");
     let app = add_subcommand_args(app);
 
     let matches = app.clone().get_matches_safe()?;
 
     let (subcommand_name, subcommand_matches) = matches.subcommand();
     let run = subcommand_run_fn(subcommand_name)
         .expect("unknown subcommand name from clap despite AppSettings::SubcommandRequired");
     let subcommand_args = subcommand_matches
         .expect("no subcommand arguments from clap despite AppSettings::SubcommandRequired");
 
     let invocation = CliInvocation {
         ui,
         subcommand_args,
         config,
         repo,
     };
     let blackbox = blackbox::Blackbox::new(&invocation, process_start_time)?;
     blackbox.log_command_start();
     let result = run(&invocation);
     blackbox.log_command_end(exit_code(&result));
     result
 }
 
 fn main() {
     // Run this first, before we find out if the blackbox extension is even
     // enabled, in order to include everything in-between in the duration
     // measurements. Reading config files can be slow if they’re on NFS.
     let process_start_time = blackbox::ProcessStartTime::now();
 
     env_logger::init();
     let ui = ui::Ui::new();
 
     let early_args = EarlyArgs::parse(std::env::args_os());
     let non_repo_config =
         Config::load(early_args.config).unwrap_or_else(|error| {
             // Normally this is decided based on config, but we don’t have that
             // available. As of this writing config loading never returns an
             // "unsupported" error but that is not enforced by the type system.
             let on_unsupported = OnUnsupported::Abort;
 
             exit(&ui, on_unsupported, Err(error.into()))
         });
 
     if let Some(repo_path_bytes) = &early_args.repo {
         lazy_static::lazy_static! {
             static ref SCHEME_RE: regex::bytes::Regex =
                 // Same as `_matchscheme` in `mercurial/util.py`
                 regex::bytes::Regex::new("^[a-zA-Z0-9+.\\-]+:").unwrap();
         }
         if SCHEME_RE.is_match(&repo_path_bytes) {
             exit(
                 &ui,
                 OnUnsupported::from_config(&non_repo_config),
                 Err(CommandError::UnsupportedFeature {
                     message: format_bytes!(
                         b"URL-like --repository {}",
                         repo_path_bytes
                     ),
                 }),
             )
         }
     }
     let repo_path = early_args.repo.as_deref().map(get_path_from_bytes);
     let repo_result = match Repo::find(&non_repo_config, repo_path) {
         Ok(repo) => Ok(repo),
         Err(RepoError::NotFound { at }) if repo_path.is_none() => {
             // Not finding a repo is not fatal yet, if `-R` was not given
             Err(NoRepoInCwdError { cwd: at })
         }
         Err(error) => exit(
             &ui,
             OnUnsupported::from_config(&non_repo_config),
             Err(error.into()),
         ),
     };
 
     let config = if let Ok(repo) = &repo_result {
         repo.config()
     } else {
         &non_repo_config
     };
 
     let result = main_with_result(
         &process_start_time,
         &ui,
         repo_result.as_ref(),
         config,
     );
     exit(&ui, OnUnsupported::from_config(config), result)
 }
 
 fn exit_code(result: &Result<(), CommandError>) -> i32 {
     match result {
         Ok(()) => exitcode::OK,
         Err(CommandError::Abort { .. }) => exitcode::ABORT,
 
         // Exit with a specific code and no error message to let a potential
         // wrapper script fallback to Python-based Mercurial.
         Err(CommandError::UnsupportedFeature { .. }) => {
             exitcode::UNIMPLEMENTED
         }
     }
 }
 
 fn exit(
     ui: &Ui,
     mut on_unsupported: OnUnsupported,
     result: Result<(), CommandError>,
 ) -> ! {
     if let (
         OnUnsupported::Fallback { executable },
         Err(CommandError::UnsupportedFeature { .. }),
     ) = (&on_unsupported, &result)
     {
         let mut args = std::env::args_os();
         let executable_path = get_path_from_bytes(&executable);
         let this_executable = args.next().expect("exepcted argv[0] to exist");
         if executable_path == &PathBuf::from(this_executable) {
             // Avoid spawning infinitely many processes until resource
             // exhaustion.
             let _ = ui.write_stderr(&format_bytes!(
                 b"Blocking recursive fallback. The 'rhg.fallback-executable = {}' config \
                 points to `rhg` itself.\n",
                 executable
             ));
             on_unsupported = OnUnsupported::Abort
         } else {
             // `args` is now `argv[1..]` since we’ve already consumed `argv[0]`
             let result = Command::new(executable_path).args(args).status();
             match result {
                 Ok(status) => std::process::exit(
                     status.code().unwrap_or(exitcode::ABORT),
                 ),
                 Err(error) => {
                     let _ = ui.write_stderr(&format_bytes!(
                         b"tried to fall back to a '{}' sub-process but got error {}\n",
                         executable, format_bytes::Utf8(error)
                     ));
                     on_unsupported = OnUnsupported::Abort
                 }
             }
         }
     }
     match &result {
         Ok(_) => {}
         Err(CommandError::Abort { message }) => {
             if !message.is_empty() {
                 // Ignore errors when writing to stderr, we’re already exiting
                 // with failure code so there’s not much more we can do.
-                let _ =
-                    ui.write_stderr(&format_bytes!(b"abort: {}\n", message));
+                let _ = ui.write_stderr(&format_bytes!(b"{}\n", message));
             }
         }
         Err(CommandError::UnsupportedFeature { message }) => {
             match on_unsupported {
                 OnUnsupported::Abort => {
                     let _ = ui.write_stderr(&format_bytes!(
                         b"unsupported feature: {}\n",
                         message
                     ));
                 }
                 OnUnsupported::AbortSilent => {}
                 OnUnsupported::Fallback { .. } => unreachable!(),
             }
         }
     }
     std::process::exit(exit_code(&result))
 }
 
 macro_rules! subcommands {
     ($( $command: ident )+) => {
         mod commands {
             $(
                 pub mod $command;
             )+
         }
 
         fn add_subcommand_args<'a, 'b>(app: App<'a, 'b>) -> App<'a, 'b> {
             app
             $(
                 .subcommand(commands::$command::args())
             )+
         }
 
         pub type RunFn = fn(&CliInvocation) -> Result<(), CommandError>;
 
         fn subcommand_run_fn(name: &str) -> Option<RunFn> {
             match name {
                 $(
                     stringify!($command) => Some(commands::$command::run),
                 )+
                 _ => None,
             }
         }
     };
 }
 
 subcommands! {
     cat
     debugdata
     debugrequirements
     files
     root
     config
 }
 pub struct CliInvocation<'a> {
     ui: &'a Ui,
     subcommand_args: &'a ArgMatches<'a>,
     config: &'a Config,
     /// References inside `Result` is a bit peculiar but allow
     /// `invocation.repo?` to work out with `&CliInvocation` since this
     /// `Result` type is `Copy`.
     repo: Result<&'a Repo, &'a NoRepoInCwdError>,
 }
 
 struct NoRepoInCwdError {
     cwd: PathBuf,
 }
 
 /// CLI arguments to be parsed "early" in order to be able to read
 /// configuration before using Clap. Ideally we would also use Clap for this,
 /// see <https://github.com/clap-rs/clap/discussions/2366>.
 ///
 /// These arguments are still declared when we do use Clap later, so that Clap
 /// does not return an error for their presence.
 struct EarlyArgs {
     /// Values of all `--config` arguments. (Possibly none)
     config: Vec<Vec<u8>>,
     /// Value of the `-R` or `--repository` argument, if any.
     repo: Option<Vec<u8>>,
 }
 
 impl EarlyArgs {
     fn parse(args: impl IntoIterator<Item = OsString>) -> Self {
         let mut args = args.into_iter().map(get_bytes_from_os_str);
         let mut config = Vec::new();
         let mut repo = None;
         // Use `while let` instead of `for` so that we can also call
         // `args.next()` inside the loop.
         while let Some(arg) = args.next() {
             if arg == b"--config" {
                 if let Some(value) = args.next() {
                     config.push(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--config=") {
                 config.push(value.to_owned())
             }
 
             if arg == b"--repository" || arg == b"-R" {
                 if let Some(value) = args.next() {
                     repo = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--repository=") {
                 repo = Some(value.to_owned())
             } else if let Some(value) = arg.drop_prefix(b"-R") {
                 repo = Some(value.to_owned())
             }
         }
         Self { config, repo }
     }
 }
 
 /// What to do when encountering some unsupported feature.
 ///
 /// See `HgError::UnsupportedFeature` and `CommandError::UnsupportedFeature`.
 enum OnUnsupported {
     /// Print an error message describing what feature is not supported,
     /// and exit with code 252.
     Abort,
     /// Silently exit with code 252.
     AbortSilent,
     /// Try running a Python implementation
     Fallback { executable: Vec<u8> },
 }
 
 impl OnUnsupported {
     const DEFAULT: Self = OnUnsupported::Abort;
     const DEFAULT_FALLBACK_EXECUTABLE: &'static [u8] = b"hg";
 
     fn from_config(config: &Config) -> Self {
         match config
             .get(b"rhg", b"on-unsupported")
             .map(|value| value.to_ascii_lowercase())
             .as_deref()
         {
             Some(b"abort") => OnUnsupported::Abort,
             Some(b"abort-silent") => OnUnsupported::AbortSilent,
             Some(b"fallback") => OnUnsupported::Fallback {
                 executable: config
                     .get(b"rhg", b"fallback-executable")
                     .unwrap_or(Self::DEFAULT_FALLBACK_EXECUTABLE)
                     .to_owned(),
             },
             None => Self::DEFAULT,
             Some(_) => {
                 // TODO: warn about unknown config value
                 Self::DEFAULT
             }
         }
     }
 }

tests/test-rhg.t

@@ -1,299 +1,299 b''
 #require rhg
 
   $ NO_FALLBACK="env RHG_ON_UNSUPPORTED=abort"
 
 Unimplemented command
   $ $NO_FALLBACK rhg unimplemented-command
   unsupported feature: error: Found argument 'unimplemented-command' which wasn't expected, or isn't valid in this context
   
   USAGE:
       rhg [OPTIONS] <SUBCOMMAND>
   
   For more information try --help
   
   [252]
   $ rhg unimplemented-command --config rhg.on-unsupported=abort-silent
   [252]
 
 Finding root
   $ $NO_FALLBACK rhg root
   abort: no repository found in '$TESTTMP' (.hg not found)!
   [255]
 
   $ hg init repository
   $ cd repository
   $ $NO_FALLBACK rhg root
   $TESTTMP/repository
 
 Reading and setting configuration
   $ echo "[ui]" >> $HGRCPATH
   $ echo "username = user1" >> $HGRCPATH
   $ $NO_FALLBACK rhg config ui.username
   user1
   $ echo "[ui]" >> .hg/hgrc
   $ echo "username = user2" >> .hg/hgrc
   $ $NO_FALLBACK rhg config ui.username
   user2
   $ $NO_FALLBACK rhg --config ui.username=user3 config ui.username
   user3
 
 Unwritable file descriptor
   $ $NO_FALLBACK rhg root > /dev/full
   abort: No space left on device (os error 28)
   [255]
 
 Deleted repository
   $ rm -rf `pwd`
   $ $NO_FALLBACK rhg root
-  abort: $ENOENT$: current directory
+  abort: error getting current working directory: $ENOENT$
   [255]
 
 Listing tracked files
   $ cd $TESTTMP
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3; do
   >   echo $i >> file$i
   >   hg add file$i
   > done
   > hg commit -m "commit $i" -q
 
 Listing tracked files from root
   $ $NO_FALLBACK rhg files
   file1
   file2
   file3
 
 Listing tracked files from subdirectory
   $ mkdir -p path/to/directory
   $ cd path/to/directory
   $ $NO_FALLBACK rhg files
   ../../../file1
   ../../../file2
   ../../../file3
 
 Listing tracked files through broken pipe
   $ $NO_FALLBACK rhg files | head -n 1
   ../../../file1
 
 Debuging data in inline index
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3 4 5 6; do
   >   echo $i >> file-$i
   >   hg add file-$i
   >   hg commit -m "Commit $i" -q
   > done
   $ $NO_FALLBACK rhg debugdata -c 2
   8d0267cb034247ebfa5ee58ce59e22e57a492297
   test
   0 0
   file-3
   
   Commit 3 (no-eol)
   $ $NO_FALLBACK rhg debugdata -m 2
   file-1\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   file-2\x005d9299349fc01ddd25d0070d149b124d8f10411e (esc)
   file-3\x002661d26c649684b482d10f91960cc3db683c38b4 (esc)
 
 Debuging with full node id
   $ $NO_FALLBACK rhg debugdata -c `hg log -r 0 -T '{node}'`
   d1d1c679d3053e8926061b6f45ca52009f011e3f
   test
   0 0
   file-1
   
   Commit 1 (no-eol)
 
 Specifying revisions by changeset ID
   $ hg log -T '{node}\n'
   c6ad58c44207b6ff8a4fbbca7045a5edaa7e908b
   d654274993d0149eecc3cc03214f598320211900
   f646af7e96481d3a5470b695cf30ad8e3ab6c575
   cf8b83f14ead62b374b6e91a0e9303b85dfd9ed7
   91c6f6e73e39318534dc415ea4e8a09c99cd74d6
   6ae9681c6d30389694d8701faf24b583cf3ccafe
   $ $NO_FALLBACK rhg files -r cf8b83
   file-1
   file-2
   file-3
   $ $NO_FALLBACK rhg cat -r cf8b83 file-2
   2
   $ $NO_FALLBACK rhg cat -r c file-2
-  abort: ambiguous revision identifier c
+  abort: ambiguous revision identifier: c
   [255]
   $ $NO_FALLBACK rhg cat -r d file-2
   2
 
 Cat files
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ echo "original content" > original
   $ hg add original
   $ hg commit -m "add original" original
   $ $NO_FALLBACK rhg cat -r 0 original
   original content
 Cat copied file should not display copy metadata
   $ hg copy original copy_of_original
   $ hg commit -m "add copy of original"
   $ $NO_FALLBACK rhg cat -r 1 copy_of_original
   original content
 
 Fallback to Python
   $ $NO_FALLBACK rhg cat original
   unsupported feature: `rhg cat` without `--rev` / `-r`
   [252]
   $ rhg cat original
   original content
 
   $ rhg cat original --config rhg.fallback-executable=false
   [1]
 
   $ rhg cat original --config rhg.fallback-executable=hg-non-existent
   tried to fall back to a 'hg-non-existent' sub-process but got error $ENOENT$
   unsupported feature: `rhg cat` without `--rev` / `-r`
   [252]
 
   $ rhg cat original --config rhg.fallback-executable=rhg
   Blocking recursive fallback. The 'rhg.fallback-executable = rhg' config points to `rhg` itself.
   unsupported feature: `rhg cat` without `--rev` / `-r`
   [252]
 
 Requirements
   $ $NO_FALLBACK rhg debugrequirements
   dotencode
   fncache
   generaldelta
   revlogv1
   sparserevlog
   store
 
   $ echo indoor-pool >> .hg/requires
   $ $NO_FALLBACK rhg files
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ $NO_FALLBACK rhg cat -r 1 copy_of_original
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ $NO_FALLBACK rhg debugrequirements
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ echo -e '\xFF' >> .hg/requires
   $ $NO_FALLBACK rhg debugrequirements
   abort: corrupted repository: parse error in 'requires' file
   [255]
 
 Persistent nodemap
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ $NO_FALLBACK rhg debugrequirements | grep nodemap
   [1]
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   $ $NO_FALLBACK rhg files -r c3ae8dec9fad
   of
 
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg --config format.use-persistent-nodemap=True init repository
   $ cd repository
   $ $NO_FALLBACK rhg debugrequirements | grep nodemap
   persistent-nodemap
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog-*.nd (glob)
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   .hg/store/00changelog.n
 
 Specifying revisions by changeset ID
   $ $NO_FALLBACK rhg files -r c3ae8dec9fad
   of
   $ $NO_FALLBACK rhg cat -r c3ae8dec9fad of
   r5000
 
 Crate a shared repository
 
   $ echo "[extensions]"      >> $HGRCPATH
   $ echo "share = "          >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo1
   $ echo a > repo1/a
   $ hg -R repo1 commit -A -m'init'
   adding a
 
   $ hg share repo1 repo2
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ $NO_FALLBACK rhg files -R repo2
   repo2/a
   $ $NO_FALLBACK rhg -R repo2 cat -r 0 repo2/a
   a
 
 Same with relative sharing
 
   $ hg share repo2 repo3 --relative
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ $NO_FALLBACK rhg files -R repo3
   repo3/a
   $ $NO_FALLBACK rhg -R repo3 cat -r 0 repo3/a
   a
 
 Same with share-safe
 
   $ echo "[format]"         >> $HGRCPATH
   $ echo "use-share-safe = True" >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo4
   $ cd repo4
   $ echo a > a
   $ hg commit -A -m'init'
   adding a
 
   $ cd ..
   $ hg share repo4 repo5
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ cd repo5
   $ $NO_FALLBACK rhg files
   a
   $ $NO_FALLBACK rhg cat -r 0 a
   a
 
 The blackbox extension is supported
 
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "blackbox =" >> $HGRCPATH
   $ echo "[blackbox]" >> $HGRCPATH
   $ echo "maxsize = 1" >> $HGRCPATH
   $ $NO_FALLBACK rhg files > /dev/null
   $ cat .hg/blackbox.log
   ????/??/?? ??:??:??.??? * @d3873e73d99ef67873dac33fbcc66268d5d2b6f4 (*)> (rust) files exited 0 after 0.??? seconds (glob)
   $ cat .hg/blackbox.log.1
   ????/??/?? ??:??:??.??? * @d3873e73d99ef67873dac33fbcc66268d5d2b6f4 (*)> (rust) files (glob)