rhg: [encode] and [decode] config sections are not supported

Differential Revision: https://phab.mercurial-scm.org/D11761

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

@@ -1,470 +1,477 b''
 // config.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 super::layer;
 use super::values;
 use crate::config::layer::{
     ConfigError, ConfigLayer, ConfigOrigin, ConfigValue,
 };
 use crate::utils::files::get_bytes_from_os_str;
 use format_bytes::{write_bytes, DisplayBytes};
 use std::collections::HashSet;
 use std::env;
 use std::fmt;
 use std::path::{Path, PathBuf};
 use std::str;
 
 use crate::errors::{HgResultExt, IoResultExt};
 
 /// Holds the config values for the current repository
 /// TODO update this docstring once we support more sources
 #[derive(Clone)]
 pub struct Config {
     layers: Vec<layer::ConfigLayer>,
 }
 
 impl DisplayBytes for Config {
     fn display_bytes(
         &self,
         out: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         for (index, layer) in self.layers.iter().rev().enumerate() {
             write_bytes!(
                 out,
                 b"==== Layer {} (trusted: {}) ====\n{}",
                 index,
                 if layer.trusted {
                     &b"yes"[..]
                 } else {
                     &b"no"[..]
                 },
                 layer
             )?;
         }
         Ok(())
     }
 }
 
 pub enum ConfigSource {
     /// Absolute path to a config file
     AbsPath(PathBuf),
     /// Already parsed (from the CLI, env, Python resources, etc.)
     Parsed(layer::ConfigLayer),
 }
 
 #[derive(Debug)]
 pub struct ConfigValueParseError {
     pub origin: ConfigOrigin,
     pub line: Option<usize>,
     pub section: Vec<u8>,
     pub item: Vec<u8>,
     pub value: Vec<u8>,
     pub expected_type: &'static str,
 }
 
 impl fmt::Display for ConfigValueParseError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         // TODO: add origin and line number information, here and in
         // corresponding python code
         write!(
             f,
             "config error: {}.{} is not a {} ('{}')",
             String::from_utf8_lossy(&self.section),
             String::from_utf8_lossy(&self.item),
             self.expected_type,
             String::from_utf8_lossy(&self.value)
         )
     }
 }
 
 impl Config {
     /// Load system and user configuration from various files.
     ///
     /// This is also affected by some environment variables.
     pub fn load_non_repo() -> Result<Self, ConfigError> {
         let mut config = Self { layers: Vec::new() };
         let opt_rc_path = env::var_os("HGRCPATH");
         // HGRCPATH replaces system config
         if opt_rc_path.is_none() {
             config.add_system_config()?
         }
 
         config.add_for_environment_variable("EDITOR", b"ui", b"editor");
         config.add_for_environment_variable("VISUAL", b"ui", b"editor");
         config.add_for_environment_variable("PAGER", b"pager", b"pager");
 
         // These are set by `run-tests.py --rhg` to enable fallback for the
         // entire test suite. Alternatives would be setting configuration
         // through `$HGRCPATH` but some tests override that, or changing the
         // `hg` shell alias to include `--config` but that disrupts tests that
         // print command lines and check expected output.
         config.add_for_environment_variable(
             "RHG_ON_UNSUPPORTED",
             b"rhg",
             b"on-unsupported",
         );
         config.add_for_environment_variable(
             "RHG_FALLBACK_EXECUTABLE",
             b"rhg",
             b"fallback-executable",
         );
         config.add_for_environment_variable("RHG_STATUS", b"rhg", b"status");
 
         // HGRCPATH replaces user config
         if opt_rc_path.is_none() {
             config.add_user_config()?
         }
         if let Some(rc_path) = &opt_rc_path {
             for path in env::split_paths(rc_path) {
                 if !path.as_os_str().is_empty() {
                     if path.is_dir() {
                         config.add_trusted_dir(&path)?
                     } else {
                         config.add_trusted_file(&path)?
                     }
                 }
             }
         }
         Ok(config)
     }
 
     pub fn load_cli_args_config(
         &mut self,
         cli_config_args: impl IntoIterator<Item = impl AsRef<[u8]>>,
     ) -> Result<(), ConfigError> {
         if let Some(layer) = ConfigLayer::parse_cli_args(cli_config_args)? {
             self.layers.push(layer)
         }
         Ok(())
     }
 
     fn add_trusted_dir(&mut self, path: &Path) -> Result<(), ConfigError> {
         if let Some(entries) = std::fs::read_dir(path)
             .when_reading_file(path)
             .io_not_found_as_none()?
         {
             let mut file_paths = entries
                 .map(|result| {
                     result.when_reading_file(path).map(|entry| entry.path())
                 })
                 .collect::<Result<Vec<_>, _>>()?;
             file_paths.sort();
             for file_path in &file_paths {
                 if file_path.extension() == Some(std::ffi::OsStr::new("rc")) {
                     self.add_trusted_file(&file_path)?
                 }
             }
         }
         Ok(())
     }
 
     fn add_trusted_file(&mut self, path: &Path) -> Result<(), ConfigError> {
         if let Some(data) = std::fs::read(path)
             .when_reading_file(path)
             .io_not_found_as_none()?
         {
             self.layers.extend(ConfigLayer::parse(path, &data)?)
         }
         Ok(())
     }
 
     fn add_for_environment_variable(
         &mut self,
         var: &str,
         section: &[u8],
         key: &[u8],
     ) {
         if let Some(value) = env::var_os(var) {
             let origin = layer::ConfigOrigin::Environment(var.into());
             let mut layer = ConfigLayer::new(origin);
             layer.add(
                 section.to_owned(),
                 key.to_owned(),
                 get_bytes_from_os_str(value),
                 None,
             );
             self.layers.push(layer)
         }
     }
 
     #[cfg(unix)] // TODO: other platforms
     fn add_system_config(&mut self) -> Result<(), ConfigError> {
         let mut add_for_prefix = |prefix: &Path| -> Result<(), ConfigError> {
             let etc = prefix.join("etc").join("mercurial");
             self.add_trusted_file(&etc.join("hgrc"))?;
             self.add_trusted_dir(&etc.join("hgrc.d"))
         };
         let root = Path::new("/");
         // TODO: use `std::env::args_os().next().unwrap()` a.k.a. argv[0]
         // instead? TODO: can this be a relative path?
         let hg = crate::utils::current_exe()?;
         // TODO: this order (per-installation then per-system) matches
         // `systemrcpath()` in `mercurial/scmposix.py`, but
         // `mercurial/helptext/config.txt` suggests it should be reversed
         if let Some(installation_prefix) = hg.parent().and_then(Path::parent) {
             if installation_prefix != root {
                 add_for_prefix(&installation_prefix)?
             }
         }
         add_for_prefix(root)?;
         Ok(())
     }
 
     #[cfg(unix)] // TODO: other plateforms
     fn add_user_config(&mut self) -> Result<(), ConfigError> {
         let opt_home = home::home_dir();
         if let Some(home) = &opt_home {
             self.add_trusted_file(&home.join(".hgrc"))?
         }
         let darwin = cfg!(any(target_os = "macos", target_os = "ios"));
         if !darwin {
             if let Some(config_home) = env::var_os("XDG_CONFIG_HOME")
                 .map(PathBuf::from)
                 .or_else(|| opt_home.map(|home| home.join(".config")))
             {
                 self.add_trusted_file(&config_home.join("hg").join("hgrc"))?
             }
         }
         Ok(())
     }
 
     /// Loads in order, which means that the precedence is the same
     /// as the order of `sources`.
     pub fn load_from_explicit_sources(
         sources: Vec<ConfigSource>,
     ) -> Result<Self, ConfigError> {
         let mut layers = vec![];
 
         for source in sources.into_iter() {
             match source {
                 ConfigSource::Parsed(c) => layers.push(c),
                 ConfigSource::AbsPath(c) => {
                     // TODO check if it should be trusted
                     // mercurial/ui.py:427
                     let data = match std::fs::read(&c) {
                         Err(_) => continue, // same as the python code
                         Ok(data) => data,
                     };
                     layers.extend(ConfigLayer::parse(&c, &data)?)
                 }
             }
         }
 
         Ok(Config { layers })
     }
 
     /// Loads the per-repository config into a new `Config` which is combined
     /// with `self`.
     pub(crate) fn combine_with_repo(
         &self,
         repo_config_files: &[PathBuf],
     ) -> Result<Self, ConfigError> {
         let (cli_layers, other_layers) = self
             .layers
             .iter()
             .cloned()
             .partition(ConfigLayer::is_from_command_line);
 
         let mut repo_config = Self {
             layers: other_layers,
         };
         for path in repo_config_files {
             // TODO: check if this file should be trusted:
             // `mercurial/ui.py:427`
             repo_config.add_trusted_file(path)?;
         }
         repo_config.layers.extend(cli_layers);
         Ok(repo_config)
     }
 
     fn get_parse<'config, T: 'config>(
         &'config self,
         section: &[u8],
         item: &[u8],
         expected_type: &'static str,
         parse: impl Fn(&'config [u8]) -> Option<T>,
     ) -> Result<Option<T>, ConfigValueParseError> {
         match self.get_inner(&section, &item) {
             Some((layer, v)) => match parse(&v.bytes) {
                 Some(b) => Ok(Some(b)),
                 None => Err(ConfigValueParseError {
                     origin: layer.origin.to_owned(),
                     line: v.line,
                     value: v.bytes.to_owned(),
                     section: section.to_owned(),
                     item: item.to_owned(),
                     expected_type,
                 }),
             },
             None => Ok(None),
         }
     }
 
     /// Returns an `Err` if the first value found is not a valid UTF-8 string.
     /// Otherwise, returns an `Ok(value)` if found, or `None`.
     pub fn get_str(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Result<Option<&str>, ConfigValueParseError> {
         self.get_parse(section, item, "ASCII or UTF-8 string", |value| {
             str::from_utf8(value).ok()
         })
     }
 
     /// Returns an `Err` if the first value found is not a valid unsigned
     /// integer. Otherwise, returns an `Ok(value)` if found, or `None`.
     pub fn get_u32(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Result<Option<u32>, ConfigValueParseError> {
         self.get_parse(section, item, "valid integer", |value| {
             str::from_utf8(value).ok()?.parse().ok()
         })
     }
 
     /// Returns an `Err` if the first value found is not a valid file size
     /// value such as `30` (default unit is bytes), `7 MB`, or `42.5 kb`.
     /// Otherwise, returns an `Ok(value_in_bytes)` if found, or `None`.
     pub fn get_byte_size(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Result<Option<u64>, ConfigValueParseError> {
         self.get_parse(section, item, "byte quantity", values::parse_byte_size)
     }
 
     /// Returns an `Err` if the first value found is not a valid boolean.
     /// Otherwise, returns an `Ok(option)`, where `option` is the boolean if
     /// found, or `None`.
     pub fn get_option(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Result<Option<bool>, ConfigValueParseError> {
         self.get_parse(section, item, "boolean", values::parse_bool)
     }
 
     /// Returns the corresponding boolean in the config. Returns `Ok(false)`
     /// if the value is not found, an `Err` if it's not a valid boolean.
     pub fn get_bool(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Result<bool, ConfigValueParseError> {
         Ok(self.get_option(section, item)?.unwrap_or(false))
     }
 
     /// If there is an `item` value in `section`, parse and return a list of
     /// byte strings.
     pub fn get_list(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Option<Vec<Vec<u8>>> {
         self.get(section, item).map(values::parse_list)
     }
 
     /// Returns the raw value bytes of the first one found, or `None`.
     pub fn get(&self, section: &[u8], item: &[u8]) -> Option<&[u8]> {
         self.get_inner(section, item)
             .map(|(_, value)| value.bytes.as_ref())
     }
 
     /// Returns the layer and the value of the first one found, or `None`.
     fn get_inner(
         &self,
         section: &[u8],
         item: &[u8],
     ) -> Option<(&ConfigLayer, &ConfigValue)> {
         for layer in self.layers.iter().rev() {
             if !layer.trusted {
                 continue;
             }
             if let Some(v) = layer.get(&section, &item) {
                 return Some((&layer, v));
             }
         }
         None
     }
 
     /// Return all keys defined for the given section
     pub fn get_section_keys(&self, section: &[u8]) -> HashSet<&[u8]> {
         self.layers
             .iter()
             .flat_map(|layer| layer.iter_keys(section))
             .collect()
     }
 
+    /// Returns whether any key is defined in the given section
+    pub fn has_non_empty_section(&self, section: &[u8]) -> bool {
+        self.layers
+            .iter()
+            .any(|layer| layer.has_non_empty_section(section))
+    }
+
     /// Get raw values bytes from all layers (even untrusted ones) in order
     /// of precedence.
     #[cfg(test)]
     fn get_all(&self, section: &[u8], item: &[u8]) -> Vec<&[u8]> {
         let mut res = vec![];
         for layer in self.layers.iter().rev() {
             if let Some(v) = layer.get(&section, &item) {
                 res.push(v.bytes.as_ref());
             }
         }
         res
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
     use std::fs::File;
     use std::io::Write;
 
     #[test]
     fn test_include_layer_ordering() {
         let tmpdir = tempfile::tempdir().unwrap();
         let tmpdir_path = tmpdir.path();
         let mut included_file =
             File::create(&tmpdir_path.join("included.rc")).unwrap();
 
         included_file.write_all(b"[section]\nitem=value1").unwrap();
         let base_config_path = tmpdir_path.join("base.rc");
         let mut config_file = File::create(&base_config_path).unwrap();
         let data =
             b"[section]\nitem=value0\n%include included.rc\nitem=value2\n\
               [section2]\ncount = 4\nsize = 1.5 KB\nnot-count = 1.5\nnot-size = 1 ub";
         config_file.write_all(data).unwrap();
 
         let sources = vec![ConfigSource::AbsPath(base_config_path)];
         let config = Config::load_from_explicit_sources(sources)
             .expect("expected valid config");
 
         let (_, value) = config.get_inner(b"section", b"item").unwrap();
         assert_eq!(
             value,
             &ConfigValue {
                 bytes: b"value2".to_vec(),
                 line: Some(4)
             }
         );
 
         let value = config.get(b"section", b"item").unwrap();
         assert_eq!(value, b"value2",);
         assert_eq!(
             config.get_all(b"section", b"item"),
             [b"value2", b"value1", b"value0"]
         );
 
         assert_eq!(config.get_u32(b"section2", b"count").unwrap(), Some(4));
         assert_eq!(
             config.get_byte_size(b"section2", b"size").unwrap(),
             Some(1024 + 512)
         );
         assert!(config.get_u32(b"section2", b"not-count").is_err());
         assert!(config.get_byte_size(b"section2", b"not-size").is_err());
     }
 }

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

@@ -1,323 +1,330 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;
 use crate::exit_codes::CONFIG_PARSE_ERROR_ABORT;
 use crate::utils::files::{get_bytes_from_path, get_path_from_bytes};
 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!(
                         "abort: malformed --config option: '{}' \
                     (use --config section.name=value)",
                         String::from_utf8_lossy(arg),
                     ),
                     CONFIG_PARSE_ERROR_ABORT,
                 ))?
             }
         }
         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)?)
     }
 
     /// Returns the keys defined in the given section
     pub fn iter_keys(&self, section: &[u8]) -> impl Iterator<Item = &[u8]> {
         self.sections
             .get(section)
             .into_iter()
             .flat_map(|section| section.keys().map(|vec| &**vec))
     }
 
+    /// Returns whether any key is defined in the given section
+    pub fn has_non_empty_section(&self, section: &[u8]) -> bool {
+        self.sections
+            .get(section)
+            .map_or(false, |section| !section.is_empty())
+    }
+
     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() {
             let line = Some(index + 1);
             if let Some(m) = INCLUDE_RE.captures(&bytes) {
                 let filename_bytes = &m[1];
                 let filename_bytes = crate::utils::expand_vars(filename_bytes);
                 // `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));
                 match std::fs::read(&filename) {
                     Ok(data) => {
                         layers.push(current_layer);
                         layers.extend(Self::parse(&filename, &data)?);
                         current_layer =
                             Self::new(ConfigOrigin::File(src.to_owned()));
                     }
                     Err(error) => {
                         if error.kind() != std::io::ErrorKind::NotFound {
                             return Err(ConfigParseError {
                                 origin: ConfigOrigin::File(src.to_owned()),
                                 line,
                                 message: format_bytes!(
                                     b"cannot include {} ({})",
                                     filename_bytes,
                                     format_bytes::Utf8(error)
                                 ),
                             }
                             .into());
                         }
                     }
                 }
             } 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, line);
             } 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,
                     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 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/rhg/src/main.rs

@@ -1,630 +1,638 b''
 extern crate log;
 use crate::error::CommandError;
 use crate::ui::Ui;
 use clap::App;
 use clap::AppSettings;
 use clap::Arg;
 use clap::ArgMatches;
 use format_bytes::{format_bytes, join};
 use hg::config::{Config, ConfigSource};
 use hg::exit_codes;
 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 ui;
 pub mod utils {
     pub mod path_utils;
 }
 
 fn main_with_result(
     process_start_time: &blackbox::ProcessStartTime,
     ui: &ui::Ui,
     repo: Result<&Repo, &NoRepoInCwdError>,
     config: &Config,
 ) -> Result<(), CommandError> {
     check_unsupported(config)?;
 
     let app = App::new("rhg")
         .global_setting(AppSettings::AllowInvalidUtf8)
         .global_setting(AppSettings::DisableVersion)
         .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),
         )
         .arg(
             Arg::with_name("cwd")
                 .help("change working directory")
                 .long("--cwd")
                 .value_name("DIR")
                 .takes_value(true)
                 .global(true),
         )
         .version("0.0.1");
     let app = add_subcommand_args(app);
 
     let matches = app.clone().get_matches_safe()?;
 
     let (subcommand_name, subcommand_matches) = matches.subcommand();
 
     // Mercurial allows users to define "defaults" for commands, fallback
     // if a default is detected for the current command
     let defaults = config.get_str(b"defaults", subcommand_name.as_bytes());
     if defaults?.is_some() {
         let msg = "`defaults` config set";
         return Err(CommandError::unsupported(msg));
     }
 
     for prefix in ["pre", "post", "fail"].iter() {
         // Mercurial allows users to define generic hooks for commands,
         // fallback if any are detected
         let item = format!("{}-{}", prefix, subcommand_name);
         let hook_for_command = config.get_str(b"hooks", item.as_bytes())?;
         if hook_for_command.is_some() {
             let msg = format!("{}-{} hook defined", prefix, subcommand_name);
             return Err(CommandError::unsupported(msg));
         }
     }
     let run = subcommand_run_fn(subcommand_name)
         .expect("unknown subcommand name from clap despite AppSettings::SubcommandRequired");
     let subcommand_args = subcommand_matches
         .expect("no subcommand arguments from clap despite AppSettings::SubcommandRequired");
 
     let invocation = CliInvocation {
         ui,
         subcommand_args,
         config,
         repo,
     };
 
     if let Ok(repo) = repo {
         // We don't support subrepos, fallback if the subrepos file is present
         if repo.working_directory_vfs().join(".hgsub").exists() {
             let msg = "subrepos (.hgsub is present)";
             return Err(CommandError::unsupported(msg));
         }
     }
 
     let blackbox = blackbox::Blackbox::new(&invocation, process_start_time)?;
     blackbox.log_command_start();
     let result = run(&invocation);
     blackbox.log_command_end(exit_code(
         &result,
         // TODO: show a warning or combine with original error if `get_bool`
         // returns an error
         config
             .get_bool(b"ui", b"detailed-exit-code")
             .unwrap_or(false),
     ));
     result
 }
 
 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 initial_current_dir = early_args.cwd.map(|cwd| {
         let cwd = get_path_from_bytes(&cwd);
         std::env::current_dir()
             .and_then(|initial| {
                 std::env::set_current_dir(cwd)?;
                 Ok(initial)
             })
             .unwrap_or_else(|error| {
                 exit(
                     &None,
                     &ui,
                     OnUnsupported::Abort,
                     Err(CommandError::abort(format!(
                         "abort: {}: '{}'",
                         error,
                         cwd.display()
                     ))),
                     false,
                 )
             })
     });
 
     let mut non_repo_config =
         Config::load_non_repo().unwrap_or_else(|error| {
             // Normally this is decided based on config, but we don’t have that
             // available. As of this writing config loading never returns an
             // "unsupported" error but that is not enforced by the type system.
             let on_unsupported = OnUnsupported::Abort;
 
             exit(
                 &initial_current_dir,
                 &ui,
                 on_unsupported,
                 Err(error.into()),
                 false,
             )
         });
 
     non_repo_config
         .load_cli_args_config(early_args.config)
         .unwrap_or_else(|error| {
             exit(
                 &initial_current_dir,
                 &ui,
                 OnUnsupported::from_config(&ui, &non_repo_config),
                 Err(error.into()),
                 non_repo_config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             )
         });
 
     if let Some(repo_path_bytes) = &early_args.repo {
         lazy_static::lazy_static! {
             static ref SCHEME_RE: regex::bytes::Regex =
                 // Same as `_matchscheme` in `mercurial/util.py`
                 regex::bytes::Regex::new("^[a-zA-Z0-9+.\\-]+:").unwrap();
         }
         if SCHEME_RE.is_match(&repo_path_bytes) {
             exit(
                 &initial_current_dir,
                 &ui,
                 OnUnsupported::from_config(&ui, &non_repo_config),
                 Err(CommandError::UnsupportedFeature {
                     message: format_bytes!(
                         b"URL-like --repository {}",
                         repo_path_bytes
                     ),
                 }),
                 // TODO: show a warning or combine with original error if
                 // `get_bool` returns an error
                 non_repo_config
                     .get_bool(b"ui", b"detailed-exit-code")
                     .unwrap_or(false),
             )
         }
     }
     let repo_arg = early_args.repo.unwrap_or(Vec::new());
     let repo_path: Option<PathBuf> = {
         if repo_arg.is_empty() {
             None
         } else {
             let local_config = {
                 if std::env::var_os("HGRCSKIPREPO").is_none() {
                     // TODO: handle errors from find_repo_root
                     if let Ok(current_dir_path) = Repo::find_repo_root() {
                         let config_files = vec![
                             ConfigSource::AbsPath(
                                 current_dir_path.join(".hg/hgrc"),
                             ),
                             ConfigSource::AbsPath(
                                 current_dir_path.join(".hg/hgrc-not-shared"),
                             ),
                         ];
                         // TODO: handle errors from
                         // `load_from_explicit_sources`
                         Config::load_from_explicit_sources(config_files).ok()
                     } else {
                         None
                     }
                 } else {
                     None
                 }
             };
 
             let non_repo_config_val = {
                 let non_repo_val = non_repo_config.get(b"paths", &repo_arg);
                 match &non_repo_val {
                     Some(val) if val.len() > 0 => home::home_dir()
                         .unwrap_or_else(|| PathBuf::from("~"))
                         .join(get_path_from_bytes(val))
                         .canonicalize()
                         // TODO: handle error and make it similar to python
                         // implementation maybe?
                         .ok(),
                     _ => None,
                 }
             };
 
             let config_val = match &local_config {
                 None => non_repo_config_val,
                 Some(val) => {
                     let local_config_val = val.get(b"paths", &repo_arg);
                     match &local_config_val {
                         Some(val) if val.len() > 0 => {
                             // presence of a local_config assures that
                             // current_dir
                             // wont result in an Error
                             let canpath = hg::utils::current_dir()
                                 .unwrap()
                                 .join(get_path_from_bytes(val))
                                 .canonicalize();
                             canpath.ok().or(non_repo_config_val)
                         }
                         _ => non_repo_config_val,
                     }
                 }
             };
             config_val.or(Some(get_path_from_bytes(&repo_arg).to_path_buf()))
         }
     };
 
     let repo_result = match Repo::find(&non_repo_config, repo_path.to_owned())
     {
         Ok(repo) => Ok(repo),
         Err(RepoError::NotFound { at }) if repo_path.is_none() => {
             // Not finding a repo is not fatal yet, if `-R` was not given
             Err(NoRepoInCwdError { cwd: at })
         }
         Err(error) => exit(
             &initial_current_dir,
             &ui,
             OnUnsupported::from_config(&ui, &non_repo_config),
             Err(error.into()),
             // TODO: show a warning or combine with original error if
             // `get_bool` returns an error
             non_repo_config
                 .get_bool(b"ui", b"detailed-exit-code")
                 .unwrap_or(false),
         ),
     };
 
     let config = if let Ok(repo) = &repo_result {
         repo.config()
     } else {
         &non_repo_config
     };
     let on_unsupported = OnUnsupported::from_config(&ui, config);
 
     let result = main_with_result(
         &process_start_time,
         &ui,
         repo_result.as_ref(),
         config,
     );
     exit(
         &initial_current_dir,
         &ui,
         on_unsupported,
         result,
         // TODO: show a warning or combine with original error if `get_bool`
         // returns an error
         config
             .get_bool(b"ui", b"detailed-exit-code")
             .unwrap_or(false),
     )
 }
 
 fn exit_code(
     result: &Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> i32 {
     match result {
         Ok(()) => exit_codes::OK,
         Err(CommandError::Abort {
             message: _,
             detailed_exit_code,
         }) => {
             if use_detailed_exit_code {
                 *detailed_exit_code
             } else {
                 exit_codes::ABORT
             }
         }
         Err(CommandError::Unsuccessful) => exit_codes::UNSUCCESSFUL,
 
         // Exit with a specific code and no error message to let a potential
         // wrapper script fallback to Python-based Mercurial.
         Err(CommandError::UnsupportedFeature { .. }) => {
             exit_codes::UNIMPLEMENTED
         }
     }
 }
 
 fn exit(
     initial_current_dir: &Option<PathBuf>,
     ui: &Ui,
     mut on_unsupported: OnUnsupported,
     result: Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> ! {
     if let (
         OnUnsupported::Fallback { executable },
         Err(CommandError::UnsupportedFeature { .. }),
     ) = (&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 mut command = Command::new(executable_path);
             command.args(args);
             if let Some(initial) = initial_current_dir {
                 command.current_dir(initial);
             }
             let result = command.status();
             match result {
                 Ok(status) => std::process::exit(
                     status.code().unwrap_or(exit_codes::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
                 }
             }
         }
     }
     exit_no_fallback(ui, on_unsupported, result, use_detailed_exit_code)
 }
 
 fn exit_no_fallback(
     ui: &Ui,
     on_unsupported: OnUnsupported,
     result: Result<(), CommandError>,
     use_detailed_exit_code: bool,
 ) -> ! {
     match &result {
         Ok(_) => {}
         Err(CommandError::Unsuccessful) => {}
         Err(CommandError::Abort {
             message,
             detailed_exit_code: _,
         }) => {
             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"{}\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, use_detailed_exit_code))
 }
 
 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
     status
 }
 
 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>>,
     /// Value of the `--cwd` argument, if any.
     cwd: 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;
         let mut cwd = None;
         // Use `while let` instead of `for` so that we can also call
         // `args.next()` inside the loop.
         while let Some(arg) = args.next() {
             if arg == b"--config" {
                 if let Some(value) = args.next() {
                     config.push(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--config=") {
                 config.push(value.to_owned())
             }
 
             if arg == b"--cwd" {
                 if let Some(value) = args.next() {
                     cwd = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--cwd=") {
                 cwd = Some(value.to_owned())
             }
 
             if arg == b"--repository" || arg == b"-R" {
                 if let Some(value) = args.next() {
                     repo = Some(value)
                 }
             } else if let Some(value) = arg.drop_prefix(b"--repository=") {
                 repo = Some(value.to_owned())
             } else if let Some(value) = arg.drop_prefix(b"-R") {
                 repo = Some(value.to_owned())
             }
         }
         Self { config, repo, cwd }
     }
 }
 
 /// What to do when encountering some unsupported feature.
 ///
 /// See `HgError::UnsupportedFeature` and `CommandError::UnsupportedFeature`.
 enum OnUnsupported {
     /// Print an error message describing what feature is not supported,
     /// and exit with code 252.
     Abort,
     /// Silently exit with code 252.
     AbortSilent,
     /// Try running a Python implementation
     Fallback { executable: Vec<u8> },
 }
 
 impl OnUnsupported {
     const DEFAULT: Self = OnUnsupported::Abort;
 
     fn from_config(ui: &Ui, 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_else(|| {
                         exit_no_fallback(
                             ui,
                             Self::Abort,
                             Err(CommandError::abort(
                                 "abort: 'rhg.on-unsupported=fallback' without \
                                 'rhg.fallback-executable' set."
                             )),
                             false,
                         )
                     })
                     .to_owned(),
             },
             None => Self::DEFAULT,
             Some(_) => {
                 // TODO: warn about unknown config value
                 Self::DEFAULT
             }
         }
     }
 }
 
 const SUPPORTED_EXTENSIONS: &[&[u8]] = &[b"blackbox", b"share"];
 
 fn check_extensions(config: &Config) -> Result<(), CommandError> {
     let enabled = config.get_section_keys(b"extensions");
 
     let mut unsupported = enabled;
     for supported in SUPPORTED_EXTENSIONS {
         unsupported.remove(supported);
     }
 
     if let Some(ignored_list) = config.get_list(b"rhg", b"ignored-extensions")
     {
         for ignored in ignored_list {
             unsupported.remove(ignored.as_slice());
         }
     }
 
     if unsupported.is_empty() {
         Ok(())
     } else {
         Err(CommandError::UnsupportedFeature {
             message: format_bytes!(
                 b"extensions: {} (consider adding them to 'rhg.ignored-extensions' config)",
                 join(unsupported, b", ")
             ),
         })
     }
 }
 
 fn check_unsupported(config: &Config) -> Result<(), CommandError> {
     check_extensions(config)?;
 
     if std::env::var_os("HG_PENDING").is_some() {
         // TODO: only if the value is `== repo.working_directory`?
         // What about relative v.s. absolute paths?
         Err(CommandError::unsupported("$HG_PENDING"))?
     }
 
+    if config.has_non_empty_section(b"encode") {
+        Err(CommandError::unsupported("[encode] config"))?
+    }
+
+    if config.has_non_empty_section(b"decode") {
+        Err(CommandError::unsupported("[decode] config"))?
+    }
+
     Ok(())
 }

tests/test-encode.t

@@ -1,76 +1,72 b''
-TODO: fix rhg bugs that make this test fail when status is enabled
-  $ unset RHG_STATUS
-
-
 Test encode/decode filters
 
   $ hg init
   $ cat > .hg/hgrc <<EOF
   > [encode]
   > not.gz = tr [:lower:] [:upper:]
   > *.gz = gzip -d
   > [decode]
   > not.gz = tr [:upper:] [:lower:]
   > *.gz = gzip
   > EOF
   $ echo "this is a test" | gzip > a.gz
   $ echo "this is a test" > not.gz
   $ hg add *
   $ hg ci -m "test"
 
 no changes
 
   $ hg status
   $ touch *
 
 no changes
 
   $ hg status
 
 check contents in repo are encoded
 
   $ hg debugdata a.gz 0
   this is a test
   $ hg debugdata not.gz 0
   THIS IS A TEST
 
 check committed content was decoded
 
   $ gunzip < a.gz
   this is a test
   $ cat not.gz
   this is a test
   $ rm *
   $ hg co -C
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 check decoding of our new working dir copy
 
   $ gunzip < a.gz
   this is a test
   $ cat not.gz
   this is a test
 
 check hg cat operation
 
   $ hg cat a.gz
   this is a test
   $ hg cat --decode a.gz | gunzip
   this is a test
   $ mkdir subdir
   $ cd subdir
   $ hg -R .. cat ../a.gz
   this is a test
   $ hg -R .. cat --decode ../a.gz | gunzip
   this is a test
   $ cd ..
 
 check tempfile filter
 
   $ hg cat a.gz --decode --config 'decode.*.gz=tempfile:gzip -c INFILE > OUTFILE' | gunzip
   this is a test
   $ hg cat a.gz --decode --config 'decode.*.gz=tempfile:sh -c "exit 1"'
   abort: command '*' failed: exited with status 1 (glob)
   [255]
 
   $ cd ..