rust: Add a log file rotation utility

This is ported to Rust from `mercurial/loggingutil.py`.

The "builder" pattern is used to make it visible at call sites what the two
numeric parameters mean. In Python they might simply by keyword arguments.

Differential Revision: https://phab.mercurial-scm.org/D10010

rust/hg-core/src/logging.rs

@@ -0,0 +1,101 b''
+use crate::errors::{HgError, HgResultExt, IoErrorContext, IoResultExt};
+use crate::repo::Vfs;
+use std::io::Write;
+
+/// An utility to append to a log file with the given name, and optionally
+/// rotate it after it reaches a certain maximum size.
+///
+/// Rotation works by renaming "example.log" to "example.log.1", after renaming
+/// "example.log.1" to "example.log.2" etc up to the given maximum number of
+/// files.
+pub struct LogFile<'a> {
+    vfs: Vfs<'a>,
+    name: &'a str,
+    max_size: Option<u64>,
+    max_files: u32,
+}
+
+impl<'a> LogFile<'a> {
+    pub fn new(vfs: Vfs<'a>, name: &'a str) -> Self {
+        Self {
+            vfs,
+            name,
+            max_size: None,
+            max_files: 0,
+        }
+    }
+
+    /// Rotate before writing to a log file that was already larger than the
+    /// given size, in bytes. `None` disables rotation.
+    pub fn max_size(mut self, value: Option<u64>) -> Self {
+        self.max_size = value;
+        self
+    }
+
+    /// Keep this many rotated files `{name}.1` up to `{name}.{max}`, in
+    /// addition to the original `{name}` file.
+    pub fn max_files(mut self, value: u32) -> Self {
+        self.max_files = value;
+        self
+    }
+
+    /// Append the given `bytes` as-is to the log file, after rotating if
+    /// needed.
+    ///
+    /// No trailing newline is added. Make sure to include one in `bytes` if
+    /// desired.
+    pub fn write(&self, bytes: &[u8]) -> Result<(), HgError> {
+        let path = self.vfs.join(self.name);
+        let context = || IoErrorContext::WritingFile(path.clone());
+        let open = || {
+            std::fs::OpenOptions::new()
+                .create(true)
+                .append(true)
+                .open(&path)
+                .with_context(context)
+        };
+        let mut file = open()?;
+        if let Some(max_size) = self.max_size {
+            if file.metadata().with_context(context)?.len() >= max_size {
+                // For example with `max_files == 5`, the first iteration of
+                // this loop has `i == 4` and renames `{name}.4` to `{name}.5`.
+                // The last iteration renames `{name}.1` to
+                // `{name}.2`
+                for i in (1..self.max_files).rev() {
+                    self.vfs
+                        .rename(
+                            format!("{}.{}", self.name, i),
+                            format!("{}.{}", self.name, i + 1),
+                        )
+                        .io_not_found_as_none()?;
+                }
+                // Then rename `{name}` to `{name}.1`. This is the
+                // previously-opened `file`.
+                self.vfs
+                    .rename(self.name, format!("{}.1", self.name))
+                    .io_not_found_as_none()?;
+                // Finally, create a new `{name}` file and replace our `file`
+                // handle.
+                file = open()?;
+            }
+        }
+        file.write_all(bytes).with_context(context)?;
+        file.sync_all().with_context(context)
+    }
+}
+
+#[test]
+fn test_rotation() {
+    let temp = tempfile::tempdir().unwrap();
+    let vfs = Vfs { base: temp.path() };
+    let logger = LogFile::new(vfs, "log").max_size(Some(3)).max_files(2);
+    logger.write(b"one\n").unwrap();
+    logger.write(b"two\n").unwrap();
+    logger.write(b"3\n").unwrap();
+    logger.write(b"four\n").unwrap();
+    logger.write(b"five\n").unwrap();
+    assert_eq!(vfs.read("log").unwrap(), b"five\n");
+    assert_eq!(vfs.read("log.1").unwrap(), b"3\nfour\n");
+    assert_eq!(vfs.read("log.2").unwrap(), b"two\n");
+    assert!(vfs.read("log.3").io_not_found_as_none().unwrap().is_none());
+}

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

@@ -1,437 +1,438 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 crate::config::layer::{
     ConfigError, ConfigLayer, ConfigOrigin, ConfigValue,
 };
 use crate::utils::files::get_bytes_from_os_str;
 use format_bytes::{write_bytes, DisplayBytes};
 use std::env;
 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
 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,
 }
 
 pub fn parse_bool(v: &[u8]) -> Option<bool> {
     match v.to_ascii_lowercase().as_slice() {
         b"1" | b"yes" | b"true" | b"on" | b"always" => Some(true),
         b"0" | b"no" | b"false" | b"off" | b"never" => Some(false),
         _ => None,
     }
 }
 
 pub fn parse_byte_size(value: &[u8]) -> Option<u64> {
     let value = str::from_utf8(value).ok()?.to_ascii_lowercase();
     const UNITS: &[(&str, u64)] = &[
         ("g", 1 << 30),
         ("gb", 1 << 30),
         ("m", 1 << 20),
         ("mb", 1 << 20),
         ("k", 1 << 10),
         ("kb", 1 << 10),
         ("b", 1 << 0), // Needs to be last
     ];
     for &(unit, multiplier) in UNITS {
         // TODO: use `value.strip_suffix(unit)` when we require Rust 1.45+
         if value.ends_with(unit) {
             let value_before_unit = &value[..value.len() - unit.len()];
             let float: f64 = value_before_unit.trim().parse().ok()?;
             if float >= 0.0 {
                 return Some((float * multiplier as f64).round() as u64);
             } else {
                 return None;
             }
         }
     }
     value.parse().ok()
 }
 
 impl Config {
     /// Load system and user configuration from various files.
     ///
     /// This is also affected by some environment variables.
     pub fn load(
         cli_config_args: impl IntoIterator<Item = impl AsRef<[u8]>>,
     ) -> 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");
         // 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)?
                     }
                 }
             }
         }
         if let Some(layer) = ConfigLayer::parse_cli_args(cli_config_args)? {
             config.layers.push(layer)
         }
         Ok(config)
     }
 
     fn add_trusted_dir(&mut self, path: &Path) -> Result<(), ConfigError> {
         if let Some(entries) = std::fs::read_dir(path)
-            .for_file(path)
+            .when_reading_file(path)
             .io_not_found_as_none()?
         {
             for entry in entries {
-                let file_path = entry.for_file(path)?.path();
+                let file_path = entry.when_reading_file(path)?.path();
                 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).for_file(path).io_not_found_as_none()?
+        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", 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", 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))
     }
 
     /// 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
     }
 
     /// 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

@@ -1,291 +1,292 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 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).for_file(&filename)?;
+                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 {
                 return Err(ConfigParseError {
                     origin: ConfigOrigin::File(src.to_owned()),
                     line: Some(index + 1),
                     bytes: bytes.to_owned(),
                 }
                 .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>,
 }
 
 #[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

@@ -1,161 +1,192 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, derive_more::From)]
+#[derive(Debug)]
 pub enum IoErrorContext {
-    /// A filesystem operation for the given file
-    #[from]
-    File(std::path::PathBuf),
+    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)
             }
             HgError::CorruptedRepository(explanation) => {
                 write!(f, "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::File(path) => path.display().fmt(f),
-            IoErrorContext::CurrentDir => f.write_str("current directory"),
-            IoErrorContext::CurrentExe => f.write_str("current executable"),
+            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"),
         }
     }
 }
 
 pub trait IoResultExt<T> {
-    /// Annotate a possible I/O error as related to a file at the given path.
+    /// 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: example.txt”
-    /// instead of just “File not found”.
+    /// 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 for_file(self, path: &std::path::Path) -> Result<T, 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 for_file(self, path: &std::path::Path) -> Result<T, HgError> {
+    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: IoErrorContext::File(path.to_owned()),
+            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/hg-core/src/lib.rs

@@ -1,120 +1,121 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 mod ancestors;
 pub mod dagops;
 pub mod errors;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 mod dirstate;
 pub mod discovery;
 pub mod requirements;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     dirstate_map::DirstateMap,
     parsers::{pack_dirstate, parse_dirstate, PARENT_SIZE},
     status::{
         status, BadMatch, BadType, DirstateStatus, StatusError, StatusOptions,
     },
     CopyMap, CopyMapIter, DirstateEntry, DirstateParents, EntryState,
     StateMap, StateMapIter,
 };
 pub mod copy_tracing;
 mod filepatterns;
 pub mod matchers;
 pub mod repo;
 pub mod revlog;
 pub use revlog::*;
 pub mod config;
+pub mod logging;
 pub mod operations;
 pub mod revset;
 pub mod utils;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
     parse_pattern_syntax, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use std::fmt;
 use twox_hash::RandomXxHashBuilder64;
 
 /// This is a contract between the `micro-timer` crate and us, to expose
 /// the `log` crate as `crate::log`.
 use log;
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     InvalidPath(HgPathError),
 }
 
 impl fmt::Display for DirstateMapError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 f.write_str("expected a value, found none")
             }
             DirstateMapError::EmptyPath => {
                 f.write_str("Overflow in dirstate.")
             }
             DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum DirstateError {
     Map(DirstateMapError),
     Common(errors::HgError),
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum PatternError {
     #[from]
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     #[from]
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
 }
 
 impl fmt::Display for PatternError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 write!(f, "Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 write!(
                     f,
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 write!(f, "matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(error) => error.fmt(f),
             PatternError::Path(error) => error.fmt(f),
             PatternError::NonRegexPattern(pattern) => {
                 write!(f, "'{:?}' cannot be turned into a regex", pattern)
             }
         }
     }
 }

rust/hg-core/src/repo.rs

@@ -1,242 +1,254 b''
 use crate::config::{Config, ConfigError, ConfigParseError};
-use crate::errors::{HgError, IoResultExt};
+use crate::errors::{HgError, IoErrorContext, IoResultExt};
 use crate::requirements;
 use crate::utils::current_dir;
 use crate::utils::files::get_path_from_bytes;
 use memmap::{Mmap, MmapOptions};
 use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 
 /// A repository on disk
 pub struct Repo {
     working_directory: PathBuf,
     dot_hg: PathBuf,
     store: PathBuf,
     requirements: HashSet<String>,
     config: Config,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum RepoError {
     NotFound {
         at: PathBuf,
     },
     #[from]
     ConfigParseError(ConfigParseError),
     #[from]
     Other(HgError),
 }
 
 impl From<ConfigError> for RepoError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 /// Filesystem access abstraction for the contents of a given "base" diretory
 #[derive(Clone, Copy)]
-pub(crate) struct Vfs<'a> {
-    base: &'a Path,
+pub struct Vfs<'a> {
+    pub(crate) base: &'a Path,
 }
 
 impl Repo {
     /// Find a repository, either at the given path (which must contain a `.hg`
     /// sub-directory) or by searching the current directory and its
     /// ancestors.
     ///
     /// A method with two very different "modes" like this usually a code smell
     /// to make two methods instead, but in this case an `Option` is what rhg
     /// sub-commands get from Clap for the `-R` / `--repository` CLI argument.
     /// Having two methods would just move that `if` to almost all callers.
     pub fn find(
         config: &Config,
         explicit_path: Option<&Path>,
     ) -> Result<Self, RepoError> {
         if let Some(root) = explicit_path {
             // Having an absolute path isn’t necessary here but can help code
             // elsewhere
             let root = current_dir()?.join(root);
             if root.join(".hg").is_dir() {
                 Self::new_at_path(root, config)
             } else {
                 Err(RepoError::NotFound {
                     at: root.to_owned(),
                 })
             }
         } else {
             let current_directory = crate::utils::current_dir()?;
             // ancestors() is inclusive: it first yields `current_directory`
             // as-is.
             for ancestor in current_directory.ancestors() {
                 if ancestor.join(".hg").is_dir() {
                     return Self::new_at_path(ancestor.to_owned(), config);
                 }
             }
             Err(RepoError::NotFound {
                 at: current_directory,
             })
         }
     }
 
     /// To be called after checking that `.hg` is a sub-directory
     fn new_at_path(
         working_directory: PathBuf,
         config: &Config,
     ) -> Result<Self, RepoError> {
         let dot_hg = working_directory.join(".hg");
 
         let mut repo_config_files = Vec::new();
         repo_config_files.push(dot_hg.join("hgrc"));
         repo_config_files.push(dot_hg.join("hgrc-not-shared"));
 
         let hg_vfs = Vfs { base: &dot_hg };
         let mut reqs = requirements::load_if_exists(hg_vfs)?;
         let relative =
             reqs.contains(requirements::RELATIVE_SHARED_REQUIREMENT);
         let shared =
             reqs.contains(requirements::SHARED_REQUIREMENT) || relative;
 
         // From `mercurial/localrepo.py`:
         //
         // if .hg/requires contains the sharesafe requirement, it means
         // there exists a `.hg/store/requires` too and we should read it
         // NOTE: presence of SHARESAFE_REQUIREMENT imply that store requirement
         // is present. We never write SHARESAFE_REQUIREMENT for a repo if store
         // is not present, refer checkrequirementscompat() for that
         //
         // However, if SHARESAFE_REQUIREMENT is not present, it means that the
         // repository was shared the old way. We check the share source
         // .hg/requires for SHARESAFE_REQUIREMENT to detect whether the
         // current repository needs to be reshared
         let share_safe = reqs.contains(requirements::SHARESAFE_REQUIREMENT);
 
         let store_path;
         if !shared {
             store_path = dot_hg.join("store");
             if share_safe {
                 reqs.extend(requirements::load(Vfs { base: &store_path })?);
             }
         } else {
             let bytes = hg_vfs.read("sharedpath")?;
             let mut shared_path = get_path_from_bytes(&bytes).to_owned();
             if relative {
                 shared_path = dot_hg.join(shared_path)
             }
             if !shared_path.is_dir() {
                 return Err(HgError::corrupted(format!(
                     ".hg/sharedpath points to nonexistent directory {}",
                     shared_path.display()
                 ))
                 .into());
             }
 
             store_path = shared_path.join("store");
 
             let source_is_share_safe =
                 requirements::load(Vfs { base: &shared_path })?
                     .contains(requirements::SHARESAFE_REQUIREMENT);
 
             if share_safe && !source_is_share_safe {
                 return Err(match config
                     .get(b"safe-mismatch", b"source-not-safe")
                 {
                     Some(b"abort") | None => HgError::abort(
                         "share source does not support share-safe requirement",
                     ),
                     _ => HgError::unsupported("share-safe downgrade"),
                 }
                 .into());
             } else if source_is_share_safe && !share_safe {
                 return Err(
                     match config.get(b"safe-mismatch", b"source-safe") {
                         Some(b"abort") | None => HgError::abort(
                             "version mismatch: source uses share-safe \
                             functionality while the current share does not",
                         ),
                         _ => HgError::unsupported("share-safe upgrade"),
                     }
                     .into(),
                 );
             }
 
             if share_safe {
                 repo_config_files.insert(0, shared_path.join("hgrc"))
             }
         }
 
         let repo_config = config.combine_with_repo(&repo_config_files)?;
 
         let repo = Self {
             requirements: reqs,
             working_directory,
             store: store_path,
             dot_hg,
             config: repo_config,
         };
 
         requirements::check(&repo)?;
 
         Ok(repo)
     }
 
     pub fn working_directory_path(&self) -> &Path {
         &self.working_directory
     }
 
     pub fn requirements(&self) -> &HashSet<String> {
         &self.requirements
     }
 
     pub fn config(&self) -> &Config {
         &self.config
     }
 
     /// For accessing repository files (in `.hg`), except for the store
     /// (`.hg/store`).
-    pub(crate) fn hg_vfs(&self) -> Vfs<'_> {
+    pub fn hg_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.dot_hg }
     }
 
     /// For accessing repository store files (in `.hg/store`)
-    pub(crate) fn store_vfs(&self) -> Vfs<'_> {
+    pub fn store_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.store }
     }
 
     /// For accessing the working copy
 
     // The undescore prefix silences the "never used" warning. Remove before
     // using.
-    pub(crate) fn _working_directory_vfs(&self) -> Vfs<'_> {
+    pub fn _working_directory_vfs(&self) -> Vfs<'_> {
         Vfs {
             base: &self.working_directory,
         }
     }
 }
 
 impl Vfs<'_> {
-    pub(crate) fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
+    pub fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
         self.base.join(relative_path)
     }
 
-    pub(crate) fn read(
+    pub fn read(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Vec<u8>, HgError> {
         let path = self.join(relative_path);
-        std::fs::read(&path).for_file(&path)
+        std::fs::read(&path).when_reading_file(&path)
     }
 
-    pub(crate) fn mmap_open(
+    pub fn mmap_open(
         &self,
         relative_path: impl AsRef<Path>,
     ) -> Result<Mmap, HgError> {
         let path = self.base.join(relative_path);
-        let file = std::fs::File::open(&path).for_file(&path)?;
+        let file = std::fs::File::open(&path).when_reading_file(&path)?;
         // TODO: what are the safety requirements here?
-        let mmap = unsafe { MmapOptions::new().map(&file) }.for_file(&path)?;
+        let mmap = unsafe { MmapOptions::new().map(&file) }
+            .when_reading_file(&path)?;
         Ok(mmap)
     }
+
+    pub fn rename(
+        &self,
+        relative_from: impl AsRef<Path>,
+        relative_to: impl AsRef<Path>,
+    ) -> Result<(), HgError> {
+        let from = self.join(relative_from);
+        let to = self.join(relative_to);
+        std::fs::rename(&from, &to)
+            .with_context(|| IoErrorContext::RenamingFile { from, to })
+    }
 }