rhg: Add support for environment variables in config include paths

Some tests rely on this.

Differential Revision: https://phab.mercurial-scm.org/D10140

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

@@ -1,310 +1,311
 // 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::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),
                 )))?
             }
         }
         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))
     }
 
     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));
                 let data = std::fs::read(&filename).map_err(|io_error| {
                     ConfigParseError {
                         origin: ConfigOrigin::File(src.to_owned()),
                         line,
                         message: format_bytes!(
                             b"cannot include {} ({})",
                             filename_bytes,
                             format_bytes::Utf8(io_error)
                         ),
                     }
                 })?;
                 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, 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/hg-core/src/utils.rs

@@ -1,430 +1,483
 // utils module
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Contains useful functions, traits, structs, etc. for use in core.
 
 use crate::errors::{HgError, IoErrorContext};
 use crate::utils::hg_path::HgPath;
 use im_rc::ordmap::DiffItem;
 use im_rc::ordmap::OrdMap;
 use std::cell::Cell;
 use std::fmt;
 use std::{io::Write, ops::Deref};
 
 pub mod files;
 pub mod hg_path;
 pub mod path_auditor;
 
 /// Useful until rust/issues/56345 is stable
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::find_slice_in_slice;
 ///
 /// let haystack = b"This is the haystack".to_vec();
 /// assert_eq!(find_slice_in_slice(&haystack, b"the"), Some(8));
 /// assert_eq!(find_slice_in_slice(&haystack, b"not here"), None);
 /// ```
 pub fn find_slice_in_slice<T>(slice: &[T], needle: &[T]) -> Option<usize>
 where
     for<'a> &'a [T]: PartialEq,
 {
     slice
         .windows(needle.len())
         .position(|window| window == needle)
 }
 
 /// Replaces the `from` slice with the `to` slice inside the `buf` slice.
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::replace_slice;
 /// let mut line = b"I hate writing tests!".to_vec();
 /// replace_slice(&mut line, b"hate", b"love");
 /// assert_eq!(
 ///     line,
 ///     b"I love writing tests!".to_vec()
 /// );
 /// ```
 pub fn replace_slice<T>(buf: &mut [T], from: &[T], to: &[T])
 where
     T: Clone + PartialEq,
 {
     if buf.len() < from.len() || from.len() != to.len() {
         return;
     }
     for i in 0..=buf.len() - from.len() {
         if buf[i..].starts_with(from) {
             buf[i..(i + from.len())].clone_from_slice(to);
         }
     }
 }
 
 pub trait SliceExt {
     fn trim_end_newlines(&self) -> &Self;
     fn trim_end(&self) -> &Self;
     fn trim_start(&self) -> &Self;
     fn trim(&self) -> &Self;
     fn drop_prefix(&self, needle: &Self) -> Option<&Self>;
     fn split_2(&self, separator: u8) -> Option<(&[u8], &[u8])>;
 }
 
 #[allow(clippy::trivially_copy_pass_by_ref)]
 fn is_not_whitespace(c: &u8) -> bool {
     !(*c as char).is_whitespace()
 }
 
 impl SliceExt for [u8] {
     fn trim_end_newlines(&self) -> &[u8] {
         if let Some(last) = self.iter().rposition(|&byte| byte != b'\n') {
             &self[..=last]
         } else {
             &[]
         }
     }
     fn trim_end(&self) -> &[u8] {
         if let Some(last) = self.iter().rposition(is_not_whitespace) {
             &self[..=last]
         } else {
             &[]
         }
     }
     fn trim_start(&self) -> &[u8] {
         if let Some(first) = self.iter().position(is_not_whitespace) {
             &self[first..]
         } else {
             &[]
         }
     }
 
     /// ```
     /// use hg::utils::SliceExt;
     /// assert_eq!(
     ///     b"  to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"  to trim".trim(),
     ///     b"to trim"
     /// );
     /// ```
     fn trim(&self) -> &[u8] {
         self.trim_start().trim_end()
     }
 
     fn drop_prefix(&self, needle: &Self) -> Option<&Self> {
         if self.starts_with(needle) {
             Some(&self[needle.len()..])
         } else {
             None
         }
     }
 
     fn split_2(&self, separator: u8) -> Option<(&[u8], &[u8])> {
         let mut iter = self.splitn(2, |&byte| byte == separator);
         let a = iter.next()?;
         let b = iter.next()?;
         Some((a, b))
     }
 }
 
 pub trait Escaped {
     /// Return bytes escaped for display to the user
     fn escaped_bytes(&self) -> Vec<u8>;
 }
 
 impl Escaped for u8 {
     fn escaped_bytes(&self) -> Vec<u8> {
         let mut acc = vec![];
         match self {
             c @ b'\'' | c @ b'\\' => {
                 acc.push(b'\\');
                 acc.push(*c);
             }
             b'\t' => {
                 acc.extend(br"\\t");
             }
             b'\n' => {
                 acc.extend(br"\\n");
             }
             b'\r' => {
                 acc.extend(br"\\r");
             }
             c if (*c < b' ' || *c >= 127) => {
                 write!(acc, "\\x{:x}", self).unwrap();
             }
             c => {
                 acc.push(*c);
             }
         }
         acc
     }
 }
 
 impl<'a, T: Escaped> Escaped for &'a [T] {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.iter().flat_map(Escaped::escaped_bytes).collect()
     }
 }
 
 impl<T: Escaped> Escaped for Vec<T> {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.deref().escaped_bytes()
     }
 }
 
 impl<'a> Escaped for &'a HgPath {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.as_bytes().escaped_bytes()
     }
 }
 
 // TODO: use the str method when we require Rust 1.45
 pub(crate) fn strip_suffix<'a>(s: &'a str, suffix: &str) -> Option<&'a str> {
     if s.ends_with(suffix) {
         Some(&s[..s.len() - suffix.len()])
     } else {
         None
     }
 }
 
 #[cfg(unix)]
 pub fn shell_quote(value: &[u8]) -> Vec<u8> {
     // TODO: Use the `matches!` macro when we require Rust 1.42+
     if value.iter().all(|&byte| match byte {
         b'a'..=b'z'
         | b'A'..=b'Z'
         | b'0'..=b'9'
         | b'.'
         | b'_'
         | b'/'
         | b'+'
         | b'-' => true,
         _ => false,
     }) {
         value.to_owned()
     } else {
         let mut quoted = Vec::with_capacity(value.len() + 2);
         quoted.push(b'\'');
         for &byte in value {
             if byte == b'\'' {
                 quoted.push(b'\\');
             }
             quoted.push(byte);
         }
         quoted.push(b'\'');
         quoted
     }
 }
 
 pub fn current_dir() -> Result<std::path::PathBuf, HgError> {
     std::env::current_dir().map_err(|error| HgError::IoError {
         error,
         context: IoErrorContext::CurrentDir,
     })
 }
 
 pub fn current_exe() -> Result<std::path::PathBuf, HgError> {
     std::env::current_exe().map_err(|error| HgError::IoError {
         error,
         context: IoErrorContext::CurrentExe,
     })
 }
 
+/// Expand `$FOO` and `${FOO}` environment variables in the given byte string
+pub fn expand_vars(s: &[u8]) -> std::borrow::Cow<[u8]> {
+    lazy_static::lazy_static! {
+        /// https://github.com/python/cpython/blob/3.9/Lib/posixpath.py#L301
+        /// The `x` makes whitespace ignored.
+        /// `-u` disables the Unicode flag, which makes `\w` like Python with the ASCII flag.
+        static ref VAR_RE: regex::bytes::Regex =
+            regex::bytes::Regex::new(r"(?x-u)
+                \$
+                (?:
+                    (\w+)
+                    |
+                    \{
+                        ([^}]*)
+                    \}
+                )
+            ").unwrap();
+    }
+    VAR_RE.replace_all(s, |captures: &regex::bytes::Captures| {
+        let var_name = files::get_os_str_from_bytes(
+            captures
+                .get(1)
+                .or_else(|| captures.get(2))
+                .expect("either side of `|` must participate in match")
+                .as_bytes(),
+        );
+        std::env::var_os(var_name)
+            .map(files::get_bytes_from_os_str)
+            .unwrap_or_else(|| {
+                // Referencing an environment variable that does not exist.
+                // Leave the $FOO reference as-is.
+                captures[0].to_owned()
+            })
+    })
+}
+
+#[test]
+fn test_expand_vars() {
+    // Modifying process-global state in a test isn’t great,
+    // but hopefully this won’t collide with anything.
+    std::env::set_var("TEST_EXPAND_VAR", "1");
+    assert_eq!(
+        expand_vars(b"before/$TEST_EXPAND_VAR/after"),
+        &b"before/1/after"[..]
+    );
+    assert_eq!(
+        expand_vars(b"before${TEST_EXPAND_VAR}${TEST_EXPAND_VAR}${TEST_EXPAND_VAR}after"),
+        &b"before111after"[..]
+    );
+    let s = b"before $SOME_LONG_NAME_THAT_WE_ASSUME_IS_NOT_AN_ACTUAL_ENV_VAR after";
+    assert_eq!(expand_vars(s), &s[..]);
+}
+
 pub(crate) enum MergeResult<V> {
     UseLeftValue,
     UseRightValue,
     UseNewValue(V),
 }
 
 /// Return the union of the two given maps,
 /// calling `merge(key, left_value, right_value)` to resolve keys that exist in
 /// both.
 ///
 /// CC https://github.com/bodil/im-rs/issues/166
 pub(crate) fn ordmap_union_with_merge<K, V>(
     left: OrdMap<K, V>,
     right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone + PartialEq,
 {
     if left.ptr_eq(&right) {
         // One of the two maps is an unmodified clone of the other
         left
     } else if left.len() / 2 > right.len() {
         // When two maps have different sizes,
         // their size difference is a lower bound on
         // how many keys of the larger map are not also in the smaller map.
         // This in turn is a lower bound on the number of differences in
         // `OrdMap::diff` and the "amount of work" that would be done
         // by `ordmap_union_with_merge_by_diff`.
         //
         // Here `left` is more than twice the size of `right`,
         // so the number of differences is more than the total size of
         // `right`. Therefore an algorithm based on iterating `right`
         // is more efficient.
         //
         // This helps a lot when a tiny (or empty) map is merged
         // with a large one.
         ordmap_union_with_merge_by_iter(left, right, merge)
     } else if left.len() < right.len() / 2 {
         // Same as above but with `left` and `right` swapped
         ordmap_union_with_merge_by_iter(right, left, |key, a, b| {
             // Also swapped in `merge` arguments:
             match merge(key, b, a) {
                 MergeResult::UseNewValue(v) => MergeResult::UseNewValue(v),
                 // … and swap back in `merge` result:
                 MergeResult::UseLeftValue => MergeResult::UseRightValue,
                 MergeResult::UseRightValue => MergeResult::UseLeftValue,
             }
         })
     } else {
         // For maps of similar size, use the algorithm based on `OrdMap::diff`
         ordmap_union_with_merge_by_diff(left, right, merge)
     }
 }
 
 /// Efficient if `right` is much smaller than `left`
 fn ordmap_union_with_merge_by_iter<K, V>(
     mut left: OrdMap<K, V>,
     right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone,
 {
     for (key, right_value) in right {
         match left.get(&key) {
             None => {
                 left.insert(key, right_value);
             }
             Some(left_value) => match merge(&key, left_value, &right_value) {
                 MergeResult::UseLeftValue => {}
                 MergeResult::UseRightValue => {
                     left.insert(key, right_value);
                 }
                 MergeResult::UseNewValue(new_value) => {
                     left.insert(key, new_value);
                 }
             },
         }
     }
     left
 }
 
 /// Fallback when both maps are of similar size
 fn ordmap_union_with_merge_by_diff<K, V>(
     mut left: OrdMap<K, V>,
     mut right: OrdMap<K, V>,
     mut merge: impl FnMut(&K, &V, &V) -> MergeResult<V>,
 ) -> OrdMap<K, V>
 where
     K: Clone + Ord,
     V: Clone + PartialEq,
 {
     // (key, value) pairs that would need to be inserted in either map
     // in order to turn it into the union.
     //
     // TODO: if/when https://github.com/bodil/im-rs/pull/168 is accepted,
     // change these from `Vec<(K, V)>` to `Vec<(&K, Cow<V>)>`
     // with `left_updates` only borrowing from `right` and `right_updates` from
     // `left`, and with `Cow::Owned` used for `MergeResult::UseNewValue`.
     //
     // This would allow moving all `.clone()` calls to after we’ve decided
     // which of `right_updates` or `left_updates` to use
     // (value ones becoming `Cow::into_owned`),
     // and avoid making clones we don’t end up using.
     let mut left_updates = Vec::new();
     let mut right_updates = Vec::new();
 
     for difference in left.diff(&right) {
         match difference {
             DiffItem::Add(key, value) => {
                 left_updates.push((key.clone(), value.clone()))
             }
             DiffItem::Remove(key, value) => {
                 right_updates.push((key.clone(), value.clone()))
             }
             DiffItem::Update {
                 old: (key, left_value),
                 new: (_, right_value),
             } => match merge(key, left_value, right_value) {
                 MergeResult::UseLeftValue => {
                     right_updates.push((key.clone(), left_value.clone()))
                 }
                 MergeResult::UseRightValue => {
                     left_updates.push((key.clone(), right_value.clone()))
                 }
                 MergeResult::UseNewValue(new_value) => {
                     left_updates.push((key.clone(), new_value.clone()));
                     right_updates.push((key.clone(), new_value))
                 }
             },
         }
     }
     if left_updates.len() < right_updates.len() {
         for (key, value) in left_updates {
             left.insert(key, value);
         }
         left
     } else {
         for (key, value) in right_updates {
             right.insert(key, value);
         }
         right
     }
 }
 
 /// Join items of the iterable with the given separator, similar to Python’s
 /// `separator.join(iter)`.
 ///
 /// Formatting the return value consumes the iterator.
 /// Formatting it again will produce an empty string.
 pub fn join_display(
     iter: impl IntoIterator<Item = impl fmt::Display>,
     separator: impl fmt::Display,
 ) -> impl fmt::Display {
     JoinDisplay {
         iter: Cell::new(Some(iter.into_iter())),
         separator,
     }
 }
 
 struct JoinDisplay<I, S> {
     iter: Cell<Option<I>>,
     separator: S,
 }
 
 impl<I, T, S> fmt::Display for JoinDisplay<I, S>
 where
     I: Iterator<Item = T>,
     T: fmt::Display,
     S: fmt::Display,
 {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         if let Some(mut iter) = self.iter.take() {
             if let Some(first) = iter.next() {
                 first.fmt(f)?;
             }
             for value in iter {
                 self.separator.fmt(f)?;
                 value.fmt(f)?;
             }
         }
         Ok(())
     }
 }

rust/hg-core/src/utils/files.rs

@@ -1,448 +1,451
 // files.rs
 //
 // Copyright 2019
 // Raphaël Gomès <[e-mail]>,
 // Yuya Nishihara <[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.
 
 //! Functions for fiddling with files.
 
 use crate::utils::{
     hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
     path_auditor::PathAuditor,
     replace_slice,
 };
 use lazy_static::lazy_static;
 use same_file::is_same_file;
 use std::borrow::{Cow, ToOwned};
 use std::ffi::OsStr;
 use std::fs::Metadata;
 use std::iter::FusedIterator;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
-pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
+pub fn get_os_str_from_bytes(bytes: &[u8]) -> &OsStr {
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(bytes);
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     // Perhaps, the return type would have to be Result<PathBuf>.
+    os_str
+}
 
-    Path::new(os_str)
+pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
+    Path::new(get_os_str_from_bytes(bytes))
 }
 
 // TODO: need to convert from WTF8 to MBCS bytes on Windows.
 // that's why Vec<u8> is returned.
 #[cfg(unix)]
 pub fn get_bytes_from_path(path: impl AsRef<Path>) -> Vec<u8> {
     get_bytes_from_os_str(path.as_ref())
 }
 
 #[cfg(unix)]
 pub fn get_bytes_from_os_str(str: impl AsRef<OsStr>) -> Vec<u8> {
     use std::os::unix::ffi::OsStrExt;
     str.as_ref().as_bytes().to_vec()
 }
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub struct Ancestors<'a> {
     next: Option<&'a HgPath>,
 }
 
 impl<'a> Iterator for Ancestors<'a> {
     type Item = &'a HgPath;
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some(s) if s.is_empty() => None,
             Some(s) => {
                 let p = s.bytes().rposition(|c| *c == b'/').unwrap_or(0);
                 Some(HgPath::new(&s.as_bytes()[..p]))
             }
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for Ancestors<'a> {}
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub(crate) struct AncestorsWithBase<'a> {
     next: Option<(&'a HgPath, &'a HgPath)>,
 }
 
 impl<'a> Iterator for AncestorsWithBase<'a> {
     type Item = (&'a HgPath, &'a HgPath);
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some((s, _)) if s.is_empty() => None,
             Some((s, _)) => Some(s.split_filename()),
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for AncestorsWithBase<'a> {}
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub fn find_dirs(path: &HgPath) -> Ancestors {
     let mut dirs = Ancestors { next: Some(path) };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub(crate) fn find_dirs_with_base(path: &HgPath) -> AncestorsWithBase {
     let mut dirs = AncestorsWithBase {
         next: Some((path, HgPath::new(b""))),
     };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// TODO more than ASCII?
 pub fn normalize_case(path: &HgPath) -> HgPathBuf {
     #[cfg(windows)] // NTFS compares via upper()
     return path.to_ascii_uppercase();
     #[cfg(unix)]
     path.to_ascii_lowercase()
 }
 
 lazy_static! {
     static ref IGNORED_CHARS: Vec<Vec<u8>> = {
         [
             0x200c, 0x200d, 0x200e, 0x200f, 0x202a, 0x202b, 0x202c, 0x202d,
             0x202e, 0x206a, 0x206b, 0x206c, 0x206d, 0x206e, 0x206f, 0xfeff,
         ]
         .iter()
         .map(|code| {
             std::char::from_u32(*code)
                 .unwrap()
                 .encode_utf8(&mut [0; 3])
                 .bytes()
                 .collect()
         })
         .collect()
     };
 }
 
 fn hfs_ignore_clean(bytes: &[u8]) -> Vec<u8> {
     let mut buf = bytes.to_owned();
     let needs_escaping = bytes.iter().any(|b| *b == b'\xe2' || *b == b'\xef');
     if needs_escaping {
         for forbidden in IGNORED_CHARS.iter() {
             replace_slice(&mut buf, forbidden, &[])
         }
         buf
     } else {
         buf
     }
 }
 
 pub fn lower_clean(bytes: &[u8]) -> Vec<u8> {
     hfs_ignore_clean(&bytes.to_ascii_lowercase())
 }
 
 #[derive(Eq, PartialEq, Ord, PartialOrd, Copy, Clone)]
 pub struct HgMetadata {
     pub st_dev: u64,
     pub st_mode: u32,
     pub st_nlink: u64,
     pub st_size: u64,
     pub st_mtime: i64,
     pub st_ctime: i64,
 }
 
 // TODO support other plaforms
 #[cfg(unix)]
 impl HgMetadata {
     pub fn from_metadata(metadata: Metadata) -> Self {
         use std::os::unix::fs::MetadataExt;
         Self {
             st_dev: metadata.dev(),
             st_mode: metadata.mode(),
             st_nlink: metadata.nlink(),
             st_size: metadata.size(),
             st_mtime: metadata.mtime(),
             st_ctime: metadata.ctime(),
         }
     }
 }
 
 /// Returns the canonical path of `name`, given `cwd` and `root`
 pub fn canonical_path(
     root: impl AsRef<Path>,
     cwd: impl AsRef<Path>,
     name: impl AsRef<Path>,
 ) -> Result<PathBuf, HgPathError> {
     // TODO add missing normalization for other platforms
     let root = root.as_ref();
     let cwd = cwd.as_ref();
     let name = name.as_ref();
 
     let name = if !name.is_absolute() {
         root.join(&cwd).join(&name)
     } else {
         name.to_owned()
     };
     let auditor = PathAuditor::new(&root);
     if name != root && name.starts_with(&root) {
         let name = name.strip_prefix(&root).unwrap();
         auditor.audit_path(path_to_hg_path_buf(name)?)?;
         Ok(name.to_owned())
     } else if name == root {
         Ok("".into())
     } else {
         // Determine whether `name' is in the hierarchy at or beneath `root',
         // by iterating name=name.parent() until it returns `None` (can't
         // check name == '/', because that doesn't work on windows).
         let mut name = name.deref();
         let original_name = name.to_owned();
         loop {
             let same = is_same_file(&name, &root).unwrap_or(false);
             if same {
                 if name == original_name {
                     // `name` was actually the same as root (maybe a symlink)
                     return Ok("".into());
                 }
                 // `name` is a symlink to root, so `original_name` is under
                 // root
                 let rel_path = original_name.strip_prefix(&name).unwrap();
                 auditor.audit_path(path_to_hg_path_buf(&rel_path)?)?;
                 return Ok(rel_path.to_owned());
             }
             name = match name.parent() {
                 None => break,
                 Some(p) => p,
             };
         }
         // TODO hint to the user about using --cwd
         // Bubble up the responsibility to Python for now
         Err(HgPathError::NotUnderRoot {
             path: original_name.to_owned(),
             root: root.to_owned(),
         })
     }
 }
 
 /// Returns the representation of the path relative to the current working
 /// directory for display purposes.
 ///
 /// `cwd` is a `HgPath`, so it is considered relative to the root directory
 /// of the repository.
 ///
 /// # Examples
 ///
 /// ```
 /// use hg::utils::hg_path::HgPath;
 /// use hg::utils::files::relativize_path;
 /// use std::borrow::Cow;
 ///
 /// let file = HgPath::new(b"nested/file");
 /// let cwd = HgPath::new(b"");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"nested/file"));
 ///
 /// let cwd = HgPath::new(b"nested");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"file"));
 ///
 /// let cwd = HgPath::new(b"other");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"../nested/file"));
 /// ```
 pub fn relativize_path(path: &HgPath, cwd: impl AsRef<HgPath>) -> Cow<[u8]> {
     if cwd.as_ref().is_empty() {
         Cow::Borrowed(path.as_bytes())
     } else {
         let mut res: Vec<u8> = Vec::new();
         let mut path_iter = path.as_bytes().split(|b| *b == b'/').peekable();
         let mut cwd_iter =
             cwd.as_ref().as_bytes().split(|b| *b == b'/').peekable();
         loop {
             match (path_iter.peek(), cwd_iter.peek()) {
                 (Some(a), Some(b)) if a == b => (),
                 _ => break,
             }
             path_iter.next();
             cwd_iter.next();
         }
         let mut need_sep = false;
         for _ in cwd_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(b"..");
         }
         for c in path_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(c);
         }
         Cow::Owned(res)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
         let mut dirs = super::find_dirs(HgPath::new(b"foo/bar/baz"));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo/bar")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn find_dirs_empty() {
         // looks weird, but mercurial.pathutil.finddirs(b"") yields b""
         let mut dirs = super::find_dirs(HgPath::new(b""));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_some() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b"foo/bar/baz"));
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo/bar"), HgPath::new(b"baz")))
         );
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo"), HgPath::new(b"bar")))
         );
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b"foo"))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_empty() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b""));
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b""))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_canonical_path() {
         let root = Path::new("/repo");
         let cwd = Path::new("/dir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/dir/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("repo/filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo/subdir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("subdir/filename"))
         );
     }
 
     #[test]
     fn test_canonical_path_not_rooted() {
         use std::fs::create_dir;
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let beneath_repo = base_dir_path.join("a");
         let root = base_dir_path.join("a/b");
         let out_of_repo = base_dir_path.join("c");
         let under_repo_symlink = out_of_repo.join("d");
 
         create_dir(&beneath_repo).unwrap();
         create_dir(&root).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
 
         assert_eq!(
             canonical_path(&root, Path::new(""), out_of_repo),
             Ok(PathBuf::from(""))
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &beneath_repo),
             Err(HgPathError::NotUnderRoot {
                 path: beneath_repo.to_owned(),
                 root: root.to_owned()
             })
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &under_repo_symlink),
             Ok(PathBuf::from("d"))
         );
     }
 }