( )⚙ D7582 hg-core: run rustfmt on configparser

This is an archive of the discontinued Mercurial Phabricator instance.

Differential D7582

hg-core: run rustfmt on configparser
AcceptedPublic

Authored by indygreg on Dec 7 2019, 5:57 PM.

Details

Reviewers
Alphare
durin42
Group Reviewers
hg-reviewers
Summary

The vendored code doesn't follow modern rustfmt's conventions.
This commit runs rustfmt so it does.

  1. skip-blame rustfmt

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Event Timeline

indygreg created this revision.Dec 7 2019, 5:57 PM
quark added a subscriber: quark.Dec 7 2019, 6:32 PM

We actually ran rustfmt, but it's an older version (rustfmt 1.3.0-stable (d334502 2019-06-09)) and I verified the code still formats under that particular version of rustfmt with empty rustfmt.toml. In other words, rustfmt itself seems to change over time.

indygreg edited parent revisions, added: D7575: hg-core: vendor Facebook's configparser crate; removed: D7581: rust-configparser: regenerate parser.rs.Dec 7 2019, 10:03 PM
indygreg retitled this revision from rust-configparser: run rustfmt to hg-core: run rustfmt on configparser.
indygreg edited the summary of this revision. (Show Details)
indygreg added a child revision: D7576: hg-core: add configparser to library.
indygreg removed a child revision: D7577: hg-core: implement Mercurial's config file discovery logic.
indygreg updated this revision to Diff 18546.
Alphare accepted this revision.Dec 9 2019, 8:16 AM
durin42 accepted this revision.Dec 11 2019, 12:45 PM
This revision is now accepted and ready to land.Dec 11 2019, 12:45 PM

Revision Contents
Changeset List

Diff 18546

rust/hg-core/src/configparser/c_api.rs

/* /*
* Copyright (c) Facebook, Inc. and its affiliates. * Copyright (c) Facebook, Inc. and its affiliates.
* *
* This software may be used and distributed according to the terms of the * This software may be used and distributed according to the terms of the
* GNU General Public License version 2. * GNU General Public License version 2.
*/ */
//! This module exports some symbols to allow calling the config parser from C/C++ //! This module exports some symbols to allow calling the config parser from
//! C/C++
use std::ffi::{CStr, OsStr}; use std::ffi::{CStr, OsStr};
use std::os::raw::c_char; use std::os::raw::c_char;
use std::path::Path; use std::path::Path;
use std::ptr; use std::ptr;
use std::slice; use std::slice;
use bytes::Bytes; use bytes::Bytes;
} }
/// Attempt to load and parse the config file at the specified path. /// Attempt to load and parse the config file at the specified path.
/// If successful, returns a nullptr. /// If successful, returns a nullptr.
/// Returns a Bytes object containing the error reason on failure; the /// Returns a Bytes object containing the error reason on failure; the
/// error object is UTF-8 encoded text, and errors can span multiple lines. /// error object is UTF-8 encoded text, and errors can span multiple lines.
#[cfg(unix)] #[cfg(unix)]
#[no_mangle] #[no_mangle]
pub extern "C" fn hgrc_configset_load_path(cfg: *mut ConfigSet, path: *const c_char) -> *mut Bytes { pub extern "C" fn hgrc_configset_load_path(
cfg: *mut ConfigSet,
path: *const c_char,
) -> *mut Bytes {
debug_assert!(!path.is_null()); debug_assert!(!path.is_null());
debug_assert!(!cfg.is_null()); debug_assert!(!cfg.is_null());
use std::os::unix::ffi::OsStrExt; use std::os::unix::ffi::OsStrExt;
let path_cstr = unsafe { CStr::from_ptr(path) }; let path_cstr = unsafe { CStr::from_ptr(path) };
let path_bytes = path_cstr.to_bytes(); let path_bytes = path_cstr.to_bytes();
let path = Path::new(OsStr::from_bytes(&path_bytes)); let path = Path::new(OsStr::from_bytes(&path_bytes));
let cfg = unsafe { &mut *cfg }; let cfg = unsafe { &mut *cfg };
load_path(cfg, path) load_path(cfg, path)
} }
/// Load system config files /// Load system config files
#[no_mangle] #[no_mangle]
pub extern "C" fn hgrc_configset_load_system(cfg: *mut ConfigSet) -> *mut Bytes { pub extern "C" fn hgrc_configset_load_system(
cfg: *mut ConfigSet,
) -> *mut Bytes {
debug_assert!(!cfg.is_null()); debug_assert!(!cfg.is_null());
let cfg = unsafe { &mut *cfg }; let cfg = unsafe { &mut *cfg };
// Forces datapath to be the empty string as it doesn't // Forces datapath to be the empty string as it doesn't
// appear to play a useful role in simply resolving config // appear to play a useful role in simply resolving config
// settings for Eden. // settings for Eden.
errors_to_bytes(cfg.load_system()) errors_to_bytes(cfg.load_system())
} }
/// Load user config files /// Load user config files
#[no_mangle] #[no_mangle]
pub extern "C" fn hgrc_configset_load_user(cfg: *mut ConfigSet) -> *mut Bytes { pub extern "C" fn hgrc_configset_load_user(cfg: *mut ConfigSet) -> *mut Bytes {
debug_assert!(!cfg.is_null()); debug_assert!(!cfg.is_null());
let cfg = unsafe { &mut *cfg }; let cfg = unsafe { &mut *cfg };
errors_to_bytes(cfg.load_user()) errors_to_bytes(cfg.load_user())
} }
/// Returns a Bytes object holding the configuration value for the corresponding /// Returns a Bytes object holding the configuration value for the
/// section name and key. If there is no matching section/key pair, returns nullptr. /// corresponding section name and key. If there is no matching section/key
/// pair, returns nullptr.
#[no_mangle] #[no_mangle]
pub extern "C" fn hgrc_configset_get( pub extern "C" fn hgrc_configset_get(
cfg: *const ConfigSet, cfg: *const ConfigSet,
section: *const u8, section: *const u8,
section_len: usize, section_len: usize,
name: *const u8, name: *const u8,
name_len: usize, name_len: usize,
) -> *mut Bytes { ) -> *mut Bytes {
} }
#[repr(C)] #[repr(C)]
pub struct ByteData { pub struct ByteData {
ptr: *const u8, ptr: *const u8,
len: usize, len: usize,
} }
/// Returns the data pointer and length for a Bytes object, suitable for constructing /// Returns the data pointer and length for a Bytes object, suitable for
/// a folly::ByteRange. /// constructing a folly::ByteRange.
#[no_mangle] #[no_mangle]
pub extern "C" fn hgrc_bytes_data(bytes: *const Bytes) -> ByteData { pub extern "C" fn hgrc_bytes_data(bytes: *const Bytes) -> ByteData {
debug_assert!(!bytes.is_null()); debug_assert!(!bytes.is_null());
let bytes = unsafe { &*bytes }; let bytes = unsafe { &*bytes };
ByteData { ByteData {
ptr: bytes.as_ptr(), ptr: bytes.as_ptr(),
len: bytes.len(), len: bytes.len(),
} }

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

struct Section { struct Section {
items: IndexMap<Bytes, Vec<ValueSource>>, items: IndexMap<Bytes, Vec<ValueSource>>,
} }
/// A config value with associated metadata like where it comes from. /// A config value with associated metadata like where it comes from.
#[derive(Clone, Debug)] #[derive(Clone, Debug)]
pub struct ValueSource { pub struct ValueSource {
value: Option<Bytes>, value: Option<Bytes>,
source: Bytes, // global, user, repo, "--config", or an extension name, etc. source: Bytes, /* global, user, repo, "--config", or an extension name,
* etc. */
location: Option<ValueLocation>, location: Option<ValueLocation>,
} }
/// The on-disk file name and byte offsets that provide the config value. /// The on-disk file name and byte offsets that provide the config value.
/// Useful if applications want to edit config values in-place. /// Useful if applications want to edit config values in-place.
#[derive(Clone, Debug)] #[derive(Clone, Debug)]
struct ValueLocation { struct ValueLocation {
path: Arc<PathBuf>, path: Arc<PathBuf>,
content: Bytes, content: Bytes,
location: Range<usize>, location: Range<usize>,
} }
/// Options that affects config setting functions like `load_path`, `parse`, /// Options that affects config setting functions like `load_path`, `parse`,
/// and `set`. /// and `set`.
#[derive(Default)] #[derive(Default)]
pub struct Options { pub struct Options {
source: Bytes, source: Bytes,
filters: Vec<Box<dyn Fn(Bytes, Bytes, Option<Bytes>) -> Option<(Bytes, Bytes, Option<Bytes>)>>>, filters: Vec<
Box<
dyn Fn(
Bytes,
Bytes,
Option<Bytes>,
) -> Option<(Bytes, Bytes, Option<Bytes>)>,
>,
>,
} }
impl ConfigSet { impl ConfigSet {
/// Return an empty `ConfigSet`. /// Return an empty `ConfigSet`.
pub fn new() -> Self { pub fn new() -> Self {
Default::default() Default::default()
} }
/// Load config files at given path. The path is a file. /// Load config files at given path. The path is a file.
/// ///
/// If `path` is a directory, it is ignored. /// If `path` is a directory, it is ignored.
/// If `path` is a file, it will be loaded directly. /// If `path` is a file, it will be loaded directly.
/// ///
/// A config file can use `%include` to load other paths (directories or files). They will /// A config file can use `%include` to load other paths (directories or
/// be loaded recursively. Includes take effect in place, instead of deferred. For example, /// files). They will be loaded recursively. Includes take effect in
/// with the following two files: /// place, instead of deferred. For example, with the following two
/// files:
/// ///
/// ```plain,ignore /// ```plain,ignore
/// # This is 1.rc /// # This is 1.rc
/// [section] /// [section]
/// x = 1 /// x = 1
/// %include 2.rc /// %include 2.rc
/// y = 2 /// y = 2
/// ///
/// # This is 2.rc /// # This is 2.rc
/// [section] /// [section]
/// x = 3 /// x = 3
/// y = 4 /// y = 4
/// ``` /// ```
/// ///
/// After loading `1.rc`. `x` is set to 3 and `y` is set to 2. /// After loading `1.rc`. `x` is set to 3 and `y` is set to 2.
/// ///
/// Loading a file that is already parsed or being parsed by this `load_path` call is ignored, /// Loading a file that is already parsed or being parsed by this
/// to avoid infinite loop. A separate `load_path` call would not ignore files loaded by /// `load_path` call is ignored, to avoid infinite loop. A separate
/// other `load_path` calls. /// `load_path` call would not ignore files loaded by other `load_path`
/// /// calls.
/// Return a list of errors. An error pasing a file will stop that file from loading, without ///
/// affecting other files. /// Return a list of errors. An error pasing a file will stop that file
pub fn load_path<P: AsRef<Path>>(&mut self, path: P, opts: &Options) -> Vec<Error> { /// from loading, without affecting other files.
pub fn load_path<P: AsRef<Path>>(
&mut self,
path: P,
opts: &Options,
) -> Vec<Error> {
let mut visited = HashSet::new(); let mut visited = HashSet::new();
let mut errors = Vec::new(); let mut errors = Vec::new();
self.load_file(path.as_ref(), opts, &mut visited, &mut errors); self.load_file(path.as_ref(), opts, &mut visited, &mut errors);
errors errors
} }
/// Load content of an unnamed config file. The `ValueLocation`s of loaded config items will /// Load content of an unnamed config file. The `ValueLocation`s of loaded
/// have an empty `path`. /// config items will have an empty `path`.
/// ///
/// Return a list of errors. /// Return a list of errors.
pub fn parse<B: Into<Bytes>>(&mut self, content: B, opts: &Options) -> Vec<Error> { pub fn parse<B: Into<Bytes>>(
&mut self,
content: B,
opts: &Options,
) -> Vec<Error> {
let mut visited = HashSet::new(); let mut visited = HashSet::new();
let mut errors = Vec::new(); let mut errors = Vec::new();
let buf = content.into(); let buf = content.into();
self.load_file_content(Path::new(""), buf, opts, &mut visited, &mut errors); self.load_file_content(
Path::new(""),
buf,
opts,
&mut visited,
&mut errors,
);
errors errors
} }
/// Get config sections. /// Get config sections.
pub fn sections(&self) -> Vec<Bytes> { pub fn sections(&self) -> Vec<Bytes> {
self.sections.keys().cloned().collect() self.sections.keys().cloned().collect()
} }
/// Get config names in the given section. Sorted by insertion order. /// Get config names in the given section. Sorted by insertion order.
pub fn keys<S: Into<Bytes>>(&self, section: S) -> Vec<Bytes> { pub fn keys<S: Into<Bytes>>(&self, section: S) -> Vec<Bytes> {
self.sections self.sections
.get(&section.into()) .get(&section.into())
.map(|section| section.items.keys().cloned().collect()) .map(|section| section.items.keys().cloned().collect())
.unwrap_or(Vec::new()) .unwrap_or(Vec::new())
} }
/// Get config value for a given config. /// Get config value for a given config.
/// Return `None` if the config item does not exist or is unset. /// Return `None` if the config item does not exist or is unset.
pub fn get<S: Into<Bytes>, N: Into<Bytes>>(&self, section: S, name: N) -> Option<Bytes> { pub fn get<S: Into<Bytes>, N: Into<Bytes>>(
&self,
section: S,
name: N,
) -> Option<Bytes> {
self.sections.get(&section.into()).and_then(|section| { self.sections.get(&section.into()).and_then(|section| {
section section.items.get(&name.into()).and_then(|values| {
.items values.last().and_then(|value| value.value.clone())
.get(&name.into()) })
.and_then(|values| values.last().and_then(|value| value.value.clone()))
}) })
} }
/// Get detailed sources of a given config, including overrides, and source information. /// Get detailed sources of a given config, including overrides, and source
/// The last item in the returned vector is the latest value that is considered effective. /// information. The last item in the returned vector is the latest
/// value that is considered effective.
/// ///
/// Return an emtpy vector if the config does not exist. /// Return an emtpy vector if the config does not exist.
pub fn get_sources<S: Into<Bytes>, N: Into<Bytes>>( pub fn get_sources<S: Into<Bytes>, N: Into<Bytes>>(
&self, &self,
section: S, section: S,
name: N, name: N,
) -> Vec<ValueSource> { ) -> Vec<ValueSource> {
self.sections self.sections
.get(&section.into()) .get(&section.into())
.and_then(|section| section.items.get(&name.into()).map(|values| values.clone())) .and_then(|section| {
section.items.get(&name.into()).map(|values| values.clone())
})
.unwrap_or(Vec::new()) .unwrap_or(Vec::new())
} }
/// Set a config item directly. `section`, `name` locates the config. `value` is the new value. /// Set a config item directly. `section`, `name` locates the config.
/// `source` is some annotation about who set it, ex. "reporc", "userrc", "--config", etc. /// `value` is the new value. `source` is some annotation about who set
/// it, ex. "reporc", "userrc", "--config", etc.
pub fn set<T: Into<Bytes>, N: Into<Bytes>>( pub fn set<T: Into<Bytes>, N: Into<Bytes>>(
&mut self, &mut self,
section: T, section: T,
name: N, name: N,
value: Option<&[u8]>, value: Option<&[u8]>,
opts: &Options, opts: &Options,
) { ) {
let section = section.into(); let section = section.into();
let name = name.into(); let name = name.into();
let value = value.map(|v| Bytes::from(v)); let value = value.map(|v| Bytes::from(v));
self.set_internal(section, name, value, None, &opts) self.set_internal(section, name, value, None, &opts)
} }
fn set_internal( fn set_internal(
&mut self, &mut self,
section: Bytes, section: Bytes,
name: Bytes, name: Bytes,
value: Option<Bytes>, value: Option<Bytes>,
location: Option<ValueLocation>, location: Option<ValueLocation>,
opts: &Options, opts: &Options,
) { ) {
let filtered = opts let filtered = opts.filters.iter().fold(
.filters Some((section, name, value)),
.iter() move |acc, func| {
.fold(Some((section, name, value)), move |acc, func| { acc.and_then(|(section, name, value)| {
acc.and_then(|(section, name, value)| func(section, name, value)) func(section, name, value)
}); })
},
);
if let Some((section, name, value)) = filtered { if let Some((section, name, value)) = filtered {
self.sections self.sections
.entry(section) .entry(section)
.or_insert_with(|| Default::default()) .or_insert_with(|| Default::default())
.items .items
.entry(name) .entry(name)
.or_insert_with(|| Vec::with_capacity(1)) .or_insert_with(|| Vec::with_capacity(1))
.push(ValueSource { .push(ValueSource {
errors.push(Error::Io(path.to_path_buf(), error)); errors.push(Error::Io(path.to_path_buf(), error));
return; return;
} }
buf.push(b'\n'); buf.push(b'\n');
let buf = Bytes::from(buf); let buf = Bytes::from(buf);
self.load_file_content(path, buf, opts, visited, errors); self.load_file_content(path, buf, opts, visited, errors);
} }
Err(error) => errors.push(Error::Io(path.to_path_buf(), error)), Err(error) => {
errors.push(Error::Io(path.to_path_buf(), error))
}
} }
} else { } else {
// On Windows, a UNC path `\\?\C:\foo\.\x` will fail to canonicalize // On Windows, a UNC path `\\?\C:\foo\.\x` will fail to
// because it contains `.`. That path can be constructed by using // canonicalize because it contains `.`. That path can
// `PathBuf::join` to concatenate a UNC path `\\?\C:\foo` with // be constructed by using `PathBuf::join` to
// a "normal" path `.\x`. // concatenate a UNC path `\\?\C:\foo` with a "normal"
// Try to fix it automatically by stripping the UNC prefix and retry // path `.\x`. Try to fix it automatically by stripping
// `canonicalize`. `C:\foo\.\x` would be canonicalized without errors. // the UNC prefix and retry `canonicalize`.
// `C:\foo\.\x` would be canonicalized without errors.
#[cfg(windows)] #[cfg(windows)]
{ {
if let Some(path_str) = path.to_str() { if let Some(path_str) = path.to_str() {
if path_str.starts_with(r"\\?\") { if path_str.starts_with(r"\\?\") {
let path = Path::new(&path_str[4..]); let path = Path::new(&path_str[4..]);
self.load_file(&path, opts, visited, errors); self.load_file(&path, opts, visited, errors);
} }
} }
} }
} }
// If `path.canonicalize` reports an error. It's usually the path cannot // If `path.canonicalize` reports an error. It's usually the path
// be resolved (ex. does not exist). It is considered normal and is not // cannot be resolved (ex. does not exist). It is considered
// reported in `errors`. // normal and is not reported in `errors`.
} }
fn load_file_content( fn load_file_content(
&mut self, &mut self,
path: &Path, path: &Path,
buf: Bytes, buf: Bytes,
opts: &Options, opts: &Options,
visited: &mut HashSet<PathBuf>, visited: &mut HashSet<PathBuf>,
errors: &mut Vec<Error>, errors: &mut Vec<Error>,
) { ) {
let mut section = Bytes::new(); let mut section = Bytes::new();
let shared_path = Arc::new(path.to_path_buf()); // use Arc to do shallow copy let shared_path = Arc::new(path.to_path_buf()); // use Arc to do shallow copy
let skip_include = path.parent().is_none(); // skip handling %include if path is empty let skip_include = path.parent().is_none(); // skip handling %include if path is empty
// Utilities to avoid too much indentation. // Utilities to avoid too much indentation.
let handle_value = |this: &mut ConfigSet, let handle_value =
|this: &mut ConfigSet,
pair: Pair, pair: Pair,
section: Bytes, section: Bytes,
name: Bytes, name: Bytes,
location: ValueLocation| { location: ValueLocation| {
let pairs = pair.into_inner(); let pairs = pair.into_inner();
let mut lines = Vec::with_capacity(1); let mut lines = Vec::with_capacity(1);
for pair in pairs { for pair in pairs {
if Rule::line == pair.as_rule() { if Rule::line == pair.as_rule() {
lines.push(extract(&buf, pair.as_span())); lines.push(extract(&buf, pair.as_span()));
} }
} }
let value = match lines.len() { let value = match lines.len() {
1 => lines[0].clone(), 1 => lines[0].clone(),
_ => Bytes::from(lines.join(&b'\n')), _ => Bytes::from(lines.join(&b'\n')),
}; };
let (start, end) = strip_offsets(&value, 0, value.len()); let (start, end) = strip_offsets(&value, 0, value.len());
let value = value.slice(start, end); let value = value.slice(start, end);
this.set_internal(section, name, value.into(), location.into(), opts) this.set_internal(
section,
name,
value.into(),
location.into(),
opts,
)
}; };
let handle_config_item = |this: &mut ConfigSet, pair: Pair, section: Bytes| { let handle_config_item =
|this: &mut ConfigSet, pair: Pair, section: Bytes| {
let pairs = pair.into_inner(); let pairs = pair.into_inner();
let mut name = Bytes::new(); let mut name = Bytes::new();
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::config_name => name = extract(&buf, pair.as_span()), Rule::config_name => {
name = extract(&buf, pair.as_span())
}
Rule::value => { Rule::value => {
let span = pair.as_span(); let span = pair.as_span();
let location = ValueLocation { let location = ValueLocation {
path: shared_path.clone(), path: shared_path.clone(),
content: buf.clone(), content: buf.clone(),
location: span.start()..span.end(), location: span.start()..span.end(),
}; };
return handle_value(this, pair, section, name, location); return handle_value(
this, pair, section, name, location,
);
} }
_ => (), _ => (),
} }
} }
unreachable!(); unreachable!();
}; };
let handle_section = |pair: Pair, section: &mut Bytes| { let handle_section = |pair: Pair, section: &mut Bytes| {
let pairs = pair.into_inner(); let pairs = pair.into_inner();
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::section_name => { Rule::section_name => {
*section = extract(&buf, pair.as_span()); *section = extract(&buf, pair.as_span());
return; return;
} }
_ => (), _ => (),
} }
} }
unreachable!(); unreachable!();
}; };
let mut handle_include = |this: &mut ConfigSet, pair: Pair, errors: &mut Vec<Error>| { let mut handle_include =
|this: &mut ConfigSet, pair: Pair, errors: &mut Vec<Error>| {
let pairs = pair.into_inner(); let pairs = pair.into_inner();
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::line => { Rule::line => {
if !skip_include { if !skip_include {
let include_path = pair.as_str(); let include_path = pair.as_str();
let full_include_path = let full_include_path = path
path.parent().unwrap().join(expand_path(include_path)); .parent()
this.load_file(&full_include_path, opts, visited, errors); .unwrap()
.join(expand_path(include_path));
this.load_file(
&full_include_path,
opts,
visited,
errors,
);
} }
} }
_ => (), _ => (),
} }
} }
}; };
let handle_unset = |this: &mut ConfigSet, pair: Pair, section: &Bytes| { let handle_unset =
|this: &mut ConfigSet, pair: Pair, section: &Bytes| {
let unset_span = pair.as_span(); let unset_span = pair.as_span();
let pairs = pair.into_inner(); let pairs = pair.into_inner();
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::config_name => { Rule::config_name => {
let name = extract(&buf, pair.as_span()); let name = extract(&buf, pair.as_span());
let location = ValueLocation { let location = ValueLocation {
path: shared_path.clone(), path: shared_path.clone(),
content: buf.clone(), content: buf.clone(),
location: unset_span.start()..unset_span.end(), location: unset_span.start()..unset_span.end(),
}; };
return this.set_internal( return this.set_internal(
section.clone(), section.clone(),
name, name,
None, None,
location.into(), location.into(),
opts, opts,
); );
} }
_ => (), _ => (),
} }
} }
unreachable!(); unreachable!();
}; };
let mut handle_directive = let mut handle_directive =
|this: &mut ConfigSet, pair: Pair, section: &Bytes, errors: &mut Vec<Error>| { |this: &mut ConfigSet,
pair: Pair,
section: &Bytes,
errors: &mut Vec<Error>| {
let pairs = pair.into_inner(); let pairs = pair.into_inner();
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::include => handle_include(this, pair, errors), Rule::include => handle_include(this, pair, errors),
Rule::unset => handle_unset(this, pair, section), Rule::unset => handle_unset(this, pair, section),
_ => (), _ => (),
} }
} }
}; };
let text = match str::from_utf8(&buf) { let text = match str::from_utf8(&buf) {
Ok(text) => text, Ok(text) => text,
Err(error) => return errors.push(Error::Utf8(path.to_path_buf(), error)), Err(error) => {
return errors.push(Error::Utf8(path.to_path_buf(), error))
}
}; };
let pairs = match ConfigParser::parse(Rule::file, &text) { let pairs = match ConfigParser::parse(Rule::file, &text) {
Ok(pairs) => pairs, Ok(pairs) => pairs,
Err(error) => { Err(error) => {
return errors.push(Error::Parse(path.to_path_buf(), format!("{}", error))); return errors.push(Error::Parse(
path.to_path_buf(),
format!("{}", error),
));
} }
}; };
for pair in pairs { for pair in pairs {
match pair.as_rule() { match pair.as_rule() {
Rule::config_item => handle_config_item(self, pair, section.clone()), Rule::config_item => {
handle_config_item(self, pair, section.clone())
}
Rule::section => handle_section(pair, &mut section), Rule::section => handle_section(pair, &mut section),
Rule::directive => handle_directive(self, pair, &section, errors), Rule::directive => {
Rule::blank_line | Rule::comment_line | Rule::new_line | Rule::EOI => (), handle_directive(self, pair, &section, errors)
}
Rule::blank_line
| Rule::comment_line
| Rule::new_line
| Rule::EOI => (),
Rule::comment_start Rule::comment_start
| Rule::compound | Rule::compound
| Rule::config_name | Rule::config_name
| Rule::equal_sign | Rule::equal_sign
| Rule::file | Rule::file
| Rule::include | Rule::include
| Rule::left_bracket | Rule::left_bracket
} }
impl ValueSource { impl ValueSource {
/// Return the actual value stored in this config value, or `None` if uset. /// Return the actual value stored in this config value, or `None` if uset.
pub fn value(&self) -> &Option<Bytes> { pub fn value(&self) -> &Option<Bytes> {
&self.value &self.value
} }
/// Return the "source" information for the config value. It's usually who sets the config, /// Return the "source" information for the config value. It's usually who
/// like "--config", "user_hgrc", "system_hgrc", etc. /// sets the config, like "--config", "user_hgrc", "system_hgrc", etc.
pub fn source(&self) -> &Bytes { pub fn source(&self) -> &Bytes {
&self.source &self.source
} }
/// Return the file path and byte range for the exact config value, /// Return the file path and byte range for the exact config value,
/// or `None` if there is no such information. /// or `None` if there is no such information.
/// ///
/// If the value is `None`, the byte range is for the "%unset" statement. /// If the value is `None`, the byte range is for the "%unset" statement.
pub fn location(&self) -> Option<(PathBuf, Range<usize>)> { pub fn location(&self) -> Option<(PathBuf, Range<usize>)> {
match self.location { match self.location {
Some(ref src) => Some((src.path.as_ref().to_path_buf(), src.location.clone())), Some(ref src) => {
Some((src.path.as_ref().to_path_buf(), src.location.clone()))
}
None => None, None => None,
} }
} }
/// Return the file content. Or `None` if there is no such information. /// Return the file content. Or `None` if there is no such information.
pub fn file_content(&self) -> Option<Bytes> { pub fn file_content(&self) -> Option<Bytes> {
match self.location { match self.location {
Some(ref src) => Some(src.content.clone()), Some(ref src) => Some(src.content.clone()),
None => None, None => None,
} }
} }
} }
impl Options { impl Options {
/// Create a default `Options`. /// Create a default `Options`.
pub fn new() -> Self { pub fn new() -> Self {
Self::default() Self::default()
} }
/// Append a filter. A filter can decide to ignore a config item, or change its section, /// Append a filter. A filter can decide to ignore a config item, or change
/// config name, or even value. The filter function takes a tuple of `(section, name, value)` /// its section, config name, or even value. The filter function takes
/// and outputs `None` to prevent inserting that value, or `Some((section, name, value))` to /// a tuple of `(section, name, value)` and outputs `None` to prevent
/// inserting that value, or `Some((section, name, value))` to
/// insert it with optionally different name or values. /// insert it with optionally different name or values.
/// ///
/// Filters inserted first will be executed first. /// Filters inserted first will be executed first.
pub fn append_filter( pub fn append_filter(
mut self, mut self,
filter: Box<dyn Fn(Bytes, Bytes, Option<Bytes>) -> Option<(Bytes, Bytes, Option<Bytes>)>>, filter: Box<
dyn Fn(
Bytes,
Bytes,
Option<Bytes>,
) -> Option<(Bytes, Bytes, Option<Bytes>)>,
>,
) -> Self { ) -> Self {
self.filters.push(filter); self.filters.push(filter);
self self
} }
/// Set `source` information. It is about who initialized the config loading. For example, /// Set `source` information. It is about who initialized the config
/// "user_hgrc" indicates it is from the user config file, "--config" indicates it is from the /// loading. For example, "user_hgrc" indicates it is from the user
/// global "--config" command line flag, "env" indicates it is translated from an environment /// config file, "--config" indicates it is from the global "--config"
/// command line flag, "env" indicates it is translated from an environment
/// variable (ex. "PAGER"), etc. /// variable (ex. "PAGER"), etc.
pub fn source<B: Into<Bytes>>(mut self, source: B) -> Self { pub fn source<B: Into<Bytes>>(mut self, source: B) -> Self {
self.source = source.into(); self.source = source.into();
self self
} }
} }
/// Convert a "source" string to an `Options`. /// Convert a "source" string to an `Options`.
impl<S: Into<Bytes>> From<S> for Options { impl<S: Into<Bytes>> From<S> for Options {
fn from(source: S) -> Options { fn from(source: S) -> Options {
Options::new().source(source.into()) Options::new().source(source.into())
} }
} }
/// Remove space characters from both ends. Remove newline characters from the end. /// Remove space characters from both ends. Remove newline characters from the
/// `start` position is inclusive, `end` is exclusive. /// end. `start` position is inclusive, `end` is exclusive.
/// Return the stripped `start` and `end` offsets. /// Return the stripped `start` and `end` offsets.
#[inline] #[inline]
fn strip_offsets(buf: &Bytes, start: usize, end: usize) -> (usize, usize) { fn strip_offsets(buf: &Bytes, start: usize, end: usize) -> (usize, usize) {
let mut start = start; let mut start = start;
let mut end = end; let mut end = end;
while start < end && b" \t".contains(&buf[start]) { while start < end && b" \t".contains(&buf[start]) {
start += 1 start += 1
} }
// Will be loaded. Shouldn't cause cycles. // Will be loaded. Shouldn't cause cycles.
write_file(dir.path().join("e.rc"), "[x]\ne=e\n%include f.rc"); write_file(dir.path().join("e.rc"), "[x]\ne=e\n%include f.rc");
write_file( write_file(
dir.path().join("f.rc"), dir.path().join("f.rc"),
"[x]\nf=f\n%include e.rc\n%include rootrc", "[x]\nf=f\n%include e.rc\n%include rootrc",
); );
let mut cfg = ConfigSet::new(); let mut cfg = ConfigSet::new();
let errors = cfg.load_path(dir.path().join("rootrc"), &"test_parse_include".into()); let errors = cfg.load_path(
dir.path().join("rootrc"),
&"test_parse_include".into(),
);
assert!(errors.is_empty()); assert!(errors.is_empty());
assert_eq!(cfg.sections(), vec![Bytes::from("x"), Bytes::from("y")]); assert_eq!(cfg.sections(), vec![Bytes::from("x"), Bytes::from("y")]);
assert_eq!( assert_eq!(
cfg.keys("x"), cfg.keys("x"),
vec![ vec![
Bytes::from("b"), Bytes::from("b"),
Bytes::from("a"), Bytes::from("a"),
"%include ./${FOO}1/$FOO/3.rc\n\ "%include ./${FOO}1/$FOO/3.rc\n\
%include ./%FOO%2/%FOO%/4.rc\n", %include ./%FOO%2/%FOO%/4.rc\n",
); );
write_file(dir.path().join("f1/f/3.rc"), "[x]\na=1\n"); write_file(dir.path().join("f1/f/3.rc"), "[x]\na=1\n");
write_file(dir.path().join("f2/f/4.rc"), "[y]\nb=2\n"); write_file(dir.path().join("f2/f/4.rc"), "[y]\nb=2\n");
let mut cfg = ConfigSet::new(); let mut cfg = ConfigSet::new();
let errors = cfg.load_path(dir.path().join("rootrc"), &"include_expand".into()); let errors =
cfg.load_path(dir.path().join("rootrc"), &"include_expand".into());
assert!(errors.is_empty()); assert!(errors.is_empty());
assert_eq!(cfg.get("x", "a"), Some(Bytes::from("1"))); assert_eq!(cfg.get("x", "a"), Some(Bytes::from("1")));
assert_eq!(cfg.get("y", "b"), Some(Bytes::from("2"))); assert_eq!(cfg.get("y", "b"), Some(Bytes::from("2")));
} }
} }

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

pub const HGPLAIN: &str = "HGPLAIN"; pub const HGPLAIN: &str = "HGPLAIN";
pub const HGPLAINEXCEPT: &str = "HGPLAINEXCEPT"; pub const HGPLAINEXCEPT: &str = "HGPLAINEXCEPT";
pub const HGRCPATH: &str = "HGRCPATH"; pub const HGRCPATH: &str = "HGRCPATH";
pub trait OptionsHgExt { pub trait OptionsHgExt {
/// Drop configs according to `$HGPLAIN` and `$HGPLAINEXCEPT`. /// Drop configs according to `$HGPLAIN` and `$HGPLAINEXCEPT`.
fn process_hgplain(self) -> Self; fn process_hgplain(self) -> Self;
/// Set read-only config items. `items` contains a list of tuple `(section, name)`. /// Set read-only config items. `items` contains a list of tuple `(section,
/// Setting those items to new value will be ignored. /// name)`. Setting those items to new value will be ignored.
fn readonly_items<S: Into<Bytes>, N: Into<Bytes>>(self, items: Vec<(S, N)>) -> Self; fn readonly_items<S: Into<Bytes>, N: Into<Bytes>>(
self,
/// Set section remap. If a section name matches an entry key, it will be treated as if the items: Vec<(S, N)>,
/// name is the entry value. The remap wouldn't happen recursively. For example, with a ) -> Self;
/// `{"A": "B", "B": "C"}` map, section name "A" will be treated as "B", not "C".
/// Set section remap. If a section name matches an entry key, it will be
/// treated as if the name is the entry value. The remap wouldn't
/// happen recursively. For example, with a `{"A": "B", "B": "C"}` map,
/// section name "A" will be treated as "B", not "C".
/// This is implemented via `append_filter`. /// This is implemented via `append_filter`.
fn remap_sections<K: Eq + Hash + Into<Bytes>, V: Into<Bytes>>( fn remap_sections<K: Eq + Hash + Into<Bytes>, V: Into<Bytes>>(
self, self,
remap: HashMap<K, V>, remap: HashMap<K, V>,
) -> Self; ) -> Self;
/// Set section whitelist. Sections outside the whitelist won't be loaded. /// Set section whitelist. Sections outside the whitelist won't be loaded.
/// This is implemented via `append_filter`. /// This is implemented via `append_filter`.
fn whitelist_sections<B: Clone + Into<Bytes>>(self, sections: Vec<B>) -> Self; fn whitelist_sections<B: Clone + Into<Bytes>>(
self,
sections: Vec<B>,
) -> Self;
} }
pub trait ConfigSetHgExt { pub trait ConfigSetHgExt {
/// Load system config files if `$HGRCPATH` is not set. /// Load system config files if `$HGRCPATH` is not set.
/// Return errors parsing files. /// Return errors parsing files.
fn load_system(&mut self) -> Vec<Error>; fn load_system(&mut self) -> Vec<Error>;
/// Load user config files (and environment variables). If `$HGRCPATH` is /// Load user config files (and environment variables). If `$HGRCPATH` is
/// set, load files listed in that environment variable instead. /// set, load files listed in that environment variable instead.
/// Return errors parsing files. /// Return errors parsing files.
fn load_user(&mut self) -> Vec<Error>; fn load_user(&mut self) -> Vec<Error>;
/// Load a specified config file. Respect HGPLAIN environment variables. /// Load a specified config file. Respect HGPLAIN environment variables.
/// Return errors parsing files. /// Return errors parsing files.
fn load_hgrc(&mut self, path: impl AsRef<Path>, source: &'static str) -> Vec<Error>; fn load_hgrc(
&mut self,
path: impl AsRef<Path>,
source: &'static str,
) -> Vec<Error>;
/// Get a config item. Convert to type `T`. /// Get a config item. Convert to type `T`.
fn get_opt<T: FromConfigValue>(&self, section: &str, name: &str) -> Result<Option<T>>; fn get_opt<T: FromConfigValue>(
&self,
section: &str,
name: &str,
) -> Result<Option<T>>;
/// Get a config item. Convert to type `T`. /// Get a config item. Convert to type `T`.
/// ///
/// If the config item is not set, calculate it using `default_func`. /// If the config item is not set, calculate it using `default_func`.
fn get_or<T: FromConfigValue>( fn get_or<T: FromConfigValue>(
&self, &self,
section: &str, section: &str,
name: &str, name: &str,
default_func: impl Fn() -> T, default_func: impl Fn() -> T,
) -> Result<T> { ) -> Result<T> {
Ok(self.get_opt(section, name)?.unwrap_or_else(default_func)) Ok(self.get_opt(section, name)?.unwrap_or_else(default_func))
} }
/// Get a config item. Convert to type `T`. /// Get a config item. Convert to type `T`.
/// ///
/// If the config item is not set, return `T::default()`. /// If the config item is not set, return `T::default()`.
fn get_or_default<T: Default + FromConfigValue>(&self, section: &str, name: &str) -> Result<T> { fn get_or_default<T: Default + FromConfigValue>(
&self,
section: &str,
name: &str,
) -> Result<T> {
self.get_or(section, name, Default::default) self.get_or(section, name, Default::default)
} }
} }
pub trait FromConfigValue: Sized { pub trait FromConfigValue: Sized {
fn try_from_bytes(bytes: &[u8]) -> Result<Self>; fn try_from_bytes(bytes: &[u8]) -> Result<Self>;
} }
let plain_exceptions: HashSet<String> = plain_except let plain_exceptions: HashSet<String> = plain_except
.unwrap_or_else(|_| "".to_string()) .unwrap_or_else(|_| "".to_string())
.split(',') .split(',')
.map(|s| s.to_string()) .map(|s| s.to_string())
.collect(); .collect();
// [defaults] and [commands] are always blacklisted. // [defaults] and [commands] are always blacklisted.
let mut section_blacklist: HashSet<Bytes> = let mut section_blacklist: HashSet<Bytes> =
["defaults", "commands"].iter().map(|&s| s.into()).collect(); ["defaults", "commands"]
.iter()
.map(|&s| s.into())
.collect();
// [alias], [revsetalias], [templatealias] are blacklisted if they are outside // [alias], [revsetalias], [templatealias] are blacklisted if
// HGPLAINEXCEPT. // they are outside HGPLAINEXCEPT.
for &name in ["alias", "revsetalias", "templatealias"].iter() { for &name in ["alias", "revsetalias", "templatealias"].iter() {
if !plain_exceptions.contains(name) { if !plain_exceptions.contains(name) {
section_blacklist.insert(Bytes::from(name)); section_blacklist.insert(Bytes::from(name));
} }
} }
// These configs under [ui] are always blacklisted. // These configs under [ui] are always blacklisted.
let mut ui_blacklist: HashSet<Bytes> = [ let mut ui_blacklist: HashSet<Bytes> = [
"debug", "debug",
"fallbackencoding", "fallbackencoding",
"quiet", "quiet",
"slash", "slash",
"logtemplate", "logtemplate",
"statuscopies", "statuscopies",
"style", "style",
"traceback", "traceback",
"verbose", "verbose",
] ]
.iter() .iter()
.map(|&s| s.into()) .map(|&s| s.into())
.collect(); .collect();
// exitcodemask is blacklisted if exitcode is outside HGPLAINEXCEPT. // exitcodemask is blacklisted if exitcode is outside
// HGPLAINEXCEPT.
if !plain_exceptions.contains("exitcode") { if !plain_exceptions.contains("exitcode") {
ui_blacklist.insert("exitcodemask".into()); ui_blacklist.insert("exitcodemask".into());
} }
(section_blacklist, ui_blacklist) (section_blacklist, ui_blacklist)
}; };
let filter = move |section: Bytes, name: Bytes, value: Option<Bytes>| { let filter =
move |section: Bytes, name: Bytes, value: Option<Bytes>| {
if section_blacklist.contains(&section) if section_blacklist.contains(&section)
|| (section.as_ref() == b"ui" && ui_blacklist.contains(&name)) || (section.as_ref() == b"ui"
&& ui_blacklist.contains(&name))
{ {
None None
} else { } else {
Some((section, name, value)) Some((section, name, value))
} }
}; };
self.append_filter(Box::new(filter)) self.append_filter(Box::new(filter))
} else { } else {
self self
} }
} }
/// Set section whitelist. Sections outside the whitelist won't be loaded. /// Set section whitelist. Sections outside the whitelist won't be loaded.
/// This is implemented via `append_filter`. /// This is implemented via `append_filter`.
fn whitelist_sections<B: Clone + Into<Bytes>>(self, sections: Vec<B>) -> Self { fn whitelist_sections<B: Clone + Into<Bytes>>(
self,
sections: Vec<B>,
) -> Self {
let whitelist: HashSet<Bytes> = sections let whitelist: HashSet<Bytes> = sections
.iter() .iter()
.cloned() .cloned()
.map(|section| section.into()) .map(|section| section.into())
.collect(); .collect();
let filter = move |section: Bytes, name: Bytes, value: Option<Bytes>| { let filter =
move |section: Bytes, name: Bytes, value: Option<Bytes>| {
if whitelist.contains(&section) { if whitelist.contains(&section) {
Some((section, name, value)) Some((section, name, value))
} else { } else {
None None
} }
}; };
self.append_filter(Box::new(filter)) self.append_filter(Box::new(filter))
} }
/// Set section remap. If a section name matches an entry key, it will be treated as if the /// Set section remap. If a section name matches an entry key, it will be
/// name is the entry value. The remap wouldn't happen recursively. For example, with a /// treated as if the name is the entry value. The remap wouldn't
/// `{"A": "B", "B": "C"}` map, section name "A" will be treated as "B", not "C". /// happen recursively. For example, with a `{"A": "B", "B": "C"}` map,
/// section name "A" will be treated as "B", not "C".
/// This is implemented via `append_filter`. /// This is implemented via `append_filter`.
fn remap_sections<K, V>(self, remap: HashMap<K, V>) -> Self fn remap_sections<K, V>(self, remap: HashMap<K, V>) -> Self
where where
K: Eq + Hash + Into<Bytes>, K: Eq + Hash + Into<Bytes>,
V: Into<Bytes>, V: Into<Bytes>,
{ {
let remap: HashMap<Bytes, Bytes> = remap let remap: HashMap<Bytes, Bytes> = remap
.into_iter() .into_iter()
.map(|(k, v)| (k.into(), v.into())) .map(|(k, v)| (k.into(), v.into()))
.collect(); .collect();
let filter = move |section: Bytes, name: Bytes, value: Option<Bytes>| { let filter =
move |section: Bytes, name: Bytes, value: Option<Bytes>| {
let section = remap.get(&section).cloned().unwrap_or(section); let section = remap.get(&section).cloned().unwrap_or(section);
Some((section, name, value)) Some((section, name, value))
}; };
self.append_filter(Box::new(filter)) self.append_filter(Box::new(filter))
} }
fn readonly_items<S: Into<Bytes>, N: Into<Bytes>>(self, items: Vec<(S, N)>) -> Self { fn readonly_items<S: Into<Bytes>, N: Into<Bytes>>(
self,
items: Vec<(S, N)>,
) -> Self {
let readonly_items: HashSet<(Bytes, Bytes)> = items let readonly_items: HashSet<(Bytes, Bytes)> = items
.into_iter() .into_iter()
.map(|(section, name)| (section.into(), name.into())) .map(|(section, name)| (section.into(), name.into()))
.collect(); .collect();
let filter = move |section: Bytes, name: Bytes, value: Option<Bytes>| { let filter =
move |section: Bytes, name: Bytes, value: Option<Bytes>| {
if readonly_items.contains(&(section.clone(), name.clone())) { if readonly_items.contains(&(section.clone(), name.clone())) {
None None
} else { } else {
Some((section, name, value)) Some((section, name, value))
} }
}; };
self.append_filter(Box::new(filter)) self.append_filter(Box::new(filter))
} }
} }
impl ConfigSetHgExt for ConfigSet { impl ConfigSetHgExt for ConfigSet {
fn load_system(&mut self) -> Vec<Error> { fn load_system(&mut self) -> Vec<Error> {
let opts = Options::new().source("system").process_hgplain(); let opts = Options::new().source("system").process_hgplain();
let mut errors = Vec::new(); let mut errors = Vec::new();
if env::var(HGRCPATH).is_err() { if env::var(HGRCPATH).is_err() {
#[cfg(unix)] #[cfg(unix)]
{ {
errors.append(&mut self.load_path("/etc/mercurial/system.rc", &opts));
// TODO(T40519286): Remove this after the tupperware overrides move out of hgrc.d
errors.append( errors.append(
&mut self.load_path("/etc/mercurial/hgrc.d/tupperware_overrides.rc", &opts), &mut self.load_path("/etc/mercurial/system.rc", &opts),
);
// TODO(T40519286): Remove this after the tupperware overrides
// move out of hgrc.d
errors.append(&mut self.load_path(
"/etc/mercurial/hgrc.d/tupperware_overrides.rc",
&opts,
));
// TODO(quark): Remove this after packages using system.rc are
// rolled out
errors.append(
&mut self
.load_path("/etc/mercurial/hgrc.d/include.rc", &opts),
); );
// TODO(quark): Remove this after packages using system.rc are rolled out
errors.append(&mut self.load_path("/etc/mercurial/hgrc.d/include.rc", &opts));
} }
#[cfg(windows)] #[cfg(windows)]
{ {
if let Ok(program_data_path) = env::var("PROGRAMDATA") { if let Ok(program_data_path) = env::var("PROGRAMDATA") {
use std::path::Path; use std::path::Path;
let hgrc_dir = Path::new(&program_data_path).join("Facebook\\Mercurial"); let hgrc_dir = Path::new(&program_data_path)
errors.append(&mut self.load_path(hgrc_dir.join("system.rc"), &opts)); .join("Facebook\\Mercurial");
// TODO(quark): Remove this after packages using system.rc are rolled out errors.append(
errors.append(&mut self.load_path(hgrc_dir.join("hgrc"), &opts)); &mut self.load_path(hgrc_dir.join("system.rc"), &opts),
);
// TODO(quark): Remove this after packages using system.rc
// are rolled out
errors.append(
&mut self.load_path(hgrc_dir.join("hgrc"), &opts),
);
} }
} }
} }
errors errors
} }
fn load_user(&mut self) -> Vec<Error> { fn load_user(&mut self) -> Vec<Error> {
let paths = rcpath.split(':'); let paths = rcpath.split(':');
#[cfg(windows)] #[cfg(windows)]
let paths = rcpath.split(';'); let paths = rcpath.split(';');
for path in paths { for path in paths {
errors.append(&mut self.load_path(expand_path(path), &opts)); errors.append(&mut self.load_path(expand_path(path), &opts));
} }
} else { } else {
if let Some(home_dir) = dirs::home_dir() { if let Some(home_dir) = dirs::home_dir() {
errors.append(&mut self.load_path(home_dir.join(".hgrc"), &opts)); errors.append(
&mut self.load_path(home_dir.join(".hgrc"), &opts),
);
#[cfg(windows)] #[cfg(windows)]
{ {
errors.append(&mut self.load_path(home_dir.join("mercurial.ini"), &opts)); errors.append(
&mut self
.load_path(home_dir.join("mercurial.ini"), &opts),
);
} }
} }
if let Some(config_dir) = dirs::config_dir() { if let Some(config_dir) = dirs::config_dir() {
errors.append(&mut self.load_path(config_dir.join("hg/hgrc"), &opts)); errors.append(
&mut self.load_path(config_dir.join("hg/hgrc"), &opts),
);
} }
} }
errors errors
} }
fn load_hgrc(&mut self, path: impl AsRef<Path>, source: &'static str) -> Vec<Error> { fn load_hgrc(
&mut self,
path: impl AsRef<Path>,
source: &'static str,
) -> Vec<Error> {
let opts = Options::new().source(source).process_hgplain(); let opts = Options::new().source(source).process_hgplain();
self.load_path(path, &opts) self.load_path(path, &opts)
} }
fn get_opt<T: FromConfigValue>(&self, section: &str, name: &str) -> Result<Option<T>> { fn get_opt<T: FromConfigValue>(
&self,
section: &str,
name: &str,
) -> Result<Option<T>> {
ConfigSet::get(self, section, name) ConfigSet::get(self, section, name)
.map(|bytes| T::try_from_bytes(&bytes)) .map(|bytes| T::try_from_bytes(&bytes))
.transpose() .transpose()
} }
} }
impl FromConfigValue for bool { impl FromConfigValue for bool {
fn try_from_bytes(bytes: &[u8]) -> Result<Self> { fn try_from_bytes(bytes: &[u8]) -> Result<Self> {
let value = std::str::from_utf8(bytes)?.to_lowercase(); let value = std::str::from_utf8(bytes)?.to_lowercase();
match value.as_ref() { match value.as_ref() {
"1" | "yes" | "true" | "on" | "always" => Ok(true), "1" | "yes" | "true" | "on" | "always" => Ok(true),
"0" | "no" | "false" | "off" | "never" => Ok(false), "0" | "no" | "false" | "off" | "never" => Ok(false),
_ => Err(Error::Convert(format!("invalid bool: {}", value)).into()), _ => {
Err(Error::Convert(format!("invalid bool: {}", value)).into())
}
} }
} }
} }
impl FromConfigValue for i8 { impl FromConfigValue for i8 {
fn try_from_bytes(bytes: &[u8]) -> Result<Self> { fn try_from_bytes(bytes: &[u8]) -> Result<Self> {
let value = std::str::from_utf8(bytes)?.parse()?; let value = std::str::from_utf8(bytes)?.parse()?;
Ok(value) Ok(value)
fn try_from_bytes(bytes: &[u8]) -> Result<Self> { fn try_from_bytes(bytes: &[u8]) -> Result<Self> {
let value = std::str::from_utf8(bytes)?.parse()?; let value = std::str::from_utf8(bytes)?.parse()?;
Ok(value) Ok(value)
} }
} }
impl FromConfigValue for String { impl FromConfigValue for String {
fn try_from_bytes(bytes: &[u8]) -> Result<Self> { fn try_from_bytes(bytes: &[u8]) -> Result<Self> {
String::from_utf8(bytes.to_vec()) String::from_utf8(bytes.to_vec()).map_err(|_| {
.map_err(|_| Error::Convert(format!("{:?} is not utf8 encoded", bytes)).into()) Error::Convert(format!("{:?} is not utf8 encoded", bytes)).into()
})
} }
} }
/// Byte count specified with a unit. For example: `1.5 MB`. /// Byte count specified with a unit. For example: `1.5 MB`.
#[derive(Copy, Clone, Default)] #[derive(Copy, Clone, Default)]
pub struct ByteCount(u64); pub struct ByteCount(u64);
impl ByteCount { impl ByteCount {
("t", 1 << 40), ("t", 1 << 40),
("b", 1), ("b", 1),
("", 1), ("", 1),
]; ];
let value = std::str::from_utf8(bytes)?.to_lowercase(); let value = std::str::from_utf8(bytes)?.to_lowercase();
for (suffix, unit) in sizeunits.iter() { for (suffix, unit) in sizeunits.iter() {
if value.ends_with(suffix) { if value.ends_with(suffix) {
let number_str: &str = value[..value.len() - suffix.len()].trim(); let number_str: &str =
value[..value.len() - suffix.len()].trim();
let number: f64 = number_str.parse()?; let number: f64 = number_str.parse()?;
if number < 0.0 { if number < 0.0 {
return Err(Error::Convert(format!( return Err(Error::Convert(format!(
"byte size '{:?}' cannot be negative", "byte size '{:?}' cannot be negative",
value value
)) ))
.into()); .into());
} }
let unit = *unit as f64; let unit = *unit as f64;
return Ok(ByteCount((number * unit) as u64)); return Ok(ByteCount((number * unit) as u64));
} }
} }
Err(Error::Convert(format!("'{:?}' cannot be parsed as a byte size", value)).into()) Err(Error::Convert(format!(
"'{:?}' cannot be parsed as a byte size",
value
))
.into())
} }
} }
impl FromConfigValue for PathBuf { impl FromConfigValue for PathBuf {
fn try_from_bytes(bytes: &[u8]) -> Result<Self> { fn try_from_bytes(bytes: &[u8]) -> Result<Self> {
let st = std::str::from_utf8(&bytes)?; let st = std::str::from_utf8(&bytes)?;
Ok(expand_path(st)) Ok(expand_path(st))
// elif s[offset:offset + 1] == '"' and parts[-1][-1:] == '\\': // elif s[offset:offset + 1] == '"' and parts[-1][-1:] == '\\':
// parts[-1] = parts[-1][:-1] + s[offset:offset + 1] // parts[-1] = parts[-1][:-1] + s[offset:offset + 1]
// return _parse_plain, parts, offset + 1 // return _parse_plain, parts, offset + 1
// parts[-1] += s[offset:offset + 1] // parts[-1] += s[offset:offset + 1]
// return _parse_plain, parts, offset + 1 // return _parse_plain, parts, offset + 1
// ``` // ```
State::Plain => { State::Plain => {
let mut whitespace = false; let mut whitespace = false;
while offset < value.len() && b" \n\r\t,".contains(&value[offset]) { while offset < value.len()
&& b" \n\r\t,".contains(&value[offset])
{
whitespace = true; whitespace = true;
offset += 1; offset += 1;
} }
if offset >= value.len() { if offset >= value.len() {
break; break;
} }
if whitespace { if whitespace {
parts.push(Vec::new()); parts.push(Vec::new());
// else: // else:
// return None, parts, offset // return None, parts, offset
// return _parse_plain, parts, offset // return _parse_plain, parts, offset
// ``` // ```
State::Quote => { State::Quote => {
if offset < value.len() && value[offset] == b'"' { if offset < value.len() && value[offset] == b'"' {
parts.push(Vec::new()); parts.push(Vec::new());
offset += 1; offset += 1;
while offset < value.len() && b" \n\r\t,".contains(&value[offset]) { while offset < value.len()
&& b" \n\r\t,".contains(&value[offset])
{
offset += 1; offset += 1;
} }
state = State::Plain; state = State::Plain;
continue; continue;
} }
while offset < value.len() && value[offset] != b'"' { while offset < value.len() && value[offset] != b'"' {
if value[offset] == b'\\' if value[offset] == b'\\'
&& offset + 1 < value.len() && offset + 1 < value.len()
&& value[offset + 1] == b'"' && value[offset + 1] == b'"'
{ {
offset += 1; offset += 1;
parts.last_mut().unwrap().push(b'"'); parts.last_mut().unwrap().push(b'"');
} else { } else {
parts.last_mut().unwrap().push(value[offset]); parts.last_mut().unwrap().push(value[offset]);
} }
offset += 1; offset += 1;
} }
if offset >= value.len() { if offset >= value.len() {
let mut real_parts: Vec<Vec<u8>> = parse_list_internal(parts.last().unwrap()) let mut real_parts: Vec<Vec<u8>> =
parse_list_internal(parts.last().unwrap())
.iter() .iter()
.map(|b| b.to_vec()) .map(|b| b.to_vec())
.collect(); .collect();
if real_parts.is_empty() { if real_parts.is_empty() {
parts.pop(); parts.pop();
parts.push(vec![b'"']); parts.push(vec![b'"']);
} else { } else {
real_parts[0].insert(0, b'"'); real_parts[0].insert(0, b'"');
parts.pop(); parts.pop();
parts.append(&mut real_parts); parts.append(&mut real_parts);
} }
assert_eq!( assert_eq!(
parse_list(b"\"hello world\", \"how are you?\""), parse_list(b"\"hello world\", \"how are you?\""),
vec![b("hello world"), b("how are you?")] vec![b("hello world"), b("how are you?")]
); );
assert_eq!( assert_eq!(
parse_list(b"Do\"Not\"Separate"), parse_list(b"Do\"Not\"Separate"),
vec![b("Do\"Not\"Separate")] vec![b("Do\"Not\"Separate")]
); );
assert_eq!(parse_list(b"\"Do\"Separate"), vec![b("Do"), b("Separate")]); assert_eq!(
parse_list(b"\"Do\"Separate"),
vec![b("Do"), b("Separate")]
);
assert_eq!( assert_eq!(
parse_list(b"\"Do\\\"NotSeparate\""), parse_list(b"\"Do\\\"NotSeparate\""),
vec![b("Do\"NotSeparate")] vec![b("Do\"NotSeparate")]
); );
assert_eq!( assert_eq!(
parse_list(&b"string \"with extraneous\" quotation mark\""[..]), parse_list(&b"string \"with extraneous\" quotation mark\""[..]),
vec![ vec![
b("string"), b("string"),
vec![b(""), b(" key = "), b("x\""), b("y"), b(""), b("\"")] vec![b(""), b(" key = "), b("x\""), b("y"), b(""), b("\"")]
); );
assert_eq!(parse_list(b",,,, "), Vec::<Bytes>::new()); assert_eq!(parse_list(b",,,, "), Vec::<Bytes>::new());
assert_eq!( assert_eq!(
parse_list(b"\" just with starting quotation"), parse_list(b"\" just with starting quotation"),
vec![b("\""), b("just"), b("with"), b("starting"), b("quotation")] vec![b("\""), b("just"), b("with"), b("starting"), b("quotation")]
); );
assert_eq!( assert_eq!(
parse_list(&b"\"longer quotation\" with \"no ending quotation"[..]), parse_list(
&b"\"longer quotation\" with \"no ending quotation"[..]
),
vec![ vec![
b("longer quotation"), b("longer quotation"),
b("with"), b("with"),
b("\"no"), b("\"no"),
b("ending"), b("ending"),
b("quotation"), b("quotation"),
] ]
); );
assert_eq!( assert_eq!(
parse_list(&b"this is \\\" \"not a quotation mark\""[..]), parse_list(&b"this is \\\" \"not a quotation mark\""[..]),
vec![b("this"), b("is"), b("\""), b("not a quotation mark")] vec![b("this"), b("is"), b("\""), b("not a quotation mark")]
); );
assert_eq!(parse_list(b"\n \n\nding\ndong"), vec![b("ding"), b("dong")]); assert_eq!(
parse_list(b"\n \n\nding\ndong"),
vec![b("ding"), b("dong")]
);
// Other manually written cases // Other manually written cases
assert_eq!(parse_list("a,b,,c"), vec![b("a"), b("b"), b("c")]); assert_eq!(parse_list("a,b,,c"), vec![b("a"), b("b"), b("c")]);
assert_eq!(parse_list("a b c"), vec![b("a"), b("b"), b("c")]); assert_eq!(parse_list("a b c"), vec![b("a"), b("b"), b("c")]);
assert_eq!( assert_eq!(
parse_list(" , a , , b, , c , "), parse_list(" , a , , b, , c , "),
vec![b("a"), b("b"), b("c")] vec![b("a"), b("b"), b("c")]
); );

rust/hg-core/src/configparser/lib.rs

/* /*
* Copyright (c) Facebook, Inc. and its affiliates. * Copyright (c) Facebook, Inc. and its affiliates.
* *
* This software may be used and distributed according to the terms of the * This software may be used and distributed according to the terms of the
* GNU General Public License version 2. * GNU General Public License version 2.
*/ */
//! # ConfigParser //! # ConfigParser
//! //!
//! ConfigParser is a utility to parse hgrc-like config files. //! ConfigParser is a utility to parse hgrc-like config files.
//! //!
//! ## Features //! ## Features
//! //!
//! - Parse valid hgrc-like config files efficiently. //! - Parse valid hgrc-like config files efficiently.
//! - Track source locations of config values. Keep multiple locations of //! - Track source locations of config values. Keep multiple locations of a
//! a same config if it is overridden. //! same config if it is overridden.
//! //!
//! ## Config Format //! ## Config Format
//! //!
//! hgrc files are similar to INI files: //! hgrc files are similar to INI files:
//! //!
//! ```plain,ignore //! ```plain,ignore
//! [section1] //! [section1]
//! name1 = value1 //! name1 = value1