view rust/hg-core/src/lib.rs @ 50692:1c31b343e514

match: add `filepath:` pattern to match an exact filepath relative to the root It's useful in certain automated workflows to make sure we recurse in directories whose name conflicts with files in other revisions. In addition it makes it possible to avoid building a potentially costly regex, improving performance when the set of files to match explicitly is large. The benchmark below are run in the following configuration : # data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # benchmark.name = files # benchmark.variants.rev = tip # benchmark.variants.files = all-list-filepath-sorted # bin-env-vars.hg.flavor = no-rust It also includes timings using the re2 engine (through the `google-re2` module) to show how much can be saved by just using a better regexp engine. Pattern time (seconds) time using re2 ----------------------------------------------------------- just "." 0.4 0.4 list of "filepath:?" 1.3 1.3 list of "path:?" 25.7 3.9 list of patterns 29.7 10.4 As you can see, Without re2, using "filepath:" instead of "path:" is a huge win. With re2, it is still about three times faster to not have to build the regex.
author Rapha?l Gom?s <rgomes@octobus.net>
date Mon, 12 Jun 2023 16:51:08 +0200
parents a8531bd9210b
children f50e71fdfcb4
line wrap: on
line source

// Copyright 2018-2020 Georges Racinet <georges.racinet@octobus.net>
//           and Mercurial contributors
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.

mod ancestors;
pub mod dagops;
pub mod errors;
pub mod narrow;
pub mod sparse;
pub use ancestors::{AncestorsIterator, MissingAncestors};
pub mod dirstate;
pub mod dirstate_tree;
pub mod discovery;
pub mod exit_codes;
pub mod requirements;
pub mod testing; // unconditionally built, for use from integration tests
pub use dirstate::{
    dirs_multiset::{DirsMultiset, DirsMultisetIter},
    status::{
        BadMatch, BadType, DirstateStatus, HgPathCow, StatusError,
        StatusOptions,
    },
    DirstateEntry, DirstateParents, EntryState,
};
pub mod copy_tracing;
mod filepatterns;
pub mod matchers;
pub mod repo;
pub mod revlog;
pub use revlog::*;
pub mod checkexec;
pub mod config;
pub mod lock;
pub mod logging;
pub mod operations;
pub mod revset;
pub mod utils;
pub mod vfs;

use crate::utils::hg_path::{HgPathBuf, HgPathError};
pub use filepatterns::{
    parse_pattern_syntax, read_pattern_file, IgnorePattern,
    PatternFileWarning, PatternSyntax,
};
use std::collections::HashMap;
use std::fmt;
use twox_hash::RandomXxHashBuilder64;

pub type LineNumber = usize;

/// Rust's default hasher is too slow because it tries to prevent collision
/// attacks. We are not concerned about those: if an ill-minded person has
/// write access to your repository, you have other issues.
pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;

// TODO: should this be the default `FastHashMap` for all of hg-core, not just
// dirstate_tree? How does XxHash compare with AHash, hashbrown’s default?
pub type FastHashbrownMap<K, V> =
    hashbrown::HashMap<K, V, RandomXxHashBuilder64>;

#[derive(Debug, PartialEq)]
pub enum DirstateMapError {
    PathNotFound(HgPathBuf),
    InvalidPath(HgPathError),
}

impl fmt::Display for DirstateMapError {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        match self {
            DirstateMapError::PathNotFound(_) => {
                f.write_str("expected a value, found none")
            }
            DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
        }
    }
}

#[derive(Debug, derive_more::From)]
pub enum DirstateError {
    Map(DirstateMapError),
    Common(errors::HgError),
}

impl fmt::Display for DirstateError {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        match self {
            DirstateError::Map(error) => error.fmt(f),
            DirstateError::Common(error) => error.fmt(f),
        }
    }
}

#[derive(Debug, derive_more::From)]
pub enum PatternError {
    #[from]
    Path(HgPathError),
    UnsupportedSyntax(String),
    UnsupportedSyntaxInFile(String, String, usize),
    TooLong(usize),
    #[from]
    IO(std::io::Error),
    /// Needed a pattern that can be turned into a regex but got one that
    /// can't. This should only happen through programmer error.
    NonRegexPattern(IgnorePattern),
}

impl fmt::Display for PatternError {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        match self {
            PatternError::UnsupportedSyntax(syntax) => {
                write!(f, "Unsupported syntax {}", syntax)
            }
            PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                write!(
                    f,
                    "{}:{}: unsupported syntax {}",
                    file_path, line, syntax
                )
            }
            PatternError::TooLong(size) => {
                write!(f, "matcher pattern is too long ({} bytes)", size)
            }
            PatternError::IO(error) => error.fmt(f),
            PatternError::Path(error) => error.fmt(f),
            PatternError::NonRegexPattern(pattern) => {
                write!(f, "'{:?}' cannot be turned into a regex", pattern)
            }
        }
    }
}