view rust/hg-core/src/lib.rs @ 51109:687e192dae16

rust-matchers: fix quadratic complexity in `FileMatcher`

Concretely, this command:

```
$ echo hg up -r <nodeid>; time hg revert dir1 dir2 -r <othernode> --debug
hg up -r <nodeid>

real	0m14.690s
user	0m14.766s
sys	0m5.430s
```

was much slower despite using 16 cores before this change.
The approach taken here is the same one used in match.py, in exactmatcher.

This changeset was originally written by Valentin Gatien-Baron in a private
repository.
I have redacted the commit message and did a minor clean up of the code.

// Copyright 2018-2020 Georges Racinet <[e-mail]>
//           and Mercurial contributors
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.

mod ancestors;
pub mod dagops;
pub mod errors;
pub 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;
pub 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 From<HgPathError> for DirstateMapError {
    fn from(error: HgPathError) -> Self {
        Self::InvalidPath(error)
    }
}

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 From<HgPathError> for DirstateError {
    fn from(error: HgPathError) -> Self {
        Self::Map(DirstateMapError::InvalidPath(error))
    }
}

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)
            }
        }
    }
}