view rust/hg-core/src/lib.rs @ 51929:f2832de2a46c

interfaces: introduce and use a protocol class for the `bdiff` module This is allowed by PEP 544[1], and we basically follow the example there. The class here is copied from `mercurial.pure.bdiff`, and the implementation removed. There are several modules that have a few different implementations, and the implementation chosen is controlled by `HGMODULEPOLICY`. The module is loaded via `mercurial/policy.py`, and has been inferred by pytype as `Any` up to this point. Therefore it and PyCharm were blind to all functions on the module, and their signatures. Also, having multiple instances of the same module allows their signatures to get out of sync. Introducing a protocol class allows the loaded module that is stored in a variable to be given type info, which cascades through the various places it is used. This change alters 11 *.pyi files, for example. In theory, this would also allow us to ensure the various implementations of the same module are kept in alignment- simply import the module in a test module, attempt to pass it to a function that uses the corresponding protocol as an argument, and run pytype on it. In practice, this doesn't work (yet). PyCharm (erroneously) flags imported modules being passed where a protocol class is used[2]. Pytype has problems the other way- it fails to detect when a module that doesn't adhere to the protocol is passed to a protocol argument. The good news is that mypy properly detects this case. The bad news is that mypy spews a bunch of other errors when importing even simple modules, like the various `bdiff` modules. Therefore I'm punting on the tests for now because the type info around a loaded module in PyCharm is a clear win by itself. [1] https://peps.python.org/pep-0544/#modules-as-implementations-of-protocols [2] https://youtrack.jetbrains.com/issue/PY-58679/Support-modules-implementing-protocols
author Matt Harbison <matt_harbison@yahoo.com>
date Sat, 28 Sep 2024 19:12:18 -0400
parents e4b9f8a74d5f
children 3ae7c43ad8aa
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;
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_kind, 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)
            }
        }
    }
}