view rust/hg-cpython/src/dirstate.rs @ 48178:f12a19d03d2c

fix: reduce number of tool executions By grouping together (path, ctx) pairs according to the inputs they would provide to fixer tools, we can deduplicate executions of fixer tools to significantly reduce the amount of time spent running slow tools. This change does not handle clean files in the working copy, which could still be deduplicated against the files in the checked out commit. It's a little harder to do that because the filerev is not available in the workingfilectx (and it doesn't exist for added files). Anecdotally, this change makes some real uses cases at Google 10x faster. I think we were originally hesitant to do this because the benefits weren't obvious, and implementing it efficiently is kind of tricky. If we simply memoized the formatter execution function, we would be keeping tons of file content in memory. Also included is a regression test for a corner case that I broke with my first attempt at optimizing this code. Differential Revision: https://phab.mercurial-scm.org/D11280
author Danny Hooper <hooper@google.com>
date Thu, 02 Sep 2021 14:08:45 -0700
parents 060cd909439f
children 269ff8978086
line wrap: on
line source

// dirstate.rs
//
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.

//! Bindings for the `hg::dirstate` module provided by the
//! `hg-core` package.
//!
//! From Python, this will be seen as `mercurial.rustext.dirstate`
mod copymap;
mod dirs_multiset;
mod dirstate_map;
mod item;
mod status;
use self::item::DirstateItem;
use crate::{
    dirstate::{
        dirs_multiset::Dirs, dirstate_map::DirstateMap, status::status_wrapper,
    },
    exceptions,
};
use cpython::{PyBytes, PyDict, PyList, PyModule, PyObject, PyResult, Python};
use hg::dirstate_tree::on_disk::V2_FORMAT_MARKER;

/// Create the module, with `__package__` given from parent
pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
    let dotted_name = &format!("{}.dirstate", package);
    let m = PyModule::new(py, dotted_name)?;

    env_logger::init();

    m.add(py, "__package__", package)?;
    m.add(py, "__doc__", "Dirstate - Rust implementation")?;

    m.add(
        py,
        "FallbackError",
        py.get_type::<exceptions::FallbackError>(),
    )?;
    m.add_class::<Dirs>(py)?;
    m.add_class::<DirstateMap>(py)?;
    m.add_class::<DirstateItem>(py)?;
    m.add(py, "V2_FORMAT_MARKER", PyBytes::new(py, V2_FORMAT_MARKER))?;
    m.add(
        py,
        "status",
        py_fn!(
            py,
            status_wrapper(
                dmap: DirstateMap,
                root_dir: PyObject,
                matcher: PyObject,
                ignorefiles: PyList,
                check_exec: bool,
                last_normal_time: i64,
                list_clean: bool,
                list_ignored: bool,
                list_unknown: bool,
                collect_traversed_dirs: bool
            )
        ),
    )?;

    let sys = PyModule::import(py, "sys")?;
    let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
    sys_modules.set_item(py, dotted_name, &m)?;

    Ok(m)
}