view rust/hg-cpython/src/conversion.rs @ 51403:f8bf1a8e9181

phases: keep internal state as rev-num instead of node-id Node-id are expensive to work with, dealing with revision is much simple and faster. The fact we still used node-id here shows how few effort have been put into making the phase logic fast. We tend to no longer use node-id internally for about ten years. This has a large impact of repository with many draft roots. For example this Mozilla-try copy have ? Million draft roots and `perf::unbundle` see a significant improvement. ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.perf.perf-unbundle # bin-env-vars.hg.flavor = no-rust # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.revs = last-1 before:: 1.746791 seconds after:: 1.278379 seconds (-26.82%) # benchmark.variants.revs = last-10 before:: 3.145774 seconds after:: 2.103735 seconds (-33.13%) # benchmark.variants.revs = last-100 before:: 3.487635 seconds after:: 2.446749 seconds (-29.85%) # benchmark.variants.revs = last-1000 before:: 5.007568 seconds after:: 3.989923 seconds (-20.32%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 20 Feb 2024 21:40:13 +0100
parents 5a7d5fd6808c
children bd8081e9fd62
line wrap: on
line source

// conversion.rs
//
// Copyright 2019 Georges Racinet <georges.racinet@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::ancestors module provided by the
//! `hg-core` crate. From Python, this will be seen as `rustext.ancestor`

use cpython::{ObjectProtocol, PyErr, PyObject, PyResult, Python};
use hg::{Revision, RevlogIndex, UncheckedRevision};

use crate::{exceptions::GraphError, PyRevision};

/// Utility function to convert a Python iterable into various collections
///
/// We need this in particular to feed to various methods of inner objects
/// with `impl IntoIterator<Item=Revision>` arguments, because
/// a `PyErr` can arise at each step of iteration, whereas these methods
/// expect iterables over `Revision`, not over some `Result<Revision, PyErr>`
pub fn rev_pyiter_collect<C, I>(
    py: Python,
    revs: &PyObject,
    index: &I,
) -> PyResult<C>
where
    C: FromIterator<Revision>,
    I: RevlogIndex,
{
    rev_pyiter_collect_or_else(py, revs, index, |r| {
        PyErr::new::<GraphError, _>(py, ("InvalidRevision", r.0))
    })
}

/// Same as [`rev_pyiter_collect`], giving control on returned errors
pub fn rev_pyiter_collect_or_else<C, I>(
    py: Python,
    revs: &PyObject,
    index: &I,
    invalid_rev_error: impl FnOnce(PyRevision) -> PyErr + Copy,
) -> PyResult<C>
where
    C: FromIterator<Revision>,
    I: RevlogIndex,
{
    revs.iter(py)?
        .map(|r| {
            r.and_then(|o| match o.extract::<PyRevision>(py) {
                Ok(r) => index
                    .check_revision(UncheckedRevision(r.0))
                    .ok_or_else(|| invalid_rev_error(r)),
                Err(e) => Err(e),
            })
        })
        .collect()
}