##// END OF EJS Templates
sidedatacopies: only fetch information once for merge...
sidedatacopies: only fetch information once for merge Before this change, merge would result in reading the data from revlog twice. With this change, we keep the information in memory until we encounter the other parent. When looking at pypy, I see about 1/3 of the changesets with copy information being merge. Not doing duplicated fetch for them provide a significant speedup. revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29 before: ! wall 0.767042 comb 0.760000 user 0.750000 sys 0.010000 (median of 11) after: ! wall 0.671162 comb 0.670000 user 0.650000 sys 0.020000 (median of 13) revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2 before: ! wall 1.170169 comb 1.170000 user 1.130000 sys 0.040000 (median of 10) after: ! wall 1.030596 comb 1.040000 user 1.010000 sys 0.030000 (median of 10) revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0 before: ! wall 0.209846 comb 0.200000 user 0.200000 sys 0.000000 (median of 46) after: ! wall 0.170981 comb 0.170000 user 0.170000 sys 0.000000 (median of 56) revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f before: ! wall 0.013248 comb 0.010000 user 0.010000 sys 0.000000 (median of 223) after: ! wall 0.013295 comb 0.020000 user 0.020000 sys 0.000000 (median of 222) revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63 before: ! wall 0.001672 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) after: ! wall 0.001666 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e before: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8010) after: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8007) revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe before: ! wall 0.168599 comb 0.160000 user 0.160000 sys 0.000000 (median of 58) after: ! wall 0.133316 comb 0.140000 user 0.140000 sys 0.000000 (median of 73) revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d before: ! wall 0.036052 comb 0.030000 user 0.030000 sys 0.000000 (median of 100) after: ! wall 0.032558 comb 0.030000 user 0.030000 sys 0.000000 (median of 100) Differential Revision: https://phab.mercurial-scm.org/D7127

File last commit:

r43563:33fe96a5 default
r43595:90213d02 default
Show More
ancestors.rs
220 lines | 8.1 KiB | application/rls-services+xml | RustLexer
// ancestors.rs
//
// Copyright 2018 Georges Racinet <gracinet@anybox.fr>
//
// 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`
//! and can be used as replacement for the the pure `ancestor` Python module.
//!
//! # Classes visible from Python:
//! - [`LazyAncestors`] is the Rust implementation of
//! `mercurial.ancestor.lazyancestors`. The only difference is that it is
//! instantiated with a C `parsers.index` instance instead of a parents
//! function.
//!
//! - [`MissingAncestors`] is the Rust implementation of
//! `mercurial.ancestor.incrementalmissingancestors`.
//!
//! API differences:
//! + it is instantiated with a C `parsers.index`
//! instance instead of a parents function.
//! + `MissingAncestors.bases` is a method returning a tuple instead of
//! a set-valued attribute. We could return a Python set easily if our
//! [PySet PR](https://github.com/dgrunwald/rust-cpython/pull/165)
//! is accepted.
//!
//! - [`AncestorsIterator`] is the Rust counterpart of the
//! `ancestor._lazyancestorsiter` Python generator. From Python, instances of
//! this should be mainly obtained by calling `iter()` on a [`LazyAncestors`]
//! instance.
//!
//! [`LazyAncestors`]: struct.LazyAncestors.html
//! [`MissingAncestors`]: struct.MissingAncestors.html
//! [`AncestorsIterator`]: struct.AncestorsIterator.html
use crate::{
cindex::Index, conversion::rev_pyiter_collect, exceptions::GraphError,
};
use cpython::{
ObjectProtocol, PyClone, PyDict, PyList, PyModule, PyObject, PyResult,
Python, PythonObject, ToPyObject,
};
use hg::Revision;
use hg::{
AncestorsIterator as CoreIterator, LazyAncestors as CoreLazy,
MissingAncestors as CoreMissing,
};
use std::cell::RefCell;
use std::collections::HashSet;
py_class!(pub class AncestorsIterator |py| {
data inner: RefCell<Box<CoreIterator<Index>>>;
def __next__(&self) -> PyResult<Option<Revision>> {
match self.inner(py).borrow_mut().next() {
Some(Err(e)) => Err(GraphError::pynew(py, e)),
None => Ok(None),
Some(Ok(r)) => Ok(Some(r)),
}
}
def __contains__(&self, rev: Revision) -> PyResult<bool> {
self.inner(py).borrow_mut().contains(rev)
.map_err(|e| GraphError::pynew(py, e))
}
def __iter__(&self) -> PyResult<Self> {
Ok(self.clone_ref(py))
}
def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision,
inclusive: bool) -> PyResult<AncestorsIterator> {
let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?;
let ait = CoreIterator::new(
Index::new(py, index)?,
initvec,
stoprev,
inclusive,
)
.map_err(|e| GraphError::pynew(py, e))?;
AncestorsIterator::from_inner(py, ait)
}
});
impl AncestorsIterator {
pub fn from_inner(py: Python, ait: CoreIterator<Index>) -> PyResult<Self> {
Self::create_instance(py, RefCell::new(Box::new(ait)))
}
}
py_class!(pub class LazyAncestors |py| {
data inner: RefCell<Box<CoreLazy<Index>>>;
def __contains__(&self, rev: Revision) -> PyResult<bool> {
self.inner(py)
.borrow_mut()
.contains(rev)
.map_err(|e| GraphError::pynew(py, e))
}
def __iter__(&self) -> PyResult<AncestorsIterator> {
AncestorsIterator::from_inner(py, self.inner(py).borrow().iter())
}
def __bool__(&self) -> PyResult<bool> {
Ok(!self.inner(py).borrow().is_empty())
}
def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision,
inclusive: bool) -> PyResult<Self> {
let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?;
let lazy =
CoreLazy::new(Index::new(py, index)?, initvec, stoprev, inclusive)
.map_err(|e| GraphError::pynew(py, e))?;
Self::create_instance(py, RefCell::new(Box::new(lazy)))
}
});
py_class!(pub class MissingAncestors |py| {
data inner: RefCell<Box<CoreMissing<Index>>>;
def __new__(_cls, index: PyObject, bases: PyObject) -> PyResult<MissingAncestors> {
let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?;
let inner = CoreMissing::new(Index::new(py, index)?, bases_vec);
MissingAncestors::create_instance(py, RefCell::new(Box::new(inner)))
}
def hasbases(&self) -> PyResult<bool> {
Ok(self.inner(py).borrow().has_bases())
}
def addbases(&self, bases: PyObject) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?;
inner.add_bases(bases_vec);
// cpython doc has examples with PyResult<()> but this gives me
// the trait `cpython::ToPyObject` is not implemented for `()`
// so let's return an explicit None
Ok(py.None())
}
def bases(&self) -> PyResult<HashSet<Revision>> {
Ok(self.inner(py).borrow().get_bases().clone())
}
def basesheads(&self) -> PyResult<HashSet<Revision>> {
let inner = self.inner(py).borrow();
inner.bases_heads().map_err(|e| GraphError::pynew(py, e))
}
def removeancestorsfrom(&self, revs: PyObject) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
// this is very lame: we convert to a Rust set, update it in place
// and then convert back to Python, only to have Python remove the
// excess (thankfully, Python is happy with a list or even an iterator)
// Leads to improve this:
// - have the CoreMissing instead do something emit revisions to
// discard
// - define a trait for sets of revisions in the core and implement
// it for a Python set rewrapped with the GIL marker
let mut revs_pyset: HashSet<Revision> = rev_pyiter_collect(py, &revs)?;
inner.remove_ancestors_from(&mut revs_pyset)
.map_err(|e| GraphError::pynew(py, e))?;
// convert as Python list
let mut remaining_pyint_vec: Vec<PyObject> = Vec::with_capacity(
revs_pyset.len());
for rev in revs_pyset {
remaining_pyint_vec.push(rev.to_py_object(py).into_object());
}
let remaining_pylist = PyList::new(py, remaining_pyint_vec.as_slice());
revs.call_method(py, "intersection_update", (remaining_pylist, ), None)
}
def missingancestors(&self, revs: PyObject) -> PyResult<PyList> {
let mut inner = self.inner(py).borrow_mut();
let revs_vec: Vec<Revision> = rev_pyiter_collect(py, &revs)?;
let missing_vec = match inner.missing_ancestors(revs_vec) {
Ok(missing) => missing,
Err(e) => {
return Err(GraphError::pynew(py, e));
}
};
// convert as Python list
let mut missing_pyint_vec: Vec<PyObject> = Vec::with_capacity(
missing_vec.len());
for rev in missing_vec {
missing_pyint_vec.push(rev.to_py_object(py).into_object());
}
Ok(PyList::new(py, missing_pyint_vec.as_slice()))
}
});
/// Create the module, with __package__ given from parent
pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
let dotted_name = &format!("{}.ancestor", package);
let m = PyModule::new(py, dotted_name)?;
m.add(py, "__package__", package)?;
m.add(
py,
"__doc__",
"Generic DAG ancestor algorithms - Rust implementation",
)?;
m.add_class::<AncestorsIterator>(py)?;
m.add_class::<LazyAncestors>(py)?;
m.add_class::<MissingAncestors>(py)?;
let sys = PyModule::import(py, "sys")?;
let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
sys_modules.set_item(py, dotted_name, &m)?;
// Example C code (see pyexpat.c and import.c) will "give away the
// reference", but we won't because it will be consumed once the
// Rust PyObject is dropped.
Ok(m)
}