Mercurial > public > mercurial-scm > hg-stable

diff rust/hg-cpython/src/revlog.rs @ 51260:7eea2e4109ae

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
rust-index: using the `hg::index::Index` in ancestors iterator and lazy set Since there is no Rust implementation for REVLOGV2/CHANGELOGv2, we declare them to be incompatible with Rust, hence indexes in these formats will use the implementations from Python `mercurial.ancestor`. If this is an unacceptable performance hit for current users of these formats, we can later on add Rust implementations based on the C index for them or implement these formats for the Rust indexes. Among the challenges that we had to meet, we wanted to avoid taking the GIL each time the inner (vcsgraph) iterator has to call the parents function. This would probably still be acceptable in terms of performance with `AncestorsIterator`, but not with `LazyAncestors` nor for the upcoming change in `MissingAncestors`. Hence we enclose the reference to the index in a `PySharedRef`, leading to more rigourous checking of mutations, which does pass now that there no logically immutable methods of `hg::index::Index` that take a mutable reference as input.
author Georges Racinet <georges.racinet@octobus.net>
date Fri, 27 Oct 2023 22:11:05 +0200
parents 456e0fe702e8
children 0b81440e2a73
line wrap: on
line diff
--- a/rust/hg-cpython/src/revlog.rs	Fri Oct 27 23:29:29 2023 +0200
+++ b/rust/hg-cpython/src/revlog.rs	Fri Oct 27 22:11:05 2023 +0200
@@ -16,7 +16,7 @@
     exc::{IndexError, ValueError},
     ObjectProtocol, PyBool, PyBytes, PyClone, PyDict, PyErr, PyInt, PyList,
     PyModule, PyObject, PyResult, PySet, PyString, PyTuple, Python,
-    PythonObject, ToPyObject,
+    PythonObject, ToPyObject, UnsafePyLeaked,
 };
 use hg::{
     errors::HgError,
@@ -25,10 +25,11 @@
         INDEX_ENTRY_SIZE,
     },
     nodemap::{Block, NodeMapError, NodeTree},
-    revlog::{nodemap::NodeMap, NodePrefix, RevlogError, RevlogIndex},
-    BaseRevision, Revision, UncheckedRevision, NULL_REVISION,
+    revlog::{nodemap::NodeMap, Graph, NodePrefix, RevlogError, RevlogIndex},
+    BaseRevision, Node, Revision, UncheckedRevision, NULL_REVISION,
 };
 use std::{cell::RefCell, collections::HashMap};
+use vcsgraph::graph::Graph as VCSGraph;
 
 /// Return a Struct implementing the Graph trait
 pub(crate) fn pyindex_to_graph(
@@ -41,9 +42,64 @@
     }
 }
 
+pub struct PySharedIndex {
+    /// The underlying hg-core index
+    pub(crate) inner: &'static hg::index::Index,
+}
+
+/// Return a Struct implementing the Graph trait
+pub(crate) fn py_rust_index_to_graph(
+    py: Python,
+    index: PyObject,
+) -> PyResult<UnsafePyLeaked<PySharedIndex>> {
+    let midx = index.extract::<MixedIndex>(py)?;
+    let leaked = midx.index(py).leak_immutable();
+    Ok(unsafe { leaked.map(py, |idx| PySharedIndex { inner: idx }) })
+}
+
+impl Clone for PySharedIndex {
+    fn clone(&self) -> Self {
+        Self { inner: self.inner }
+    }
+}
+
+impl Graph for PySharedIndex {
+    fn parents(&self, rev: Revision) -> Result<[Revision; 2], hg::GraphError> {
+        self.inner.parents(rev)
+    }
+}
+
+impl VCSGraph for PySharedIndex {
+    fn parents(
+        &self,
+        rev: BaseRevision,
+    ) -> Result<vcsgraph::graph::Parents, vcsgraph::graph::GraphReadError>
+    {
+        // FIXME This trait should be reworked to decide between Revision
+        // and UncheckedRevision, get better errors names, etc.
+        match Graph::parents(self, Revision(rev)) {
+            Ok(parents) => {
+                Ok(vcsgraph::graph::Parents([parents[0].0, parents[1].0]))
+            }
+            Err(hg::GraphError::ParentOutOfRange(rev)) => {
+                Err(vcsgraph::graph::GraphReadError::KeyedInvalidKey(rev.0))
+            }
+        }
+    }
+}
+
+impl RevlogIndex for PySharedIndex {
+    fn len(&self) -> usize {
+        self.inner.len()
+    }
+    fn node(&self, rev: Revision) -> Option<&Node> {
+        self.inner.node(rev)
+    }
+}
+
 py_class!(pub class MixedIndex |py| {
     data cindex: RefCell<cindex::Index>;
-    data index: RefCell<hg::index::Index>;
+    @shared data index: hg::index::Index;
     data nt: RefCell<Option<NodeTree>>;
     data docket: RefCell<Option<PyObject>>;
     // Holds a reference to the mmap'ed persistent nodemap data
@@ -668,17 +724,15 @@
         Self::create_instance(
             py,
             RefCell::new(cindex::Index::new(py, cindex)?),
-            RefCell::new(
-                hg::index::Index::new(
-                    bytes,
-                    IndexHeader::parse(&header.to_be_bytes())
-                        .expect("default header is broken")
-                        .unwrap(),
-                )
-                .map_err(|e| {
-                    revlog_error_with_msg(py, e.to_string().as_bytes())
-                })?,
-            ),
+            hg::index::Index::new(
+                bytes,
+                IndexHeader::parse(&header.to_be_bytes())
+                    .expect("default header is broken")
+                    .unwrap(),
+            )
+            .map_err(|e| {
+                revlog_error_with_msg(py, e.to_string().as_bytes())
+            })?,
             RefCell::new(None),
             RefCell::new(None),
             RefCell::new(None),