changeset 51190:6ec8387eb0be

rust-index: pass data down to the Rust index

This will allow us to start keeping the Rust index synchronized with the
cindex as we gradually implement more and more methods in Rust. This will
eventually be removed.

--- a/mercurial/revlog.py	Tue Jun 27 16:32:09 2023 +0200
+++ b/mercurial/revlog.py	Tue Jun 27 17:34:51 2023 +0200
@@ -226,7 +226,7 @@
 
 def parse_index_v1_mixed(data, inline):
     index, cache = parse_index_v1(data, inline)
-    return rustrevlog.MixedIndex(index), cache
+    return rustrevlog.MixedIndex(index, data), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte

--- a/rust/hg-cpython/src/revlog.rs	Tue Jun 27 16:32:09 2023 +0200
+++ b/rust/hg-cpython/src/revlog.rs	Tue Jun 27 17:34:51 2023 +0200
@@ -36,13 +36,20 @@
 
 py_class!(pub class MixedIndex |py| {
     data cindex: RefCell<cindex::Index>;
+    data index: RefCell<hg::index::Index>;
     data nt: RefCell<Option<NodeTree>>;
     data docket: RefCell<Option<PyObject>>;
     // Holds a reference to the mmap'ed persistent nodemap data
     data nodemap_mmap: RefCell<Option<PyBuffer>>;
+    // Holds a reference to the mmap'ed persistent index data
+    data index_mmap: RefCell<Option<PyBuffer>>;
 
-    def __new__(_cls, cindex: PyObject) -> PyResult<MixedIndex> {
-        Self::new(py, cindex)
+    def __new__(
+        _cls,
+        cindex: PyObject,
+        data: PyObject
+    ) -> PyResult<MixedIndex> {
+        Self::new(py, cindex, data)
     }
 
     /// Compatibility layer used for Python consumers needing access to the C index
@@ -353,13 +360,22 @@
 }
 
 impl MixedIndex {
-    fn new(py: Python, cindex: PyObject) -> PyResult<MixedIndex> {
+    fn new(
+        py: Python,
+        cindex: PyObject,
+        data: PyObject,
+    ) -> PyResult<MixedIndex> {
+        // Safety: we keep the buffer around inside the class as `index_mmap`
+        let (buf, bytes) = unsafe { mmap_keeparound(py, data)? };
+
         Self::create_instance(
             py,
             RefCell::new(cindex::Index::new(py, cindex)?),
+            RefCell::new(hg::index::Index::new(bytes).unwrap()),
             RefCell::new(None),
             RefCell::new(None),
             RefCell::new(None),
+            RefCell::new(Some(buf)),
         )
     }
 

--- a/tests/test-rust-revlog.py	Tue Jun 27 16:32:09 2023 +0200
+++ b/tests/test-rust-revlog.py	Tue Jun 27 17:34:51 2023 +0200
@@ -22,24 +22,24 @@
 class RustRevlogIndexTest(revlogtesting.RevlogBasedTestBase):
     def test_heads(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
         self.assertEqual(rustidx.headrevs(), idx.headrevs())
 
     def test_get_cindex(self):
         # drop me once we no longer need the method for shortest node
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
         cidx = rustidx.get_cindex()
         self.assertTrue(idx is cidx)
 
     def test_len(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
         self.assertEqual(len(rustidx), len(idx))
 
     def test_ancestors(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
         lazy = LazyAncestors(rustidx, [3], 0, True)
         # we have two more references to the index:
         # - in its inner iterator for __contains__ and __bool__