Patchwork [5,of,5,V3] rust: rustlazyancestors.__contains__

login
register
mail settings
Submitter Georges Racinet
Date Oct. 13, 2018, 1:59 p.m.
Message ID <5c3f0974b9afb074df9a.1539439183@ishtar>
Download mbox | patch
Permalink /patch/35931/
State Accepted
Headers show

Comments

Georges Racinet - Oct. 13, 2018, 1:59 p.m.
# HG changeset patch
# User Georges Racinet <gracinet@anybox.fr>
# Date 1539018701 -7200
#      Mon Oct 08 19:11:41 2018 +0200
# Node ID 5c3f0974b9afb074df9acd626813064eb6f2ffec
# Parent  98f0f668f63b143eba344a74c8b22a0588f46935
# EXP-Topic rustancestors-contains
rust: rustlazyancestors.__contains__

This changeset provides a Rust implementation of
the iteration performed by lazyancestor.__contains__

It has the advantage over the Python iteration to use
the 'seen' set encapsuled into the dedicated iterator (self._containsiter),
rather than storing emitted items in another set (self._containsseen),
and hence should reduce the memory footprint.

Also, there's no need to convert intermediate emitted revisions back into
Python integers.

At this point, it would be tempting to implement the whole lazyancestor object
in Rust, but that would lead to more C wrapping code (two objects) for
little expected benefits.

Patch

diff -r 98f0f668f63b -r 5c3f0974b9af mercurial/ancestor.py
--- a/mercurial/ancestor.py	Thu Sep 27 16:55:44 2018 +0200
+++ b/mercurial/ancestor.py	Mon Oct 08 19:11:41 2018 +0200
@@ -383,7 +383,7 @@ 
             self._containsiter = None
             return False
 
-class rustlazyancestors(lazyancestors):
+class rustlazyancestors(object):
 
     def __init__(self, index, revs, stoprev=0, inclusive=False):
         self._index = index
@@ -395,12 +395,26 @@ 
         # constructor (from C code) doesn't understand anything else yet
         self._initrevs = initrevs = list(revs)
 
-        self._containsseen = set()
         self._containsiter = parsers.rustlazyancestors(
             index, initrevs, stoprev, inclusive)
 
+    def __nonzero__(self):
+        """False if the set is empty, True otherwise.
+
+        It's better to duplicate this essentially trivial method than
+        to subclass lazyancestors
+        """
+        try:
+            next(iter(self))
+            return True
+        except StopIteration:
+            return False
+
     def __iter__(self):
         return parsers.rustlazyancestors(self._index,
                                          self._initrevs,
                                          self._stoprev,
                                          self._inclusive)
+
+    def __contains__(self, target):
+        return target in self._containsiter
diff -r 98f0f668f63b -r 5c3f0974b9af mercurial/cext/revlog.c
--- a/mercurial/cext/revlog.c	Thu Sep 27 16:55:44 2018 +0200
+++ b/mercurial/cext/revlog.c	Mon Oct 08 19:11:41 2018 +0200
@@ -2316,6 +2316,7 @@ 
 	int inclusive);
 void rustlazyancestors_drop(rustlazyancestorsObject *self);
 int rustlazyancestors_next(rustlazyancestorsObject *self);
+int rustlazyancestors_contains(rustlazyancestorsObject *self, long rev);
 
 /* CPython instance methods */
 static int rustla_init(rustlazyancestorsObject *self,
@@ -2394,6 +2395,24 @@ 
 	return PyInt_FromLong(res);
 }
 
+static int rustla_contains(rustlazyancestorsObject *self, PyObject *rev) {
+  if (!(PyInt_Check(rev))) {
+    return 0;
+  }
+  return rustlazyancestors_contains(self->iter, PyInt_AS_LONG(rev));
+}
+
+static PySequenceMethods rustla_sequence_methods = {
+        0,                       /* sq_length */
+	0,                       /* sq_concat */
+	0,                       /* sq_repeat */
+	0,                       /* sq_item */
+	0,                       /* sq_slice */
+	0,                       /* sq_ass_item */
+	0,                       /* sq_ass_slice */
+	(objobjproc)rustla_contains, /* sq_contains */
+};
+
 static PyTypeObject rustlazyancestorsType = {
 	PyVarObject_HEAD_INIT(NULL, 0) /* header */
 	"parsers.rustlazyancestors",           /* tp_name */
@@ -2406,7 +2425,7 @@ 
 	0,                         /* tp_compare */
 	0,                         /* tp_repr */
 	0,                         /* tp_as_number */
-	0,                         /* tp_as_sequence */
+	&rustla_sequence_methods,  /* tp_as_sequence */
 	0,                         /* tp_as_mapping */
 	0,                         /* tp_hash */
 	0,                         /* tp_call */
diff -r 98f0f668f63b -r 5c3f0974b9af rust/hg-core/src/ancestors.rs
--- a/rust/hg-core/src/ancestors.rs	Thu Sep 27 16:55:44 2018 +0200
+++ b/rust/hg-core/src/ancestors.rs	Mon Oct 08 19:11:41 2018 +0200
@@ -81,6 +81,26 @@ 
         self.conditionally_push_rev(parents.1);
         Ok(())
     }
+
+    /// Consumes partially the iterator to tell if the given target
+    /// revision
+    /// is in the ancestors it emits.
+    /// This is meant for iterators actually dedicated to that kind of
+    /// purpose
+    pub fn contains(&mut self, target: Revision) -> bool {
+        if self.seen.contains(&target) && target != NULL_REVISION {
+            return true;
+        }
+        for rev in self {
+            if rev == target {
+                return true;
+            }
+            if rev < target {
+                return false;
+            }
+        }
+        false
+    }
 }
 
 /// Main implementation.
@@ -204,6 +224,18 @@ 
         assert_eq!(iter.next(), None)
     }
 
+    #[test]
+    fn test_contains() {
+        let mut lazy =
+            AncestorsIterator::new(Stub, vec![10, 1], 0, true).unwrap();
+        assert!(lazy.contains(1));
+        assert!(!lazy.contains(3));
+
+        let mut lazy =
+            AncestorsIterator::new(Stub, vec![0], 0, false).unwrap();
+        assert!(!lazy.contains(NULL_REVISION));
+    }
+
     /// A corrupted Graph, supporting error handling tests
     struct Corrupted;
 
diff -r 98f0f668f63b -r 5c3f0974b9af rust/hg-direct-ffi/rustfmt.toml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/rust/hg-direct-ffi/rustfmt.toml	Mon Oct 08 19:11:41 2018 +0200
@@ -0,0 +1,3 @@ 
+max_width = 79
+wrap_comments = true
+error_on_line_overflow = true
diff -r 98f0f668f63b -r 5c3f0974b9af rust/hg-direct-ffi/src/ancestors.rs
--- a/rust/hg-direct-ffi/src/ancestors.rs	Thu Sep 27 16:55:44 2018 +0200
+++ b/rust/hg-direct-ffi/src/ancestors.rs	Mon Oct 08 19:11:41 2018 +0200
@@ -16,9 +16,12 @@ 
 use std::slice;
 
 type IndexPtr = *mut c_void;
-type IndexParentsFn =
-    unsafe extern "C" fn(index: IndexPtr, rev: ssize_t, ps: *mut [c_int; 2], max_rev: c_int)
-        -> c_int;
+type IndexParentsFn = unsafe extern "C" fn(
+    index: IndexPtr,
+    rev: ssize_t,
+    ps: *mut [c_int; 2],
+    max_rev: c_int,
+) -> c_int;
 
 /// A Graph backed up by objects and functions from revlog.c
 ///
@@ -41,10 +44,19 @@ 
 
 impl Graph for Index {
     /// wrap a call to the C extern parents function
-    fn parents(&self, rev: Revision) -> Result<(Revision, Revision), GraphError> {
+    fn parents(
+        &self,
+        rev: Revision,
+    ) -> Result<(Revision, Revision), GraphError> {
         let mut res: [c_int; 2] = [0; 2];
-        let code =
-            unsafe { (self.parents)(self.index, rev as ssize_t, &mut res as *mut [c_int; 2], rev) };
+        let code = unsafe {
+            (self.parents)(
+                self.index,
+                rev as ssize_t,
+                &mut res as *mut [c_int; 2],
+                rev,
+            )
+        };
         match code {
             0 => Ok((res[0], res[1])),
             _ => Err(GraphError::ParentOutOfRange(rev)),
@@ -110,7 +122,9 @@ 
 
 /// Deallocator to be called from C code
 #[no_mangle]
-pub extern "C" fn rustlazyancestors_drop(raw_iter: *mut AncestorsIterator<Index>) {
+pub extern "C" fn rustlazyancestors_drop(
+    raw_iter: *mut AncestorsIterator<Index>,
+) {
     raw_drop(raw_iter);
 }
 
@@ -128,7 +142,9 @@ 
 /// it will be up to the C wrapper to convert that back into a Python end of
 /// iteration
 #[no_mangle]
-pub extern "C" fn rustlazyancestors_next(raw: *mut AncestorsIterator<Index>) -> c_long {
+pub extern "C" fn rustlazyancestors_next(
+    raw: *mut AncestorsIterator<Index>,
+) -> c_long {
     raw_next(raw)
 }
 
@@ -139,6 +155,27 @@ 
     as_ref.next().unwrap_or(NULL_REVISION) as c_long
 }
 
+#[no_mangle]
+pub extern "C" fn rustlazyancestors_contains(
+    raw: *mut AncestorsIterator<Index>,
+    target: c_long,
+) -> c_long {
+    raw_contains(raw, target)
+}
+
+/// Testable (for any Graph) version of rustlazayancestors_next
+#[inline]
+fn raw_contains<G: Graph>(
+    raw: *mut AncestorsIterator<G>,
+    target: c_long,
+) -> c_long {
+    let as_ref = unsafe { &mut *raw };
+    if as_ref.contains(target as Revision) {
+        return 1;
+    }
+    0
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -148,7 +185,10 @@ 
     struct Stub;
 
     impl Graph for Stub {
-        fn parents(&self, r: Revision) -> Result<(Revision, Revision), GraphError> {
+        fn parents(
+            &self,
+            r: Revision,
+        ) -> Result<(Revision, Revision), GraphError> {
             match r {
                 25 => Err(GraphError::ParentOutOfRange(25)),
                 _ => Ok((1, 2)),
@@ -199,7 +239,9 @@ 
         let mut initrevs: Vec<c_long> = vec![11, 13];
         let initrevs_len = initrevs.len();
         let initrevs_ptr = initrevs.as_mut_ptr() as usize;
-        let handler = thread::spawn(move || stub_raw_init(initrevs_len, initrevs_ptr, 0, 1));
+        let handler = thread::spawn(move || {
+            stub_raw_init(initrevs_len, initrevs_ptr, 0, 1)
+        });
         let raw = handler.join().unwrap() as *mut AncestorsIterator<Stub>;
 
         assert_eq!(raw_next(raw), 13);
@@ -226,4 +268,18 @@ 
     fn test_init_err_out_of_range() {
         assert!(stub_raw_init_from_vec(vec![25], 0, 0).is_null());
     }
+
+    #[test]
+    fn test_contains() {
+        let raw = stub_raw_init_from_vec(vec![5, 6], 0, 1);
+        assert_eq!(raw_contains(raw, 5), 1);
+        assert_eq!(raw_contains(raw, 2), 1);
+    }
+
+    #[test]
+    fn test_contains_exclusive() {
+        let raw = stub_raw_init_from_vec(vec![5, 6], 0, 0);
+        assert_eq!(raw_contains(raw, 5), 0);
+        assert_eq!(raw_contains(raw, 2), 1);
+    }
 }
diff -r 98f0f668f63b -r 5c3f0974b9af rust/hg-direct-ffi/src/lib.rs
--- a/rust/hg-direct-ffi/src/lib.rs	Thu Sep 27 16:55:44 2018 +0200
+++ b/rust/hg-direct-ffi/src/lib.rs	Mon Oct 08 19:11:41 2018 +0200
@@ -13,4 +13,7 @@ 
 extern crate libc;
 
 mod ancestors;
-pub use ancestors::{rustlazyancestors_drop, rustlazyancestors_init, rustlazyancestors_next};
+pub use ancestors::{
+    rustlazyancestors_contains, rustlazyancestors_drop,
+    rustlazyancestors_init, rustlazyancestors_next,
+};