Merge branch 'main' into fix-dot-recall

.github/workflows/ci.yml

@@ -0,0 +1,25 @@
+name: Annoy
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  unit-tests:
+    runs-on: ubuntu-22.04
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        os: ["ubuntu-20.04", "macos-latest", "windows-latest"]
+
+    steps:
+      - uses: actions/checkout@v3 # Pull the repository
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: pip install .
+      - run: pip install h5py numpy pytest
+      - run: pytest -v

CMakeLists.txt

@@ -1,21 +1,33 @@
-cmake_minimum_required(VERSION 3.14)
+cmake_minimum_required(VERSION 3.15...3.25 FATAL_ERROR)
+
 project(Annoy
-    DESCRIPTION "Approximate Nearest Neighbors Oh Yeah"
-    VERSION 1.17.0
-    LANGUAGES CXX
-)
+  DESCRIPTION "Approximate Nearest Neighbors Oh Yeah"
+  VERSION 1.17.1
+  LANGUAGES CXX)
 
 add_library(Annoy INTERFACE)
+add_library(Annoy::Annoy ALIAS Annoy)
 
-set(ANNOY_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/include/annoy)
-file(MAKE_DIRECTORY ${ANNOY_INCLUDE_DIR})
 foreach (HEADER annoylib.h kissrandom.h mman.h)
-    file(COPY ${CMAKE_CURRENT_SOURCE_DIR}/src/${HEADER} DESTINATION ${ANNOY_INCLUDE_DIR})
-endforeach()
+  configure_file("${CMAKE_CURRENT_SOURCE_DIR}/src/${HEADER}" "${CMAKE_CURRENT_BINARY_DIR}/include/annoy/${HEADER}" COPYONLY)
+endforeach ()
+
+target_include_directories(Annoy INTERFACE
+  $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}/include>
+  $<INSTALL_INTERFACE:include>)
+
+# Install
+include(GNUInstallDirs)
+
+install(DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/include/
+  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
 
-target_include_directories(Annoy INTERFACE include/)
+install(TARGETS Annoy
+  EXPORT AnnoyTargets)
 
-if(CMAKE_PROJECT_NAME STREQUAL PROJECT_NAME)
-    # Add Python set-up code here.
-endif()
+install(EXPORT AnnoyTargets
+  FILE AnnoyConfig.cmake
+  NAMESPACE Annoy::
+  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/annoy)
 
+export(TARGETS Annoy NAMESPACE Annoy:: FILE AnnoyConfig.cmake)

README.rst

@@ -7,14 +7,8 @@ Annoy
    :alt: Annoy example
    :align: center
 
-.. image:: https://img.shields.io/travis/spotify/annoy/master.svg?style=flat
-    :target: https://travis-ci.org/spotify/annoy
-
-.. image:: https://ci.appveyor.com/api/projects/status/github/spotify/annoy?svg=true&pendingText=windows%20-%20Pending&passingText=windows%20-%20OK&failingText=windows%20-%20Failing
-    :target: https://ci.appveyor.com/project/erikbern/annoy
-
-.. image:: https://img.shields.io/pypi/v/annoy.svg?style=flat
-   :target: https://pypi.python.org/pypi/annoy
+.. image:: https://github.com/spotify/annoy/actions/workflows/ci.yml/badge.svg
+    :target: https://github.com/spotify/annoy/actions
 
 Annoy (`Approximate Nearest Neighbors <http://en.wikipedia.org/wiki/Nearest_neighbor_search#Approximate_nearest_neighbor>`__ Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are `mmapped <https://en.wikipedia.org/wiki/Mmap>`__ into memory so that many processes may share the same data.
 

annoy/__init__.pyi

@@ -3,7 +3,7 @@ from typing import Sized, overload
 from typing_extensions import Literal, Protocol
 
 class _Vector(Protocol, Sized):
-    def __getitem__(self, i: int) -> float: ...
+    def __getitem__(self, __index: int) -> float: ...
 
 class AnnoyIndex:
     f: int

examples/precision_test.cpp

@@ -16,7 +16,7 @@
 #include <map>
 #include <random>
 
-
+using namespace Annoy;
 int precision(int f=40, int n=1000000){
 	std::chrono::high_resolution_clock::time_point t_start, t_end;
 

setup.py

@@ -38,14 +38,14 @@
 # Various platform-dependent extras
 extra_compile_args = ['-D_CRT_SECURE_NO_WARNINGS', '-fpermissive']
 extra_link_args = []
-
-# Not all CPUs have march as a tuning parameter
-cputune = ['-march=native',]
 if platform.machine() == 'ppc64le':
     extra_compile_args += ['-mcpu=native',]
 
 if platform.machine() == 'x86_64':
-    extra_compile_args += cputune
+    # do not apply march on Intel Darwin
+    if platform.system() != 'Darwin':
+        # Not all CPUs have march as a tuning parameter
+        extra_compile_args += ['-march=native',]
 
 if os.name != 'nt':
     extra_compile_args += ['-O3', '-ffast-math', '-fno-associative-math']
@@ -73,7 +73,7 @@
     extra_link_args = manual_linker_args.split(',')
 
 setup(name='annoy',
-      version='1.17.1',
+      version='1.17.3',
       description='Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk.',
       packages=['annoy'],
       package_data={'annoy': ['__init__.pyi', 'py.typed']},

src/annoylib.h

@@ -1011,7 +1011,11 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
 
   bool on_disk_build(const char* file, char** error=NULL) {
     _on_disk = true;
+#ifndef _MSC_VER
     _fd = open(file, O_RDWR | O_CREAT | O_TRUNC, (int) 0600);
+#else
+    _fd = _open(file, _O_RDWR | _O_CREAT | _O_TRUNC, (int) 0600);
+#endif
     if (_fd == -1) {
       set_error_from_errno(error, "Unable to open");
       _fd = 0;
@@ -1095,7 +1099,11 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
       return true;
     } else {
       // Delete file if it already exists (See issue #335)
+#ifndef _MSC_VER
       unlink(filename);
+#else
+      _unlink(filename);
+#endif
 
       FILE *f = fopen(filename, "wb");
       if (f == NULL) {
@@ -1132,12 +1140,20 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
 
   void unload() {
     if (_on_disk && _fd) {
+#ifndef _MSC_VER
       close(_fd);
+#else
+      _close(_fd);
+#endif
       munmap(_nodes, _s * _nodes_size);
     } else {
       if (_fd) {
         // we have mmapped data
+#ifndef _MSC_VER
         close(_fd);
+#else
+        _close(_fd);
+#endif
         munmap(_nodes, _n_nodes * _s);
       } else if (_nodes) {
         // We have heap allocated data
@@ -1149,7 +1165,11 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
   }
 
   bool load(const char* filename, bool prefault=false, char** error=NULL) {
+#ifndef _MSC_VER
     _fd = open(filename, O_RDONLY, (int)0400);
+#else
+    _fd = _open(filename, _O_RDONLY, (int)0400);
+#endif
     if (_fd == -1) {
       set_error_from_errno(error, "Unable to open");
       _fd = 0;
@@ -1197,7 +1217,7 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
     _loaded = true;
     _built = true;
     _n_items = m;
-    if (_verbose) annoylib_showUpdate("found %lu roots with degree %d\n", _roots.size(), m);
+    if (_verbose) annoylib_showUpdate("found %zu roots with degree %d\n", _roots.size(), m);
     return true;
   }
 
@@ -1387,7 +1407,7 @@ template<typename S, typename T, typename Distance, typename Random, class Threa
     // If we didn't find a hyperplane, just randomize sides as a last option
     while (_split_imbalance(children_indices[0], children_indices[1]) > 0.99) {
       if (_verbose)
-        annoylib_showUpdate("\tNo hyperplane found (left has %ld children, right has %ld children)\n",
+        annoylib_showUpdate("\tNo hyperplane found (left has %zu children, right has %zu children)\n",
           children_indices[0].size(), children_indices[1].size());
 
       children_indices[0].clear();

src/annoymodule.cc

@@ -270,6 +270,8 @@ get_nns_to_python(const vector<int32_t>& result, const vector<float>& distances,
   if ((t = PyTuple_Pack(2, l, d)) == NULL) {
     goto error;
   }
+  Py_XDECREF(l);
+  Py_XDECREF(d);
 
   return t;