Merge pull request #19 from jlmelville/hnsw0.8.0

Hnsw0.8.0

DESCRIPTION

@@ -1,23 +1,30 @@
 Package: RcppHNSW
-Title: 'Rcpp' Bindings for 'hnswlib', a Library for Approximate Nearest Neighbors
-Version: 0.5.9000
-Authors@R: c(person("James", "Melville", email = "[email protected]", 
-  role = c("aut", "cre")), 
-  person("Aaron", "Lun", role = "ctb"), 
-  person("Samuel", "Granjeaud", role = "ctb"),
-  person("Dmitriy", "Selivanov", role = "ctb"),
-  person("Yuxing", "Liao", role = "ctb"))
-Description: 'Hnswlib' is a C++ library for Approximate Nearest Neighbors. This 
- package provides a minimal R interface by relying on the 'Rcpp' package. See 
- <https://github.com/nmslib/hnswlib> for more on 'hnswlib'. 'hnswlib' is 
- released under Version 2.0 of the Apache License.
+Title: 'Rcpp' Bindings for 'hnswlib', a Library for Approximate Nearest
+    Neighbors
+Version: 0.6.0
+Authors@R: c(
+    person("James", "Melville", , "[email protected]", role = c("aut", "cre", "cph")),
+    person("Aaron", "Lun", role = "ctb"),
+    person("Samuel", "Granjeaud", role = "ctb"),
+    person("Dmitriy", "Selivanov", role = "ctb"),
+    person("Yuxing", "Liao", role = "ctb")
+  )
+Description: 'Hnswlib' is a C++ library for Approximate Nearest Neighbors.
+    This package provides a minimal R interface by relying on the 'Rcpp'
+    package. See <https://github.com/nmslib/hnswlib> for more on
+    'hnswlib'. 'hnswlib' is released under Version 2.0 of the Apache
+    License.
 License: GPL (>= 3)
 URL: https://github.com/jlmelville/rcpphnsw
 BugReports: https://github.com/jlmelville/rcpphnsw/issues
+Imports: 
+    methods,
+    Rcpp (>= 0.11.3)
+Suggests: 
+    covr,
+    testthat
+LinkingTo: 
+    Rcpp
 Encoding: UTF-8
-Imports: methods, Rcpp (>= 0.11.3)
-LinkingTo: Rcpp
-RoxygenNote: 7.2.3
-Suggests: testthat,
-    covr
 Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.3.1

NEWS.md

@@ -1,4 +1,8 @@
-# RcppHNSW 0.5.9000
+# RcppHNSW 0.6.0
+
+## New features
+
+* Updated hnswlib to [version 0.8.0](https://github.com/nmslib/hnswlib/releases/tag/v0.8.0).
 
 # RcppHNSW 0.5.0
 

cran-comments.md

@@ -1,64 +1,46 @@
 ## Release Summary
 
-This is a patch release to fix various CRAN check errors.
+This is a patch release for a new version of the underlying hnswlib library.
 
 ## Test environments
 
-* ubuntu 22.04 (on github actions), R 4.2.3, R 4.3.1, devel
-* local ubuntu 23.04 R 4.2.2
+* ubuntu 22.04 (on github actions), R 4.2.3, R 4.3.2, devel
+* local ubuntu 23.10 R 4.3.1
 * Debian Linux, R-devel, GCC ASAN/UBSAN (via rhub)
 * Debian Linux, R-release, GCC (via rhub)
+* Debian Linux, R-release, GCC valgrind (via rhub)
 * Ubuntu Linux 20.04.1 LTS, R-release, GCC (via rhub)
 * Fedora Linux, R-devel, clang, gfortran (via rhub)
-* Windows Server 2022 (on github actions), R 4.2.3, R 4.3.1
+* Windows Server 2022 (on github actions), R 4.2.3, R 4.3.2
 * Windows Server 2022, R-devel, 64 bit (via rhub)
-* local Windows 11 build, R 4.3.1
+* local Windows 11 build, R 4.3.2
 * win-builder (devel)
-* mac OS X Monterey (on github actions) R 4.3.1
+* local mac OS X Sonoma R 4.3.2
+* mac OS X Monterey (on github actions) R 4.3.2
 
 ## R CMD check results
 
 There were no ERRORs or WARNINGs.
 
 There was one NOTE:
 
-N  checking installed package size ...
-     installed size is  6.6Mb
-     sub-directories of 1Mb or more:
-       libs   6.3Mb
+* checking installed package size ... NOTE
+  installed size is  6.7Mb
+  sub-directories of 1Mb or more:
+    libs   6.4Mb
 
 This is expected due to the use of C++ templates in hnswlib.
 
-This is spelled correctly.
-
 ## CRAN checks
 
 There are no ERRORs or WARNINGs.
 
-There is a NOTE:
-
-Check: C++ specification
-Result: NOTE
-     Specified C++11: please drop specification unless essential
-
-This submission fixes this.
-
-There is a NOTE:
-
-Check: Rd metadata
-Result: NOTE
-    Invalid package aliases in Rd file ‘RcppHnsw-package.Rd’:
-     ‘RcppHnsw-package’
-
-This submissions fixes this.
-
-There are four flavors with NOTEs about installed package size (r-release-macos-arm64,
-r-release-macos-x86_64, r-oldrel-macos-arm64, r-oldrel-macos-x86_64). This is expected and won't be
-fixed.
+There are three flavors with NOTEs about installed package size (r-release-macos-arm64,
+r-release-macos-x86_64, r-oldrel-macos-arm64). This is expected and won't be fixed.
 
 ## Downstream dependencies
 
-We checked 2 reverse dependencies (0 from CRAN + 2 from Bioconductor), comparing R CMD check
+We checked 3 reverse dependencies (1 from CRAN + 2 from Bioconductor), comparing R CMD check
 results across CRAN and dev versions of this package.
 
 * We saw 0 new problems

inst/include/bruteforce.h

@@ -84,10 +84,16 @@ class BruteforceSearch : public AlgorithmInterface<dist_t> {
 
 
     void removePoint(labeltype cur_external) {
-        size_t cur_c = dict_external_to_internal[cur_external];
+        std::unique_lock<std::mutex> lock(index_lock);
 
-        dict_external_to_internal.erase(cur_external);
+        auto found = dict_external_to_internal.find(cur_external);
+        if (found == dict_external_to_internal.end()) {
+            return;
+        }
+
+        dict_external_to_internal.erase(found);
 
+        size_t cur_c = found->second;
         labeltype label = *((labeltype*)(data_ + size_per_element_ * (cur_element_count-1) + data_size_));
         dict_external_to_internal[label] = cur_c;
         memcpy(data_ + size_per_element_ * cur_c,
@@ -106,7 +112,7 @@ class BruteforceSearch : public AlgorithmInterface<dist_t> {
             dist_t dist = fstdistfunc_(query_data, data_ + size_per_element_ * i, dist_func_param_);
             labeltype label = *((labeltype*) (data_ + size_per_element_ * i + data_size_));
             if ((!isIdAllowed) || (*isIdAllowed)(label)) {
-                topResults.push(std::pair<dist_t, labeltype>(dist, label));
+                topResults.emplace(dist, label);
             }
         }
         dist_t lastdist = topResults.empty() ? std::numeric_limits<dist_t>::max() : topResults.top().first;
@@ -115,7 +121,7 @@ class BruteforceSearch : public AlgorithmInterface<dist_t> {
             if (dist <= lastdist) {
                 labeltype label = *((labeltype *) (data_ + size_per_element_ * i + data_size_));
                 if ((!isIdAllowed) || (*isIdAllowed)(label)) {
-                    topResults.push(std::pair<dist_t, labeltype>(dist, label));
+                    topResults.emplace(dist, label);
                 }
                 if (topResults.size() > k)
                     topResults.pop();