datasketches 0.2.3 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ea00e444de6dc1bebc2b8cf878a250f08717d55eaa55f63f6bec28f4be2af00d
-  data.tar.gz: 161b9089e3b8d0dbd99cfb6cc0af463934c42ba85f4788a08306369966f28571
+  metadata.gz: 897dbc30f97ce17f0415630b6347a0092dac05196b0ef61e80939410d65cdf17
+  data.tar.gz: 61302f9cadde8a8badc97b455eb5c32d913c3b1fea8ed571e2da93a29e65afa9
 SHA512:
-  metadata.gz: '09eede1e6e4c0fe57c0116c4e8873670192fea845783687ca34890bd9358af9dd19a535774ab7dd667055cf6acd0d3913f044dcf2274e0ec092b33307250a74a'
-  data.tar.gz: b8bcaeb7af0d27e836f21941663229a2750922914c4f31f4ffbd6e3c3876320f9ce92916eb9730e02227b87e8f244bc08e5bc38541bf4ef4e3485203fff01942
+  metadata.gz: 4d541ba7f96a86f3f8de44f069f6e39d51ba6f28fa5d8c8d1d99a8434a95c5fe1a26470e6b062f348808fe5c0a444134d0dc96385437b4cb946c4a92044a2a5c
+  data.tar.gz: bc1bdacb7cbe69f9bb1382fd2ac7019bec04baf444dc963d63a594e989fd201d9eb9aadd0e463ac4efef8f7ba53915a594d8fb00f74ae295674b9024269a0406

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.2.4 (2021-12-28)
+
+- Updated DataSketches to 3.3.0
+
 ## 0.2.3 (2021-09-29)
 
 - Updated DataSketches to 3.2.0

data/README.md

@@ -1,8 +1,8 @@
-# DataSketches
+# DataSketches Ruby
 
 [DataSketches](https://datasketches.apache.org/) - sketch data structures - for Ruby
 
-[![Build Status](https://github.com/ankane/datasketches/workflows/build/badge.svg?branch=master)](https://github.com/ankane/datasketches/actions)
+[![Build Status](https://github.com/ankane/datasketches-ruby/workflows/build/badge.svg?branch=master)](https://github.com/ankane/datasketches-ruby/actions)
 
 ## Installation
 
@@ -292,22 +292,22 @@ This library is modeled after the DataSketches [Python API](https://github.com/a
 
 ## History
 
-View the [changelog](https://github.com/ankane/datasketches/blob/master/CHANGELOG.md)
+View the [changelog](https://github.com/ankane/datasketches-ruby/blob/master/CHANGELOG.md)
 
 ## Contributing
 
 Everyone is encouraged to help improve this project. Here are a few ways you can help:
 
-- [Report bugs](https://github.com/ankane/datasketches/issues)
-- Fix bugs and [submit pull requests](https://github.com/ankane/datasketches/pulls)
+- [Report bugs](https://github.com/ankane/datasketches-ruby/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/datasketches-ruby/pulls)
 - Write, clarify, or fix documentation
 - Suggest or add new features
 
 To get started with development:
 
 ```sh
-git clone --recursive https://github.com/ankane/datasketches.git
-cd datasketches
+git clone --recursive https://github.com/ankane/datasketches-ruby.git
+cd datasketches-ruby
 bundle install
 bundle exec rake compile
 bundle exec rake test

data/ext/datasketches/theta_wrapper.cpp

@@ -20,10 +20,26 @@ using Rice::Arg;
 
 void init_theta(Rice::Module& m) {
   Rice::define_class_under<theta_sketch>(m, "ThetaSketch")
-    .define_method("empty?", &theta_sketch::is_empty)
-    .define_method("estimate", &theta_sketch::get_estimate)
-    .define_method("lower_bound", &theta_sketch::get_lower_bound)
-    .define_method("upper_bound", &theta_sketch::get_upper_bound);
+    .define_method(
+      "empty?",
+      [](theta_sketch& self) {
+        return self.is_empty();
+      })
+    .define_method(
+      "estimate",
+      [](theta_sketch& self) {
+        return self.get_estimate();
+      })
+    .define_method(
+      "lower_bound",
+      [](theta_sketch& self, uint8_t num_std_devs) {
+        return self.get_lower_bound(num_std_devs);
+      })
+    .define_method(
+      "upper_bound",
+      [](theta_sketch& self, uint8_t num_std_devs) {
+        return self.get_upper_bound(num_std_devs);
+      });
 
   Rice::define_class_under<compact_theta_sketch, theta_sketch>(m, "CompactThetaSketch")
     .define_singleton_function(

data/lib/datasketches/version.rb

@@ -1,3 +1,3 @@
 module DataSketches
-  VERSION = "0.2.3"
+  VERSION = "0.2.4"
 end

data/vendor/datasketches-cpp/CMakeLists.txt

@@ -17,7 +17,7 @@
 
 cmake_minimum_required(VERSION 3.12.0)
 project(DataSketches
-        VERSION 0.12.0
+        VERSION 3.2.0
         LANGUAGES CXX)
 
 include(GNUInstallDirs)
@@ -126,11 +126,30 @@ endif()
 
 # # Installation
 install(TARGETS datasketches
-  EXPORT ${PROJCT_NAME}
+  EXPORT ${PROJECT_NAME}
   PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/DataSketches
   INCLUDES DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/DataSketches
 )
 
+# Packaging
+include(CMakePackageConfigHelpers)
+write_basic_package_version_file(
+    "${CMAKE_CURRENT_BINARY_DIR}/DataSketchesConfigVersion.cmake"
+    VERSION ${PROJECT_VERSION}
+    COMPATIBILITY SameMajorVersion
+)
+configure_package_config_file(
+    cmake/DataSketchesConfig.cmake.in
+    "${CMAKE_CURRENT_BINARY_DIR}/DataSketchesConfig.cmake"
+    INSTALL_DESTINATION lib/DataSketches/cmake
+    PATH_VARS CMAKE_INSTALL_INCLUDEDIR
+)
+install(EXPORT ${PROJECT_NAME} DESTINATION lib/DataSketches/cmake)
+install(FILES "${CMAKE_CURRENT_BINARY_DIR}/DataSketchesConfigVersion.cmake"
+              "${CMAKE_CURRENT_BINARY_DIR}/DataSketchesConfig.cmake"
+        DESTINATION lib/DataSketches/cmake)
+
+
 #set(CPACK_PROJECT_NAME ${PROJECT_NAME})
 #set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
-#include(CPack)
+include(CPack)

data/vendor/datasketches-cpp/MANIFEST.in

@@ -9,11 +9,14 @@ global-exclude .git*
 
 recursive-include python/pybind11 *
 
+graft cmake
 graft common
 graft cpc
 graft fi
 graft hll
 graft kll
+graft req
 graft theta
+graft tuple
 graft sampling
 graft python

data/vendor/datasketches-cpp/README.md

@@ -25,18 +25,85 @@ Installing the latest cmake on OSX: brew install cmake
 Building and running unit tests using cmake for OSX and Linux:
 
 ```
-	$ cd build
-	$ cmake ..
-	$ make
-	$ make test
+    $ cmake -S . -B build/Release -DCMAKE_BUILD_TYPE=Release
+    $ cmake --build build/Release -t all test
 ```
 
 Building and running unit tests using cmake for Windows from the command line:
 
 ```
-	$ cd build
-	$ cmake ..
-	$ cd ..
-	$ cmake --build build --config Release
-	$ cmake --build build --config Release --target RUN_TESTS
+    $ cd build
+    $ cmake ..
+    $ cd ..
+    $ cmake --build build --config Release
+    $ cmake --build build --config Release --target RUN_TESTS
 ```
+
+To install a local distribution (OSX and Linux), use the following command. The
+CMAKE_INSTALL_PREFIX variable controls the destination. If not specified, it 
+defaults to installing in /usr (/usr/include, /usr/lib, etc). In the command below,
+the installation will be in /tmp/install/DataSketches (/tmp/install/DataSketches/include,
+/tmp/install/DataSketches/lib, etc)
+
+```
+    $ cmake -S . -B build/Release -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/tmp/install/DataSketches
+    $ cmake --build build/Release -t install
+```
+
+To generate an installable package using cmake's built in cpack packaging tool,
+use the following command. The type of packaging is controlled by the CPACK_GENERATOR
+variable (semi-colon separated list). Cmake usually supports packaging types such as RPM,
+DEB, STGZ, TGZ, TZ, ZIP, etc.
+
+```
+    $ cmake3 -S . -B build/Release -DCMAKE_BUILD_TYPE=Release -DCPACK_GENERATOR="RPM;STGZ;TGZ" 
+    $ cmake3 --build build/Release -t package
+```
+
+The DataSketches project can be included in other projects' CMakeLists.txt files in one of two ways.
+If DataSketches has been installed on the host (using an RPM, DEB, "make install" into /usr/local, or some 
+way, then CMake's `find_package` command can be used like this:
+
+```
+    find_package(DataSketches 3.2 REQUIRED)
+    target_link_library(my_dependent_target PUBLIC ${DATASKETCHES_LIB})
+```
+
+When used with find_package, DataSketches exports several variables, including
+
+   - `DATASKETCHES_VERSION`: The version number of the datasketches package that was imported.
+   - `DATASKETCHES_INCLUDE_DIR`: The directory that should be added to access DataSketches include files.
+   Because cmake automatically includes the interface directories for included target libraries when
+   using `target_link_library`, under normal circumstances there will be no need to include this directly.
+   - `DATASKETCHES_LIB`: The name of the DataSketches target to include as a dependency. Projects pulling
+   in DataSketches should reference this with `target_link_library` in order to set up all the correct dependencies 
+   and include paths.
+
+If you don't have DataSketches installed locally, dependent projects can pull it directly
+from GitHub using CMake's `ExternalProject` module. The code would look something like this:
+
+```
+    cmake_policy(SET CMP0097 NEW)
+    include(ExternalProject)
+    ExternalProject_Add(datasketches
+        GIT_REPOSITORY https://github.com/apache/datasketches-cpp.git
+        GIT_TAG 3.2.0
+        GIT_SHALLOW true
+        GIT_SUBMODULES ""
+        INSTALL_DIR /tmp/datasketches-prefix
+        CMAKE_ARGS -DBUILD_TESTS=OFF -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DCMAKE_INSTALL_PREFIX=/tmp/datasketches-prefix
+
+        # Override the install command to add DESTDIR
+        # This is necessary to work around an oddity in the RPM (but not other) package
+        # generation, as CMake otherwise picks up the Datasketch files when building
+        # an RPM for a dependent package. (RPM scans the directory for files in addition to installing
+        # those files referenced in an "install" rule in the cmake file)
+        INSTALL_COMMAND env DESTDIR= ${CMAKE_COMMAND} --build . --target install
+    )
+    ExternalProject_Get_property(datasketches INSTALL_DIR)
+    set(datasketches_INSTALL_DIR ${INSTALL_DIR})
+    message("Source dir of datasketches = ${datasketches_INSTALL_DIR}")
+    target_include_directories(my_dependent_target 
+                                PRIVATE ${datasketches_INSTALL_DIR}/include/DataSketches)
+    add_dependencies(my_dependent_target datasketches)
+```

data/vendor/datasketches-cpp/cmake/DataSketchesConfig.cmake.in

@@ -0,0 +1,10 @@
+set(DATASKETCHES_VERSION "@PROJECT_VERSION@")
+
+@PACKAGE_INIT@
+
+include("${CMAKE_CURRENT_LIST_DIR}/DataSketches.cmake")
+
+set_and_check(DATASKETCHES_INCLUDE_DIR "@PACKAGE_CMAKE_INSTALL_INCLUDEDIR@/DataSketches")
+set(DATASKETCHES_LIB "datasketches")
+
+check_required_components("@PROJECT_NAME@")

data/vendor/datasketches-cpp/common/CMakeLists.txt

@@ -29,17 +29,18 @@ target_include_directories(common
 
 target_compile_features(common INTERFACE cxx_std_11)
 
-target_sources(common
-  INTERFACE
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/common_defs.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/memory_operations.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/MurmurHash3.h
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/serde.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/count_zeros.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/inv_pow2_table.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/binomial_bounds.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/conditional_back_inserter.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/conditional_forward.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/ceiling_power_of_2.hpp
-)
+install(TARGETS common EXPORT ${PROJECT_NAME})
 
+install(FILES 
+			include/common_defs.hpp
+			include/memory_operations.hpp
+			include/MurmurHash3.h
+			include/serde.hpp
+			include/count_zeros.hpp
+			include/inv_pow2_table.hpp
+			include/binomial_bounds.hpp
+			include/conditional_back_inserter.hpp
+			include/conditional_forward.hpp
+			include/ceiling_power_of_2.hpp
+			include/bounds_binomial_proportions.hpp
+  DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}/DataSketches")

data/vendor/datasketches-cpp/cpc/CMakeLists.txt

@@ -32,43 +32,23 @@ target_include_directories(cpc
 target_link_libraries(cpc INTERFACE common)
 target_compile_features(cpc INTERFACE cxx_std_11)
 
-set(cpc_HEADERS "")
-list(APPEND cpc_HEADERS "include/compression_data.hpp")
-list(APPEND cpc_HEADERS "include/cpc_common.hpp")
-list(APPEND cpc_HEADERS "include/cpc_compressor.hpp")
-list(APPEND cpc_HEADERS "include/cpc_compressor_impl.hpp")
-list(APPEND cpc_HEADERS "include/cpc_confidence.hpp")
-list(APPEND cpc_HEADERS "include/cpc_sketch.hpp")
-list(APPEND cpc_HEADERS "include/cpc_sketch_impl.hpp")
-list(APPEND cpc_HEADERS "include/cpc_union.hpp")
-list(APPEND cpc_HEADERS "include/cpc_union_impl.hpp")
-list(APPEND cpc_HEADERS "include/cpc_util.hpp")
-list(APPEND cpc_HEADERS "include/icon_estimator.hpp")
-list(APPEND cpc_HEADERS "include/kxp_byte_lookup.hpp")
-list(APPEND cpc_HEADERS "include/u32_table.hpp")
-list(APPEND cpc_HEADERS "include/u32_table_impl.hpp")
-
 install(TARGETS cpc
   EXPORT ${PROJECT_NAME}
 )
 
-install(FILES ${cpc_HEADERS}
+install(FILES 
+			include/compression_data.hpp
+			include/cpc_common.hpp
+			include/cpc_compressor.hpp
+			include/cpc_compressor_impl.hpp
+			include/cpc_confidence.hpp
+			include/cpc_sketch.hpp
+			include/cpc_sketch_impl.hpp
+			include/cpc_union.hpp
+			include/cpc_union_impl.hpp
+			include/cpc_util.hpp
+			include/icon_estimator.hpp
+			include/kxp_byte_lookup.hpp
+			include/u32_table.hpp
+			include/u32_table_impl.hpp
   DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}/DataSketches")
-
-target_sources(cpc
-  INTERFACE
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/compression_data.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_common.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_compressor.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_compressor_impl.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_confidence.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_sketch.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_sketch_impl.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_union.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_union_impl.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/cpc_util.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/icon_estimator.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/kxp_byte_lookup.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/u32_table.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/u32_table_impl.hpp
-)

data/vendor/datasketches-cpp/cpc/include/cpc_sketch_impl.hpp

@@ -381,7 +381,9 @@ void cpc_sketch_alloc<A>::refresh_kxp(const uint64_t* bit_matrix) {
 
 template<typename A>
 string<A> cpc_sketch_alloc<A>::to_string() const {
-  std::basic_ostringstream<char, std::char_traits<char>, AllocChar<A>> os;
+  // Using a temporary stream for implementation here does not comply with AllocatorAwareContainer requirements.
+  // The stream does not support passing an allocator instance, and alternatives are complicated.
+  std::ostringstream os;
   os << "### CPC sketch summary:" << std::endl;
   os << "   lg_k           : " << std::to_string(lg_k) << std::endl;
   os << "   seed hash      : " << std::hex << compute_seed_hash(seed) << std::dec << std::endl;
@@ -392,14 +394,14 @@ string<A> cpc_sketch_alloc<A>::to_string() const {
     os << "   HIP estimate   : " << hip_est_accum << std::endl;
     os << "   kxp            : " << kxp << std::endl;
   }
-  os << "   intresting col : " << std::to_string(first_interesting_column) << std::endl;
+  os << "   interesting col: " << std::to_string(first_interesting_column) << std::endl;
   os << "   table entries  : " << surprising_value_table.get_num_items() << std::endl;
   os << "   window         : " << (sliding_window.size() == 0 ? "not " : "") <<  "allocated" << std::endl;
   if (sliding_window.size() > 0) {
     os << "   window offset  : " << std::to_string(window_offset) << std::endl;
   }
   os << "### End sketch summary" << std::endl;
-  return os.str();
+  return string<A>(os.str().c_str(), sliding_window.get_allocator());
 }
 
 template<typename A>

data/vendor/datasketches-cpp/cpc/include/cpc_union_impl.hpp

@@ -34,7 +34,7 @@ bit_matrix(allocator)
   if (lg_k < CPC_MIN_LG_K || lg_k > CPC_MAX_LG_K) {
     throw std::invalid_argument("lg_k must be >= " + std::to_string(CPC_MIN_LG_K) + " and <= " + std::to_string(CPC_MAX_LG_K) + ": " + std::to_string(lg_k));
   }
-  accumulator = new (AllocCpc().allocate(1)) cpc_sketch_alloc<A>(lg_k, seed, allocator);
+  accumulator = new (AllocCpc(allocator).allocate(1)) cpc_sketch_alloc<A>(lg_k, seed, allocator);
 }
 
 template<typename A>
@@ -45,7 +45,7 @@ accumulator(other.accumulator),
 bit_matrix(other.bit_matrix)
 {
   if (accumulator != nullptr) {
-    accumulator = new (AllocCpc().allocate(1)) cpc_sketch_alloc<A>(*other.accumulator);
+    accumulator = new (AllocCpc(accumulator->get_allocator()).allocate(1)) cpc_sketch_alloc<A>(*other.accumulator);
   }
 }
 
@@ -62,8 +62,9 @@ bit_matrix(std::move(other.bit_matrix))
 template<typename A>
 cpc_union_alloc<A>::~cpc_union_alloc() {
   if (accumulator != nullptr) {
+    AllocCpc allocator(accumulator->get_allocator());
     accumulator->~cpc_sketch_alloc<A>();
-    AllocCpc().deallocate(accumulator, 1);
+    allocator.deallocate(accumulator, 1);
   }
 }
 
@@ -181,7 +182,7 @@ template<typename A>
 cpc_sketch_alloc<A> cpc_union_alloc<A>::get_result_from_accumulator() const {
   if (lg_k != accumulator->get_lg_k()) throw std::logic_error("lg_k != accumulator->lg_k");
   if (accumulator->get_num_coupons() == 0) {
-    return cpc_sketch_alloc<A>(lg_k, seed);
+    return cpc_sketch_alloc<A>(lg_k, seed, accumulator->get_allocator());
   }
   if (accumulator->determine_flavor() != cpc_sketch_alloc<A>::flavor::SPARSE) throw std::logic_error("wrong flavor");
   cpc_sketch_alloc<A> copy(*accumulator);
@@ -242,8 +243,9 @@ cpc_sketch_alloc<A> cpc_union_alloc<A>::get_result_from_bit_matrix() const {
 template<typename A>
 void cpc_union_alloc<A>::switch_to_bit_matrix() {
   bit_matrix = accumulator->build_bit_matrix();
+  AllocCpc allocator(accumulator->get_allocator());
   accumulator->~cpc_sketch_alloc<A>();
-  AllocCpc().deallocate(accumulator, 1);
+  allocator.deallocate(accumulator, 1);
   accumulator = nullptr;
 }
 
@@ -324,7 +326,7 @@ void cpc_union_alloc<A>::reduce_k(uint8_t new_lg_k) {
     if (bit_matrix.size() > 0) throw std::logic_error("bit_matrix is not expected");
     if (!accumulator->is_empty()) {
       cpc_sketch_alloc<A> old_accumulator(*accumulator);
-      *accumulator = cpc_sketch_alloc<A>(new_lg_k, seed);
+      *accumulator = cpc_sketch_alloc<A>(new_lg_k, seed, old_accumulator.get_allocator());
       walk_table_updating_sketch(old_accumulator.surprising_value_table);
     }
     lg_k = new_lg_k;

data/vendor/datasketches-cpp/cpc/test/cpc_sketch_allocation_test.cpp

@@ -25,6 +25,7 @@
 #include <catch.hpp>
 
 #include "cpc_sketch.hpp"
+#include "cpc_union.hpp"
 #include "test_allocator.hpp"
 
 namespace datasketches {
@@ -234,4 +235,20 @@ TEST_CASE("cpc sketch allocation: serialize deserialize sliding, bytes", "[cpc_s
   REQUIRE(test_allocator_net_allocations == 0);
 }
 
+using cpc_union_test_alloc = cpc_union_alloc<test_allocator<uint8_t>>;
+
+TEST_CASE("cpc sketch allocation: union") {
+  cpc_sketch_test_alloc s1(11, DEFAULT_SEED, 0);
+  s1.update(1);
+
+  cpc_sketch_test_alloc s2(11, DEFAULT_SEED, 0);
+  s2.update(2);
+
+  cpc_union_test_alloc u(11, DEFAULT_SEED, 0);
+  u.update(s1);
+  u.update(s2);
+  auto s3 = u.get_result();
+  REQUIRE_FALSE(s3.is_empty());
+}
+
 } /* namespace datasketches */

data/vendor/datasketches-cpp/fi/CMakeLists.txt

@@ -32,23 +32,13 @@ target_include_directories(fi
 target_link_libraries(fi INTERFACE common)
 target_compile_features(fi INTERFACE cxx_std_11)
 
-set(fi_HEADERS "")
-list(APPEND fi_HEADERS "include/frequent_items_sketch.hpp")
-list(APPEND fi_HEADERS "include/frequent_items_sketch_impl.hpp")
-list(APPEND fi_HEADERS "include/reverse_purge_hash_map.hpp")
-list(APPEND fi_HEADERS "include/reverse_purge_hash_map_impl.hpp")
-
 install(TARGETS fi
   EXPORT ${PROJECT_NAME}
 )
 
-install(FILES ${fi_HEADERS}
+install(FILES 
+		include/frequent_items_sketch.hpp
+		include/frequent_items_sketch_impl.hpp
+		include/reverse_purge_hash_map.hpp
+		include/reverse_purge_hash_map_impl.hpp
   DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}/DataSketches")
-
-target_sources(fi
-  INTERFACE
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/frequent_items_sketch.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/frequent_items_sketch_impl.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/reverse_purge_hash_map.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/reverse_purge_hash_map_impl.hpp
-)

data/vendor/datasketches-cpp/fi/include/frequent_items_sketch_impl.hpp

@@ -421,7 +421,9 @@ void frequent_items_sketch<T, W, H, E, S, A>::check_size(uint8_t lg_cur_size, ui
 
 template<typename T, typename W, typename H, typename E, typename S, typename A>
 string<A> frequent_items_sketch<T, W, H, E, S, A>::to_string(bool print_items) const {
-  std::basic_ostringstream<char, std::char_traits<char>, AllocChar<A>> os;
+  // Using a temporary stream for implementation here does not comply with AllocatorAwareContainer requirements.
+  // The stream does not support passing an allocator instance, and alternatives are complicated.
+  std::ostringstream os;
   os << "### Frequent items sketch summary:" << std::endl;
   os << "   lg cur map size  : " << (int) map.get_lg_cur_size() << std::endl;
   os << "   lg max map size  : " << (int) map.get_lg_max_size() << std::endl;
@@ -444,7 +446,7 @@ string<A> frequent_items_sketch<T, W, H, E, S, A>::to_string(bool print_items) c
     }
     os << "### End items" << std::endl;
   }
-  return os.str();
+  return string<A>(os.str().c_str(), map.get_allocator());
 }
 
 // version for integral signed type

data/vendor/datasketches-cpp/hll/CMakeLists.txt

@@ -32,64 +32,41 @@ target_include_directories(hll
 target_link_libraries(hll INTERFACE common)
 target_compile_features(hll INTERFACE cxx_std_11)
 
-# TODO: would be useful if this didn't need to be reproduced in target_sources(), too
-set(hll_HEADERS "")
-list(APPEND hll_HEADERS "include/hll.hpp;include/AuxHashMap.hpp;include/CompositeInterpolationXTable.hpp")
-list(APPEND hll_HEADERS "include/hll.private.hpp;include/HllSketchImplFactory.hpp")
-list(APPEND hll_HEADERS "include/CouponHashSet.hpp;include/CouponList.hpp")
-list(APPEND hll_HEADERS "include/CubicInterpolation.hpp;include/HarmonicNumbers.hpp;include/Hll4Array.hpp")
-list(APPEND hll_HEADERS "include/Hll6Array.hpp;include/Hll8Array.hpp;include/HllArray.hpp")
-list(APPEND hll_HEADERS "include/HllSketchImpl.hpp")
-list(APPEND hll_HEADERS "include/HllUtil.hpp;include/coupon_iterator.hpp")
-list(APPEND hll_HEADERS "include/RelativeErrorTables.hpp;include/AuxHashMap-internal.hpp")
-list(APPEND hll_HEADERS "include/CompositeInterpolationXTable-internal.hpp")
-list(APPEND hll_HEADERS "include/CouponHashSet-internal.hpp;include/CouponList-internal.hpp")
-list(APPEND hll_HEADERS "include/CubicInterpolation-internal.hpp;include/HarmonicNumbers-internal.hpp")
-list(APPEND hll_HEADERS "include/Hll4Array-internal.hpp;include/Hll6Array-internal.hpp")
-list(APPEND hll_HEADERS "include/Hll8Array-internal.hpp;include/HllArray-internal.hpp")
-list(APPEND hll_HEADERS "include/HllSketch-internal.hpp")
-list(APPEND hll_HEADERS "include/HllSketchImpl-internal.hpp;include/HllUnion-internal.hpp")
-list(APPEND hll_HEADERS "include/coupon_iterator-internal.hpp;include/RelativeErrorTables-internal.hpp")
-
 install(TARGETS hll
   EXPORT ${PROJECT_NAME}
 )
 
-install(FILES ${hll_HEADERS}
+install(FILES 
+			include/hll.hpp
+			include/AuxHashMap.hpp
+			include/CompositeInterpolationXTable.hpp
+			include/hll.private.hpp
+			include/HllSketchImplFactory.hpp
+			include/CouponHashSet.hpp
+			include/CouponList.hpp
+			include/CubicInterpolation.hpp
+			include/HarmonicNumbers.hpp
+			include/Hll4Array.hpp
+			include/Hll6Array.hpp
+			include/Hll8Array.hpp
+			include/HllArray.hpp
+			include/HllSketchImpl.hpp
+			include/HllUtil.hpp
+			include/coupon_iterator.hpp
+			include/RelativeErrorTables.hpp
+			include/AuxHashMap-internal.hpp
+			include/CompositeInterpolationXTable-internal.hpp
+			include/CouponHashSet-internal.hpp
+			include/CouponList-internal.hpp
+			include/CubicInterpolation-internal.hpp
+			include/HarmonicNumbers-internal.hpp
+			include/Hll4Array-internal.hpp
+			include/Hll6Array-internal.hpp
+			include/Hll8Array-internal.hpp
+			include/HllArray-internal.hpp
+			include/HllSketch-internal.hpp
+			include/HllSketchImpl-internal.hpp
+			include/HllUnion-internal.hpp
+			include/coupon_iterator-internal.hpp
+			include/RelativeErrorTables-internal.hpp
   DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}/DataSketches")
-
-target_sources(hll
-  INTERFACE
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/hll.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/hll.private.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/AuxHashMap.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CompositeInterpolationXTable.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CouponHashSet.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CouponList.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CubicInterpolation.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HarmonicNumbers.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll4Array.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll6Array.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll8Array.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllArray.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllSketchImpl.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllSketchImplFactory.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllUtil.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/RelativeErrorTables.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/coupon_iterator.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/AuxHashMap-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CompositeInterpolationXTable-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CouponHashSet-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CouponList-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/CubicInterpolation-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HarmonicNumbers-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll4Array-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll6Array-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/Hll8Array-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllArray-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllSketch-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllSketchImpl-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/HllUnion-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/RelativeErrorTables-internal.hpp
-    ${CMAKE_CURRENT_SOURCE_DIR}/include/coupon_iterator-internal.hpp
-)

data/vendor/datasketches-cpp/hll/include/HllSketch-internal.hpp

@@ -246,10 +246,12 @@ string<A> hll_sketch_alloc<A>::to_string(const bool summary,
                                          const bool detail,
                                          const bool aux_detail,
                                          const bool all) const {
-  std::basic_ostringstream<char, std::char_traits<char>, AllocChar<A>> os;
+  // Using a temporary stream for implementation here does not comply with AllocatorAwareContainer requirements.
+  // The stream does not support passing an allocator instance, and alternatives are complicated.
+  std::stringstream os;
   if (summary) {
     os << "### HLL sketch summary:" << std::endl
-       << "  Log Config K   : " << get_lg_config_k() << std::endl
+       << "  Log Config K   : " << std::to_string(get_lg_config_k()) << std::endl
        << "  Hll Target     : " << type_as_string() << std::endl
        << "  Current Mode   : " << mode_as_string() << std::endl
        << "  LB             : " << get_lower_bound(1) << std::endl
@@ -258,7 +260,7 @@ string<A> hll_sketch_alloc<A>::to_string(const bool summary,
        << "  OutOfOrder flag: " << (is_out_of_order_flag() ? "true" : "false") << std::endl;
     if (get_current_mode() == HLL) {
       HllArray<A>* hllArray = (HllArray<A>*) sketch_impl;
-      os << "  CurMin         : " << hllArray->getCurMin() << std::endl
+      os << "  CurMin         : " << std::to_string(hllArray->getCurMin()) << std::endl
          << "  NumAtCurMin    : " << hllArray->getNumAtCurMin() << std::endl
          << "  HipAccum       : " << hllArray->getHipAccum() << std::endl
          << "  KxQ0           : " << hllArray->getKxQ0() << std::endl
@@ -338,7 +340,7 @@ string<A> hll_sketch_alloc<A>::to_string(const bool summary,
     }
   }
 
-  return os.str();
+  return string<A>(os.str().c_str(), sketch_impl->getAllocator());
 }
 
 template<typename A>