Pull master into 6.1.X

.github/workflows/check_cpp_files.yml → .github/workflows/auto-check_cpp_files.yml

@@ -2,8 +2,7 @@ name: Serialization Compatibility Test
 
 on:
   push:
-    branches:
-      - master
+    branches: [ master, main ]
   workflow_dispatch:
 
 jobs:
@@ -12,12 +11,17 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Checkout C++
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           repository: apache/datasketches-cpp
           path: cpp
+      - name: Setup Java
+        uses: actions/setup-java@v4
+        with:
+          java-version: '11'
+          distribution: 'temurin'
       - name: Configure C++ build
         run: cd cpp/build && cmake .. -DGENERATE=true
       - name: Build C++ unit tests

.github/workflows/auto-jdk-matrix.yml

@@ -3,7 +3,7 @@ name: DataSketches-Java Auto JDK Matrix Test & Install
 on:
     pull_request:
     push:
-        branches: [ master ]
+        branches: [ master, main ]
     workflow_dispatch:
 
 env:
@@ -13,43 +13,47 @@ jobs:
     build:
         name: Build, Test, Install
         runs-on: ubuntu-latest
+
         strategy:
           fail-fast: false
           matrix:
               jdk: [ 8,11 ]
+
         env:
           JDK_VERSION: ${{ matrix.jdk }}
 
         steps:
         - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
-          uses: actions/checkout@v3
+          uses: actions/checkout@v4
           with:
               persist-credentials: false
 
+        - name: Print Current workflow
+          run: >
+             cat .github/workflows/auto-jdk-matrix.yml
+
         - name: Cache local Maven repository
-          uses: actions/cache@v3
+          uses: actions/cache@v4
           with:
               path: ~/.m2/repository
               key: build-${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}
               restore-keys: build-${{ runner.os }}-maven-
 
         - name: Install Matrix JDK
-          uses: actions/setup-java@v3
+          uses: actions/setup-java@v4
           with:
               java-version: ${{ matrix.jdk }}
               distribution: 'temurin'
               java-package: jdk
               architecture: x64 
-# Architecture options: x86, x64, armv7, aarch64, ppc64le
-# setup-java@v3 has a "with cache" option
 
         - name: Echo Java Version
           run: >
               java -version
 
         - name: Test
           run: >
-              mvn clean test
+              mvn clean test -B
               -Dmaven.javadoc.skip=true
               -Dgpg.skip=true
 
@@ -59,7 +63,10 @@ jobs:
               -DskipTests=true
               -Dgpg.skip=true
 
+# Architecture options: x86, x64, armv7, aarch64, ppc64le
+# setup-java@v3 has a "with cache" option
 # Lifecycle: validate, compile, test, package, verify, install, deploy
 # -B batch mode
 # -V show Version without stopping
+# -X debug mode
 # -q quiet, only show errors

.github/workflows/manual-os-matrix.yml → .github/workflows/auto-os-matrix.yml

@@ -1,19 +1,23 @@
-name: DataSketches-Java Manual OS Matrix Test & Install
+name: DataSketches-Java 8 Auto OS Matrix Test & Install
 
 on:
+    pull_request:
+    push:
+        branches: [ master, main ]
     workflow_dispatch:
 
 env:
-    MAVEN_OPTS: -Xmx4g -Xms1g
+    MAVEN_OPTS: -Xmx1g -Xms1g
 
 jobs:
     build:
         name: Build, Test, Install
-        runs-on: ${{matrix.os}}
+
         strategy:
           fail-fast: false
+
           matrix:
-            jdk: [ 8, 11 ]
+            jdk: [ 8 ]
             os: [ windows-latest, ubuntu-latest, macos-latest ]
             include:
               - os: windows-latest
@@ -26,31 +30,31 @@ jobs:
                 skip_javadoc: -Dmaven.javadoc.skip=true
                 skip_gpg: -Dgpg.skip=true
 
+        runs-on: ${{matrix.os}}
+
         env:
           JDK_VERSION: ${{ matrix.jdk }}
 
         steps:
         - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
-          uses: actions/checkout@v3
+          uses: actions/checkout@v4
           with:
               persist-credentials: false
 
         - name: Cache local Maven repository
-          uses: actions/cache@v3
+          uses: actions/cache@v4
           with:
               path: ~/.m2/repository
               key: build-${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}
               restore-keys: build-${{ runner.os }}-maven-
 
         - name: Install Matrix JDK
-          uses: actions/setup-java@v3
+          uses: actions/setup-java@v4
           with:
               java-version: ${{ matrix.jdk }}
               distribution: 'temurin'
               java-package: jdk
               architecture: x64 
-# Architecture options: x86, x64, armv7, aarch64, ppc64le
-# setup-java@v3 has a "with cache" option
 
         - name: Echo Java Version
           run: >
@@ -69,6 +73,8 @@ jobs:
               -D skipTests=true
               ${{matrix.os.skip_gpg}}
 
+# Architecture options: x86, x64, armv7, aarch64, ppc64le
+# setup-java@v4 has a "with cache" option
 # Lifecycle: validate, compile, test, package, verify, install, deploy
 # -B batch mode
 # -V show Version without stopping

.github/workflows/codeql-analysis.yml → .github/workflows/manual-codeql-analysis.yml

@@ -1,13 +1,6 @@
 name: "CodeQL"
 
 on:
-  push:
-    branches: [ 'master' ]
-  pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [ 'master' ]
-  schedule:
-    - cron: '10 17 * * 4'
   workflow_dispatch:
 
 jobs:
@@ -28,11 +21,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.

.github/workflows/javadoc.yml → .github/workflows/manual-javadoc.yml

@@ -1,17 +1,14 @@
 name: JavaDoc
 
 on:
-  push:
-    branches:
-      - master
   workflow_dispatch:
 
 jobs:
   javadoc:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Generate JavaDoc
         run: mvn javadoc:javadoc
       - name: Deploy JavaDoc

.gitignore

@@ -10,6 +10,9 @@
 *.ipr
 *.iws
 
+# VSCode project files
+**/.vscode/
+
 # Additional tools
 .clover/
 

pom.xml

@@ -33,7 +33,7 @@ under the License.
 
   <groupId>org.apache.datasketches</groupId>
   <artifactId>datasketches-java</artifactId>
-  <version>6.1.0-SNAPSHOT</version>
+  <version>6.2.0-SNAPSHOT</version>
   <packaging>jar</packaging>
 
   <name>${project.artifactId}</name>
@@ -83,7 +83,7 @@ under the License.
   </developers>
 
   <properties>
-    <datasketches-memory.version>3.0.0</datasketches-memory.version>
+    <datasketches-memory.version>3.0.2</datasketches-memory.version>
 
     <!-- Test -->
     <testng.version>7.5.1</testng.version>

src/main/java/org/apache/datasketches/filters/bloomfilter/BloomFilter.java

@@ -33,8 +33,8 @@
 import org.apache.datasketches.memory.XxHash;
 
 /**
- * <p>A Bloom filter is a data structure that can be used for probabilistic
- * set membership.</p>
+ * A Bloom filter is a data structure that can be used for probabilistic
+ * set membership.
  *
  * <p>When querying a Bloom filter, there are no false positives. Specifically:
  * When querying an item that has already been inserted to the filter, the filter will

src/main/java/org/apache/datasketches/filters/bloomfilter/BloomFilterBuilder.java

@@ -25,8 +25,8 @@
 import org.apache.datasketches.memory.WritableMemory;
 
 /**
- * <p>This class provides methods to help estimate the correct parameters when
- * creating a Bloom filter, and methods to create the filter using those values.</p>
+ * This class provides methods to help estimate the correct parameters when
+ * creating a Bloom filter, and methods to create the filter using those values.
  *
  * <p>The underlying math is described in the
  * <a href='https://en.wikipedia.org/wiki/Bloom_filter#Optimal_number_of_hash_functions'>

src/main/java/org/apache/datasketches/frequencies/ItemsSketch.java

@@ -55,10 +55,10 @@
 import org.apache.datasketches.memory.WritableMemory;
 
 /**
- * <p>This sketch is useful for tracking approximate frequencies of items of type <i>&lt;T&gt;</i>
+ * This sketch is useful for tracking approximate frequencies of items of type <i>&lt;T&gt;</i>
  * with optional associated counts (<i>&lt;T&gt;</i> item, <i>long</i> count) that are members of a
  * multiset of such items. The true frequency of an item is defined to be the sum of associated
- * counts.</p>
+ * counts.
  *
  * <p>This implementation provides the following capabilities:</p>
  * <ul>

src/main/java/org/apache/datasketches/frequencies/LongsSketch.java

@@ -54,9 +54,9 @@
 import org.apache.datasketches.memory.WritableMemory;
 
 /**
- * <p>This sketch is useful for tracking approximate frequencies of <i>long</i> items with optional
+ * This sketch is useful for tracking approximate frequencies of <i>long</i> items with optional
  * associated counts (<i>long</i> item, <i>long</i> count) that are members of a multiset of
- * such items. The true frequency of an item is defined to be the sum of associated counts.</p>
+ * such items. The true frequency of an item is defined to be the sum of associated counts.
  *
  * <p>This implementation provides the following capabilities:</p>
  * <ul>

src/main/java/org/apache/datasketches/frequencies/PreambleUtil.java

@@ -31,12 +31,11 @@
 /**
  * This class defines the preamble data structure and provides basic utilities for some of the key
  * fields.
- * <p>
- * The intent of the design of this class was to isolate the detailed knowledge of the bit and byte
+ *
+ * <p>The intent of the design of this class was to isolate the detailed knowledge of the bit and byte
  * layout of the serialized form of the sketches derived from the Sketch class into one place. This
  * allows the possibility of the introduction of different serialization schemes with minimal impact
- * on the rest of the library.
- * </p>
+ * on the rest of the library.</p>
  *
  * <p>
  * MAP: Low significance bytes of this <i>long</i> data structure are on the right. However, the

src/main/java/org/apache/datasketches/hash/MurmurHash3.java

@@ -29,10 +29,8 @@
 import org.apache.datasketches.memory.Memory;
 
 /**
- * <p>
  * The MurmurHash3 is a fast, non-cryptographic, 128-bit hash function that has
  * excellent avalanche and 2-way bit independence properties.
- * </p>
  *
  * <p>
  * Austin Appleby's C++