Merge branch 'master' into java8-11_changes_consistent_with_17

README.md

@@ -18,8 +18,6 @@
 -->
 
 [![Maven Central](https://maven-badges.herokuapp.com/maven-central/org.apache.datasketches/datasketches-java/badge.svg)](https://maven-badges.herokuapp.com/maven-central/org.apache.datasketches/datasketches-java)
-[![Language grade: Java](https://img.shields.io/lgtm/grade/java/g/apache/datasketches-java.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/apache/datasketches-java/context:java)
-[![Total alerts](https://img.shields.io/lgtm/alerts/g/apache/datasketches-java.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/apache/datasketches-java/alerts/)
 [![Coverage Status](https://coveralls.io/repos/github/apache/datasketches-java/badge.svg)](https://coveralls.io/github/apache/datasketches-java)
 
 =================
@@ -29,8 +27,7 @@ This is the core Java component of the DataSketches library.  It contains all of
 
 This component is also a dependency of other components of the library that create adaptors for target systems, such as the [Apache Pig adaptor](https://github.com/apache/datasketches-pig) and the [Apache Hive adaptor](https://github.com/apache/datasketches-hive).
 
-Note that we have a parallel core component for C++ and Python implementations of the same sketch algorithms, 
-[datasketches-cpp](https://github.com/apache/datasketches-cpp).
+Note that we have a parallel core components for [C++](https://github.com/apache/datasketches-cpp) and [Python](https://github.com/apache/datasketches-python) implementations of the same sketch algorithms.
 
 Please visit the main [DataSketches website](https://datasketches.apache.org) for more information. 
 

src/main/java/org/apache/datasketches/kll/KllHeapItemsSketch.java

@@ -36,7 +36,7 @@
 import org.apache.datasketches.memory.WritableMemory;
 
 /**
- * This class implements an on-heap doubles KllSketch.
+ * This class implements an on-heap items KllSketch.
  *
  * <p>Please refer to the documentation in the package-info:<br>
  * {@link org.apache.datasketches.kll}</p>

src/test/java/org/apache/datasketches/kll/KllItemsSketchTest.java

@@ -570,7 +570,7 @@ public void checkCDF_PDF() {
   }
 
   @Test
-  public void checkWrapCase1Floats() {
+  public void checkWrapCase1Item() {
     KllItemsSketch<String> sk = KllItemsSketch.newHeapInstance(20, Comparator.naturalOrder(), serDe);
     final int n = 21;
     final int digits = Util.numDigits(n);

src/test/java/org/apache/datasketches/kll/KllMiscItemsTest.java

@@ -293,7 +293,7 @@ public void checkSketchInitializeItemsHeap() {
     final int digits = Util.numDigits(n);
     KllItemsSketch<String> sk;
 
-    println("#### CASE: FLOAT FULL HEAP");
+    println("#### CASE: ITEM FULL HEAP");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     for (int i = 1; i <= n; i++) { sk.update(Util.longToFixedLengthString(i, digits)); }
     println(sk.toString(true, true));
@@ -310,7 +310,7 @@ public void checkSketchInitializeItemsHeap() {
     assertEquals(sk.getNumLevels(), 2);
     assertFalse(sk.isLevelZeroSorted());
 
-    println("#### CASE: FLOAT HEAP EMPTY");
+    println("#### CASE: ITEM HEAP EMPTY");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     println(sk.toString(true, true));
     assertEquals(sk.getK(), k);
@@ -326,7 +326,7 @@ public void checkSketchInitializeItemsHeap() {
     assertEquals(sk.getNumLevels(), 1);
     assertFalse(sk.isLevelZeroSorted());
 
-    println("#### CASE: FLOAT HEAP SINGLE");
+    println("#### CASE: ITEM HEAP SINGLE");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     sk.update("1");
     println(sk.toString(true, true));
@@ -354,7 +354,7 @@ public void checkSketchInitializeItemsHeapifyCompactMem() {
     byte[] compBytes;
     Memory mem;
 
-    println("#### CASE: FLOAT FULL HEAPIFIED FROM COMPACT");
+    println("#### CASE: ITEM FULL HEAPIFIED FROM COMPACT");
     sk2 = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     for (int i = 1; i <= n; i++) { sk2.update(Util.longToFixedLengthString(i, digits)); }
     println(sk2.toString(true, true));
@@ -375,7 +375,7 @@ public void checkSketchInitializeItemsHeapifyCompactMem() {
     assertEquals(sk.getNumLevels(), 2);
     assertFalse(sk.isLevelZeroSorted());
 
-    println("#### CASE: FLOAT EMPTY HEAPIFIED FROM COMPACT");
+    println("#### CASE: ITEM EMPTY HEAPIFIED FROM COMPACT");
     sk2 =  KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     //println(sk.toString(true, true));
     compBytes = sk2.toByteArray();
@@ -395,7 +395,7 @@ public void checkSketchInitializeItemsHeapifyCompactMem() {
     assertEquals(sk.getNumLevels(), 1);
     assertFalse(sk.isLevelZeroSorted());
 
-    println("#### CASE: FLOAT SINGLE HEAPIFIED FROM COMPACT");
+    println("#### CASE: ITEM SINGLE HEAPIFIED FROM COMPACT");
     sk2 = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     sk2.update("1");
     //println(sk2.toString(true, true));
@@ -417,7 +417,7 @@ public void checkSketchInitializeItemsHeapifyCompactMem() {
     assertFalse(sk.isLevelZeroSorted());
   }
 
-  //public void checkSketchInitializeFloatHeapifyUpdatableMem() Not Supported
+  //public void checkSketchInitializeItemHeapifyUpdatableMem() Not Supported
 
   @Test //set static enablePrinting = true for visual checking
   public void checkMemoryToStringItemsCompact() {
@@ -431,7 +431,7 @@ public void checkMemoryToStringItemsCompact() {
     Memory mem;
     String s;
 
-    println("#### CASE: FLOAT FULL COMPACT");
+    println("#### CASE: ITEM FULL COMPACT");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     for (int i = 1; i <= n; i++) { sk.update(Util.longToFixedLengthString(i, digits)); }
     compBytes = sk.toByteArray();
@@ -447,7 +447,7 @@ public void checkMemoryToStringItemsCompact() {
     println(s);
     assertEquals(compBytes, compBytes2);
 
-    println("#### CASE: FLOAT EMPTY COMPACT");
+    println("#### CASE: ITEM EMPTY COMPACT");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     compBytes = sk.toByteArray();
     mem = Memory.wrap(compBytes);
@@ -462,7 +462,7 @@ public void checkMemoryToStringItemsCompact() {
     println(s);
     assertEquals(compBytes, compBytes2);
 
-    println("#### CASE: FLOAT SINGLE COMPACT");
+    println("#### CASE: ITEM SINGLE COMPACT");
     sk = KllItemsSketch.newHeapInstance(k, Comparator.naturalOrder(), serDe);
     sk.update("1");
     compBytes = sk.toByteArray();

src/test/java/org/apache/datasketches/theta/ThetaSketchCrossLanguageTest.java

@@ -49,6 +49,16 @@ public void generateBinariesForCompatibilityTesting() throws IOException {
     }
   }
 
+  @Test(groups = {GENERATE_JAVA_FILES})
+  public void generateBinariesForCompatibilityTestingCompressed() throws IOException {
+    final int[] nArr = {10, 100, 1000, 10_000, 100_000, 1_000_000};
+    for (int n: nArr) {
+      final UpdateSketch sk = UpdateSketch.builder().build();
+      for (int i = 0; i < n; i++) sk.update(i);
+      Files.newOutputStream(javaPath.resolve("theta_compressed_n" + n + "_java.sk")).write(sk.compact().toByteArrayCompressed());
+    }
+  }
+
   @Test(groups = {GENERATE_JAVA_FILES})
   public void generateBinariesForCompatibilityTestingNonEmptyNoEntries() throws IOException {
     final UpdateSketch sk = UpdateSketch.builder().setP(0.01f).build();