Revision 1 of the 1st Edition

.gitignore

@@ -1,8 +1,9 @@
 # Compiled class file
 *.class
+target/
 
-# Log file
-*.log
+# Log filea
+logs/
 
 # BlueJ files
 *.ctxt
@@ -13,12 +14,25 @@
 # Package Files #
 *.jar
 *.war
-*.nar
 *.ear
 *.zip
 *.tar.gz
 *.rar
 
 # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
 hs_err_pid*
-replay_pid*
+
+# IDE files #
+*.iml
+.idea
+
+bin/*
+.classpath
+.project
+.settings
+
+src/main/java/com/phasmidsoftware/dsaipg/sort/elementary/MergeSortDecisionTree\.java
+*.kml
+
+/api/
+/SelectBenchmark.csv

README.md

@@ -1,2 +1,54 @@
 # DSAIPG
-Companion repository to "Data Structures, Algorithms and Invariants"
+## Introduction and Provenance
+Companion repository to:
+"Data Structures, Algorithms, and Invariants--A Practical Guide"
+by Robin Hillyard, College of Engineering, Northeastern University, Boston, MA, USA.
+Published by Cognella.
+
+This is version 1-1 (first revision of the first edition).
+
+## Installation
+This project is designed to be cloned from https://github.com/rchillyard/DSAIPG.git
+Alternatively, if you will be submitting assignments based on the repository,
+then you might want to fork it instead.
+
+This repository contains a Maven project (see the `pom.xnl` file in the top level).
+Ideally, you will use an IDE that is suited to Maven projects.
+I recommend IntelliJ IDEA.
+
+## Navigation
+The simplest way to find code is just to use the `Navigate/Class` menu.
+It is good at recognizing what you're looking for.
+However, note that the first character of all classes is upper case (and you will need to search thus).
+
+Exercises and code relating to the various chapters can be found as given below and under the package `com.phasmidsoftware.dsaipg`:
+* Chapters 1 and 2: `misc` and `util`; (if any)
+* Chapters 3 through 6: `adt`;
+* Chapters 7 and 8: `sort` (and `select`);
+* Chapters 9 and 10: `graphs`;
+* Team Project: `projects`.
+
+Other package directories contain other code.
+
+In order to find TODOs, etc. you should use the TODO tool window.
+I recommend adding the following pattern to be recognized as needing attention
+(TODO is already a known pattern):
+* \bTO BE IMPLEMENTED\b.*
+
+This will make it easy to see where you have to write code.
+
+## Building and Testing
+If you have cloned (or forked) the repository into IDEA, it should build the project
+for you without much intervention on your part.
+You will need at least Java 17 as your SDK.
+Recommended: Oracle OpenJDK 18.0.2
+
+To test the installation, run all the tests in `src/test/java`.
+There are about a thousand active tests, of which two-thirds should run green.
+Don't worry about the failing tests--they fail because there are stubs in the code
+that you need to replace with functioning code in many places
+(see above in Navigation).
+
+There are also functional tests in the `src/it/java` directory.
+However, these take significantly longer to run and are really not necessary. 
+

pom.xml

@@ -0,0 +1,107 @@
+<!--
+  ~ Copyright (c) 2018, 2019, 2020. Phasmid Software
+  -
+  - NOTE: this POM file is designed to include both unit and integration tests.
+  - The mechanism has not been entirely tested.
+  -->
+
+<project>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>edu.neu.coe.mgen</groupId>
+    <artifactId>INFO6205</artifactId>
+    <version>1</version>
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
+                <configuration>
+                    <source>17</source>
+                    <target>18</target>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+    <properties>
+        <maven.compiler.source>1.17</maven.compiler.source>
+        <maven.compiler.target>1.18</maven.compiler.target>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
+    </properties>
+    <repositories>
+        <repository>
+            <id>OSGeo</id>
+            <url>https://repo.osgeo.org/repository/release/</url>
+        </repository>
+    </repositories>
+    <dependencies>
+        <dependency>
+            <groupId>com.phasmidsoftware</groupId>
+            <artifactId>args_2.13</artifactId>
+            <version>1.0.3</version>
+        </dependency>
+        <dependency>
+            <groupId>com.phasmidsoftware</groupId>
+            <artifactId>number_2.13</artifactId>
+            <version>1.0.12</version>
+        </dependency>
+      <dependency>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-api</artifactId>
+            <version>2.19.0</version>
+        </dependency>
+        <dependency>
+            <groupId>log4j</groupId>
+            <artifactId>log4j</artifactId>
+            <version>1.2.17</version>
+        </dependency>
+        <!-- The following dependency is required ONLY for MyTree and MyTreeTest in lab_1 package. -->
+        <!-- https://mvnrepository.com/artifact/com.google.guava/guava -->
+        <dependency>
+            <groupId>com.google.guava</groupId>
+            <artifactId>guava</artifactId>
+            <version>31.1-jre</version>
+        </dependency>
+        <!-- https://mvnrepository.com/artifact/org.ini4j/ini4j -->
+        <dependency>
+            <groupId>org.ini4j</groupId>
+            <artifactId>ini4j</artifactId>
+            <version>0.5.4</version>
+        </dependency>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>4.13.2</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>io.cucumber</groupId>
+            <artifactId>cucumber-java</artifactId>
+            <version>7.8.1</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>io.cucumber</groupId>
+            <artifactId>cucumber-junit</artifactId>
+            <version>7.8.1</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>com.belerweb</groupId>
+            <artifactId>pinyin4j</artifactId>
+            <version>2.5.1</version>
+        </dependency>
+        <dependency>
+            <groupId>org.jetbrains</groupId>
+            <artifactId>annotations</artifactId>
+            <version>13.0</version>
+            <scope>compile</scope>
+        </dependency>
+        <!--        <dependency>
+                    <groupId>edu.neu.coe.mgen</groupId>
+                    <artifactId>INFO6205</artifactId>
+                    <version>1</version>
+                </dependency>
+                -->
+    </dependencies>
+</project>

src/it/java/com/phasmidsoftware/dsaipg/adt/hashtable/FrequencyCounterFuncTest.java

@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2017. Phasmid Software
+ */
+
+package com.phasmidsoftware.dsaipg.adt.hashtable;
+
+import com.phasmidsoftware.dsaipg.adt.symbolTable.hashtable.FrequencyCounter;
+import org.junit.Test;
+
+import static org.junit.Assert.assertEquals;
+
+public class FrequencyCounterFuncTest {
+    @Test
+    public void testIncrementVeryLargeCount() {
+        FrequencyCounter<String> fc = new FrequencyCounter<>();
+        String key = "LargeKey";
+        for (int i = 0; i < Integer.MAX_VALUE / 2; i++) {
+            fc.increment(key);
+            if (i % 100000000 == 0) { // Periodic checkpoint to avoid exceeding memory limit
+                assertEquals(i + 1, fc.get(key).intValue());
+            }
+        }
+        assertEquals((long) Integer.MAX_VALUE / 2, fc.get(key).intValue());
+    }
+}

src/it/java/com/phasmidsoftware/dsaipg/adt/threesum/ThreeSumFuncTest.java

@@ -0,0 +1,45 @@
+package com.phasmidsoftware.dsaipg.adt.threesum;
+
+import org.junit.Ignore;
+import org.junit.Test;
+
+import java.util.function.Supplier;
+
+import static org.junit.Assert.assertEquals;
+
+public class ThreeSumFuncTest {
+
+    @Ignore // Slow
+    public void testGetTriples3() {
+        Supplier<int[]> intsSupplier = new Source(1000, 1000).intsSupplier(10);
+        int[] ints = intsSupplier.get();
+        ThreeSum target = new ThreeSumQuadratic(ints);
+        Triple[] triplesQuadratic = target.getTriples();
+        Triple[] triplesCubic = new ThreeSumCubic(ints).getTriples();
+        int expected1 = triplesCubic.length;
+        assertEquals(expected1, triplesQuadratic.length);
+    }
+
+    @Ignore // Slow
+    public void testGetTriples4() {
+        Supplier<int[]> intsSupplier = new Source(1500, 1000).intsSupplier(10);
+        int[] ints = intsSupplier.get();
+        ThreeSum target = new ThreeSumQuadratic(ints);
+        Triple[] triplesQuadratic = target.getTriples();
+        Triple[] triplesCubic = new ThreeSumCubic(ints).getTriples();
+        int expected1 = triplesCubic.length;
+        assertEquals(expected1, triplesQuadratic.length);
+    }
+
+    @Test
+    public void testGetTriplesC4() {
+        // CONSIDER move this into it directory.
+        Supplier<int[]> intsSupplier = new Source(1500, 1000).intsSupplier(10);
+        int[] ints = intsSupplier.get();
+        ThreeSum target = new ThreeSumQuadraticWithCalipers(ints);
+        Triple[] triplesQuadratic = target.getTriples();
+        Triple[] triplesCubic = new ThreeSumCubic(ints).getTriples();
+        assertEquals(triplesCubic.length, triplesQuadratic.length);
+    }
+
+}

src/it/java/com/phasmidsoftware/dsaipg/huskySort/sort/huskySort/BenchmarkIntegrationTest.java

@@ -0,0 +1,92 @@
+/*
+ * Copyright (c) 2017. Phasmid Software
+ */
+
+package com.phasmidsoftware.dsaipg.huskySort.sort.huskySort;
+
+import com.phasmidsoftware.dsaipg.huskySort.sort.huskySortUtils.HuskySequenceCoder;
+import com.phasmidsoftware.dsaipg.huskySort.sort.huskySortUtils.HuskySortHelper;
+import com.phasmidsoftware.dsaipg.huskySort.util.Config;
+import com.phasmidsoftware.dsaipg.huskySort.util.LazyLogger;
+import com.phasmidsoftware.dsaipg.huskySort.util.ProcessorDependentTimeout;
+import org.apache.log4j.Logger;
+import org.junit.BeforeClass;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.Timeout;
+
+import java.io.FileNotFoundException;
+import java.io.IOException;
+import java.util.concurrent.TimeUnit;
+import java.util.regex.Pattern;
+
+/**
+ * Benchmark Integration Test.
+ * This is suitable for inclusion in integration tests, but not unit tests.
+ *
+ * <p>
+ * The expected time for a pure quicksort of N items and M runs is 1.39 k M N lg N (where lg represents log to the base 2).
+ * Bear in mind that the Benchmark code does M/10 warmup runs also.
+ */
+
+@SuppressWarnings("ALL")
+public class BenchmarkIntegrationTest {
+
+    @BeforeClass
+    public static void BeforeClass() throws IOException {
+        config = Config.load();
+        benchmark = new HuskySortBenchmark(config);
+        String huskysort = "huskysort";
+        String name = config.get(huskysort, "version");
+        huskyCoder = HuskySortHelper.getSequenceCoderByName(config.get(huskysort, "huskycoder", "Unicode"));
+        logger.info("HuskySortBenchmark.main: " + name);
+    }
+
+    @Rule
+    public Timeout timeoutBuilder = new ProcessorDependentTimeout(10, TimeUnit.SECONDS, config);
+
+    @Test
+    public void testStrings10K() throws Exception {
+        String corpus = "eng-uk_web_2002_10K-sentences.txt";
+        benchmark.benchmarkStringSorters(corpus, getWordsLeipzig(corpus), 10000, 3800, huskyCoder);
+    }
+
+    private final static String[] getWordsLeipzig(String s) throws FileNotFoundException {
+        return HuskySortBenchmarkHelper.getWords(s, line -> HuskySortBenchmarkHelper.splitLineIntoStrings(line, REGEX_LEIPZIG, HuskySortBenchmarkHelper.REGEX_STRING_SPLITTER));
+    }
+
+    @Test
+    public void testStrings100K() throws Exception {
+        // NOTE: you cannot include insertionSort among the sort methods to be used: it WILL time out here.
+        String corpus = "eng-uk_web_2002_100K-sentences.txt";
+        benchmark.benchmarkStringSorters(corpus, getWordsLeipzig(corpus), 100000, 255, huskyCoder);
+    }
+
+    @Test
+    public void testDates10K() throws Exception {
+        benchmark.sortLocalDateTimes(37000, 1000000);
+    }
+
+    @Test
+    public void testDates100K() throws Exception {
+        benchmark.sortLocalDateTimes(44000, 1000000);
+    }
+
+    @Test
+    public void testStrings10KInstrumented() throws Exception {
+        benchmark.benchmarkStringSortersInstrumented(getWordsLeipzig("eng-uk_web_2002_10K-sentences.txt"), 10000, 950, huskyCoder);
+    }
+
+//    @Test(timeout = 140000)
+//    public void testStrings100KInstrumented() throws Exception {
+//        // NOTE: you cannot include insertionSort among the sort methods to be used: it WILL time out here.
+//        huskyCoder = asciiCoder;
+//        benchmark.benchmarkStringSortersInstrumented(getWords("eng-uk_web_2002_100K-sentences.txt", line -> getWords(regexLeipzig, line)), 100000, 200, huskyCoder);
+//    }
+
+    private final static Pattern REGEX_LEIPZIG = Pattern.compile("[~\\t]*\\t(([\\s\\p{Punct}\\uFF0C]*\\p{L}+)*)");
+    private static Logger logger = new LazyLogger(BenchmarkIntegrationTest.class);
+    private static HuskySortBenchmark benchmark;
+    private static Config config;
+    private static HuskySequenceCoder<String> huskyCoder;
+}

src/it/java/com/phasmidsoftware/dsaipg/huskySort/sort/huskySort/ChineseCharacterIntegrationTest.java

@@ -0,0 +1,22 @@
+package com.phasmidsoftware.dsaipg.huskySort.sort.huskySort;
+
+import com.phasmidsoftware.dsaipg.huskySort.sort.huskySortUtils.ChineseCharacter;
+import org.junit.Test;
+
+import static com.phasmidsoftware.dsaipg.huskySort.sort.huskySort.HuskySortBenchmark.CHINESE_NAMES_CORPUS;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.fail;
+
+public class ChineseCharacterIntegrationTest {
+    @Test
+    public void testParsePinyinN() {
+        for (final String word : HuskySortBenchmarkHelper.getWords(CHINESE_NAMES_CORPUS, HuskySortBenchmark::lineAsList)) {
+            try {
+                final String[] parsedPinyin = ChineseCharacter.parsePinyin(ChineseCharacter.convertToPinyin(word), word.length());
+                assertEquals(word.length(), parsedPinyin.length);
+            } catch (final Exception e) {
+                fail("Failed parse pinyin for: " + word + ": " + e.getLocalizedMessage());
+            }
+        }
+    }
+}