Code minor fixes. Documentation improvement with markdown integration in Javadoc, README.md as Javadoc docs overview description.

Author: nunoachenriques

.gitignore

@@ -1,3 +1,4 @@
+/*.iml
 /.gradle
 /.idea
 /build

README.md

@@ -12,15 +12,15 @@ from the [original project](https://github.com/cjhutto/vaderSentiment) by
 the paper's author C.J. Hutto. It's the same algorithm as an improved
 tool by extensive rewriting with **relevant changes**:
 
- - Android ready.
- - API and package names breaking changes.
- - Java 1.7 compatible.
- - Performance improvements (e.g., `LinkedList` where's better O() than
+ - [x] Android ready.
+ - [x] API and package names breaking changes.
+ - [x] Java 1.7 compatible.
+ - [x] Performance improvements (e.g., `LinkedList` where's better O() than
    `ArrayList`).
 
 **In progress**
 
- - Multi-language (refer to section [Languages](#languages)).
+ - [ ] Multi-language (refer to section [Languages](#languages)).
 
 ## Repository
 
@@ -50,8 +50,7 @@ https://github.com/nunoachenriques/vader-sentiment-analysis/releases
 1. Get the code from the repository (clone or download).
 
 2. Change to the package root directory and `./gradlew installDist`.
-   Notice: remember to change `gradle.properties` accordingly to your
-   JDK home for 1.7 version compatibility.
+   NOTICE: check [Troubleshooting](#troubleshooting) for Java version 1.7 compatibility.
 
 3. The JAR packages will be in `build/install/vader-sentiment-analysis`
    directory.
@@ -130,11 +129,21 @@ https://github.com/nunoachenriques/vader-sentiment-analysis/releases
 1. Get the code from the repository (clone or download).
 
 2. Change to the package root directory and `./gradlew javadoc`.
-   Notice: remember to change `gradle.properties` accordingly to your
-   JDK home for 1.7 version compatibility.
+   NOTICE: check [Troubleshooting](#troubleshooting) for Java version 1.7 compatibility.
 
 3. The docs will be in `build/docs/javadoc` directory.
 
+## Troubleshooting
+
+### Java 1.7 compatibility
+
+1. Install OpenJDK 7.
+2. Suffix Gradle command-line with `-Dorg.gradle.java.home=/path_to_jdk_7` such as (Debian GNU/Linux):
+
+```shell
+./gradlew test -Dorg.gradle.java.home=/usr/lib/jvm/java-7-openjdk-amd64/
+```
+
 ## License
 
 Copyright 2017 Nuno A. C. Henriques [http://nunoachenriques.net/]

VERSION

@@ -1 +1 @@
-2.0.0
+2.0.1

bin/markdowntohtml.js

@@ -0,0 +1,33 @@
+/* 
+ * Copyright 2017 Nuno A. C. Henriques [nunoachenriques.net]
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * markdowntohtml.js
+ *
+ * Converts a Markdown text file to an HTML one.
+ * Depends: Showdown [https://github.com/showdownjs/showdown] JavaScript library v1.8.6
+ * Depends: jjs (Java 8)
+ * Arguments: arguments[0] = Markdown file name.
+ * Use case: jjs -scripting showdown.min.js markdowntohtml.js -- README.md > README.html
+ * @author Nuno A. C. Henriques [nunoachenriques.net]
+ */
+
+var converter = new showdown.Converter();
+converter.setFlavor('github');
+converter.setOption('simpleLineBreaks', false);
+converter.setOption('openLinksInNewWindow', true);
+converter.setOption('taskLists', true);
+print(converter.makeHtml(readFully(arguments[0])));

bin/showdown.min.js

@@ -5,6 +5,9 @@ sourceCompatibility = 1.7
 targetCompatibility = 1.7
 version = file('VERSION').getText()
 String applicationName = 'VADER Sentiment Analysis in Java'
+String readmeMDFile = "${projectDir}/README.md"
+String readmeHTMLFile = "${buildDir}/README.html"
+String overviewFile = "${buildDir}/overview.html"
 
 println "${applicationName} ${version}"
 
@@ -25,6 +28,44 @@ test {
     exclude 'net/nunoachenriques/vader/text/Tokenizer*'
 }
 
+// JAVADOC
+
+javadoc {
+    dependsOn = ['javadocOverview']
+    title = "${applicationName}" + ' API'
+    options.overview = "${overviewFile}"
+}
+
+task buildDirectory {
+    project.getBuildDir().mkdirs()
+}
+
+task markdownToHTML(type: Exec) {
+    description = 'Converts a Markdown text file to an HTML one.'
+    commandLine 'jjs', '-scripting', 'bin/showdown.min.js', 'bin/markdowntohtml.js', '--', "${->javadocOverview.mdFileName()}"
+}
+
+task javadocOverview(dependsOn: ['buildDirectory', 'markdownToHTML']) {
+    description = 'Generates the overview.html for the Javadoc API documentation.'
+    ext.mdFileName = { return "${readmeMDFile}" } // arg1 for markdownToHTML
+    markdownToHTML.standardOutput = new FileOutputStream("${readmeHTMLFile}") // arg2
+    doLast { // Complete overview.html with the head and tail HTML tags.
+        def overviewOutput = new File("${overviewFile}")
+        overviewOutput.text = '''\
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+  <head>
+    <title>''' + "${applicationName}" + ''' API</title>
+    <meta http-equiv="content-type" content="text/html;charset=utf-8" />
+  </head>
+  <body>
+''' + file("${readmeHTMLFile}").getText() + '''
+  </body>
+</html>
+'''
+    }
+}
+
 // EXTRA PACKAGING FOR RELEASE DISTRIBUTION
 
 task release(dependsOn: ['test', 'distZip', 'sourcesZip', 'javadocZip'])

build.gradle

@@ -23,9 +23,7 @@
  */
 class Constant {
 
-    // Private constructor to avoid instantiation.
     private Constant() {
-        // Void!
     }
 
     // TODO check SentimentAnalysis for missing constants!

gradle.properties

@@ -29,12 +29,13 @@
 import java.util.Map;
 
 /**
- * The SentimentAnalysis class is the main class for VADER Sentiment Analysis.
- * Since version 2.0 is multi-language ready and Android ready! Use cases:
+ * <p>The SentimentAnalysis class is the main class for VADER Sentiment Analysis.
+ * Since version 2.0 is multi-language ready and Android ready! Use cases:</p>
+ *
  * <h2>I. Several samples, same language.</h2>
  * <pre>
  * ...
- * {@code
+ * <code>
  * SentimentAnalysis sa = new SentimentAnalysis(new TokenizerEnglish(), new English());
  * Map<String,Float> sp;
  * String s1 = "VADER is smart, handsome, and funny!";
@@ -44,13 +45,14 @@
  * System.out.println(s1 + " *** " + sp.toString());
  * sp = sa.getSentimentAnalysis(s2);
  * System.out.println(s2 + " *** " + sp.toString());
- * }
+ * </code>
  * ...
  * </pre>
+ *
  * <h2>II. Several samples, multiple languages.</h2>
  * <pre>
  * ...
- * {@code
+ * <code>
  * SentimentAnalysis sa = new SentimentAnalysis();
  * Map<String,Float> sp;
  * String s1 = "VADER is smart, handsome, and funny!";
@@ -60,15 +62,12 @@
  * System.out.println(s1 + " *** " + sp.toString());
  * sp = sa.getSentimentAnalysis(s2, new TokenizerPortuguese(), new Portuguese());
  * System.out.println(s2 + " *** " + sp.toString());
- * }
+ * </code>
  * ...
  * </pre>
  *
  * @author Nuno A. C. Henriques [nunoachenriques.net]
- * @see
- * <a href="http://comp.social.gatech.edu/papers/icwsm14.vader.hutto.pdf">VADER:
- * A Parsimonious Rule-based Model for Sentiment Analysis of Social Media
- * Text</a>
+ * @see <a href="http://comp.social.gatech.edu/papers/icwsm14.vader.hutto.pdf" target="_blank">VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text</a>
  */
 public class SentimentAnalysis {
 
@@ -84,6 +83,7 @@ public class SentimentAnalysis {
     /**
      * Default constructor with all parameters {@code null}.
      */
+    @SuppressWarnings("WeakerAccess")
     public SentimentAnalysis() {
         text = null;
         language = null;
@@ -92,13 +92,15 @@ public SentimentAnalysis() {
     }
 
     /**
-     * Default constructor with two required parameters: tokenizer and language.
+     * Sets two required parameters: tokenizer and language. All the others
+     * initialize as {@code null}.
      *
      * @param l The text {@link Language}
      *          (e.g., {@link net.nunoachenriques.vader.lexicon.English}).
      * @param t The text {@link Tokenizer} to be used
      *          (e.g., {@link net.nunoachenriques.vader.text.TokenizerEnglish}).
      */
+    @SuppressWarnings("WeakerAccess")
     public SentimentAnalysis(Language l, Tokenizer t) {
         text = null;
         language = l;
@@ -300,23 +302,20 @@ private float checkForIdioms(float currentValence, int i) {
         final Map<String, Float> boosterDictionary = language.getBoosterDictionary();
         final Map<String, Float> sentimentLadenIdioms = language.getSentimentLadenIdioms();
 
-        List<String> leftGramSequences = new ArrayList<String>() {
-            {
-                add(leftBiGramFromCurrent);
-                add(leftTriGramFromCurrent);
-                add(leftBiGramFromOnePrevious);
-                add(leftTriGramFromOnePrevious);
-                add(leftBiGramFromTwoPrevious);
-            }
-        };
+        List<String> leftGramSequences = new ArrayList<String>() {{
+            add(leftBiGramFromCurrent);
+            add(leftTriGramFromCurrent);
+            add(leftBiGramFromOnePrevious);
+            add(leftTriGramFromOnePrevious);
+            add(leftBiGramFromTwoPrevious);
+        }};
 
         for (String leftGramSequence : leftGramSequences) {
             if (sentimentLadenIdioms.containsKey(leftGramSequence)) {
                 currentValence = sentimentLadenIdioms.get(leftGramSequence);
                 break;
             }
         }
-
         if (wordsAndEmoticons.size() - 1 > i) {
             final String rightBiGramFromCurrent = String.format("%s %s", wordsAndEmoticons.get(i), wordsAndEmoticons.get(i + 1));
             if (sentimentLadenIdioms.containsKey(rightBiGramFromCurrent)) {
@@ -329,11 +328,9 @@ private float checkForIdioms(float currentValence, int i) {
                 currentValence = sentimentLadenIdioms.get(rightTriGramFromCurrent);
             }
         }
-
         if (boosterDictionary.containsKey(leftBiGramFromTwoPrevious) || boosterDictionary.containsKey(leftBiGramFromOnePrevious)) {
             currentValence += -0.293f; // TODO review Language and English.DAMPENER_WORD_DECREMENT;
         }
-
         return currentValence;
     }
 
@@ -387,23 +384,19 @@ private Map<String, Float> polarityScores(List<Float> currentSentimentState) {
             final float normalizedNegativePolarity = roundDecimal(Math.abs(negativeSentimentScore / normalizationFactor), 3);
             final float normalizedNeutralPolarity = roundDecimal(Math.abs(neutralSentimentCount / normalizationFactor), 3);
             final float normalizedCompoundPolarity = roundDecimal(compoundPolarity, 4);
-            return new HashMap<String, Float>() {
-                {
-                    put("compound", normalizedCompoundPolarity);
-                    put("positive", normalizedPositivePolarity);
-                    put("negative", normalizedNegativePolarity);
-                    put("neutral", normalizedNeutralPolarity);
-                }
-            };
+            return new HashMap<String, Float>() {{
+                put("compound", normalizedCompoundPolarity);
+                put("positive", normalizedPositivePolarity);
+                put("negative", normalizedNegativePolarity);
+                put("neutral", normalizedNeutralPolarity);
+            }};
         } else {
-            return new HashMap<String, Float>() {
-                {
-                    put("compound", 0.0f);
-                    put("positive", 0.0f);
-                    put("negative", 0.0f);
-                    put("neutral", 0.0f);
-                }
-            };
+            return new HashMap<String, Float>() {{
+                put("compound", 0.0f);
+                put("positive", 0.0f);
+                put("negative", 0.0f);
+                put("neutral", 0.0f);
+            }};
         }
     }
 
@@ -455,10 +448,7 @@ private boolean hasAtLeast(List<String> tokenList) {
         // TODO English language dependent!
         if (tokenList.contains("least")) {
             int index = tokenList.indexOf("least");
-            if (index > 0 && tokenList.get(index - 1).equals("at")) {
-
-                return true;
-            }
+            return index > 0 && tokenList.get(index - 1).equals("at");
         }
         return false;
     }
@@ -468,7 +458,6 @@ private boolean hasContraction(List<String> tokenList) {
 
             // TODO English language dependent!
             if (s.endsWith("n't")) {
-
                 return true;
             }
         }

src/main/java/net/nunoachenriques/vader/Constant.java

@@ -32,11 +32,8 @@
  * original Python implementation.
  *
  * @author Nuno A. C. Henriques [nunoachenriques.net]
- * @see <a href="http://www.nltk.org/_modules/nltk/sentiment/vader.html">NLTK
- * source</a>
- * @see
- * <a href="https://github.com/cjhutto/vaderSentiment/blob/master/vaderSentiment/vaderSentiment.py">
- * vaderSentiment original Python source</a>
+ * @see <a href="http://www.nltk.org/_modules/nltk/sentiment/vader.html" target="_blank">NLTK source</a>
+ * @see <a href="https://github.com/cjhutto/vaderSentiment/blob/master/vaderSentiment/vaderSentiment.py target="_blank"">vaderSentiment original Python source</a>
  */
 public final class English
         implements Language {
@@ -112,7 +109,6 @@ private static Map<String, Float> createBoosterDictionary() {
         m.put("more", BOOSTER_WORD_INCREMENT);
         m.put("considerably", BOOSTER_WORD_INCREMENT);
         m.put("fabulously", BOOSTER_WORD_INCREMENT);
-        m.put("sort of", DAMPENER_WORD_DECREMENT);
         m.put("hardly", DAMPENER_WORD_DECREMENT);
         m.put("very", BOOSTER_WORD_INCREMENT);
         m.put("sortof", DAMPENER_WORD_DECREMENT);
@@ -178,11 +174,7 @@ private static Map<String, Float> getWordValenceDictionary(String filename) {
         return lexDictionary;
     }
 
-    /**
-     * Default constructor.
-     */
     public English() {
-        // Void.
     }
 
     @Override

src/main/java/net/nunoachenriques/vader/SentimentAnalysis.java

@@ -51,11 +51,7 @@ public class TokenizerEnglish
      */
     private static final Pattern PUNCTUATION_EXCLUDE_CONTRACTION_PATTERN = Pattern.compile("[\\p{Punct}&&[^.']]|(?<=(^|\\s|\\p{Punct}))[.']|[.'](?=($|\\s|\\p{Punct}))");
 
-    /**
-     * Default constructor.
-     */
     public TokenizerEnglish() {
-        // Void.
     }
 
     @Override