further refactoring

README.md

@@ -4,6 +4,8 @@ Kumo's goal is to create a powerful and user friendly Word Cloud API in Java. Ku
 
 Please feel free to jump in and help improve Kumo! There are many places for performance optimization in Kumo!
 
+[![Maven Central](https://maven-badges.herokuapp.com/maven-central/com.kennycason/kumo/badge.svg?style=flat)](https://maven-badges.herokuapp.com/maven-central/com.kennycason/kumo)<br/>
+
 ### Current Features
 
 - Draw Rectangle, Circle or Image Overlay word clouds. Image Overlay will draw words over all non-transparent pixels.
@@ -26,7 +28,7 @@ Please feel free to jump in and help improve Kumo! There are many places for per
 <dependency>
     <groupId>com.kennycason</groupId>
     <artifactId>kumo</artifactId>
-    <version>1.8</version>
+    <version>1.9</version>
 </dependency>
 ```
 
@@ -382,3 +384,8 @@ Create a layered word cloud
 ```
 kumo --input "https://www.haskell.org/, https://en.wikipedia.org/wiki/Haskell_(programming_language)" --output "/tmp/nintendo_vs_playstation.png" --type layered --background "https://raw.githubusercontent.com/kennycason/kumo/master/src/test/resources/backgrounds/haskell_1.bmp,https://raw.githubusercontent.com/kennycason/kumo/master/src/test/resources/backgrounds/haskell_2.bmp" --color "(0xFA6C07),(0xFF7614),(0xFF8936)|(0x080706),(0x3B3029),(0x47362A)"
 ```
+
+
+### Contributing
+
+My primary IDE of choice is IntelliJ due to their robust tooling as well as code analysis/inspections. If using [IntelliJ IDEA](https://www.jetbrains.com/idea/), I recommend importing `KumoIntelliJInspections.xml`. I am also consiering adding Checkstyle support.

kumo-cli/pom.xml

@@ -11,21 +11,27 @@
 
     <artifactId>kumo-cli</artifactId>
 
+    <properties>
+        <cli.main.class>com.kennycason.kumo.cli.KumoCli</cli.main.class>
+    </properties>
+
     <dependencies>
         <dependency>
             <groupId>com.kennycason</groupId>
-            <artifactId>kumo-api</artifactId>
-            <version>1.9</version>
+            <artifactId>kumo-core</artifactId>
         </dependency>
         <dependency>
             <groupId>com.kennycason</groupId>
-            <artifactId>kumo-nlp</artifactId>
-            <version>1.9</version>
-        </dependency>  <dependency>
-            <groupId>com.kennycason</groupId>
-            <artifactId>kumo-core</artifactId>
-            <version>1.9</version>
+            <artifactId>kumo-tokenizers</artifactId>
         </dependency>
+
+        <!-- third party -->
+        <dependency>
+            <groupId>com.beust</groupId>
+            <artifactId>jcommander</artifactId>
+        </dependency>
+
+        <!-- test -->
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
@@ -51,9 +57,30 @@
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-surefire-plugin</artifactId>
             </plugin>
+
+            <!-- for cli executable -->
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-shade-plugin</artifactId>
+                <version>2.4.3</version>
+                <configuration>
+                    <transformers>
+                        <transformer
+                                implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
+                            <manifestEntries>
+                                <Main-Class>${cli.main.class}</Main-Class>
+                            </manifestEntries>
+                        </transformer>
+                    </transformers>
+                </configuration>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>shade</goal>
+                        </goals>
+                    </execution>
+                </executions>
             </plugin>
         </plugins>
     </build>

kumo-cli/src/main/java/com/kennycason/kumo/cli/KumoCli.java

@@ -18,10 +18,10 @@
 import com.kennycason.kumo.font.scale.SqrtFontScalar;
 import com.kennycason.kumo.nlp.FrequencyAnalyzer;
 import com.kennycason.kumo.nlp.normalize.*;
-import com.kennycason.kumo.nlp.tokenizer.ChineseWordTokenizer;
-import com.kennycason.kumo.nlp.tokenizer.EnglishWordTokenizer;
 import com.kennycason.kumo.nlp.tokenizer.WhiteSpaceWordTokenizer;
 import com.kennycason.kumo.nlp.tokenizer.WordTokenizer;
+import com.kennycason.kumo.nlp.tokenizers.ChineseWordTokenizer;
+import com.kennycason.kumo.nlp.tokenizers.EnglishWordTokenizer;
 import com.kennycason.kumo.palette.ColorPalette;
 import com.kennycason.kumo.wordstart.CenterWordStart;
 import com.kennycason.kumo.wordstart.RandomWordStart;

kumo-cli/src/main/java/com/kennycason/kumo/cli/ParenthesisSerializer.java

@@ -19,11 +19,11 @@ public class ParenthesisSerializer {
     public static <T> String serialize(final Collection<T> collection) {
         if (collection.isEmpty()) { return ""; }
 
-        String joined = collection.stream()
-                .map(i -> i.toString())
-                .collect(Collectors.joining("),("));
+        final String joined = collection.stream()
+                                        .map(i -> i.toString())
+                                        .collect(Collectors.joining("),("));
 
-        return "(" + joined + ")";
+        return '(' + joined + ')';
     }
 
     public static List<String> deserialize(final String value) {

kumo-cli/src/test/java/com/kennycason/kumo/cli/KumoCliITest.java

@@ -1,23 +1,21 @@
 package com.kennycason.kumo.cli;
 
-import com.kennycason.kumo.IntegrationTest;
-import org.junit.Ignore;
-import org.junit.experimental.categories.Category;
+import org.junit.Test;
 
 /**
  * Created by kenny on 6/12/16.
  */
-@Category(IntegrationTest.class)
-@Ignore
 public class KumoCliITest {
 
+    @Test
     public void simple() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
                 "--output", "/tmp/nintendo.png"
         });
     }
 
+    @Test
     public void stopwords() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -26,6 +24,7 @@ public void stopwords() {
         });
     }
 
+    @Test
     public void wordCount() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -34,6 +33,7 @@ public void wordCount() {
         });
     }
 
+    @Test
     public void widthAndHeight() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -43,6 +43,7 @@ public void widthAndHeight() {
         });
     }
 
+    @Test
     public void randomWordStart() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -51,6 +52,7 @@ public void randomWordStart() {
         });
     }
 
+    @Test
     public void font() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -63,7 +65,7 @@ public void font() {
         });
     }
 
-
+    @Test
     public void normalizer() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -72,7 +74,7 @@ public void normalizer() {
         });
     }
 
-
+    @Test
     public void backgroundImage() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -83,7 +85,7 @@ public void backgroundImage() {
         });
     }
 
-
+    @Test
     public void colorRgb() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -92,7 +94,7 @@ public void colorRgb() {
         });
     }
 
-
+    @Test
     public void colorRgbHex() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -101,7 +103,7 @@ public void colorRgbHex() {
         });
     }
 
-
+    @Test
     public void colorHex() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo",
@@ -110,7 +112,7 @@ public void colorHex() {
         });
     }
 
-
+    @Test
     public void chinese() {
         KumoCli.main(new String[] {
                 "--input", "https://zh.wikipedia.org/wiki/%E4%BB%BB%E5%A4%A9%E5%A0%82",
@@ -119,7 +121,7 @@ public void chinese() {
         });
     }
 
-
+    @Test
     public void polar() {
         KumoCli.main(new String[] {
                 "--input", "https://en.wikipedia.org/wiki/Nintendo, https://en.wikipedia.org/wiki/PlayStation",
@@ -129,7 +131,7 @@ public void polar() {
         });
     }
 
-
+    @Test
     public void layered() {
         KumoCli.main(new String[] {
                 "--input", "https://www.haskell.org/, https://en.wikipedia.org/wiki/Haskell_(programming_language)",

kumo-core/pom.xml

@@ -15,19 +15,17 @@
         <dependency>
             <groupId>com.kennycason</groupId>
             <artifactId>kumo-api</artifactId>
-            <version>1.9</version>
-        </dependency>
-        <dependency>
-            <groupId>com.kennycason</groupId>
-            <artifactId>kumo-nlp</artifactId>
-            <version>1.9</version>
-            <scope>test</scope>
         </dependency>
+
         <!--3rd party -->
         <dependency>
             <groupId>log4j</groupId>
             <artifactId>log4j</artifactId>
         </dependency>
+        <dependency>
+            <groupId>org.jsoup</groupId>
+            <artifactId>jsoup</artifactId>
+        </dependency>
         <dependency>
             <groupId>commons-io</groupId>
             <artifactId>commons-io</artifactId>
@@ -36,14 +34,12 @@
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-lang3</artifactId>
         </dependency>
-        <dependency>
-            <groupId>com.beust</groupId>
-            <artifactId>jcommander</artifactId>
-        </dependency>
         <dependency>
             <groupId>com.github.davidmoten</groupId>
             <artifactId>rtree</artifactId>
         </dependency>
+
+        <!-- test -->
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
@@ -65,10 +61,6 @@
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-javadoc-plugin</artifactId>
             </plugin>
-            <plugin>
-                <groupId>org.apache.maven.plugins</groupId>
-                <artifactId>maven-surefire-plugin</artifactId>
-            </plugin>
         </plugins>
     </build>
 </project>

kumo-core/src/test/java/com/kennycason/kumo/examples/PolarWordCloudITest.java

@@ -12,8 +12,6 @@
 import com.kennycason.kumo.font.scale.LinearFontScalar;
 import com.kennycason.kumo.font.scale.SqrtFontScalar;
 import com.kennycason.kumo.nlp.FrequencyAnalyzer;
-import com.kennycason.kumo.nlp.tokenizer.ChineseWordTokenizer;
-import com.kennycason.kumo.palette.ColorPalette;
 import org.apache.commons.io.IOUtils;
 import org.apache.log4j.Logger;
 import org.junit.Test;
@@ -98,36 +96,6 @@ public void newyorkPolarRectangle() throws IOException {
     }
 
     @Test
-    public void chineseVsEnglishTideComments() throws IOException {
-        final FrequencyAnalyzer frequencyAnalyzer = new FrequencyAnalyzer();
-        frequencyAnalyzer.setWordFrequenciesToReturn(750);
-        frequencyAnalyzer.setMinWordLength(3);
-        frequencyAnalyzer.setStopWords(loadStopWords());
-        final List<WordFrequency> wordFrequencies = frequencyAnalyzer.load(getInputStream("text/english_tide.txt"));
-
-        final FrequencyAnalyzer chineseFrequencyAnalyzer = new FrequencyAnalyzer();
-        chineseFrequencyAnalyzer.setWordFrequenciesToReturn(750);
-        chineseFrequencyAnalyzer.setMinWordLength(2);
-        chineseFrequencyAnalyzer.setWordTokenizer(new ChineseWordTokenizer());
-        final List<WordFrequency> wordFrequencies2 = chineseFrequencyAnalyzer.load(getInputStream("text/chinese_tide.txt"));
-
-        final Dimension dimension = new Dimension(800, 600);
-        final PolarWordCloud wordCloud = new PolarWordCloud(dimension, CollisionMode.PIXEL_PERFECT, PolarBlendMode.BLUR);
-        wordCloud.setPadding(2);
-        wordCloud.setBackground(new RectangleBackground(dimension));
-        wordCloud.setFontScalar(new SqrtFontScalar(10, 70));
-
-        final ColorPalette colorPalette = new ColorPalette(new Color(0xD5CFFA), new Color(0xBBB1FA), new Color(0x9A8CF5), new Color(0x806EF5));
-        final ColorPalette colorPalette2 = new ColorPalette(new Color(0xFA8E8E), new Color(0xF77979), new Color(0xF55F5F), new Color(0xF24949));
-        wordCloud.setColorPalette(colorPalette);
-        wordCloud.setColorPalette2(colorPalette2);
-
-        final long startTime = System.currentTimeMillis();
-        wordCloud.build(wordFrequencies, wordFrequencies2);
-        LOGGER.info("Took " + (System.currentTimeMillis() - startTime) + "ms to build");
-        wordCloud.writeToFile("output/polar_tide_chinese_vs_english2.png");
-    }
-
     public void tidyCatLitter() throws IOException {
         final FrequencyAnalyzer frequencyAnalyzer = new FrequencyAnalyzer();
         frequencyAnalyzer.setWordFrequenciesToReturn(400);