8.0.0 (#7)

* Generalized SharedNPPreParticipalExtractor.

* Changed order of discourse extraction rules.

* Fix in SignalPhraseClassifier.

* Included sentence simplification. Refactored and restructured project.

* 8.0.0-SNAPSHOT. Leaf-classes contain Tree-instance instead of String.

* Bugfixes: ignore-case in classifier.

* Updated rule-implementations and used relations. Used external resources for signal phrases and attribution verbs.

* Licence fixes.

* Updated README.

* Release version 5.0.0

Author: Mischn

README.md

@@ -20,8 +20,18 @@ Clone and install locally
     mvn package
 
 ### Run the program
+Create a new text file with the input
+
+    vim input.txt
+     
+Run program
 
     mvn clean compile exec:java
+    
+Inspect output
+
+    cat output_default.txt
+    cat output_flat.txt
 
 ## Use as library
 Check `App.java`. 

pom.xml

@@ -26,7 +26,7 @@
 
     <groupId>org.lambda3.text.simplification</groupId>
     <artifactId>discourse-simplification</artifactId>
-    <version>7.1.0</version>
+    <version>8.0.0</version>
     <packaging>jar</packaging>
 
     <name>Discourse Simplification</name>
@@ -41,6 +41,9 @@
 
     <properties>
         <config.version>1.3.1</config.version>
+        <jackson.version>2.8.8</jackson.version>
+
+        <simplification.version>5.0.0</simplification.version>
 
         <corenlp.version>3.7.0</corenlp.version>
         <logback.version>1.1.8</logback.version>
@@ -62,23 +65,35 @@
             <version>${config.version}</version>
         </dependency>
 
-        <!-- Stanford NLP -->
+        <!-- Jackson -->
         <dependency>
-            <groupId>edu.stanford.nlp</groupId>
-            <artifactId>stanford-corenlp</artifactId>
-            <version>${corenlp.version}</version>
-            <exclusions>
-                <exclusion>
-                    <artifactId>slf4j-api</artifactId>
-                    <groupId>org.slf4j</groupId>
-                </exclusion>
-            </exclusions>
+            <groupId>com.fasterxml.jackson.core</groupId>
+            <artifactId>jackson-annotations</artifactId>
+            <version>${jackson.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>com.fasterxml.jackson.core</groupId>
+            <artifactId>jackson-core</artifactId>
+            <version>${jackson.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>com.fasterxml.jackson.core</groupId>
+            <artifactId>jackson-databind</artifactId>
+            <version>${jackson.version}</version>
         </dependency>
+
+        <!-- Sentence Simplification -->
+        <dependency>
+            <groupId>org.lambda3.text.simplification</groupId>
+            <artifactId>sentence-simplification</artifactId>
+            <version>${simplification.version}</version>
+        </dependency>
+
+        <!-- Stanford NLP -->
         <dependency>
             <groupId>edu.stanford.nlp</groupId>
             <artifactId>stanford-corenlp</artifactId>
             <version>${corenlp.version}</version>
-            <classifier>models</classifier>
             <exclusions>
                 <exclusion>
                     <artifactId>slf4j-api</artifactId>

src/main/java/org/lambda3/text/simplification/discourse/App.java

@@ -22,21 +22,40 @@
 
 package org.lambda3.text.simplification.discourse;
 
-import org.lambda3.text.simplification.discourse.processing.OutSentence;
-import org.lambda3.text.simplification.discourse.processing.Processor;
+import org.lambda3.text.simplification.discourse.processing.DiscourseSimplifier;
+import org.lambda3.text.simplification.discourse.processing.ProcessingType;
+import org.lambda3.text.simplification.discourse.model.SimplificationContent;
 import org.slf4j.LoggerFactory;
 
+import java.io.BufferedWriter;
 import java.io.File;
+import java.io.FileWriter;
 import java.io.IOException;
+import java.util.Arrays;
 import java.util.List;
+import java.util.stream.Collectors;
 
 public class App {
     private static final org.slf4j.Logger LOGGER = LoggerFactory.getLogger(App.class);
-    private static final Processor PROCESSOR = new Processor();
+    private static final DiscourseSimplifier DISCOURSE_SIMPLIFIER = new DiscourseSimplifier();
+
+    private static void saveLines(File file, List<String> lines) {
+        try (BufferedWriter bw = new BufferedWriter(new FileWriter(file))) {
+            bw.write(lines.stream().collect(Collectors.joining("\n")));
+
+            // no need to close it.
+            //bw.close()
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+    }
 
     public static void main(String[] args) throws IOException {
 
-        List<OutSentence> sentences = PROCESSOR.process(new File("input.txt"), Processor.ProcessingType.WHOLE);
-//        List<OutSentence> sentences = PROCESSOR.process("The text.", Processor.ProcessingType.WHOLE);
+        SimplificationContent content = DISCOURSE_SIMPLIFIER.doDiscourseSimplification(new File("input.txt"), ProcessingType.WHOLE);
+        content.serializeToJSON(new File("output.json"));
+        saveLines(new File("output_default.txt"), Arrays.asList(content.defaultFormat(false)));
+        saveLines(new File("output_flat.txt"), Arrays.asList(content.flatFormat(false)));
+        LOGGER.info("done");
     }
 }

src/main/java/org/lambda3/text/simplification/discourse/Test.java

@@ -0,0 +1,71 @@
+/*
+ * ==========================License-Start=============================
+ * DiscourseSimplification : Content
+ *
+ * Copyright © 2017 Lambda³
+ *
+ * GNU General Public License 3
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see http://www.gnu.org/licenses/.
+ * ==========================License-End==============================
+ */
+
+package org.lambda3.text.simplification.discourse.model;
+
+import com.fasterxml.jackson.annotation.JsonAutoDetect;
+import com.fasterxml.jackson.annotation.PropertyAccessor;
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.module.SimpleModule;
+import edu.stanford.nlp.trees.Tree;
+import org.lambda3.text.simplification.discourse.model.serializer.TreeDeserializer;
+import org.lambda3.text.simplification.discourse.model.serializer.TreeSerializer;
+
+import java.io.File;
+import java.io.IOException;
+
+public abstract class Content {
+	private static final ObjectMapper MAPPER = new ObjectMapper();
+	private static final SimpleModule MODULE = new SimpleModule();
+
+	static {
+		MAPPER.setVisibility(PropertyAccessor.ALL, JsonAutoDetect.Visibility.NONE);
+		MAPPER.setVisibility(PropertyAccessor.FIELD, JsonAutoDetect.Visibility.ANY);
+
+		// register custom de-/serializers
+		MODULE.addSerializer(Tree.class, new TreeSerializer());
+		MODULE.addDeserializer(Tree.class, new TreeDeserializer());
+
+		MAPPER.registerModule(MODULE);
+	}
+
+	public static <T extends Content> T deserializeFromJSON(String json, Class<T> clazz) throws IOException {
+		return MAPPER.readValue(json, clazz);
+	}
+
+	public static <T extends Content> T deserializeFromJSON(File file, Class<T> clazz) throws IOException {
+		return MAPPER.readValue(file, clazz);
+	}
+
+	public String prettyPrintJSON() throws JsonProcessingException {
+		return MAPPER.writerWithDefaultPrettyPrinter().writeValueAsString(this);
+	}
+
+	public String serializeToJSON() throws JsonProcessingException {
+		return MAPPER.writeValueAsString(this);
+	}
+
+	public void serializeToJSON(File file) throws IOException {
+		MAPPER.writeValue(file, this);
+	}
+}

src/main/java/org/lambda3/text/simplification/discourse/model/Content.java

@@ -0,0 +1,116 @@
+/*
+ * ==========================License-Start=============================
+ * DiscourseSimplification : Element
+ *
+ * Copyright © 2017 Lambda³
+ *
+ * GNU General Public License 3
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see http://www.gnu.org/licenses/.
+ * ==========================License-End==============================
+ */
+
+package org.lambda3.text.simplification.discourse.model;
+
+import edu.stanford.nlp.trees.Tree;
+import org.lambda3.text.simplification.discourse.utils.IDGenerator;
+import org.lambda3.text.simplification.discourse.utils.parseTree.ParseTreeException;
+import org.lambda3.text.simplification.discourse.utils.parseTree.ParseTreeExtractionUtils;
+import org.lambda3.text.simplification.discourse.utils.parseTree.ParseTreeParser;
+import org.lambda3.text.simplification.discourse.utils.words.WordsUtils;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ *
+ */
+public class Element {
+    private String id;
+    private Tree parseTree;
+    private int sentenceIdx;
+    private int contextLayer;
+    private List<SimpleContext> simpleContexts;
+    private List<LinkedContext> linkedContexts;
+
+    // for deserialization
+    public Element() {
+    }
+
+    public Element(Tree parseTree, int sentenceIdx, int contextLayer) {
+        this.id = IDGenerator.generateUUID();
+        this.parseTree = parseTree;
+        this.sentenceIdx = sentenceIdx;
+        this.contextLayer = contextLayer;
+        this.simpleContexts = new ArrayList<>();
+        this.linkedContexts = new ArrayList<>();
+    }
+
+    // not efficient -> prefer to use constructor with tree
+    public Element(String text, int sentenceIdx, int contextLayer) throws ParseTreeException {
+        this(ParseTreeParser.parse(text), sentenceIdx, contextLayer);
+    }
+
+    public void addLinkedContext(LinkedContext context) {
+        if (!linkedContexts.contains(context)) {
+            linkedContexts.add(context);
+        }
+    }
+
+    public void addSimpleContext(SimpleContext context) {
+        if (!simpleContexts.contains(context)) {
+            simpleContexts.add(context);
+        }
+    }
+
+    public String getId() {
+        return id;
+    }
+
+    public Tree getParseTree() {
+        return parseTree;
+    }
+
+    public void setParseTree(Tree parseTree) {
+        this.parseTree = parseTree;
+    }
+
+    public String getText() {
+        return WordsUtils.wordsToString(ParseTreeExtractionUtils.getContainingWords(parseTree));
+    }
+
+    public int getSentenceIdx() {
+        return sentenceIdx;
+    }
+
+    public int getContextLayer() {
+        return contextLayer;
+    }
+
+    public List<SimpleContext> getSimpleContexts() {
+        return simpleContexts;
+    }
+
+    public List<LinkedContext> getLinkedContexts() {
+        return linkedContexts;
+    }
+
+    @Override
+    public String toString() {
+        StringBuilder strb = new StringBuilder();
+        strb.append(id + "     " + contextLayer + "     " + getText() + "\n");
+        getSimpleContexts().forEach(c -> strb.append("\tS:" + c.getRelation() + "    " + c.getText() + "\n"));
+        getLinkedContexts().forEach(c -> strb.append("\tL:" + c.getRelation() + "    " + c.getTargetID() + "\n"));
+        return strb.toString();
+    }
+}