JAVA-29281 Create new module Text Processing Libraries Modules (#15479)

pom.xml

@@ -686,7 +686,6 @@
             <modules>
                 <module>akka-modules</module>
                 <module>algorithms-modules</module>
-                <module>antlr</module>
                 <module>apache-cxf-modules</module>
                 <module>apache-httpclient-2</module>
                 <module>apache-httpclient4</module>
@@ -700,9 +699,7 @@
                 <module>apache-poi-3</module>
                 <module>apache-poi</module>
                 <module>apache-thrift</module>
-                <module>apache-tika</module>
                 <module>apache-velocity</module>
-                <module>asciidoctor</module>
                 <module>atomix</module>
                 <module>aws-modules</module>
                 <module>azure</module>
@@ -813,8 +810,6 @@
                 <module>osgi</module>
                 <module>parent-boot-3</module>
                 <module>patterns-modules</module>
-                <module>pdf-2</module>
-                <module>pdf</module>
                 <module>performance-tests</module>
                 <module>persistence-modules</module>
                 <!--<module>persistence-modules/java-harperdb</module>--> <!-- This module requires a library to download manually -->
@@ -896,6 +891,7 @@
                 <module>tensorflow-java</module>
                 <module>testing-modules</module>
                 <module>testing-modules/mockito-simple</module>
+                <module>text-processing-libraries-modules</module>
                 <module>timefold-solver</module>
                 <module>vaadin</module>
                 <module>vavr-modules</module>
@@ -940,7 +936,6 @@
             <modules>
                 <module>akka-modules</module>
                 <module>algorithms-modules</module>
-                <module>antlr</module>
                 <module>apache-cxf-modules</module>
                 <module>apache-httpclient-2</module>
                 <module>apache-httpclient4</module>
@@ -954,9 +949,7 @@
                 <module>apache-poi-3</module>
                 <module>apache-poi</module>
                 <module>apache-thrift</module>
-                <module>apache-tika</module>
                 <module>apache-velocity</module>
-                <module>asciidoctor</module>
                 <module>atomix</module>
                 <module>aws-modules</module>
                 <module>azure</module>
@@ -1067,8 +1060,6 @@
                 <module>osgi</module>
                 <module>parent-boot-3</module>
                 <module>patterns-modules</module>
-                <module>pdf-2</module>
-                <module>pdf</module>
                 <module>performance-tests</module>
                 <module>persistence-modules</module>
                 <module>persistence-modules/spring-data-neo4j</module>
@@ -1148,6 +1139,7 @@
                 <module>tensorflow-java</module>
                 <module>testing-modules</module>
                 <module>testing-modules/mockito-simple</module>
+                <module>text-processing-libraries-modules</module>
                 <module>timefold-solver</module>
                 <module>vaadin</module>
                 <module>vavr-modules</module>

text-processing-libraries-modules/README.md

@@ -0,0 +1,3 @@
+## Text Processing Libraries 
+
+This module contains modules about Text Processing Libraries. 

text-processing-libraries-modules/antlr/pom.xml

@@ -8,7 +8,7 @@
 
     <parent>
         <groupId>com.baeldung</groupId>
-        <artifactId>parent-modules</artifactId>
+        <artifactId>text-processing-libraries-modules</artifactId>
         <version>1.0.0-SNAPSHOT</version>
     </parent>
 

text-processing-libraries-modules/apache-tika/pom.xml

@@ -9,7 +9,7 @@
 
     <parent>
         <groupId>com.baeldung</groupId>
-        <artifactId>parent-modules</artifactId>
+        <artifactId>text-processing-libraries-modules</artifactId>
         <version>1.0.0-SNAPSHOT</version>
     </parent>
 

text-processing-libraries-modules/asciidoctor/pom.xml

@@ -8,7 +8,7 @@
 
     <parent>
         <groupId>com.baeldung</groupId>
-        <artifactId>parent-modules</artifactId>
+        <artifactId>text-processing-libraries-modules</artifactId>
         <version>1.0.0-SNAPSHOT</version>
     </parent>
 

text-processing-libraries-modules/pdf-2/pom.xml

@@ -9,7 +9,7 @@
 
     <parent>
         <groupId>com.baeldung</groupId>
-        <artifactId>parent-modules</artifactId>
+        <artifactId>text-processing-libraries-modules</artifactId>
         <version>1.0.0-SNAPSHOT</version>
     </parent>
 

text-processing-libraries-modules/pdf-2/src/main/java/com/baeldung/pdfedition/PdfContentRemover.java

@@ -1,43 +1,43 @@
-package com.baeldung.pdfedition;
-
-import java.io.IOException;
-import java.util.Arrays;
-import java.util.List;
-
-import com.itextpdf.kernel.geom.Rectangle;
-import com.itextpdf.kernel.pdf.PdfDocument;
-import com.itextpdf.kernel.pdf.PdfReader;
-import com.itextpdf.kernel.pdf.PdfWriter;
-import com.itextpdf.pdfcleanup.CleanUpProperties;
-import com.itextpdf.pdfcleanup.PdfCleanUpLocation;
-import com.itextpdf.pdfcleanup.PdfCleanUpTool;
-import com.itextpdf.pdfcleanup.PdfCleaner;
-import com.itextpdf.pdfcleanup.autosweep.CompositeCleanupStrategy;
-import com.itextpdf.pdfcleanup.autosweep.RegexBasedCleanupStrategy;
-
-public class PdfContentRemover {
-
-    private static final String SOURCE = "src/main/resources/baeldung-modified.pdf";
-    private static final String DESTINATION = "src/main/resources/baeldung-cleaned.pdf";
-
-    public static void main(String[] args) throws IOException {
-        PdfReader reader = new PdfReader(SOURCE);
-        PdfWriter writer = new PdfWriter(DESTINATION);
-        PdfDocument pdfDocument = new PdfDocument(reader, writer);
-        removeContentFromDocument(pdfDocument);
-        pdfDocument.close();
-    }
-
-    private static void removeContentFromDocument(PdfDocument pdfDocument) throws IOException {
-        // 5.1. remove text
-        CompositeCleanupStrategy strategy = new CompositeCleanupStrategy();
-        strategy.add(new RegexBasedCleanupStrategy("Baeldung"));
-        PdfCleaner.autoSweepCleanUp(pdfDocument, strategy);
-
-        // 5.2. remove other areas
-        List<PdfCleanUpLocation> cleanUpLocations = Arrays.asList(new PdfCleanUpLocation(1, new Rectangle(10, 50, 90, 70)), new PdfCleanUpLocation(2, new Rectangle(35, 400, 100, 35)));
-        PdfCleanUpTool cleaner = new PdfCleanUpTool(pdfDocument, cleanUpLocations, new CleanUpProperties());
-        cleaner.cleanUp();
-    }
-
-}
+package com.baeldung.pdfedition;
+
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.List;
+
+import com.itextpdf.kernel.geom.Rectangle;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfReader;
+import com.itextpdf.kernel.pdf.PdfWriter;
+import com.itextpdf.pdfcleanup.CleanUpProperties;
+import com.itextpdf.pdfcleanup.PdfCleanUpLocation;
+import com.itextpdf.pdfcleanup.PdfCleanUpTool;
+import com.itextpdf.pdfcleanup.PdfCleaner;
+import com.itextpdf.pdfcleanup.autosweep.CompositeCleanupStrategy;
+import com.itextpdf.pdfcleanup.autosweep.RegexBasedCleanupStrategy;
+
+public class PdfContentRemover {
+
+    private static final String SOURCE = "src/main/resources/baeldung-modified.pdf";
+    private static final String DESTINATION = "src/main/resources/baeldung-cleaned.pdf";
+
+    public static void main(String[] args) throws IOException {
+        PdfReader reader = new PdfReader(SOURCE);
+        PdfWriter writer = new PdfWriter(DESTINATION);
+        PdfDocument pdfDocument = new PdfDocument(reader, writer);
+        removeContentFromDocument(pdfDocument);
+        pdfDocument.close();
+    }
+
+    private static void removeContentFromDocument(PdfDocument pdfDocument) throws IOException {
+        // 5.1. remove text
+        CompositeCleanupStrategy strategy = new CompositeCleanupStrategy();
+        strategy.add(new RegexBasedCleanupStrategy("Baeldung"));
+        PdfCleaner.autoSweepCleanUp(pdfDocument, strategy);
+
+        // 5.2. remove other areas
+        List<PdfCleanUpLocation> cleanUpLocations = Arrays.asList(new PdfCleanUpLocation(1, new Rectangle(10, 50, 90, 70)), new PdfCleanUpLocation(2, new Rectangle(35, 400, 100, 35)));
+        PdfCleanUpTool cleaner = new PdfCleanUpTool(pdfDocument, cleanUpLocations, new CleanUpProperties());
+        cleaner.cleanUp();
+    }
+
+}

text-processing-libraries-modules/pdf-2/src/main/java/com/baeldung/pdfedition/PdfEditor.java

@@ -1,86 +1,86 @@
-package com.baeldung.pdfedition;
-
-import java.io.IOException;
-import java.net.MalformedURLException;
-
-import com.itextpdf.forms.PdfAcroForm;
-import com.itextpdf.forms.fields.PdfFormField;
-import com.itextpdf.forms.fields.PdfTextFormField;
-import com.itextpdf.io.image.ImageData;
-import com.itextpdf.io.image.ImageDataFactory;
-import com.itextpdf.kernel.geom.Rectangle;
-import com.itextpdf.kernel.pdf.PdfDocument;
-import com.itextpdf.kernel.pdf.PdfReader;
-import com.itextpdf.kernel.pdf.PdfString;
-import com.itextpdf.kernel.pdf.PdfWriter;
-import com.itextpdf.kernel.pdf.annot.PdfAnnotation;
-import com.itextpdf.kernel.pdf.annot.PdfTextAnnotation;
-import com.itextpdf.layout.Document;
-import com.itextpdf.layout.element.Image;
-import com.itextpdf.layout.element.Paragraph;
-import com.itextpdf.layout.element.Table;
-import com.itextpdf.layout.element.Text;
-import com.itextpdf.layout.properties.UnitValue;
-
-public class PdfEditor {
-
-    private static final String SOURCE = "src/main/resources/baeldung.pdf";
-    private static final String DESTINATION = "src/main/resources/baeldung-modified.pdf";
-
-    public static void main(String[] args) throws IOException {
-        PdfReader reader = new PdfReader(SOURCE);
-        PdfWriter writer = new PdfWriter(DESTINATION);
-        PdfDocument pdfDocument = new PdfDocument(reader, writer);
-        addContentToDocument(pdfDocument);
-    }
-
-    private static void addContentToDocument(PdfDocument pdfDocument) throws MalformedURLException {
-        // 4.1. add form
-        PdfFormField personal = PdfFormField.createEmptyField(pdfDocument);
-        personal.setFieldName("information");
-        PdfTextFormField name = PdfFormField.createText(pdfDocument, new Rectangle(35, 400, 100, 30), "name", "");
-        personal.addKid(name);
-        PdfAcroForm.getAcroForm(pdfDocument, true)
-            .addField(personal, pdfDocument.getFirstPage());
-
-        // 4.2. add new page
-        pdfDocument.addNewPage(1);
-
-        // 4.3. add annotation
-        PdfAnnotation ann = new PdfTextAnnotation(new Rectangle(40, 435, 0, 0)).setTitle(new PdfString("name"))
-            .setContents("Your name");
-        pdfDocument.getPage(2)
-            .addAnnotation(ann);
-
-        // create document form pdf document
-        Document document = new Document(pdfDocument);
-
-        // 4.4. add an image
-        ImageData imageData = ImageDataFactory.create("src/main/resources/baeldung.png");
-        Image image = new Image(imageData).scaleAbsolute(550, 100)
-            .setFixedPosition(1, 10, 50);
-        document.add(image);
-
-        // 4.5. add a paragraph
-        Text title = new Text("This is a demo").setFontSize(16);
-        Text author = new Text("Baeldung tutorials.");
-        Paragraph p = new Paragraph().setFontSize(8)
-            .add(title)
-            .add(" from ")
-            .add(author);
-        document.add(p);
-
-        // 4.6. add a table
-        Table table = new Table(UnitValue.createPercentArray(2));
-        table.addHeaderCell("#");
-        table.addHeaderCell("company");
-        table.addCell("name");
-        table.addCell("baeldung");
-        document.add(table);
-
-        // close the document
-        // this automatically closes the pdfDocument, which then closes automatically the pdfReader and pdfWriter
-        document.close();
-    }
-
-}
+package com.baeldung.pdfedition;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+
+import com.itextpdf.forms.PdfAcroForm;
+import com.itextpdf.forms.fields.PdfFormField;
+import com.itextpdf.forms.fields.PdfTextFormField;
+import com.itextpdf.io.image.ImageData;
+import com.itextpdf.io.image.ImageDataFactory;
+import com.itextpdf.kernel.geom.Rectangle;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfReader;
+import com.itextpdf.kernel.pdf.PdfString;
+import com.itextpdf.kernel.pdf.PdfWriter;
+import com.itextpdf.kernel.pdf.annot.PdfAnnotation;
+import com.itextpdf.kernel.pdf.annot.PdfTextAnnotation;
+import com.itextpdf.layout.Document;
+import com.itextpdf.layout.element.Image;
+import com.itextpdf.layout.element.Paragraph;
+import com.itextpdf.layout.element.Table;
+import com.itextpdf.layout.element.Text;
+import com.itextpdf.layout.properties.UnitValue;
+
+public class PdfEditor {
+
+    private static final String SOURCE = "src/main/resources/baeldung.pdf";
+    private static final String DESTINATION = "src/main/resources/baeldung-modified.pdf";
+
+    public static void main(String[] args) throws IOException {
+        PdfReader reader = new PdfReader(SOURCE);
+        PdfWriter writer = new PdfWriter(DESTINATION);
+        PdfDocument pdfDocument = new PdfDocument(reader, writer);
+        addContentToDocument(pdfDocument);
+    }
+
+    private static void addContentToDocument(PdfDocument pdfDocument) throws MalformedURLException {
+        // 4.1. add form
+        PdfFormField personal = PdfFormField.createEmptyField(pdfDocument);
+        personal.setFieldName("information");
+        PdfTextFormField name = PdfFormField.createText(pdfDocument, new Rectangle(35, 400, 100, 30), "name", "");
+        personal.addKid(name);
+        PdfAcroForm.getAcroForm(pdfDocument, true)
+            .addField(personal, pdfDocument.getFirstPage());
+
+        // 4.2. add new page
+        pdfDocument.addNewPage(1);
+
+        // 4.3. add annotation
+        PdfAnnotation ann = new PdfTextAnnotation(new Rectangle(40, 435, 0, 0)).setTitle(new PdfString("name"))
+            .setContents("Your name");
+        pdfDocument.getPage(2)
+            .addAnnotation(ann);
+
+        // create document form pdf document
+        Document document = new Document(pdfDocument);
+
+        // 4.4. add an image
+        ImageData imageData = ImageDataFactory.create("src/main/resources/baeldung.png");
+        Image image = new Image(imageData).scaleAbsolute(550, 100)
+            .setFixedPosition(1, 10, 50);
+        document.add(image);
+
+        // 4.5. add a paragraph
+        Text title = new Text("This is a demo").setFontSize(16);
+        Text author = new Text("Baeldung tutorials.");
+        Paragraph p = new Paragraph().setFontSize(8)
+            .add(title)
+            .add(" from ")
+            .add(author);
+        document.add(p);
+
+        // 4.6. add a table
+        Table table = new Table(UnitValue.createPercentArray(2));
+        table.addHeaderCell("#");
+        table.addHeaderCell("company");
+        table.addCell("name");
+        table.addCell("baeldung");
+        document.add(table);
+
+        // close the document
+        // this automatically closes the pdfDocument, which then closes automatically the pdfReader and pdfWriter
+        document.close();
+    }
+
+}

text-processing-libraries-modules/pdf-2/src/main/java/com/baeldung/pdfedition/PdfTextReplacement.java

@@ -1,45 +1,45 @@
-package com.baeldung.pdfedition;
-
-import java.io.IOException;
-
-import com.itextpdf.kernel.colors.ColorConstants;
-import com.itextpdf.kernel.pdf.PdfDocument;
-import com.itextpdf.kernel.pdf.PdfPage;
-import com.itextpdf.kernel.pdf.PdfReader;
-import com.itextpdf.kernel.pdf.PdfWriter;
-import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
-import com.itextpdf.kernel.pdf.canvas.parser.listener.IPdfTextLocation;
-import com.itextpdf.layout.Canvas;
-import com.itextpdf.layout.element.Paragraph;
-import com.itextpdf.pdfcleanup.PdfCleaner;
-import com.itextpdf.pdfcleanup.autosweep.CompositeCleanupStrategy;
-import com.itextpdf.pdfcleanup.autosweep.RegexBasedCleanupStrategy;
-
-public class PdfTextReplacement {
-
-    private static final String SOURCE = "src/main/resources/baeldung-modified.pdf";
-    private static final String DESTINATION = "src/main/resources/baeldung-fixed.pdf";
-
-    public static void main(String[] args) throws IOException {
-        PdfReader reader = new PdfReader(SOURCE);
-        PdfWriter writer = new PdfWriter(DESTINATION);
-        PdfDocument pdfDocument = new PdfDocument(reader, writer);
-        replaceTextContentFromDocument(pdfDocument);
-        pdfDocument.close();
-    }
-
-    private static void replaceTextContentFromDocument(PdfDocument pdfDocument) throws IOException {
-        CompositeCleanupStrategy strategy = new CompositeCleanupStrategy();
-        strategy.add(new RegexBasedCleanupStrategy("Baeldung tutorials").setRedactionColor(ColorConstants.WHITE));
-        PdfCleaner.autoSweepCleanUp(pdfDocument, strategy);
-
-        for (IPdfTextLocation location : strategy.getResultantLocations()) {
-            PdfPage page = pdfDocument.getPage(location.getPageNumber() + 1);
-            PdfCanvas pdfCanvas = new PdfCanvas(page.newContentStreamAfter(), page.getResources(), page.getDocument());
-            Canvas canvas = new Canvas(pdfCanvas, location.getRectangle());
-            canvas.add(new Paragraph("HIDDEN").setFontSize(8)
-                .setMarginTop(0f));
-        }
-    }
-
-}
+package com.baeldung.pdfedition;
+
+import java.io.IOException;
+
+import com.itextpdf.kernel.colors.ColorConstants;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfPage;
+import com.itextpdf.kernel.pdf.PdfReader;
+import com.itextpdf.kernel.pdf.PdfWriter;
+import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
+import com.itextpdf.kernel.pdf.canvas.parser.listener.IPdfTextLocation;
+import com.itextpdf.layout.Canvas;
+import com.itextpdf.layout.element.Paragraph;
+import com.itextpdf.pdfcleanup.PdfCleaner;
+import com.itextpdf.pdfcleanup.autosweep.CompositeCleanupStrategy;
+import com.itextpdf.pdfcleanup.autosweep.RegexBasedCleanupStrategy;
+
+public class PdfTextReplacement {
+
+    private static final String SOURCE = "src/main/resources/baeldung-modified.pdf";
+    private static final String DESTINATION = "src/main/resources/baeldung-fixed.pdf";
+
+    public static void main(String[] args) throws IOException {
+        PdfReader reader = new PdfReader(SOURCE);
+        PdfWriter writer = new PdfWriter(DESTINATION);
+        PdfDocument pdfDocument = new PdfDocument(reader, writer);
+        replaceTextContentFromDocument(pdfDocument);
+        pdfDocument.close();
+    }
+
+    private static void replaceTextContentFromDocument(PdfDocument pdfDocument) throws IOException {
+        CompositeCleanupStrategy strategy = new CompositeCleanupStrategy();
+        strategy.add(new RegexBasedCleanupStrategy("Baeldung tutorials").setRedactionColor(ColorConstants.WHITE));
+        PdfCleaner.autoSweepCleanUp(pdfDocument, strategy);
+
+        for (IPdfTextLocation location : strategy.getResultantLocations()) {
+            PdfPage page = pdfDocument.getPage(location.getPageNumber() + 1);
+            PdfCanvas pdfCanvas = new PdfCanvas(page.newContentStreamAfter(), page.getResources(), page.getDocument());
+            Canvas canvas = new Canvas(pdfCanvas, location.getRectangle());
+            canvas.add(new Paragraph("HIDDEN").setFontSize(8)
+                .setMarginTop(0f));
+        }
+    }
+
+}

text-processing-libraries-modules/pdf/pom.xml

@@ -9,7 +9,7 @@
 
     <parent>
         <groupId>com.baeldung</groupId>
-        <artifactId>parent-modules</artifactId>
+        <artifactId>text-processing-libraries-modules</artifactId>
         <version>1.0.0-SNAPSHOT</version>
     </parent>
 

text-processing-libraries-modules/pom.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>text-processing-libraries-modules</artifactId>
+    <name>text-processing-libraries-modules</name>
+    <packaging>pom</packaging>
+
+    <parent>
+        <artifactId>parent-modules</artifactId>
+        <groupId>com.baeldung</groupId>
+        <version>1.0.0-SNAPSHOT</version>
+    </parent>
+
+    <modules>
+        <module>antlr</module>
+        <module>apache-tika</module>
+        <module>asciidoctor</module>
+        <module>pdf</module>
+        <module>pdf-2</module>
+    </modules>
+
+</project>