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

text-processing-libraries-modules/apache-tika/src/main/java/com/baeldung/tika/TikaAnalysis.java

@@ -0,0 +1,67 @@
+package com.baeldung.tika;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.tika.Tika;
+import org.apache.tika.detect.DefaultDetector;
+import org.apache.tika.detect.Detector;
+import org.apache.tika.exception.TikaException;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
+import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.BodyContentHandler;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.SAXException;
+
+public class TikaAnalysis {
+    public static String detectDocTypeUsingDetector(InputStream stream) throws IOException {
+        Detector detector = new DefaultDetector();
+        Metadata metadata = new Metadata();
+
+        MediaType mediaType = detector.detect(stream, metadata);
+        return mediaType.toString();
+    }
+
+    public static String detectDocTypeUsingFacade(InputStream stream) throws IOException {
+        Tika tika = new Tika();
+        String mediaType = tika.detect(stream);
+        return mediaType;
+    }
+
+    public static String extractContentUsingParser(InputStream stream) throws IOException, TikaException, SAXException {
+        Parser parser = new AutoDetectParser();
+        ContentHandler handler = new BodyContentHandler();
+        Metadata metadata = new Metadata();
+        ParseContext context = new ParseContext();
+
+        parser.parse(stream, handler, metadata, context);
+        return handler.toString();
+    }
+
+    public static String extractContentUsingFacade(InputStream stream) throws IOException, TikaException {
+        Tika tika = new Tika();
+        String content = tika.parseToString(stream);
+        return content;
+    }
+
+    public static Metadata extractMetadatatUsingParser(InputStream stream) throws IOException, SAXException, TikaException {
+        Parser parser = new AutoDetectParser();
+        ContentHandler handler = new BodyContentHandler();
+        Metadata metadata = new Metadata();
+        ParseContext context = new ParseContext();
+
+        parser.parse(stream, handler, metadata, context);
+        return metadata;
+    }
+
+    public static Metadata extractMetadatatUsingFacade(InputStream stream) throws IOException, TikaException {
+        Tika tika = new Tika();
+        Metadata metadata = new Metadata();
+
+        tika.parse(stream, metadata);
+        return metadata;
+    }
+}

text-processing-libraries-modules/apache-tika/src/main/resources/logback.xml

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configuration>
+    <appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
+        <encoder>
+            <pattern>%d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n
+            </pattern>
+        </encoder>
+    </appender>
+
+    <root level="INFO">
+        <appender-ref ref="STDOUT" />
+    </root>
+</configuration>

text-processing-libraries-modules/apache-tika/src/test/java/com/baeldung/tika/TikaUnitTest.java

@@ -0,0 +1,79 @@
+package com.baeldung.tika;
+
+import static org.hamcrest.CoreMatchers.containsString;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertThat;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.tika.exception.TikaException;
+import org.apache.tika.metadata.Metadata;
+import org.junit.Test;
+import org.xml.sax.SAXException;
+
+public class TikaUnitTest {
+    @Test
+    public void whenUsingDetector_thenDocumentTypeIsReturned() throws IOException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.txt");
+        String mediaType = TikaAnalysis.detectDocTypeUsingDetector(stream);
+
+        assertEquals("application/pdf", mediaType);
+
+        stream.close();
+    }
+
+    @Test
+    public void whenUsingFacade_thenDocumentTypeIsReturned() throws IOException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.txt");
+        String mediaType = TikaAnalysis.detectDocTypeUsingFacade(stream);
+
+        assertEquals("application/pdf", mediaType);
+
+        stream.close();
+    }
+
+    @Test
+    public void whenUsingParser_thenContentIsReturned() throws IOException, TikaException, SAXException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.docx");
+        String content = TikaAnalysis.extractContentUsingParser(stream);
+
+        assertThat(content, containsString("Apache Tika - a content analysis toolkit"));
+        assertThat(content, containsString("detects and extracts metadata and text"));
+
+        stream.close();
+    }
+
+    @Test
+    public void whenUsingFacade_thenContentIsReturned() throws IOException, TikaException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.docx");
+        String content = TikaAnalysis.extractContentUsingFacade(stream);
+
+        assertThat(content, containsString("Apache Tika - a content analysis toolkit"));
+        assertThat(content, containsString("detects and extracts metadata and text"));
+
+        stream.close();
+    }
+
+    @Test
+    public void whenUsingParser_thenMetadataIsReturned() throws IOException, TikaException, SAXException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.xlsx");
+        Metadata metadata = TikaAnalysis.extractMetadatatUsingParser(stream);
+
+        assertEquals("org.apache.tika.parser.DefaultParser", metadata.get("X-Parsed-By"));
+        assertEquals("Microsoft Office User", metadata.get("Author"));
+
+        stream.close();
+    }
+
+    @Test
+    public void whenUsingFacade_thenMetadataIsReturned() throws IOException, TikaException {
+        InputStream stream = this.getClass().getClassLoader().getResourceAsStream("tika.xlsx");
+        Metadata metadata = TikaAnalysis.extractMetadatatUsingFacade(stream);
+
+        assertEquals("org.apache.tika.parser.DefaultParser", metadata.get("X-Parsed-By"));
+        assertEquals("Microsoft Office User", metadata.get("Author"));
+
+        stream.close();
+    }
+}