Apache Tika 範例

2017/11/19

可利用 Tika 來取得檔案的內文、Metadata 以及 MIME type

  1. 先準備 pom.xml，在 <dependency> 中加入：

    <dependencies>
    <dependency>
       <groupId>org.apache.tika</groupId>
       <artifactId>tika-core</artifactId>
       <version>1.16</version>
    </dependency>
    <dependency>
       <groupId>org.apache.tika</groupId>
       <artifactId>tika-parsers</artifactId>
       <version>1.16</version>
       <!-- 不知為何 tika-parsers 會依賴於 cxf-rt-rs-client 和 quartz，在這個範例中我先把它排除掉 -->
       <exclusions>
         <exclusion>
          <groupId>org.apache.cxf</groupId>
          <artifactId>cxf-rt-rs-client</artifactId>
         </exclusion>
         <exclusion>
          <groupId>org.quartz-scheduler</groupId>
          <artifactId>quartz</artifactId>
         </exclusion>
       </exclusions>
    </dependency>
    <dependency>
       <groupId>junit</groupId>
       <artifactId>junit</artifactId>
       <version>4.12</version>
       <scope>test</scope>
    </dependency>
</dependencies>

  2. 執行 mvn eclipse:eclipse

  3. 打開 Eclipse，並將剛剛建立的 project 匯入

  4. 建立 TikaTest.java

    package idv.shunyi.tika;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.Reader;

import org.apache.tika.Tika;
import org.apache.tika.metadata.Metadata;
import org.junit.Before;
import org.junit.Test;

public class TikaTest {
    private Tika tika;
    private File file;

    @Before
    public void setUp() throws Exception {
       tika = new Tika();
       file = new File(TikaTest.class.getResource("/test.html").toURI());
    }

    @Test
    public void testParse() throws Exception {
       Metadata metadata = new Metadata();

       try (InputStream in = new FileInputStream(file)) {
         Reader reader = tika.parse(in, metadata);

         try (BufferedReader br = new BufferedReader(reader)) {

          // Print extracted text content
          System.out.println("### extracted text content");
          for (String text; (text = br.readLine()) != null;) {
              System.out.println(text);
          }
          System.out.println();

          // Print meta data
          System.out.println("### metadata");
          for (String name : metadata.names()) {
              System.out.println(name + " = " + metadata.get(name));
          }
          System.out.println();
         }
       }
    }

    @Test
    public void testParseToString() throws Exception {
       System.out.println("### parse to string");
       try (InputStream stream = new FileInputStream(file)) {
         String text =  tika.parseToString(stream);
         System.out.println(text);
       }
       System.out.println();
    }

    @Test
    public void testDetect() throws Exception {
       System.out.println("### detect media type");
       String mimeType = tika.detect(file);
       System.out.println(mimeType);
    }
}

  5. 執行結果如下：

    ### extracted text content

    這是內文

### metadata
X-Parsed-By = org.apache.tika.parser.DefaultParser
dc:title = 這是標題
Content-Encoding = UTF-8
title = 這是標題
Content-Type = text/html; charset=UTF-8

### parse to string

    這是內文


### detect media type
text/html