Springboot集成Tika实现文档解析

<dependencies>
 
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>2.9.2</version>
        </dependency>
 
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-parsers-standard-package</artifactId>
            <version>2.9.2</version>
        </dependency>
 
    </dependencies>

<?xml version="1.0" encoding="UTF-8"?>
<properties>
    <encodingDetectors>
        <!-- 检测 HTML 文件的字符编码，它会根据 HTML 元素（如 <meta> 标签）中的声明来判断编码。 -->
        <encodingDetector class="org.apache.tika.parser.html.HtmlEncodingDetector">
            <params>
                <!-- 读取的最大字节数（这里是 64,000 字节）用于判断编码 -->
                <param name="markLimit" type="int">64000</param>
            </params>
        </encodingDetector>
        <!-- Tika 的通用编码检测器 -->
        <encodingDetector class="org.apache.tika.parser.txt.UniversalEncodingDetector">
            <params>
                <param name="markLimit" type="int">64000</param>
            </params>
        </encodingDetector>
        <!-- 基于 ICU4J 库的编码检测器。ICU4J 是一个强大的国际化库，能够更准确地检测多语言文本的编码。 -->
        <encodingDetector class="org.apache.tika.parser.txt.Icu4jEncodingDetector">
            <params>
                <param name="markLimit" type="int">64000</param>
            </params>
        </encodingDetector>
    </encodingDetectors>
</properties>

@Configuration
public class ApplicationTikaConfig {
 
    @Autowired
    private ResourceLoader resourceLoader;
 
    @Bean
    public Tika tika() throws TikaException, IOException, SAXException {
        Resource resource = resourceLoader.getResource("classpath:tika-config.xml");
        InputStream inputStream = resource.getInputStream();
 
        TikaConfig config = new TikaConfig(inputStream);
        Detector detector = config.getDetector();
        Parser autoDetectParser = new AutoDetectParser(config);
        return new Tika(detector, autoDetectParser);
    }
}

@Service
public class TikaParserService {
 
    @Autowired
    private Tika tika;
 
    public void parser(Path srcPath) throws TikaException, IOException {
        String result = tika.parseToString(srcPath);
        System.out.println(result);
    }
 
}

@SpringBootTest(classes = Main.class)
@RunWith(SpringRunner.class)
public class TikaParserDemoTest {
 
    @Autowired
    private TikaParserService tikaParserService;
 
    @Test
    public void testTikaParser() throws TikaException, IOException {
        tikaParserService.parser(Paths.get("F:", "Java开发手册（黄山版）.pdf"));
    }
 
}