SpringBoot使用Tika进行文档解析的完整指南

<!-- pom.xml中添加Tika依赖 -->  
<dependencyManagement>  
    <dependencies>  
        <dependency>  
            <groupId>org.apache.tika</groupId>  
            <artifactId>tika-bom</artifactId>  
            <version>2.6.2</version> <!-- 按需选择最新版 -->  
            <type>pom</type>  
            <scope>import</scope>  
        </dependency>  
    </dependencies>  
</dependencyManagement>  

<dependency>  
    <groupId>org.apache.tika</groupId>  
    <artifactId>tika-core</artifactId>  
</dependency>  
<dependency>  
    <groupId>org.apache.tika</groupId>  
    <artifactId>tika-parsers-standard-package</artifactId>  
    <scope>runtime</scope>  
</dependency>  

// TikaConfig.java：定制解析器（如OCR支持）  
@Configuration  
public class TikaConfig {  
    @Bean  
    public Tika tika() {  
        // 启用OCR（需安装Tesseract）  
        TesseractOCRConfig config = new TesseractOCRConfig();  
        config.setLanguage("chi_sim"); // 中文识别  
        return new Tika(config);  
    }  
}  

// DocumentParserService.java：解析器核心逻辑  
@Service  
public class DocumentParserService {  
    private final Tika tika = new Tika();  

    /**  
     * 解析文件内容（文本+元数据）  
     * @param file 需要解析的文件  
     * @return 包含文本和元数据的Map  
     */  
    public Map<String, Object> parseDocument(File file) {  
        Map<String, Object> result = new HashMap<>();  

        try (InputStream stream = new FileInputStream(file)) {  
            // 1. 检测文件类型（自动识别格式）  
            String mimeType = tika.detect(file);  
            System.out.println("检测到文件类型：" + mimeType);  

            // 2. 提取文本内容  
            String textContent = tika.parseToString(file);  
            result.put("text", textContent);  

            // 3. 提取元数据（如作者、创建时间等）  
            Metadata metadata = new Metadata();  
            tika.parse(stream, metadata);  
            Map<String, String> metaMap = new HashMap<>();  
            for (String name : metadata.names()) {  
                metaMap.put(name, metadata.get(name));  
            }  
            result.put("metadata", metaMap);  

        } catch (Exception e) {  
            e.printStackTrace();  
            result.put("error", "解析失败：" + e.getMessage());  
        }  

        return result;  
    }  
}  

// OCRExample.java：从图片中提取文字  
public class OCRExample {  
    public static void main(String[] args) throws Exception {  
        TesseractOCRConfig config = new TesseractOCRConfig();  
        config.setLanguage("eng"); // 英文识别  
        Tika tika = new Tika(config);  

        File imageFile = new File("test.jpg");  
        String text = tika.parseToString(imageFile);  
        System.out.println("图片中的文字：" + text);  
    }  
}  

// LanguageDetectionExample.java：自动识别文本语言  
public class LanguageDetectionExample {  
    public static void main(String[] args) throws Exception {  
        LanguageIdentifier identifier = new LanguageIdentifier("这是一段中文文本");  
        System.out.println("检测到语言：" + identifier.getLanguage()); // 输出：zh  
    }  
}  

// DocumentController.java：Spring Boot控制器  
@RestController  
public class DocumentController {  
    @Autowired  
    private DocumentParserService parserService;  

    @PostMapping("/parse")  
    public ResponseEntity<Map<String, Object>> parseDocument(@RequestParam("file") MultipartFile file) {  
        try {  
            File tempFile = convertMultiPartToFile(file);  
            Map<String, Object> result = parserService.parseDocument(tempFile);  
            return ResponseEntity.ok(result);  
        } catch (Exception e) {  
            return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR).body(Map.of("error", e.getMessage()));  
        }  
    }  

    // 辅助方法：转换MultipartFile为File  
    private File convertMultiPartToFile(MultipartFile file) throws IOException {  
        File convertedFile = new File(file.getOriginalFilename());  
        convertedFile.createNewFile();  
        FileOutputStream fos = new FileOutputStream(convertedFile);  
        fos.write(file.getBytes());  
        fos.close();  
        return convertedFile;  
    }  
}  

{  
  "text": "这是PDF中的内容...",  
  "metadata": {  
    "Author": "张三",  
    "Creation-Date": "2023:10:05"  
  }  
}  

// 异步解析示例  
@Service  
public class AsyncParserService {  
    @Async("tikaTaskExecutor")  
    public CompletableFuture<String> asyncParse(File file) {  
        return CompletableFuture.supplyAsync(() -> parserService.parseDocument(file).toString());  
    }  
}  

// 使用Spring Cache缓存解析结果  
@Cacheable(value = "documentCache", key = "#file.name")  
public Map<String, Object> parseDocument(File file) {  
    // 原始解析逻辑  
}  

<!-- 补充依赖 -->  
<dependency>  
    <groupId>org.apache.poi</groupId>  
    <artifactId>poi</artifactId>  
    <version>5.2.3</version>  
</dependency>  

// 在解析前设置编码  
BodyContentHandler handler = new BodyContentHandler();  
handler.setCharset("UTF-8"); // 或"GB2312"