通过Spring Boot构建自定义Tika服务以实现上下文路径配置

<dependencies>
    <!-- Spring Boot Web Starter -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>

    <!-- Apache Tika Parsers -->
    <dependency>
        <groupId>org.apache.tika</groupId>
        <artifactId>tika-parsers</artifactId>
        <version>2.x.x</version> <!-- 请替换为最新稳定版本 -->
    </dependency>

    <!-- Spring Boot Test Starter (可选) -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-test</artifactId>
        <scope>test</scope>
    </dependency>
</dependencies>

import org.apache.tika.Tika;
import org.springframework.http.HttpStatus;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;

import java.io.IOException;
import java.io.InputStream;

@RestController
@RequestMapping("/tika-service") // 控制器级别的基础路径
public class TikaController {

    private final Tika tika = new Tika(); // Tika实例通常是线程安全的，可以重用

    /**
     * 接收多部分文件请求，并使用Tika检测文件内容类型。
     * @param file 上传的文件
     * @return 包含文件内容类型的响应
     */
    @PostMapping("/detect-type")
    public ResponseEntity<String> detectContentType(@RequestParam("file") MultipartFile file) {
        if (file.isEmpty()) {
            return new ResponseEntity<>("Please select a file to upload.", HttpStatus.BAD_REQUEST);
        }

        try (InputStream stream = file.getInputStream()) {
            String contentType = tika.detect(stream, file.getOriginalFilename());
            return new ResponseEntity<>("Detected Content Type: " + contentType, HttpStatus.OK);
        } catch (IOException e) {
            // 记录异常
            System.err.println("Error processing file: " + e.getMessage());
            return new ResponseEntity<>("Failed to process file: " + e.getMessage(), HttpStatus.INTERNAL_SERVER_ERROR);
        }
    }

    // 可以添加更多端点，例如：
    // @PostMapping("/extract-text")
    // public ResponseEntity<String> extractText(@RequestParam("file") MultipartFile file) { ... }
}

server.port=8080
server.servlet.context-path=/tika-server

server:
  port: 8080
  servlet:
    context-path: /tika-server