SpringBoot使用Apache Tika实现多种文档的内容解析

<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-core</artifactId>
    <version>2.7.0</version>
</dependency>
<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-parsers</artifactId>
    <version>2.7.0</version>
</dependency>

import org.apache.tika.Tika;
import org.apache.tika.exception.TikaException;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.io.InputStream;

@Service
public class DocumentParserService {

    private final Tika tika;

    public DocumentParserService() {
        this.tika = new Tika(); // 初始化 Tika 实例
    }

    /**
     * 解析文档内容
     * @param inputStream 文件输入流
     * @return 提取的内容
     * @throws IOException 文件读取异常
     * @throws TikaException Tika 解析异常
     */
    public String parseContent(InputStream inputStream) throws IOException, TikaException {
        return tika.parseToString(inputStream); // 提取文档内容
    }
}

import org.apache.tika.exception.TikaException;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;

import java.io.IOException;

@RestController
@RequestMapping("/documents")
public class DocumentController {

    @Autowired
    private DocumentParserService documentParserService;

    /**
     * 上传文档并解析内容
     * @param file 上传的文档
     * @return 解析的内容
     */
    @PostMapping("/upload")
    public String uploadDocument(@RequestParam("file") MultipartFile file) {
        try {
            return documentParserService.parseContent(file.getInputStream());
        } catch (IOException | TikaException e) {
            return "文档解析失败: " + e.getMessage();
        }
    }
}

curl -X POST -F "file=@example.pdf" http://localhost:8080/documents/upload

This is a sample PDF document.
Content extraction with Apache Tika is easy and efficient.

import org.apache.tika.metadata.Metadata;

public String parseMetadata(InputStream inputStream) throws IOException, TikaException {
    Metadata metadata = new Metadata();
    tika.parse(inputStream, metadata);

    StringBuilder metadataInfo = new StringBuilder();
    for (String name : metadata.names()) {
        metadataInfo.append(name).append(": ").append(metadata.get(name)).append("\n");
    }
    return metadataInfo.toString();
}

public String detectDocumentType(InputStream inputStream) throws IOException {
    return tika.detect(inputStream);
}

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

@Service
public class DocumentParserService {

    private static final Logger logger = LoggerFactory.getLogger(DocumentParserService.class);
    private final Tika tika;

    public DocumentParserService() {
        this.tika = new Tika();
    }

    public String parseContent(InputStream inputStream, String fileName) throws IOException, TikaException {
        long startTime = System.currentTimeMillis();
        String content = tika.parseToString(inputStream);
        logger.info("Parsed file [{}] in {} ms", fileName, System.currentTimeMillis() - startTime);
        return content;
    }
}

src
├── main
│   ├── java
│   │   ├── com.example.tika
│   │   │   ├── DocumentParserService.java
│   │   │   ├── DocumentController.java
│   ├── resources
│   │   └── application.yml