Apache-Tika

Apache Tika 文档解析

---

文档解析示例

@Test
@SneakyThrows
public void testParser() {
    AutoDetectParser parser = new AutoDetectParser();
    BodyContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    String filePath = "/path-to-doc.docx";
    try (InputStream stream = new FileInputStream(filePath)) {
        parser.parse(stream, handler, metadata);
        log.info(handler.toString());
    } catch (Exception e) {
        log.error("解析失败", e);
    }
}

---