O poder do Apache Tika: extraindo texto e metadados de arquivos em Java

<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0
                             http://maven.apache.org/xsd/maven-4.0.0.xsd">

  <modelVersion>4.0.0</modelVersion>

  <groupId>com.gasparbarancelli</groupId>
  <artifactId>demo-apache-tika</artifactId>
  <version>1.0-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>demo-apache-tika</name>
  <url>http://maven.apache.org</url>

  <properties>
    <maven.compiler.parameters>true</maven.compiler.parameters>
    <maven.compiler.source>21</maven.compiler.source>
    <maven.compiler.target>21</maven.compiler.target>
    <java.version>21</java.version>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <tika.version>3.0.0</tika.version>
  </properties>

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

</project>

package com.gasparbarancelli;

import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;

import java.io.FileInputStream;
import java.io.InputStream;
import java.net.URL;

public class Demo {

    public static void main(String[] args) throws Exception {
        try (InputStream htmlInputStream = new URL("https://gasparbarancelli.com/about").openStream();
             InputStream pdfInputStream = new FileInputStream("src/main/resources/post-spring-ai-vector-database.pdf")) {

            parse(htmlInputStream, pdfInputStream);
        }
    }

    public static void parse(InputStream... inputs) throws Exception {
        for (InputStream input : inputs) {
            // Handler que será responsável por armazenar o conteúdo parseado
            BodyContentHandler handler = new BodyContentHandler(-1);
            // -1 remove a limitação do tamanho do conteúdo a ser armazenado

            // Metadados
            Metadata metadata = new Metadata();

            // O parser que detecta o tipo de arquivo automaticamente
            AutoDetectParser parser = new AutoDetectParser();

            // Contexto de parsing
            ParseContext parseContext = new ParseContext();

            // Faz o parse do arquivo (seja HTML ou PDF)
            parser.parse(input, handler, metadata, parseContext);

            // Exibe o texto extraído
            System.out.println("Texto extraído:");
            System.out.println(handler);

            // Exibe metadados
            System.out.println("Metadados:");
            String[] metadataNames = metadata.names();
            for (String name : metadataNames) {
                System.out.println(name + ": " + metadata.get(name));
            }
        }
    }

}