GroupDocs.Search for Java を使用した効率的なドキュメント検索のマスター

<repositories>
    <repository>
        <id>repository.groupdocs.com</id>
        <name>GroupDocs Repository</name>
        <url>https://releases.groupdocs.com/search/java/</url>
    </repository>
</repositories>

<dependencies>
    <dependency>
        <groupId>com.groupdocs</groupId>
        <artifactId>groupdocs-search</artifactId>
        <version>25.4</version>
    </dependency>
</dependencies>

import com.groupdocs.search.*;
import java.io.ByteArrayOutputStream;

public class FeatureIndexCreation {
    public static void main(String[] args) {
        // Define the folder paths for indexing
        String indexFolder = YOUR_DOCUMENT_DIRECTORY + "/OutputAdapters/Index";
        String documentsFolder = YOUR_DOCUMENT_DIRECTORY + "/DocumentsPath";  // Adjust as needed

        // Creating an index settings instance with compression enabled
        IndexSettings settings = new IndexSettings();
        settings.setTextStorageSettings(new TextStorageSettings(Compression.High));

        // Creating the index in the specified folder
        Index index = new Index(indexFolder, settings);

        // Adding documents from the specified folder to the index
        index.add(documentsFolder);
    }
}

import com.groupdocs.search.*;

public class FeatureOutputToFile {
    public static void main(String[] args) {
        String indexFolder = YOUR_DOCUMENT_DIRECTORY + "/OutputAdapters/Index";
        Index index = new Index(indexFolder);

        // Assuming documents are already indexed, retrieve the first document
        DocumentInfo[] documents = index.getIndexedDocuments();
        if (documents.length > 0) {
            DocumentInfo document = documents[0];

            // Output document text to an HTML file
            FileOutputAdapter fileOutputAdapter = new FileOutputAdapter(OutputFormat.Html, YOUR_OUTPUT_DIRECTORY + "/Text.html");
            index.getDocumentText(document, fileOutputAdapter);
        }
    }
}

import com.groupdocs.search.*;
import java.io.ByteArrayOutputStream;

public class FeatureOutputToStream {
    public static void main(String[] args) {
        String indexFolder = YOUR_DOCUMENT_DIRECTORY + "/OutputAdapters/Index";
        Index index = new Index(indexFolder);

        // Assuming documents are already indexed, retrieve the first document
        DocumentInfo[] documents = index.getIndexedDocuments();
        if (documents.length > 0) {
            DocumentInfo document = documents[0];

            // Output document text to a stream in HTML format
            ByteArrayOutputStream stream = new ByteArrayOutputStream();
            StreamOutputAdapter streamOutputAdapter = new StreamOutputAdapter(OutputFormat.Html, stream);
            index.getDocumentText(document, streamOutputAdapter);
        }
    }
}

import com.groupdocs.search.*;

public class FeatureOutputToString {
    public static void main(String[] args) {
        String indexFolder = YOUR_DOCUMENT_DIRECTORY + "/OutputAdapters/Index";
        Index index = new Index(indexFolder);

        // Assuming documents are already indexed, retrieve the first document
        DocumentInfo[] documents = index.getIndexedDocuments();
        if (documents.length > 0) {
            DocumentInfo document = documents[0];

            // Output document text to a string in HTML format
            StringOutputAdapter stringOutputAdapter = new StringOutputAdapter(OutputFormat.Html);
            index.getDocumentText(document, stringOutputAdapter);
            String result = stringOutputAdapter.getResult();
        }
    }
}

import com.groupdocs.search.*;

public class FeatureOutputToStructure {
    public static void main(String[] args) {
        String indexFolder = YOUR_DOCUMENT_DIRECTORY + "/OutputAdapters/Index";
        Index index = new Index(indexFolder);

        // Assuming documents are already indexed, retrieve the first document
        DocumentInfo[] documents = index.getIndexedDocuments();
        if (documents.length > 0) {
            DocumentInfo document = documents[0];

            // Output document text to a structured format like PlainText
            StructuredOutputAdapter structuredOutputAdapter = new StructuredOutputAdapter(OutputFormat.PlainText);
            index.getDocumentText(document, structuredOutputAdapter);
        }
    }
}