提取 pdf 註釋 java 與 GroupDocs – 快速指南

<repositories>
   <repository>
      <id>repository.groupdocs.com</id>
      <name>GroupDocs Repository</name>
      <url>https://releases.groupdocs.com/annotation/java/</url>
   </repository>
</repositories>
<dependencies>
   <dependency>
      <groupId>com.groupdocs</groupId>
      <artifactId>groupdocs-annotation</artifactId>
      <version>25.2</version>
   </dependency>
</dependencies>

// For temporary or commercial licenses
License license = new License();
license.setLicense("path/to/your/license.lic");

String inputFile = "YOUR_DOCUMENT_DIRECTORY/document.pdf";
try (final InputStream inputStream = new FileInputStream(inputFile)) {
    final Annotator annotator = new Annotator(inputStream);
    // Your annotation extraction logic goes here
} catch (IOException e) {
    e.printStackTrace();
}

String inputFile = "YOUR_DOCUMENT_DIRECTORY/document.pdf";
try (final InputStream inputStream = new FileInputStream(inputFile)) {
    final Annotator annotator = new Annotator(inputStream);
    
    // Optional: Validate document before processing
    if (annotator.get().isEmpty()) {
        System.out.println("No annotations found in document");
        return;
    }
} catch (IOException e) {
    System.err.println("Error opening document: " + e.getMessage());
}

List<AnnotationBase> annotations = annotator.get();

Iterator<AnnotationBase> items = annotations.iterator();
while (items.hasNext()) {
    AnnotationBase annotation = items.next();
    
    // Extract key information
    System.out.println("Annotation Type: " + annotation.getType());
    System.out.println("Content: " + annotation.getMessage());
    System.out.println("Page Number: " + annotation.getPageNumber());
    System.out.println("Created By: " + annotation.getCreatedBy());
    System.out.println("---");
}

try (final InputStream inputStream = new FileInputStream(inputFile)) {
    // All your annotation processing here
} // Stream automatically closed here

// Try different annotation types
for (AnnotationType type : AnnotationType.values()) {
    List<AnnotationBase> specificAnnotations = annotator.get(type);
    if (!specificAnnotations.isEmpty()) {
        System.out.println("Found " + specificAnnotations.size() + " " + type + " annotations");
    }
}

// Set JVM options: -Xmx4g -XX:+UseG1GC
// Process in smaller chunks
List<AnnotationBase> annotations = annotator.get();
int batchSize = 100;
for (int i = 0; i < annotations.size(); i += batchSize) {
    int end = Math.min(i + batchSize, annotations.size());
    List<AnnotationBase> batch = annotations.subList(i, end);
    processBatch(batch);
}

// When reading file paths or annotation content
String content = new String(annotation.getMessage().getBytes(), StandardCharsets.UTF_8);

// Instead of loading entire document into memory
try (InputStream stream = Files.newInputStream(Paths.get(filePath))) {
    Annotator annotator = new Annotator(stream);
    // Process immediately, don't store all annotations
    processAnnotationsImmediately(annotator.get());
}

List<Path> pdfFiles = Files.list(Paths.get("documents/"))
    .filter(path -> path.toString().endsWith(".pdf"))
    .collect(Collectors.toList());

pdfFiles.parallelStream().forEach(this::extractAnnotations);

// Extract and categorize reviewer feedback
Map<String, List<AnnotationBase>> reviewerComments = annotations.stream()
    .collect(Collectors.groupingBy(AnnotationBase::getCreatedBy));

reviewerComments.forEach((reviewer, comments) -> {
    System.out.println("Reviewer: " + reviewer + " (" + comments.size() + " comments)");
});

// Analyze annotation patterns
long highlightCount = annotations.stream()
    .filter(a -> a.getType() == AnnotationType.Highlight)
    .count();
    
System.out.println("Student made " + highlightCount + " highlights");

// Filter critical issues marked with specific annotation types
List<AnnotationBase> criticalIssues = annotations.stream()
    .filter(a -> a.getMessage().toLowerCase().contains("critical"))
    .collect(Collectors.toList());

@Service
public class AnnotationExtractionService {
    
    public List<AnnotationData> extractAnnotations(MultipartFile file) {
        try (InputStream inputStream = file.getInputStream()) {
            Annotator annotator = new Annotator(inputStream);
            return annotator.get().stream()
                .map(this::convertToAnnotationData)
                .collect(Collectors.toList());
        } catch (IOException e) {
            throw new DocumentProcessingException("Failed to extract annotations", e);
        }
    }
}

LoadOptions loadOptions = new LoadOptions();
loadOptions.setPassword("your-password");
Annotator annotator = new Annotator(inputStream, loadOptions);