Java Entity类代码示例

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
/**
 * Identifies entities in the string {@code text}.
 */
public static void analyzeEntitiesText(String text) throws Exception {
  // [START analyze_entities_text]
  // Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
  try (LanguageServiceClient language = LanguageServiceClient.create()) {
    Document doc = Document.newBuilder()
        .setContent(text)
        .setType(Type.PLAIN_TEXT)
        .build();
    AnalyzeEntitiesRequest request = AnalyzeEntitiesRequest.newBuilder()
        .setDocument(doc)
        .setEncodingType(EncodingType.UTF16)
        .build();

    AnalyzeEntitiesResponse response = language.analyzeEntities(request);

    // Print the response
    for (Entity entity : response.getEntitiesList()) {
      System.out.printf("Entity: %s", entity.getName());
      System.out.printf("Salience: %.3f\n", entity.getSalience());
      System.out.println("Metadata: ");
      for (Map.Entry<String, String> entry : entity.getMetadataMap().entrySet()) {
        System.out.printf("%s : %s", entry.getKey(), entry.getValue());
      }
      for (EntityMention mention : entity.getMentionsList()) {
        System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
        System.out.printf("Content: %s\n", mention.getText().getContent());
        System.out.printf("Type: %s\n\n", mention.getType());
      }
    }
  }
  // [END analyze_entities_text]
}
 

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
/**
 * Identifies entities in the contents of the object at the given GCS {@code path}.
 */
public static void analyzeEntitiesFile(String gcsUri) throws Exception {
  // [START analyze_entities_gcs]
  // Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
  try (LanguageServiceClient language = LanguageServiceClient.create()) {
    // set the GCS Content URI path to the file to be analyzed
    Document doc = Document.newBuilder()
        .setGcsContentUri(gcsUri)
        .setType(Type.PLAIN_TEXT)
        .build();
    AnalyzeEntitiesRequest request = AnalyzeEntitiesRequest.newBuilder()
        .setDocument(doc)
        .setEncodingType(EncodingType.UTF16)
        .build();

    AnalyzeEntitiesResponse response = language.analyzeEntities(request);

    // Print the response
    for (Entity entity : response.getEntitiesList()) {
      System.out.printf("Entity: %s", entity.getName());
      System.out.printf("Salience: %.3f\n", entity.getSalience());
      System.out.println("Metadata: ");
      for (Map.Entry<String, String> entry : entity.getMetadataMap().entrySet()) {
        System.out.printf("%s : %s", entry.getKey(), entry.getValue());
      }
      for (EntityMention mention : entity.getMentionsList()) {
        System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
        System.out.printf("Content: %s\n", mention.getText().getContent());
        System.out.printf("Type: %s\n\n", mention.getType());
      }
    }
  }
  // [END analyze_entities_gcs]
}
 

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
/**
 * Detects the entity sentiments in the string {@code text} using the Language Beta API.
 */
public static void entitySentimentText(String text) throws Exception {
  // [START entity_sentiment_text]
  // Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
  try (LanguageServiceClient language = LanguageServiceClient.create()) {
    Document doc = Document.newBuilder()
        .setContent(text).setType(Type.PLAIN_TEXT).build();
    AnalyzeEntitySentimentRequest request = AnalyzeEntitySentimentRequest.newBuilder()
        .setDocument(doc)
        .setEncodingType(EncodingType.UTF16).build();
    // detect entity sentiments in the given string
    AnalyzeEntitySentimentResponse response = language.analyzeEntitySentiment(request);
    // Print the response
    for (Entity entity : response.getEntitiesList()) {
      System.out.printf("Entity: %s\n", entity.getName());
      System.out.printf("Salience: %.3f\n", entity.getSalience());
      System.out.printf("Sentiment : %s\n", entity.getSentiment());
      for (EntityMention mention : entity.getMentionsList()) {
        System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
        System.out.printf("Content: %s\n", mention.getText().getContent());
        System.out.printf("Magnitude: %.3f\n", mention.getSentiment().getMagnitude());
        System.out.printf("Sentiment score : %.3f\n", mention.getSentiment().getScore());
        System.out.printf("Type: %s\n\n", mention.getType());
      }
    }
  }
  // [END entity_sentiment_text]
}
 

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
/**
 * Identifies the entity sentiments in the the GCS hosted file using the Language Beta API.
 */
public static void entitySentimentFile(String gcsUri) throws Exception {
  // [START entity_sentiment_file]
  // Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
  try (LanguageServiceClient language = LanguageServiceClient.create()) {
    Document doc = Document.newBuilder()
        .setGcsContentUri(gcsUri)
        .setType(Type.PLAIN_TEXT)
        .build();
    AnalyzeEntitySentimentRequest request = AnalyzeEntitySentimentRequest.newBuilder()
        .setDocument(doc)
        .setEncodingType(EncodingType.UTF16)
        .build();
    // Detect entity sentiments in the given file
    AnalyzeEntitySentimentResponse response = language.analyzeEntitySentiment(request);
    // Print the response
    for (Entity entity : response.getEntitiesList()) {
      System.out.printf("Entity: %s\n", entity.getName());
      System.out.printf("Salience: %.3f\n", entity.getSalience());
      System.out.printf("Sentiment : %s\n", entity.getSentiment());
      for (EntityMention mention : entity.getMentionsList()) {
        System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
        System.out.printf("Content: %s\n", mention.getText().getContent());
        System.out.printf("Magnitude: %.3f\n", mention.getSentiment().getMagnitude());
        System.out.printf("Sentiment score : %.3f\n", mention.getSentiment().getScore());
        System.out.printf("Type: %s\n\n", mention.getType());
      }
    }
  }
  // [END entity_sentiment_file]
}
 

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
@ProcessElement
public void processElement(ProcessContext c) {
	ContentIndexSummary is = c.element();

	try {

		if (this.languageClient == null)
			throw new Exception("CNLP client not initialized");
		
		com.google.cloud.language.v1.Document doc = com.google.cloud.language.v1.Document.newBuilder()
			.setContent(is.doc.text).setType(Type.PLAIN_TEXT).build();

		AnalyzeEntitiesRequest request = AnalyzeEntitiesRequest.newBuilder()
			.setDocument(doc).setEncodingType(EncodingType.UTF16).build();

		AnalyzeEntitiesResponse response = languageClient.analyzeEntities(request);
		
		// get at most as many entities as we have tags in the Sirocco-based output
		// int entitiesToGet = Math.min(is.doc.tags.length, response.getEntitiesList().size());
		int entitiesToGet = response.getEntitiesList().size();
		DocumentTag[] newTags = new DocumentTag[entitiesToGet];
		
		// Create additional Document Tags and add them to the output index summary
		for (int idx = 0; idx < entitiesToGet; idx++) {
			// Entities are sorted by salience in the response list, so pick the first ones
			Entity entity = response.getEntitiesList().get(idx);
			DocumentTag dt = new DocumentTag();
			String tag = IndexerPipelineUtils.CNLP_TAG_PREFIX + entity.getName();
			Float weight = entity.getSalience();
			Boolean goodAsTopic = null;
			dt.initialize(tag, weight, goodAsTopic);
			newTags[idx] = dt;
		}
		
		if (entitiesToGet>0)
		{
			ContentIndexSummary iscopy = is.copy();
			DocumentTag[] combinedTags = new DocumentTag[newTags.length + iscopy.doc.tags.length];
			System.arraycopy(iscopy.doc.tags, 0, combinedTags, 0, iscopy.doc.tags.length);
			System.arraycopy(newTags, 0, combinedTags, iscopy.doc.tags.length, newTags.length);
			iscopy.doc.tags = combinedTags;
			c.output(iscopy);
		}
		else
			c.output(is);
		
	} catch (Exception e) {
		LOG.warn(e.getMessage());
	}

}
 

import com.google.cloud.language.v1.Entity; //导入依赖的package包/类
@ProcessElement
public void processElement(ProcessContext c) {
	ContentIndexSummary is = c.element();

	try {

		if (this.languageClient == null)
			throw new Exception("CNLP client not initialized");
		
		com.google.cloud.language.v1.Document doc = com.google.cloud.language.v1.Document.newBuilder()
			.setContent(is.doc.text).setType(Type.PLAIN_TEXT).build();

		AnalyzeEntitiesRequest request = AnalyzeEntitiesRequest.newBuilder()
			.setDocument(doc).setEncodingType(EncodingType.UTF16).build();

		AnalyzeEntitiesResponse response = languageClient.analyzeEntities(request);
		
		// get at most as many entities as we have tags in the Sirocco-based output
		int entitiesToGet = Math.min(is.doc.tags.length, response.getEntitiesList().size());
		DocumentTag[] newTags = new DocumentTag[entitiesToGet];
		
		// Create additional Document Tags and add them to the output index summary
		for (int idx = 0; idx < entitiesToGet; idx++) {
			// Entities are sorted by salience in the response list, so pick the first ones
			Entity entity = response.getEntitiesList().get(idx);
			DocumentTag dt = new DocumentTag();
			String tag = IndexerPipelineUtils.CNLP_TAG_PREFIX + entity.getName();
			Float weight = entity.getSalience();
			Boolean goodAsTopic = null;
			dt.initialize(tag, weight, goodAsTopic);
			newTags[idx] = dt;
		}
		
		if (entitiesToGet>0)
		{
			ContentIndexSummary iscopy = is.copy();
			DocumentTag[] combinedTags = new DocumentTag[newTags.length + iscopy.doc.tags.length];
			System.arraycopy(iscopy.doc.tags, 0, combinedTags, 0, iscopy.doc.tags.length);
			System.arraycopy(newTags, 0, combinedTags, iscopy.doc.tags.length, newTags.length);
			iscopy.doc.tags = combinedTags;
			c.output(iscopy);
		}
		else
			c.output(is);
		
	} catch (Exception e) {
		LOG.warn(e.getMessage());
	}

}