此页面由 Cloud Translation API 翻译。

分析 Cloud Storage 文件中的实体

检查 Cloud Storage 存储的文件中的文本以找出已知实体（公众人物和地标等专有名词），并返回这些实体的相关信息。

深入探索

如需查看包含此代码示例的详细文档，请参阅以下内容：

分析实体

代码示例

Go

如需了解如何安装和使用 Natural Language 的客户端库，请参阅 Natural Language 客户端库。如需了解详情，请参阅 Natural Language Go API 参考文档。

如需向 Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。


func analyzeEntitiesFromGCS(ctx context.Context, gcsURI string) (*languagepb.AnalyzeEntitiesResponse, error) {
	return client.AnalyzeEntities(ctx, &languagepb.AnalyzeEntitiesRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_GcsContentUri{
				GcsContentUri: gcsURI,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
		EncodingType: languagepb.EncodingType_UTF8,
	})
}

Java

如需了解如何安装和使用 Natural Language 的客户端库，请参阅 Natural Language 客户端库。如需了解详情，请参阅 Natural Language Java API 参考文档。

如需向 Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

// Instantiate the Language client com.google.cloud.language.v2.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\n", entity.getName());
    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());
      System.out.printf("Probability: %s\n\n", mention.getProbability());
    }
  }
}

Node.js

如需了解如何安装和使用 Natural Language 的客户端库，请参阅 Natural Language 客户端库。如需了解详情，请参阅 Natural Language Node.js API 参考文档。

如需向 Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

// Imports the Google Cloud client library
const language = require('@google-cloud/language').v2;

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following lines to run this code
 */
// const bucketName = 'Your bucket name, e.g. my-bucket';
// const fileName = 'Your file name, e.g. my-file.txt';

// Prepares a document, representing a text file in Cloud Storage
const document = {
  gcsContentUri: `gs://${bucketName}/${fileName}`,
  type: 'PLAIN_TEXT',
};

// Detects entities in the document
const [result] = await client.analyzeEntities({document});
const entities = result.entities;

console.log('Entities:');
entities.forEach(entity => {
  console.log(entity.name);
  console.log(` - Type: ${entity.type}`);
  if (entity.metadata) {
    console.log(` - Metadata: ${entity.metadata}`);
  }
});

PHP

如需了解如何安装和使用 Natural Language 的客户端库，请参阅 Natural Language 客户端库。

如需向 Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

use Google\Cloud\Language\V1\AnalyzeEntitiesRequest;
use Google\Cloud\Language\V1\Client\LanguageServiceClient;
use Google\Cloud\Language\V1\Document;
use Google\Cloud\Language\V1\Document\Type;
use Google\Cloud\Language\V1\Entity\Type as EntityType;

/**
 * @param string $uri The cloud storage object to analyze (gs://your-bucket-name/your-object-name)
 */
function analyze_entities_from_file(string $uri): void
{
    // Create the Natural Language client
    $languageServiceClient = new LanguageServiceClient();

    // Create a new Document, pass GCS URI and set type to PLAIN_TEXT
    $document = (new Document())
        ->setGcsContentUri($uri)
        ->setType(Type::PLAIN_TEXT);

    // Call the analyzeEntities function
    $request = (new AnalyzeEntitiesRequest())
        ->setDocument($document);
    $response = $languageServiceClient->analyzeEntities($request);
    $entities = $response->getEntities();
    // Print out information about each entity
    foreach ($entities as $entity) {
        printf('Name: %s' . PHP_EOL, $entity->getName());
        printf('Type: %s' . PHP_EOL, EntityType::name($entity->getType()));
        printf('Salience: %s' . PHP_EOL, $entity->getSalience());
        if ($entity->getMetadata()->offsetExists('wikipedia_url')) {
            printf('Wikipedia URL: %s' . PHP_EOL, $entity->getMetadata()->offsetGet('wikipedia_url'));
        }
        if ($entity->getMetadata()->offsetExists('mid')) {
            printf('Knowledge Graph MID: %s' . PHP_EOL, $entity->getMetadata()->offsetGet('mid'));
        }
        printf(PHP_EOL);
    }
}

Python

如需了解如何安装和使用 Natural Language 的客户端库，请参阅 Natural Language 客户端库。如需了解详情，请参阅 Natural Language Python API 参考文档。

如需向 Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import language_v2


def sample_analyze_entities(
    gcs_content_uri: str = "gs://cloud-samples-data/language/entity.txt",
) -> None:
    """
    Analyzes Entities in text file stored in Cloud Storage.

    Args:
      gcs_content_uri: Google Cloud Storage URI where the file content is located.
        e.g. gs://[Your Bucket]/[Path to File]
    """

    client = language_v2.LanguageServiceClient()

    # Available types: PLAIN_TEXT, HTML
    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language_code = "en"
    document = {
        "gcs_content_uri": gcs_content_uri,
        "type_": document_type_in_plain_text,
        "language_code": language_code,
    }

    # Available values: NONE, UTF8, UTF16, UTF32.
    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
    encoding_type = language_v2.EncodingType.UTF8

    response = client.analyze_entities(
        request={"document": document, "encoding_type": encoding_type}
    )

    for entity in response.entities:
        print(f"Representative name for the entity: {entity.name}")

        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al.
        # See https://cloud.google.com/natural-language/docs/reference/rest/v2/Entity#type.
        print(f"Entity type: {language_v2.Entity.Type(entity.type_).name}")

        # Loop over the metadata associated with entity.
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        for metadata_name, metadata_value in entity.metadata.items():
            print(f"{metadata_name}: {metadata_value}")

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        for mention in entity.mentions:
            print(f"Mention text: {mention.text.content}")

            # Get the mention type, e.g. PROPER for proper noun
            print(
                "Mention type:" f" {language_v2.EntityMention.Type(mention.type_).name}"
            )

            # Get the probability score associated with the first mention of the entity in the (0, 1.0] range.
            print(f"Probability score: {mention.probability}")

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(f"Language of the text: {response.language_code}")

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅 Google Cloud 示例浏览器。