忽略包含子字符串“TEST”的扫描匹配项。
包含此代码示例的文档页面
如需查看上下文中使用的代码示例，请参阅以下文档：
代码示例
C#
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
using System;
using System.Collections.Generic;
using System.Linq;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
public class InspectStringWithExclusionDictSubstring
{
public static InspectContentResponse Inspect(string projectId, string textToInspect, List<String> excludedSubstringList)
{
var dlp = DlpServiceClient.Create();
var byteItem = new ByteContentItem
{
Type = ByteContentItem.Types.BytesType.TextUtf8,
Data = Google.Protobuf.ByteString.CopyFromUtf8(textToInspect)
};
var contentItem = new ContentItem { ByteItem = byteItem };
var infoTypes = new string[]
{
"EMAIL_ADDRESS",
"DOMAIN_NAME",
"PHONE_NUMBER",
"PERSON_NAME"
}.Select(it => new InfoType { Name = it });
var exclusionRule = new ExclusionRule
{
MatchingType = MatchingType.PartialMatch,
Dictionary = new CustomInfoType.Types.Dictionary
{
WordList = new CustomInfoType.Types.Dictionary.Types.WordList
{
Words = { excludedSubstringList }
}
}
};
var ruleSet = new InspectionRuleSet
{
InfoTypes = { infoTypes },
Rules = { new InspectionRule { ExclusionRule = exclusionRule } }
};
var config = new InspectConfig
{
InfoTypes = { infoTypes },
IncludeQuote = true,
RuleSet = { ruleSet }
};
var request = new InspectContentRequest
{
Parent = new LocationName(projectId, "global").ToString(),
Item = contentItem,
InspectConfig = config
};
var response = dlp.InspectContent(request);
Console.WriteLine($"Findings: {response.Result.Findings.Count}");
foreach (var f in response.Result.Findings)
{
Console.WriteLine("\tQuote: " + f.Quote);
Console.WriteLine("\tInfo type: " + f.InfoType.Name);
Console.WriteLine("\tLikelihood: " + f.Likelihood);
}
return response;
}
}
Java
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.ByteContentItem;
import com.google.privacy.dlp.v2.ByteContentItem.BytesType;
import com.google.privacy.dlp.v2.ContentItem;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary.WordList;
import com.google.privacy.dlp.v2.ExclusionRule;
import com.google.privacy.dlp.v2.Finding;
import com.google.privacy.dlp.v2.InfoType;
import com.google.privacy.dlp.v2.InspectConfig;
import com.google.privacy.dlp.v2.InspectContentRequest;
import com.google.privacy.dlp.v2.InspectContentResponse;
import com.google.privacy.dlp.v2.InspectionRule;
import com.google.privacy.dlp.v2.InspectionRuleSet;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.MatchingType;
import com.google.protobuf.ByteString;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public class InspectStringWithExclusionDictSubstring {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String textToInspect = "Some email addresses: gary@example.com, TEST@example.com";
List<String> excludedSubstringList = Arrays.asList("TEST");
inspectStringWithExclusionDictSubstring(projectId, textToInspect, excludedSubstringList);
}
// Inspects the provided text, avoiding matches specified in the exclusion list.
public static void inspectStringWithExclusionDictSubstring(
String projectId, String textToInspect, List<String> excludedSubstringList)
throws IOException {
// Initialize client that will be used to send requests. This client only needs to be created
// once, and can be reused for multiple requests. After completing all of your requests, call
// the "close" method on the client to safely clean up any remaining background resources.
try (DlpServiceClient dlp = DlpServiceClient.create()) {
// Specify the type and content to be inspected.
ByteContentItem byteItem =
ByteContentItem.newBuilder()
.setType(BytesType.TEXT_UTF8)
.setData(ByteString.copyFromUtf8(textToInspect))
.build();
ContentItem item = ContentItem.newBuilder().setByteItem(byteItem).build();
// Specify the type of info the inspection will look for.
// See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types.
List<InfoType> infoTypes = new ArrayList<>();
for (String typeName :
new String[] {"EMAIL_ADDRESS", "DOMAIN_NAME", "PHONE_NUMBER", "PERSON_NAME"}) {
infoTypes.add(InfoType.newBuilder().setName(typeName).build());
}
// Exclude partial matches from the specified excludedSubstringList.
ExclusionRule exclusionRule =
ExclusionRule.newBuilder()
.setMatchingType(MatchingType.MATCHING_TYPE_PARTIAL_MATCH)
.setDictionary(
Dictionary.newBuilder()
.setWordList(WordList.newBuilder().addAllWords(excludedSubstringList)))
.build();
// Construct a ruleset that applies the exclusion rule to the EMAIL_ADDRESSES infotype.
InspectionRuleSet ruleSet =
InspectionRuleSet.newBuilder()
.addAllInfoTypes(infoTypes)
.addRules(InspectionRule.newBuilder().setExclusionRule(exclusionRule))
.build();
// Construct the configuration for the Inspect request, including the ruleset.
InspectConfig config =
InspectConfig.newBuilder()
.addAllInfoTypes(infoTypes)
.setIncludeQuote(true)
.addRuleSet(ruleSet)
.build();
// Construct the Inspect request to be sent by the client.
InspectContentRequest request =
InspectContentRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setItem(item)
.setInspectConfig(config)
.build();
// Use the client to send the API request.
InspectContentResponse response = dlp.inspectContent(request);
// Parse the response and process results
System.out.println("Findings: " + response.getResult().getFindingsCount());
for (Finding f : response.getResult().getFindingsList()) {
System.out.println("\tQuote: " + f.getQuote());
System.out.println("\tInfo type: " + f.getInfoType().getName());
System.out.println("\tLikelihood: " + f.getLikelihood());
}
}
}
}Python
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
def inspect_string_with_exclusion_dict_substring(
project, content_string, exclusion_list=["TEST"]
):
"""Inspects the provided text, avoiding matches that contain excluded tokens
Uses the Data Loss Prevention API to omit matches if they include tokens
in the specified exclusion list.
Args:
project: The Google Cloud project id to use as a parent resource.
content_string: The string to inspect.
exclusion_list: The list of strings to ignore partial matches on
Returns:
None; the response from the API is printed to the terminal.
"""
# Import the client library.
import google.cloud.dlp
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Construct a list of infoTypes for DLP to locate in `content_string`. See
# https://cloud.google.com/dlp/docs/concepts-infotypes for more information
# about supported infoTypes.
info_types_to_locate = [{"name": "EMAIL_ADDRESS"}, {"name": "DOMAIN_NAME"}]
# Construct a rule set that will only match if the match text does not
# contains tokens from the exclusion list.
rule_set = [
{
"info_types": info_types_to_locate,
"rules": [
{
"exclusion_rule": {
"dictionary": {"word_list": {"words": exclusion_list}},
"matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_PARTIAL_MATCH,
}
}
],
}
]
# Construct the configuration dictionary
inspect_config = {
"info_types": info_types_to_locate,
"rule_set": rule_set,
"include_quote": True,
}
# Construct the `item`.
item = {"value": content_string}
# Convert the project id into a full resource id.
parent = f"projects/{project}"
# Call the API.
response = dlp.inspect_content(
request={"parent": parent, "inspect_config": inspect_config, "item": item}
)
# Print out the results.
if response.result.findings:
for finding in response.result.findings:
print(f"Quote: {finding.quote}")
print(f"Info type: {finding.info_type.name}")
print(f"Likelihood: {finding.likelihood}")
else:
print("No findings.")
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。