说明如何应用排除规则和热词规则。此代码段的规则集同时包含热词规则以及字典和正则表达式排除规则。请注意,rules 元素内的数组中指定了这四个规则。
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:
代码示例
C#
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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。
using System;
using System.Text.RegularExpressions;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using static Google.Cloud.Dlp.V2.CustomInfoType.Types;
public class InspectStringMultipleRules
{
public static InspectContentResponse Inspect(string projectId, string textToInspect)
{
var dlp = DlpServiceClient.Create();
var byteContentItem = new ByteContentItem
{
Type = ByteContentItem.Types.BytesType.TextUtf8,
Data = Google.Protobuf.ByteString.CopyFromUtf8(textToInspect)
};
var contentItem = new ContentItem
{
ByteItem = byteContentItem
};
var patientRule = new DetectionRule.Types.HotwordRule
{
HotwordRegex = new CustomInfoType.Types.Regex { Pattern = "patient" },
Proximity = new DetectionRule.Types.Proximity { WindowBefore = 10 },
LikelihoodAdjustment = new DetectionRule.Types.LikelihoodAdjustment { FixedLikelihood = Likelihood.VeryLikely }
};
var doctorRule = new DetectionRule.Types.HotwordRule
{
HotwordRegex = new CustomInfoType.Types.Regex { Pattern = "doctor" },
Proximity = new DetectionRule.Types.Proximity { WindowBefore = 10 },
LikelihoodAdjustment = new DetectionRule.Types.LikelihoodAdjustment { FixedLikelihood = Likelihood.Unlikely }
};
// Construct exclusion rules
var quasimodoRule = new ExclusionRule
{
Dictionary = new Dictionary { WordList = new Dictionary.Types.WordList { Words = { "Quasimodo" } } },
MatchingType = MatchingType.PartialMatch
};
var redactedRule = new ExclusionRule
{
Regex = new CustomInfoType.Types.Regex { Pattern = "REDACTED" },
MatchingType = MatchingType.PartialMatch
};
var infoType = new InfoType { Name = "PERSON_NAME" };
var inspectionRuleSet = new InspectionRuleSet
{
InfoTypes = { infoType },
Rules =
{
new InspectionRule { HotwordRule = patientRule },
new InspectionRule { HotwordRule = doctorRule},
new InspectionRule { ExclusionRule = quasimodoRule },
new InspectionRule { ExclusionRule = redactedRule }
}
};
var inspectConfig = new InspectConfig
{
InfoTypes = { infoType },
IncludeQuote = true,
RuleSet = { inspectionRuleSet }
};
var request = new InspectContentRequest
{
Parent = new LocationName(projectId, "global").ToString(),
Item = contentItem,
InspectConfig = inspectConfig
};
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;
}
}
Go
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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。
import (
"context"
"fmt"
"io"
dlp "cloud.google.com/go/dlp/apiv2"
"cloud.google.com/go/dlp/apiv2/dlppb"
)
// inspectStringMultipleRules inspects the provided text,
// avoiding matches specified in the exclusion list.
// this function implements the both exclusion and hot word rules.
func inspectStringMultipleRules(w io.Writer, projectID, textToInspect string) error {
// projectID := "my-project-id"
// textToInspect := "patient: Jane Doe"
ctx := context.Background()
// Initialize a client once and reuse it to send multiple requests. Clients
// are safe to use across goroutines. When the client is no longer needed,
// call the Close method to cleanup its resources.
client, err := dlp.NewClient(ctx)
if err != nil {
return err
}
// Closing the client safely cleans up background resources.
defer client.Close()
// Specify the type and content to be inspected.
ContentItem := &dlppb.ContentItem{
DataItem: &dlppb.ContentItem_ByteItem{
ByteItem: &dlppb.ByteContentItem{
Type: dlppb.ByteContentItem_TEXT_UTF8,
Data: []byte(textToInspect),
},
},
}
// Construct the rule that adjust the likelihood of findings
// within a certain proximity of hot-word("patient").
patientRule := &dlppb.InspectionRule_HotwordRule{
HotwordRule: &dlppb.CustomInfoType_DetectionRule_HotwordRule{
HotwordRegex: &dlppb.CustomInfoType_Regex{
Pattern: "patient",
},
Proximity: &dlppb.CustomInfoType_DetectionRule_Proximity{
WindowBefore: 10,
},
LikelihoodAdjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment{
Adjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment_FixedLikelihood{
FixedLikelihood: dlppb.Likelihood_VERY_LIKELY,
},
},
},
}
// Construct the rule that adjust the likelihood of findings
// within a certain proximity of hot-word("doctor").
doctorRule := &dlppb.InspectionRule_HotwordRule{
HotwordRule: &dlppb.CustomInfoType_DetectionRule_HotwordRule{
HotwordRegex: &dlppb.CustomInfoType_Regex{
Pattern: "doctor",
},
Proximity: &dlppb.CustomInfoType_DetectionRule_Proximity{
WindowBefore: 10,
},
LikelihoodAdjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment{
Adjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment_FixedLikelihood{
FixedLikelihood: dlppb.Likelihood_UNLIKELY,
},
},
},
}
// Construct the exclusion rule that avoids the matches for the specified word list.
quasimodoRule := &dlppb.ExclusionRule{
Type: &dlppb.ExclusionRule_Dictionary{
Dictionary: &dlppb.CustomInfoType_Dictionary{
Source: &dlppb.CustomInfoType_Dictionary_WordList_{
WordList: &dlppb.CustomInfoType_Dictionary_WordList{
Words: []string{"Quasimodo"},
},
},
},
},
MatchingType: dlppb.MatchingType_MATCHING_TYPE_PARTIAL_MATCH,
}
// Construct the exclusion rule that avoids the matches for the specified regex pattern.
redactedRule := &dlppb.ExclusionRule{
Type: &dlppb.ExclusionRule_Regex{
Regex: &dlppb.CustomInfoType_Regex{
Pattern: "REDACTED",
},
},
MatchingType: dlppb.MatchingType_MATCHING_TYPE_PARTIAL_MATCH,
}
// Construct a ruleSet that applies the rules to the PERSON_NAME infoType.
ruleSet := &dlppb.InspectionRuleSet{
InfoTypes: []*dlppb.InfoType{
{Name: "PERSON_NAME"},
},
Rules: []*dlppb.InspectionRule{
{Type: &dlppb.InspectionRule_HotwordRule{HotwordRule: doctorRule.HotwordRule}},
{Type: &dlppb.InspectionRule_HotwordRule{HotwordRule: patientRule.HotwordRule}},
{Type: &dlppb.InspectionRule_ExclusionRule{ExclusionRule: quasimodoRule}},
{Type: &dlppb.InspectionRule_ExclusionRule{ExclusionRule: redactedRule}},
},
}
// Construct the configuration for the Inspect request, including the ruleSet.
inspectConfig := &dlppb.InspectConfig{
InfoTypes: []*dlppb.InfoType{
{Name: "PERSON_NAME"},
},
IncludeQuote: true,
RuleSet: []*dlppb.InspectionRuleSet{
ruleSet,
},
}
// Create and send the request.
req := &dlppb.InspectContentRequest{
Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
Item: ContentItem,
InspectConfig: inspectConfig,
}
// Send the request.
resp, err := client.InspectContent(ctx, req)
if err != nil {
return err
}
// Process the results.
fmt.Fprintf(w, "Findings: %v\n", len(resp.Result.Findings))
for _, v := range resp.GetResult().Findings {
fmt.Fprintf(w, "Quote: %v\n", v.GetQuote())
fmt.Fprintf(w, "Infotype Name: %v\n", v.GetInfoType().GetName())
fmt.Fprintf(w, "Likelihood: %v\n", v.GetLikelihood())
}
return nil
}
Java
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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。
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.DetectionRule.HotwordRule;
import com.google.privacy.dlp.v2.CustomInfoType.DetectionRule.LikelihoodAdjustment;
import com.google.privacy.dlp.v2.CustomInfoType.DetectionRule.Proximity;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary.WordList;
import com.google.privacy.dlp.v2.CustomInfoType.Regex;
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.Likelihood;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.MatchingType;
import com.google.protobuf.ByteString;
import java.io.IOException;
public class InspectStringMultipleRules {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String textToInspect = "patient: Jane Doe";
inspectStringMultipleRules(projectId, textToInspect);
}
// Inspects the provided text, avoiding matches specified in the exclusion list.
public static void inspectStringMultipleRules(String projectId, String textToInspect)
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();
// Construct hotword rules
HotwordRule patientRule =
HotwordRule.newBuilder()
.setHotwordRegex(Regex.newBuilder().setPattern("patient"))
.setProximity(Proximity.newBuilder().setWindowBefore(10))
.setLikelihoodAdjustment(
LikelihoodAdjustment.newBuilder().setFixedLikelihood(Likelihood.VERY_LIKELY))
.build();
HotwordRule doctorRule =
HotwordRule.newBuilder()
.setHotwordRegex(Regex.newBuilder().setPattern("doctor"))
.setProximity(Proximity.newBuilder().setWindowBefore(10))
.setLikelihoodAdjustment(
LikelihoodAdjustment.newBuilder().setFixedLikelihood(Likelihood.UNLIKELY))
.build();
// Construct exclusion rules
ExclusionRule quasimodoRule =
ExclusionRule.newBuilder()
.setDictionary(
Dictionary.newBuilder().setWordList(WordList.newBuilder().addWords("Quasimodo")))
.setMatchingType(MatchingType.MATCHING_TYPE_PARTIAL_MATCH)
.build();
ExclusionRule redactedRule =
ExclusionRule.newBuilder()
.setRegex(Regex.newBuilder().setPattern("REDACTED"))
.setMatchingType(MatchingType.MATCHING_TYPE_PARTIAL_MATCH)
.build();
// Construct a ruleset that applies the rules to the PERSON_NAME infotype.
InspectionRuleSet ruleSet =
InspectionRuleSet.newBuilder()
.addInfoTypes(InfoType.newBuilder().setName("PERSON_NAME"))
.addRules(InspectionRule.newBuilder().setHotwordRule(patientRule))
.addRules(InspectionRule.newBuilder().setHotwordRule(doctorRule))
.addRules(InspectionRule.newBuilder().setExclusionRule(quasimodoRule))
.addRules(InspectionRule.newBuilder().setExclusionRule(redactedRule))
.build();
// Construct the configuration for the Inspect request, including the ruleset.
InspectConfig config =
InspectConfig.newBuilder()
.addInfoTypes(InfoType.newBuilder().setName("PERSON_NAME"))
.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());
}
}
}
}
Node.js
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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 Data Loss Prevention library
const DLP = require('@google-cloud/dlp');
// Instantiates a client
const dlp = new DLP.DlpServiceClient();
// The project ID to run the API call under
// const projectId = 'my-project';
// The string to inspect
// const string = 'patient: Jane Doe';
async function inspectStringMultipleRules() {
// Construct item to inspect
const item = {value: string};
// Construct hotword rules
const patientRule = {
hotwordRegex: {pattern: 'patient'},
proximity: {windowBefore: 10},
likelihoodAdjustment: {
fixedLikelihood:
DLP.protos.google.privacy.dlp.v2.Likelihood.VERY_LIKELY,
},
};
const doctorRule = {
hotwordRegex: {pattern: 'doctor'},
proximity: {windowBefore: 10},
likelihoodAdjustment: {
fixedLikelihood: DLP.protos.google.privacy.dlp.v2.Likelihood.UNLIKELY,
},
};
// Construct exclusion rules
const quasimodoRule = {
dictionary: {wordList: {words: ['quasimodo']}},
matchingType:
DLP.protos.google.privacy.dlp.v2.MatchingType
.MATCHING_TYPE_PARTIAL_MATCH,
};
const redactedRule = {
regex: {pattern: 'REDACTED'},
matchingType:
DLP.protos.google.privacy.dlp.v2.MatchingType
.MATCHING_TYPE_PARTIAL_MATCH,
};
// The infoTypes of information to match
const infoTypes = [{name: 'PERSON_NAME'}];
// Construct a ruleset that applies the rules to the PERSON_NAME infotype.
const ruleSet = [
{
infoTypes: infoTypes,
rules: [
{hotwordRule: patientRule},
{hotwordRule: doctorRule},
{exclusionRule: quasimodoRule},
{exclusionRule: redactedRule},
],
},
];
// Construct the configuration for the Inspect request, including the ruleset.
const inspectConfig = {
infoTypes: infoTypes,
ruleSet: ruleSet,
includeQuote: true,
};
// Construct the Inspect request to be sent by the client.
const request = {
parent: `projects/${projectId}/locations/global`,
inspectConfig: inspectConfig,
item: item,
};
// Use the client to send the API request.
const [response] = await dlp.inspectContent(request);
// Print findings.
const findings = response.result.findings;
if (findings.length > 0) {
console.log(`Findings: ${findings.length}\n`);
findings.forEach(finding => {
console.log(`InfoType: ${finding.infoType.name}`);
console.log(`\tQuote: ${finding.quote}`);
console.log(`\tLikelihood: ${finding.likelihood} \n`);
});
} else {
console.log('No findings.');
}
}
inspectStringMultipleRules();
PHP
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\HotwordRule;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\LikelihoodAdjustment;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\Proximity;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary\WordList;
use Google\Cloud\Dlp\V2\CustomInfoType\Regex;
use Google\Cloud\Dlp\V2\ExclusionRule;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectContentRequest;
use Google\Cloud\Dlp\V2\InspectionRule;
use Google\Cloud\Dlp\V2\InspectionRuleSet;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\MatchingType;
/**
* Inspect a string for sensitive data by using multiple rules
* Illustrates applying both exclusion and hotword rules. This snippet's rule set includes both hotword rules and dictionary and regex exclusion rules. Notice that the four rules are specified in an array within the rules element.
*
* @param string $projectId The Google Cloud project id to use as a parent resource.
* @param string $textToInspect The string to inspect.
*/
function inspect_string_multiple_rules(
// TODO(developer): Replace sample parameters before running the code.
string $projectId,
string $textToInspect = 'patient: Jane Doe'
): void {
// Instantiate a client.
$dlp = new DlpServiceClient();
$parent = "projects/$projectId/locations/global";
// Specify what content you want the service to Inspect.
$item = (new ContentItem())
->setValue($textToInspect);
// Construct hotword rules
$patientRule = (new HotwordRule())
->setHotwordRegex((new Regex())
->setPattern('patient'))
->setProximity((new Proximity())
->setWindowBefore(10))
->setLikelihoodAdjustment((new LikelihoodAdjustment())
->setFixedLikelihood(Likelihood::VERY_LIKELY));
$doctorRule = (new HotwordRule())
->setHotwordRegex((new Regex())
->setPattern('doctor'))
->setProximity((new Proximity())
->setWindowBefore(10))
->setLikelihoodAdjustment((new LikelihoodAdjustment())
->setFixedLikelihood(Likelihood::VERY_UNLIKELY));
// Construct exclusion rules
$wordList = (new Dictionary())
->setWordList((new WordList())
->setWords(['Quasimodo']));
$quasimodoRule = (new ExclusionRule())
->setMatchingType(MatchingType::MATCHING_TYPE_PARTIAL_MATCH)
->setDictionary($wordList);
$redactedRule = (new ExclusionRule())
->setMatchingType(MatchingType::MATCHING_TYPE_PARTIAL_MATCH)
->setRegex((new Regex())
->setPattern('REDACTED'));
// Specify the exclusion rule and build-in info type the inspection will look for.
$personName = (new InfoType())
->setName('PERSON_NAME');
$inspectionRuleSet = (new InspectionRuleSet())
->setInfoTypes([$personName])
->setRules([
(new InspectionRule())
->setHotwordRule($patientRule),
(new InspectionRule())
->setHotwordRule($doctorRule),
(new InspectionRule())
->setExclusionRule($quasimodoRule),
(new InspectionRule())
->setExclusionRule($redactedRule),
]);
// Construct the configuration for the Inspect request, including the ruleset.
$inspectConfig = (new InspectConfig())
->setInfoTypes([$personName])
->setIncludeQuote(true)
->setRuleSet([$inspectionRuleSet]);
// Run request
$inspectContentRequest = (new InspectContentRequest())
->setParent($parent)
->setInspectConfig($inspectConfig)
->setItem($item);
$response = $dlp->inspectContent($inspectContentRequest);
// Print the results
$findings = $response->getResult()->getFindings();
if (count($findings) == 0) {
printf('No findings.' . PHP_EOL);
} else {
printf('Findings:' . PHP_EOL);
foreach ($findings as $finding) {
printf(' Quote: %s' . PHP_EOL, $finding->getQuote());
printf(' Info type: %s' . PHP_EOL, $finding->getInfoType()->getName());
printf(' Likelihood: %s' . PHP_EOL, Likelihood::name($finding->getLikelihood()));
}
}
}
Python
如需了解如何安装和使用敏感数据保护客户端库,请参阅 敏感数据保护客户端库。
如需向 Sensitive Data Protection 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。
import google.cloud.dlp
def inspect_string_multiple_rules(project: str, content_string: str) -> None:
"""Uses the Data Loss Prevention API to modify likelihood for matches on
PERSON_NAME combining multiple hotword and exclusion rules.
Args:
project: The Google Cloud project id to use as a parent resource.
content_string: The string to inspect.
Returns:
None; the response from the API is printed to the terminal.
"""
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Construct hotword rules
patient_rule = {
"hotword_regex": {"pattern": "patient"},
"proximity": {"window_before": 10},
"likelihood_adjustment": {
"fixed_likelihood": google.cloud.dlp_v2.Likelihood.VERY_LIKELY
},
}
doctor_rule = {
"hotword_regex": {"pattern": "doctor"},
"proximity": {"window_before": 10},
"likelihood_adjustment": {
"fixed_likelihood": google.cloud.dlp_v2.Likelihood.UNLIKELY
},
}
# Construct exclusion rules
quasimodo_rule = {
"dictionary": {"word_list": {"words": ["quasimodo"]}},
"matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_PARTIAL_MATCH,
}
redacted_rule = {
"regex": {"pattern": "REDACTED"},
"matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_PARTIAL_MATCH,
}
# Construct the rule set, combining the above rules
rule_set = [
{
"info_types": [{"name": "PERSON_NAME"}],
"rules": [
{"hotword_rule": patient_rule},
{"hotword_rule": doctor_rule},
{"exclusion_rule": quasimodo_rule},
{"exclusion_rule": redacted_rule},
],
}
]
# Construct the configuration dictionary
inspect_config = {
"info_types": [{"name": "PERSON_NAME"}],
"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。