Como inspecionar texto estruturado de dados confidenciais
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
O Cloud Data Loss Prevention pode detectar e classificar dados confidenciais em conteúdo estruturado, como CSV. Ao inspecionar ou desidentificar como uma tabela, a
estrutura e as colunas fornecem outras pistas ao Cloud DLP que
poderão permitir resultados melhores para alguns casos de uso.
Como inspecionar uma tabela
Veja os exemplos de código abaixo para saber como verificar conteúdo confidencial em uma tabela de dados.
As tabelas são compatíveis com vários tipos.
Protocolo
Consulte o Início rápido do JSON para ver mais informações sobre o uso da API DLP com o JSON.
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.ContentItem;
import com.google.privacy.dlp.v2.FieldId;
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.LocationName;
import com.google.privacy.dlp.v2.Table;
import com.google.privacy.dlp.v2.Table.Row;
import com.google.privacy.dlp.v2.Value;
public class InspectTable {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
Table tableToInspect =
Table.newBuilder()
.addHeaders(FieldId.newBuilder().setName("name").build())
.addHeaders(FieldId.newBuilder().setName("phone").build())
.addRows(
Row.newBuilder()
.addValues(Value.newBuilder().setStringValue("John Doe").build())
.addValues(Value.newBuilder().setStringValue("(206) 555-0123").build()))
.build();
inspectTable(projectId, tableToInspect);
}
// Inspects the provided text.
public static void inspectTable(String projectId, Table tableToInspect) {
// 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 table to be inspected.
ContentItem item = ContentItem.newBuilder().setTable(tableToInspect).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
InfoType infoType = InfoType.newBuilder().setName("PHONE_NUMBER").build();
// Construct the configuration for the Inspect request.
InspectConfig config =
InspectConfig.newBuilder().addInfoTypes(infoType).setIncludeQuote(true).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());
}
} catch (Exception e) {
System.out.println("Error during inspectString: \n" + e.toString());
}
}
}
from typing import List, Optional # noqa: E402, I100
import google.cloud.dlp # noqa: F811, E402
def inspect_table(
project: str,
data: str,
info_types: List[str],
custom_dictionaries: List[str] = None,
custom_regexes: List[str] = None,
min_likelihood: Optional[str] = None,
max_findings: Optional[int] = None,
include_quote: bool = True,
) -> None:
"""Uses the Data Loss Prevention API to analyze strings for protected data.
Args:
project: The Google Cloud project id to use as a parent resource.
data: Json string representing table data.
info_types: A list of strings representing info types to look for.
A full list of info type categories can be fetched from the API.
min_likelihood: A string representing the minimum likelihood threshold
that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
max_findings: The maximum number of findings to report; 0 = no maximum.
include_quote: Boolean for whether to display a quote of the detected
information in the results.
Returns:
None; the response from the API is printed to the terminal.
Example:
data = {
"header":[
"email",
"phone number"
],
"rows":[
[
"robertfrost@xyz.com",
"4232342345"
],
[
"johndoe@pqr.com",
"4253458383"
]
]
}
>> $ python inspect_content.py table \
'{"header": ["email", "phone number"],
"rows": [["robertfrost@xyz.com", "4232342345"],
["johndoe@pqr.com", "4253458383"]]}'
>> Quote: robertfrost@xyz.com
Info type: EMAIL_ADDRESS
Likelihood: 4
Quote: johndoe@pqr.com
Info type: EMAIL_ADDRESS
Likelihood: 4
"""
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Prepare info_types by converting the list of strings into a list of
# dictionaries (protos are also accepted).
info_types = [{"name": info_type} for info_type in info_types]
# Prepare custom_info_types by parsing the dictionary word lists and
# regex patterns.
if custom_dictionaries is None:
custom_dictionaries = []
dictionaries = [
{
"info_type": {"name": f"CUSTOM_DICTIONARY_{i}"},
"dictionary": {"word_list": {"words": custom_dict.split(",")}},
}
for i, custom_dict in enumerate(custom_dictionaries)
]
if custom_regexes is None:
custom_regexes = []
regexes = [
{
"info_type": {"name": f"CUSTOM_REGEX_{i}"},
"regex": {"pattern": custom_regex},
}
for i, custom_regex in enumerate(custom_regexes)
]
custom_info_types = dictionaries + regexes
# Construct the configuration dictionary. Keys which are None may
# optionally be omitted entirely.
inspect_config = {
"info_types": info_types,
"custom_info_types": custom_info_types,
"min_likelihood": min_likelihood,
"include_quote": include_quote,
"limits": {"max_findings_per_request": max_findings},
}
# Construct the `table`. For more details on the table schema, please see
# https://cloud.google.com/dlp/docs/reference/rest/v2/ContentItem#Table
headers = [{"name": val} for val in data["header"]]
rows = []
for row in data["rows"]:
rows.append({"values": [{"string_value": cell_val} for cell_val in row]})
table = {}
table["headers"] = headers
table["rows"] = rows
item = {"table": table}
# 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:
try:
if finding.quote:
print(f"Quote: {finding.quote}")
except AttributeError:
pass
print(f"Info type: {finding.info_type.name}")
print(f"Likelihood: {finding.likelihood}")
else:
print("No findings.")
Texto estruturado
A estruturação de texto pode ajudar a contextualizar. A mesma solicitação do exemplo anterior, se inspecionada como uma string, ou seja, apenas "John Doe, (206) 555-0123", traria resultados menos precisos. Isso porque o Cloud DLP tem menos pistas contextuais sobre qual poderia ser a finalidade do número. Quando possível, considere analisar as strings em um objeto de tabela para conseguir os resultados de verificação mais precisos.