com.google.privacy.dlp.v2.Value Java Examples

@Test
public void testConvertTableRowToRow() {
  DLPTokenizationDoFn dlp =
      new DLPTokenizationDoFn(
          "Project Name",
          ValueProvider.StaticValueProvider.of("DeidentifyTemplateName"),
          ValueProvider.StaticValueProvider.of("IdentifyTemplateName"));

  String[] header = {"header0", "header1"};
  String key = "Key name";
  Table.Row.Builder tableRowBuilder = Table.Row.newBuilder();
  tableRowBuilder.addValues(0, Value.newBuilder().setStringValue("value0"));
  tableRowBuilder.addValues(1, Value.newBuilder().setStringValue("value1"));
  Table.Row row = tableRowBuilder.build();

  Row result = dlp.convertTableRowToRow(header, key, row);
  assertEquals(result.getTableId(), key);
  assertEquals(result.getHeader()[0], "header0");
  assertEquals(result.getValue()[1], "value1");
}
 

public static void deIdentifyTableRowSuppress() throws IOException {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();

  deIdentifyTableRowSuppress(projectId, tableToDeIdentify);
}
 

@Test
public void mapsDelimitedStringToRow() {
  PCollection<KV<String, Table.Row>> rowCollection =
      testPipeline
          .apply(Create.of(KV.of("key", "value,secondValue")))
          .apply(ParDo.of(new MapStringToDlpRow(",")));
  PAssert.that(rowCollection)
      .containsInAnyOrder(
          KV.of(
              "key",
              Table.Row.newBuilder()
                  .addValues(Value.newBuilder().setStringValue("value").build())
                  .addValues(Value.newBuilder().setStringValue("secondValue").build())
                  .build()));
  testPipeline.run().waitUntilFinish();
}
 

public static void deIdentifyTableConditionMasking() throws IOException {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();

  deIdentifyTableConditionMasking(projectId, tableToDeIdentify);
}
 

public static void main(String[] args) throws Exception {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  String kmsKeyName =
      "projects/YOUR_PROJECT/"
          + "locations/YOUR_KEYRING_REGION/"
          + "keyRings/YOUR_KEYRING_NAME/"
          + "cryptoKeys/YOUR_KEY_NAME";
  String wrappedAesKey = "YOUR_ENCRYPTED_AES_256_KEY";
  Table tableToReIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("Employee ID").build())
      .addRows(
          Row.newBuilder().addValues(
              Value.newBuilder().setStringValue("28777").build())
              .build())
      .build();
  reIdentifyTableWithFpe(projectId, tableToReIdentify, kmsKeyName, wrappedAesKey);
}
 

public static void deIdentifyTableBucketing() throws IOException {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();

  deIdentifyTableBucketing(projectId, tableToDeIdentify);
}
 

public static void deIdentifyTableConditionInfoTypes() throws IOException {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "Charles Dickens name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in Jane Austen's novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
          .build())
      .build();

  deIdentifyTableConditionInfoTypes(projectId, tableToDeIdentify);
}
 

@Test
public void testInspectTable() {
  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.inspectTable(PROJECT_ID, tableToInspect);

  String output = bout.toString();
  assertThat(output).contains("Info type: PHONE_NUMBER");
}
 

@Test
public void testReIdentifyTableWithFpe() throws IOException {
  Table tableToReIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("Employee ID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("28777").build()).build())
      .build();

  ReIdentifyTableWithFpe.reIdentifyTableWithFpe(
      PROJECT_ID, tableToReIdentify, kmsKeyName, wrappedKey);

  String output = bout.toString();
  assertThat(output).contains("Table after re-identification:");
}
 

@Test
public void testDeIdentifyTableWithFpe() throws IOException {
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("Employee ID").build())
      .addHeaders(FieldId.newBuilder().setName("Date").build())
      .addHeaders(FieldId.newBuilder().setName("Compensation").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("11111").build())
          .addValues(Value.newBuilder().setStringValue("2015").build())
          .addValues(Value.newBuilder().setStringValue("$10").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("11111").build())
          .addValues(Value.newBuilder().setStringValue("2016").build())
          .addValues(Value.newBuilder().setStringValue("$20").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22222").build())
          .addValues(Value.newBuilder().setStringValue("2016").build())
          .addValues(Value.newBuilder().setStringValue("$15").build())
          .build())
      .build();

  DeIdentifyTableWithFpe.deIdentifyTableWithFpe(
      PROJECT_ID, tableToDeIdentify, kmsKeyName, wrappedKey);

  String output = bout.toString();
  assertThat(output).contains("Table after format-preserving encryption:");
}
 

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);
}
 

private Table.Row convertCsvRowToTableRow(CSVRecord csvRow) {
  /** convert from CSV row to DLP Table Row */
  Iterator<String> valueIterator = csvRow.iterator();
  Table.Row.Builder tableRowBuilder = Table.Row.newBuilder();
  while (valueIterator.hasNext()) {
    String value = valueIterator.next();
    if (value != null) {
      tableRowBuilder.addValues(Value.newBuilder().setStringValue(value.toString()).build());
    } else {
      tableRowBuilder.addValues(Value.newBuilder().setStringValue("").build());
    }
  }

  return tableRowBuilder.build();
}
 

public static void deIdentifyTableInfoTypes() throws IOException {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "Charles Dickens name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in Jane Austen's novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
          .build())
      .build();

  deIdentifyTableInfoTypes(projectId, tableToDeIdentify);
}
 

public static Table.Row convertCsvRowToTableRow(String row) {
  String[] values = row.split(",");
  Table.Row.Builder tableRowBuilder = Table.Row.newBuilder();
  for (String value : values) {
    tableRowBuilder.addValues(Value.newBuilder().setStringValue(value).build());
  }

  return tableRowBuilder.build();
}
 

public static String joinRow(List<Value> values) {
  String name = values.get(0).getStringValue();
  String birthDate = formatDate(values.get(1).getDateValue());
  String creditCardNumber = values.get(2).getStringValue();
  String registerDate = formatDate(values.get(3).getDateValue());
  return String.join(",", name, birthDate, creditCardNumber, registerDate);
}
 

public static Table.Row parseLineAsRow(String line) {
  List<String> values = Splitter.on(",").splitToList(line);
  Value name = Value.newBuilder().setStringValue(values.get(0)).build();
  Value birthDate = Value.newBuilder().setDateValue(parseAsDate(values.get(1))).build();
  Value creditCardNumber = Value.newBuilder().setStringValue(values.get(2)).build();
  Value registerDate = Value.newBuilder().setDateValue(parseAsDate(values.get(3))).build();
  return Table.Row.newBuilder()
      .addValues(name)
      .addValues(birthDate)
      .addValues(creditCardNumber)
      .addValues(registerDate)
      .build();
}
 

public static void main(String[] args) throws Exception {
  // TODO(developer): Replace these variables before running the sample.
  String projectId = "your-project-id";
  String kmsKeyName =
      "projects/YOUR_PROJECT/"
          + "locations/YOUR_KEYRING_REGION/"
          + "keyRings/YOUR_KEYRING_NAME/"
          + "cryptoKeys/YOUR_KEY_NAME";
  String wrappedAesKey = "YOUR_ENCRYPTED_AES_256_KEY";
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("Employee ID").build())
      .addHeaders(FieldId.newBuilder().setName("Date").build())
      .addHeaders(FieldId.newBuilder().setName("Compensation").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("11111").build())
          .addValues(Value.newBuilder().setStringValue("2015").build())
          .addValues(Value.newBuilder().setStringValue("$10").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("11111").build())
          .addValues(Value.newBuilder().setStringValue("2016").build())
          .addValues(Value.newBuilder().setStringValue("$20").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22222").build())
          .addValues(Value.newBuilder().setStringValue("2016").build())
          .addValues(Value.newBuilder().setStringValue("$15").build())
          .build())
      .build();
  deIdentifyTableWithFpe(projectId, tableToDeIdentify, kmsKeyName, wrappedAesKey);
}
 

@Test
public void mapsStringToRow() {
  PCollection<KV<String, Table.Row>> rowCollection =
      testPipeline
          .apply(Create.of(KV.of("key", "value")))
          .apply(ParDo.of(new MapStringToDlpRow(null)));
  PAssert.that(rowCollection)
      .containsInAnyOrder(
          KV.of(
              "key",
              Table.Row.newBuilder()
                  .addValues(Value.newBuilder().setStringValue("value").build())
                  .build()));
  testPipeline.run().waitUntilFinish();
}
 

@ProcessElement
public void processElement(ProcessContext context) {
  Table.Row.Builder rowBuilder = Table.Row.newBuilder();
  String line = Objects.requireNonNull(context.element().getValue());
  if (delimiter != null) {
    List<String> values = Arrays.asList(line.split(delimiter));
    values.forEach(
        value -> rowBuilder.addValues(Value.newBuilder().setStringValue(value).build()));
  } else {
    rowBuilder.addValues(Value.newBuilder().setStringValue(line).build());
  }
  context.output(KV.of(context.element().getKey(), rowBuilder.build()));
}
 

private Table.Row convertCsvRowToTableRow(CSVRecord csvRow) {
  /** convert from CSV row to DLP Table Row */
  Iterator<String> valueIterator = csvRow.iterator();
  Table.Row.Builder tableRowBuilder = Table.Row.newBuilder();
  while (valueIterator.hasNext()) {
    String value = valueIterator.next();
    if (value != null) {
      tableRowBuilder.addValues(Value.newBuilder().setStringValue(value.toString()).build());
    } else {
      tableRowBuilder.addValues(Value.newBuilder().setStringValue("").build());
    }
  }

  return tableRowBuilder.build();
}
 

public static Table deIdentifyTableRowSuppress(String projectId, Table tableToDeIdentify)
    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 what content you want the service to de-identify.
    ContentItem contentItem = ContentItem.newBuilder().setTable(tableToDeIdentify).build();

    // Specify when the content should be de-identified.
    Condition condition = Condition.newBuilder()
        .setField(FieldId.newBuilder().setName("AGE").build())
        .setOperator(RelationalOperator.GREATER_THAN)
        .setValue(Value.newBuilder().setIntegerValue(89).build()).build();
    // Apply the condition to record suppression.
    RecordSuppression recordSuppressions =
        RecordSuppression.newBuilder()
            .setCondition(RecordCondition.newBuilder()
                .setExpressions(Expressions.newBuilder()
                    .setConditions(Conditions.newBuilder().addConditions(condition).build())
                    .build())
                .build())
            .build();
    // Use record suppression as the only transformation
    RecordTransformations transformations =
        RecordTransformations.newBuilder()
            .addRecordSuppressions(recordSuppressions)
            .build();

    DeidentifyConfig deidentifyConfig =
        DeidentifyConfig.newBuilder().setRecordTransformations(transformations).build();

    // Combine configurations into a request for the service.
    DeidentifyContentRequest request =
        DeidentifyContentRequest.newBuilder()
            .setParent(LocationName.of(projectId, "global").toString())
            .setItem(contentItem)
            .setDeidentifyConfig(deidentifyConfig)
            .build();

    // Send the request and receive response from the service.
    DeidentifyContentResponse response = dlp.deidentifyContent(request);

    // Print the results.
    System.out.println(
        "Table after de-identification: " + response.getItem().getTable());

    return response.getItem().getTable();
  }
}
 

@Test
public void testDeIdentifyTableConditionsInfoTypes() throws IOException {
  // Transform findings only when specific conditions are met on another field
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "Charles Dickens name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in Jane Austen's novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
          .build())
      .build();
  Table expectedTable = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("[PERSON_NAME]").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "[PERSON_NAME] name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in Jane Austen's novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
          .build())
      .build();

  Table table = DeIdentifyTableConditionInfoTypes.deIdentifyTableConditionInfoTypes(
      PROJECT_ID, tableToDeIdentify);

  String output = bout.toString();
  assertThat(output).contains("Table after de-identification:");
  assertThat(table).isEqualTo(expectedTable);
}
 

@Test
public void testDeIdentifyTableRowSuppress() throws IOException {
  // Suppress a row based on the content of a column
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();
  Table expectedTable = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();

  Table table = DeIdentifyTableRowSuppress.deIdentifyTableRowSuppress(
      PROJECT_ID, tableToDeIdentify);

  String output = bout.toString();
  assertThat(output).contains("Table after de-identification:");
  assertThat(table).isEqualTo(expectedTable);
}
 

@Test
public void testDeIdentifyTableInfoTypes() throws IOException {
  // Transform findings found in column
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "Charles Dickens name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in Jane Austen's novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
          .build())
      .build();
  Table expectedTable = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("[PERSON_NAME]").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .addValues(Value.newBuilder().setStringValue(
              "[PERSON_NAME] name was a curse, possibly invented by Shakespeare.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("[PERSON_NAME]").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .addValues(Value.newBuilder().setStringValue(
              "There are 14 kisses in [PERSON_NAME] novels.").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("[PERSON_NAME]").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .addValues(Value.newBuilder().setStringValue("[PERSON_NAME] loved cats.").build())
          .build())
      .build();

  Table table = DeIdentifyTableInfoTypes.deIdentifyTableInfoTypes(PROJECT_ID, tableToDeIdentify);

  String output = bout.toString();
  assertThat(output).contains("Table after de-identification:");
  assertThat(table).isEqualTo(expectedTable);
}
 

@Test
public void testDeIdentifyTableConditionMasking() throws IOException {
  // Transform a column based on the value of another column
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();
  Table expectedTable = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("**").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();

  Table table = DeIdentifyTableConditionMasking.deIdentifyTableConditionMasking(
      PROJECT_ID, tableToDeIdentify);

  String output = bout.toString();
  assertThat(output).contains("Table after de-identification:");
  assertThat(table).isEqualTo(expectedTable);
}
 

@Test
public void testDeIdentifyTableBucketing() throws IOException {
  // Transform a column based on the value of another column
  Table tableToDeIdentify = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("95").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("21").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("75").build())
          .build())
      .build();
  Table expectedTable = Table.newBuilder()
      .addHeaders(FieldId.newBuilder().setName("AGE").build())
      .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
      .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("101").build())
          .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
          .addValues(Value.newBuilder().setStringValue("90:100").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("22").build())
          .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
          .addValues(Value.newBuilder().setStringValue("20:30").build())
          .build())
      .addRows(Row.newBuilder()
          .addValues(Value.newBuilder().setStringValue("55").build())
          .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
          .addValues(Value.newBuilder().setStringValue("70:80").build())
          .build())
      .build();

  Table table = DeIdentifyTableBucketing.deIdentifyTableBucketing(PROJECT_ID, tableToDeIdentify);

  String output = bout.toString();
  assertThat(output).contains("Table after de-identification:");
  assertThat(table).isEqualTo(expectedTable);
}
 

public static void numericalStatsAnalysis(
    String projectId, String datasetId, String tableId, String topicId, String subscriptionId)
    throws ExecutionException, InterruptedException, 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 dlpServiceClient = DlpServiceClient.create()) {

    // Specify the BigQuery table to analyze
    BigQueryTable bigQueryTable =
        BigQueryTable.newBuilder()
            .setTableId(tableId)
            .setDatasetId(datasetId)
            .setProjectId(projectId)
            .build();

    // This represents the name of the column to analyze, which must contain numerical data
    String columnName = "Age";

    // Configure the privacy metric for the job
    FieldId fieldId = FieldId.newBuilder().setName(columnName).build();
    NumericalStatsConfig numericalStatsConfig =
        NumericalStatsConfig.newBuilder().setField(fieldId).build();
    PrivacyMetric privacyMetric =
        PrivacyMetric.newBuilder().setNumericalStatsConfig(numericalStatsConfig).build();

    // Create action to publish job status notifications over Google Cloud Pub/Sub
    ProjectTopicName topicName = ProjectTopicName.of(projectId, topicId);
    PublishToPubSub publishToPubSub =
        PublishToPubSub.newBuilder().setTopic(topicName.toString()).build();
    Action action = Action.newBuilder().setPubSub(publishToPubSub).build();

    // Configure the risk analysis job to perform
    RiskAnalysisJobConfig riskAnalysisJobConfig =
        RiskAnalysisJobConfig.newBuilder()
            .setSourceTable(bigQueryTable)
            .setPrivacyMetric(privacyMetric)
            .addActions(action)
            .build();

    CreateDlpJobRequest createDlpJobRequest =
        CreateDlpJobRequest.newBuilder()
            .setParent(LocationName.of(projectId, "global").toString())
            .setRiskJob(riskAnalysisJobConfig)
            .build();

    // Send the request to the API using the client
    DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);

    // Set up a Pub/Sub subscriber to listen on the job completion status
    final SettableApiFuture<Boolean> done = SettableApiFuture.create();

    ProjectSubscriptionName subscriptionName =
        ProjectSubscriptionName.of(projectId, subscriptionId);

    MessageReceiver messageHandler =
        (PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
          handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
        };
    Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
    subscriber.startAsync();

    // Wait for job completion semi-synchronously
    // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
    try {
      done.get(15, TimeUnit.MINUTES);
    } catch (TimeoutException e) {
      System.out.println("Job was not completed after 15 minutes.");
      return;
    } finally {
      subscriber.stopAsync();
      subscriber.awaitTerminated();
    }

    // Build a request to get the completed job
    GetDlpJobRequest getDlpJobRequest =
        GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();

    // Retrieve completed job status
    DlpJob completedJob = dlpServiceClient.getDlpJob(getDlpJobRequest);
    System.out.println("Job status: " + completedJob.getState());

    // Get the result and parse through and process the information
    NumericalStatsResult result = completedJob.getRiskDetails().getNumericalStatsResult();

    System.out.printf(
        "Value range : [%.3f, %.3f]\n",
        result.getMinValue().getFloatValue(), result.getMaxValue().getFloatValue());

    int percent = 1;
    Double lastValue = null;
    for (Value quantileValue : result.getQuantileValuesList()) {
      Double currentValue = quantileValue.getFloatValue();
      if (lastValue == null || !lastValue.equals(currentValue)) {
        System.out.printf("Value at %s %% quantile : %.3f", percent, currentValue);
      }
      lastValue = currentValue;
    }
  }
}
 

public static void deIdentifyWithReplacement(String projectId, String textToRedact) {
  // 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 content to be inspected.
    ContentItem item = ContentItem.newBuilder()
        .setValue(textToRedact).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("EMAIL_ADDRESS").build();
    InspectConfig inspectConfig = InspectConfig.newBuilder().addInfoTypes(infoType).build();
    // Specify replacement string to be used for the finding.
    ReplaceValueConfig replaceValueConfig = ReplaceValueConfig.newBuilder()
        .setNewValue(Value.newBuilder().setStringValue("[email-address]").build())
        .build();
    // Define type of deidentification as replacement.
    PrimitiveTransformation primitiveTransformation = PrimitiveTransformation.newBuilder()
        .setReplaceConfig(replaceValueConfig)
        .build();
    // Associate deidentification type with info type.
    InfoTypeTransformation transformation = InfoTypeTransformation.newBuilder()
        .addInfoTypes(infoType)
        .setPrimitiveTransformation(primitiveTransformation)
        .build();
    // Construct the configuration for the Redact request and list all desired transformations.
    DeidentifyConfig redactConfig = DeidentifyConfig.newBuilder()
        .setInfoTypeTransformations(InfoTypeTransformations.newBuilder()
            .addTransformations(transformation))
        .build();

    // Construct the Redact request to be sent by the client.
    DeidentifyContentRequest request =
        DeidentifyContentRequest.newBuilder()
            .setParent(LocationName.of(projectId, "global").toString())
            .setItem(item)
            .setDeidentifyConfig(redactConfig)
            .setInspectConfig(inspectConfig)
            .build();

    // Use the client to send the API request.
    DeidentifyContentResponse response = dlp.deidentifyContent(request);

    // Parse the response and process results
    System.out.println("Text after redaction: " + response.getItem().getValue());
  } catch (Exception e) {
    System.out.println("Error during inspectString: \n" + e.toString());
  }
}
 

public static Table deIdentifyTableConditionMasking(String projectId, Table tableToDeIdentify)
    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 what content you want the service to de-identify.
    ContentItem contentItem = ContentItem.newBuilder().setTable(tableToDeIdentify).build();

    // Specify how the content should be de-identified.
    CharacterMaskConfig characterMaskConfig =
        CharacterMaskConfig.newBuilder()
            .setMaskingCharacter("*")
            .build();
    PrimitiveTransformation primitiveTransformation =
        PrimitiveTransformation.newBuilder()
            .setCharacterMaskConfig(characterMaskConfig)
            .build();

    // Specify field to be de-identified.
    FieldId fieldId = FieldId.newBuilder().setName("HAPPINESS SCORE").build();

    // Specify when the above field should be de-identified.
    Condition condition = Condition.newBuilder()
        .setField(FieldId.newBuilder().setName("AGE").build())
        .setOperator(RelationalOperator.GREATER_THAN)
        .setValue(Value.newBuilder().setIntegerValue(89).build())
        .build();
    // Apply the condition to records
    RecordCondition recordCondition = RecordCondition.newBuilder()
        .setExpressions(Expressions.newBuilder()
            .setConditions(Conditions.newBuilder()
                .addConditions(condition)
                .build())
            .build())
        .build();

    // Associate the de-identification and conditions with the specified field.
    FieldTransformation fieldTransformation =
        FieldTransformation.newBuilder()
            .setPrimitiveTransformation(primitiveTransformation)
            .addFields(fieldId)
            .setCondition(recordCondition)
            .build();
    RecordTransformations transformations =
        RecordTransformations.newBuilder().addFieldTransformations(fieldTransformation).build();

    DeidentifyConfig deidentifyConfig =
        DeidentifyConfig.newBuilder().setRecordTransformations(transformations).build();

    // Combine configurations into a request for the service.
    DeidentifyContentRequest request =
        DeidentifyContentRequest.newBuilder()
            .setParent(LocationName.of(projectId, "global").toString())
            .setItem(contentItem)
            .setDeidentifyConfig(deidentifyConfig)
            .build();

    // Send the request and receive response from the service.
    DeidentifyContentResponse response = dlp.deidentifyContent(request);

    // Print the results.
    System.out.println(
        "Table after de-identification: " + response.getItem().getTable());

    return response.getItem().getTable();
  }
}
 

public static Table deIdentifyTableConditionInfoTypes(String projectId, Table tableToDeIdentify)
    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 what content you want the service to de-identify.
    ContentItem contentItem = ContentItem.newBuilder().setTable(tableToDeIdentify).build();

    // Specify how the content should be de-identified.
    // Select type of info to be replaced.
    InfoType infoType = InfoType.newBuilder().setName("PERSON_NAME").build();
    // Specify that findings should be replaced with corresponding info type name.
    ReplaceWithInfoTypeConfig replaceWithInfoTypeConfig =
        ReplaceWithInfoTypeConfig.getDefaultInstance();
    PrimitiveTransformation primitiveTransformation = PrimitiveTransformation.newBuilder()
        .setReplaceWithInfoTypeConfig(replaceWithInfoTypeConfig).build();
    // Associate info type with the replacement strategy
    InfoTypeTransformation infoTypeTransformation =
        InfoTypeTransformation.newBuilder()
            .addInfoTypes(infoType)
            .setPrimitiveTransformation(primitiveTransformation)
            .build();
    InfoTypeTransformations infoTypeTransformations =
        InfoTypeTransformations.newBuilder()
            .addTransformations(infoTypeTransformation)
            .build();

    // Specify fields to be de-identified.
    List<FieldId> fieldIds = Stream.of("PATIENT", "FACTOID")
        .map(id -> FieldId.newBuilder().setName(id).build())
        .collect(Collectors.toList());

    // Specify when the above fields should be de-identified.
    Condition condition = Condition.newBuilder()
        .setField(FieldId.newBuilder().setName("AGE").build())
        .setOperator(RelationalOperator.GREATER_THAN)
        .setValue(Value.newBuilder().setIntegerValue(89).build())
        .build();
    // Apply the condition to records
    RecordCondition recordCondition = RecordCondition.newBuilder()
        .setExpressions(Expressions.newBuilder()
            .setConditions(Conditions.newBuilder()
                .addConditions(condition)
                .build())
            .build())
        .build();

    // Associate the de-identification and conditions with the specified fields.
    FieldTransformation fieldTransformation =
        FieldTransformation.newBuilder()
            .setInfoTypeTransformations(infoTypeTransformations)
            .addAllFields(fieldIds)
            .setCondition(recordCondition)
            .build();
    RecordTransformations transformations =
        RecordTransformations.newBuilder().addFieldTransformations(fieldTransformation).build();

    DeidentifyConfig deidentifyConfig =
        DeidentifyConfig.newBuilder().setRecordTransformations(transformations).build();

    // Combine configurations into a request for the service.
    DeidentifyContentRequest request =
        DeidentifyContentRequest.newBuilder()
            .setParent(LocationName.of(projectId, "global").toString())
            .setItem(contentItem)
            .setDeidentifyConfig(deidentifyConfig)
            .build();

    // Send the request and receive response from the service.
    DeidentifyContentResponse response = dlp.deidentifyContent(request);

    // Print the results.
    System.out.println(
        "Table after de-identification: " + response.getItem().getTable());

    return response.getItem().getTable();
  }
}