Examples of custom infotype detectors

Protocol

The sample JSON objects on this page are a few examples of Sensitive Data Protection custom infoType detectors that you can use during inspection and de-identification.

For more information about the different kinds of custom infoType detectors and how to create them, see Creating custom infoType detectors.

Example customInfoTypes contents

The JSON given in the following table can be inserted into any inspection or de-identification job definition, inside the "customInfoTypes" attribute. The following complete JSON request, which sends a short string to Sensitive Data Protection, includes a custom infoType detector definition that defines a medical record number format.

JSON input:

POST https://dlp.googleapis.com/v2/projects/[PROJECT_ID]/content:inspect?key={YOUR_API_KEY}

{
  "item":{
    "value":"Patients MRN 444-5-22222"
  },
  "inspectConfig":{
    "customInfoTypes":[
      {
        "infoType":{
          "name":"C_MRN"
        },
        "regex":{
          "pattern":"[1-9]{3}-[1-9]{1}-[1-9]{5}"
        },
        "likelihood":"POSSIBLE"
      }
    ]
  }
}
Example description Custom infoType detector
Generic alpha-numeric identifier 
{
  "infoType":{
    "name":"GENERIC_ID2"
  },
  "regex":{
    "pattern":"\\b(([0-9]|([a-zA-Z()]{1,2}[0-9]{1}))[0-9-\\[\\]:(), ._]+)[0-9]{1}"
  },
  "likelihood":"POSSIBLE"
}
Generic currency 
{
  "infoType":{
    "name":"GENERIC_CURRENCY"
  },
  "regex":{
    "pattern":"((\\p{Sc}{1})( ){0,1}[0-9,()]+)(.){0,1}[0-9]{0,}"
  },
  "likelihood":"VERY_LIKELY"
}
Generic percentage 
{
  "infoType":{
    "name":"GENERIC_PERCENT"
  },
  "regex":{
    "pattern":"\\b([0-9,.()]+)( ){0,1}(%){1}"
  },
  "likelihood":"VERY_LIKELY"
}
Generic unit of measurement 
{
  "infoType":{
    "name":"GENERIC_MEASURE"
  },
  "regex":{
    "pattern":"(?i)([0-9])([0-9,.]+)( ){0,1}(?i)(°C|°F|K|°Ré|°N|°Ra|m³|dm³|cm³|l|dl|cl|ml|fl oz|in³|ft³|yd³|gal|bbl|pt|km|m|dm|cm|mm|mi|in|ft|yd|nautical mile|kg|hg|g|dg|cg|mg|µg|mcg|carat|grain|oz|lb|cwt|ton|km²|m²|dm²|cm²|mm²|ha|ca|mile²|in²|yd²|ft²|acre|nautical mile²|kmph|mps|mph|knot|km/h|m/s|mi/h|Hz|KHz|MHz|GHz|atm|bar|mbar|Pa|hPa|Psi|Torr|J|KJ|cal|kcal|Wh|kWh|BTU|thm|ft-lb|degrees|Celsius|Fahrenheit|Kelvin|Reaumur|Newton|Rankine|cubic |liter|deciliter|centiliter|milliliter|fluid ounce|gallon|petroleum barrel|pint|kilometer|meter|decimeter|centimeter|millimeter|mile|inch|foot|yard|nautical mile|tonne|kilogram|hectogram|gram|decigram|centigram|milligram|microgram|carat|grain|ounce|pound|square|hectare|centiare|square mile|square inch|square yard|square foot|acre|square nautical mile|kilometer|meter|mile per hour|knot|Hertz|Kilohertz|Megahertz|Gigahertz|Atmosphère|Bar|Millibar|Pascal|Hectopascal|Torr|Joule|Kilojoule|Calorie|Kilocalorie|Watt-hour|Kilowatt-hour|Foot-Pound|mpg){1}(s){0,1}\\b"
  },
  "likelihood":"VERY_LIKELY"
}
Generic Requests for Comments (RFC) identifier 
{
  "infoType":{
    "name":"GENERIC_RFC"
  },
  "regex":{
    "pattern":"\\b(?i)(rfc)( ){0,1}(20|768|783|791|792|793|826|854|855|862|863|864|868|903|937|951|959|1034|1035|1036|1055|1058|1059|1087|1119|1149|1157|1176|1305|1321|1350|1436|1441|1459|1730|1777|1855|1918|1939|1945|1948|1950|1951|1952|1964|2080|2119|2131|2177|2195|2228|2230|2246|2251|2252|2253|2254|2255|2256|2326|2327|2328|2351|2362|2397|2407|2408|2409|2427|2453|2460|2549|2555|2570|2595|2606|2740|2743|2744|2810|2811|2812|2813|2853|2865|2866|2974|3022|3031|3053|3056|3080|3162|3207|3261|3284|3286|3315|3339|3376|3401|3402|3403|3404|3405|3492|3501|3530|3550|3711|3720|3730|3783|3801|3830|3977|4122|4213|4217|4271|4287|4251|4291|4353|4408|4422|4541|4575|4579|4634|4646|4655|4787|4880|4960|5023|5321|5322|5533|5545|5849|5880|5881|5905|5969|6238|6265|6409|6455|6508|6726|6749|6797|6805|7230|7231|7232|7233|7234|7235|7301|7348|7469|7540|7541|7567|7725|7871|8391){0,1}"
  },
  "likelihood":"LIKELY"
}
Generic RJ45 network connector identifier 
{
  "infoType":{
    "name":"GENERIC_RJ_NETWORK"
  },
  "regex":{
    "pattern":"\\b(?i)(rj)(-){0,1}(?i)(A1X|A2X|A3X|2MB|11|12|13|14|15C|18|21X|25|26X|27X|31X|32X|33X|34X|35X|38X|41S|45S|45|48C|48S|48X|49C|61X|71C)"
  },
  "likelihood":"VERY_LIKELY"
}
Generic data size 
{
  "infoType":{
    "name":"GENERIC_DATA_SIZE"
  },
  "regex":{
    "pattern":"\\b([0-9,. ]+)(?i)(byte|Kilobyte|KiB|Kilobit|kbit|bit|Megabyte|MiB|Megabit|Mbit|meg|Gigabyte|GiB|Gigabit|Gbit|gig|Terabyte|TiB|Terabit|Tbit|Petabyte|PiB|Petabit|Pbit|Exabyte|EiB|Exabit|Ebit|Zettabyte|ZiB|Zettabit|Zbit|Yottabyte|YiB|Yottabit|Ybit|KB|MB|GB|TB|PB|EB|ZB|YB)(p){0,1}(s){0,1}"
  },
  "likelihood":"VERY_LIKELY"
}
Numerical identifier 
{
  "infoType":{
    "name":"GENERIC_ID1"
  },
  "regex":{
    "pattern":"\\w*[0-9][0-9-()\\[\\].:/]+[0-9]\\w*"
  },
  "likelihood":"POSSIBLE"
}

Java

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 


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;
import com.google.privacy.dlp.v2.CustomInfoType.Regex;
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.Likelihood;
import com.google.privacy.dlp.v2.LocationName;
import com.google.protobuf.ByteString;
import java.io.IOException;

public class InspectWithCustomRegex {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String textToInspect = "Patients MRN 444-5-22222";
    String customRegexPattern = "[1-9]{3}-[1-9]{1}-[1-9]{5}";
    inspectWithCustomRegex(projectId, textToInspect, customRegexPattern);
  }

  // Inspects a BigQuery Table
  public static void inspectWithCustomRegex(
      String projectId, String textToInspect, String customRegexPattern) 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 regex pattern the inspection will look for.
      Regex regex = Regex.newBuilder().setPattern(customRegexPattern).build();

      // Construct the custom regex detector.
      InfoType infoType = InfoType.newBuilder().setName("C_MRN").build();
      CustomInfoType customInfoType =
          CustomInfoType.newBuilder().setInfoType(infoType).setRegex(regex).build();

      // Construct the configuration for the Inspect request.
      InspectConfig config =
          InspectConfig.newBuilder()
              .addCustomInfoTypes(customInfoType)
              .setIncludeQuote(true)
              .setMinLikelihood(Likelihood.POSSIBLE)
              .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());
      }
    }
  }
}