Add DLP sample code for inspecting with custom regex detector (#4031)

* code sample and test for medical record number custom regex detector

* fix linter error

* Using f-strings instead of string.format

Co-authored-by: Bu Sun Kim <[email protected]>

Co-authored-by: Bu Sun Kim <[email protected]>
Co-authored-by: gcf-merge-on-green[bot] <60162190+gcf-merge-on-green[bot]@users.noreply.github.com>

Author: 3 people

dlp/custom_infotype.py

@@ -83,3 +83,63 @@ def omit_name_if_also_email(
 
 
 # [END dlp_omit_name_if_also_email]
+
+# [START dlp_inspect_with_medical_record_number_custom_regex_detector]
+def inspect_with_medical_record_number_custom_regex_detector(
+    project,
+    content_string,
+):
+    """Uses the Data Loss Prevention API to analyze string with medical record
+       number custom regex detector
+    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.
+    """
+
+    # Import the client library.
+    import google.cloud.dlp
+
+    # Instantiate a client.
+    dlp = google.cloud.dlp_v2.DlpServiceClient()
+
+    # Construct a custom regex detector info type called "C_MRN",
+    # with ###-#-##### pattern, where each # represents a digit from 1 to 9.
+    # The detector has a detection likelihood of POSSIBLE.
+    custom_info_types = [
+        {
+            "info_type": {"name": "C_MRN"},
+            "regex": {"pattern": "[1-9]{3}-[1-9]{1}-[1-9]{5}"},
+            "likelihood": "POSSIBLE",
+        }
+    ]
+
+    # Construct the configuration dictionary with the custom regex info type.
+    inspect_config = {
+        "custom_info_types": custom_info_types,
+    }
+
+    # Construct the `item`.
+    item = {"value": content_string}
+
+    # Convert the project id into a full resource id.
+    parent = dlp.project_path(project)
+
+    # Call the API.
+    response = dlp.inspect_content(parent, inspect_config, 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.")
+
+# [END dlp_inspect_with_medical_record_number_custom_regex_detector]

dlp/custom_infotype_test.py

@@ -26,3 +26,11 @@ def test_omit_name_if_also_email(capsys):
     # Ensure we found only EMAIL_ADDRESS, and not PERSON_NAME.
     assert len(info_types) == 1
     assert info_types[0] == "EMAIL_ADDRESS"
+
+
+def test_inspect_with_medical_record_number_custom_regex_detector(capsys):
+    custom_infotype.inspect_with_medical_record_number_custom_regex_detector(
+        GCLOUD_PROJECT, "Patients MRN 444-5-22222")
+
+    out, _ = capsys.readouterr()
+    assert "Info type: C_MRN" in out