From 5f7b9825cdf9367d8596a32b8d213a0287b73822 Mon Sep 17 00:00:00 2001
From: jlmwise <66651702+jlmwise@users.noreply.github.com>
Date: Thu, 11 Jun 2020 11:28:05 -0700
Subject: [PATCH] Add code sample and tests for redaction (#4037)

Add A DLP code sample for redacting text.

Code will be linked to this documentation: https://cloud.google.com/dlp/docs/deidentify-sensitive-data
---
 dlp/deid.py      | 58 ++++++++++++++++++++++++++++++++++++++++++++++++
 dlp/deid_test.py |  8 +++++++
 2 files changed, 66 insertions(+)

diff --git a/dlp/deid.py b/dlp/deid.py
index d6afea08b430..af5213256962 100644
--- a/dlp/deid.py
+++ b/dlp/deid.py
@@ -83,6 +83,64 @@ def deidentify_with_mask(
 
 # [END dlp_deidentify_masking]
 
+# [START dlp_deidentify_redact]
+def deidentify_with_redact(
+    project,
+    input_str,
+    info_types,
+):
+    """Uses the Data Loss Prevention API to deidentify sensitive data in a
+    string by redacting matched input values.
+    Args:
+        project: The Google Cloud project id to use as a parent resource.
+        input_str: The string to deidentify (will be treated as text).
+        info_types: A list of strings representing info types to look for.
+    Returns:
+        None; the response from the API is printed to the terminal.
+    """
+    import google.cloud.dlp
+
+    # Instantiate a client
+    dlp = google.cloud.dlp_v2.DlpServiceClient()
+
+    # Convert the project id into a full resource id.
+    parent = dlp.project_path(project)
+
+    # Construct inspect configuration dictionary
+    inspect_config = {
+        "info_types": [{"name": info_type} for info_type in info_types]
+    }
+
+    # Construct deidentify configuration dictionary
+    deidentify_config = {
+        "info_type_transformations": {
+            "transformations": [
+                {
+                    "primitive_transformation": {
+                        "redact_config": {}
+                    }
+                }
+            ]
+        }
+    }
+
+    # Construct item
+    item = {"value": input_str}
+
+    # Call the API
+    response = dlp.deidentify_content(
+        parent,
+        inspect_config=inspect_config,
+        deidentify_config=deidentify_config,
+        item=item,
+    )
+
+    # Print out the results.
+    print(response.item.value)
+
+
+# [END dlp_deidentify_redact]
+
 # [START dlp_deidentify_replace]
 def deidentify_with_replace(
     project,
diff --git a/dlp/deid_test.py b/dlp/deid_test.py
index 0a2c53829613..a407fff97fc7 100644
--- a/dlp/deid_test.py
+++ b/dlp/deid_test.py
@@ -88,6 +88,14 @@ def test_deidentify_with_mask_masking_number_specified(capsys):
     assert "My SSN is *******27" in out
 
 
+def test_deidentify_with_redact(capsys):
+    deid.deidentify_with_redact(
+        GCLOUD_PROJECT, HARMFUL_STRING + "!", ["US_SOCIAL_SECURITY_NUMBER"]
+    )
+    out, _ = capsys.readouterr()
+    assert "My SSN is !" in out
+
+
 def test_deidentify_with_replace(capsys):
     deid.deidentify_with_replace(
         GCLOUD_PROJECT, HARMFUL_STRING, ["US_SOCIAL_SECURITY_NUMBER"],