Skip to content

Add DLP sample code for reid w/ fpe using surrogate type and unwrapped security key #4051

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 12, 2020
Merged

Add DLP sample code for reid w/ fpe using surrogate type and unwrapped security key #4051

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
984e01d
add code sample and test for reid w/ fpe using surrogate type and unw…
lxhfirenking Jun 10, 2020
1066cbc
refactor reidentify_config
lxhfirenking Jun 11, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 80 additions & 0 deletions dlp/deid.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,6 +336,86 @@ def reidentify_with_fpe(

# [END dlp_reidentify_fpe]

# [START dlp_reidentify_free_text_with_fpe_using_surrogate]
def reidentify_free_text_with_fpe_using_surrogate(
project,
input_str,
alphabet="NUMERIC",
surrogate_type="PHONE_TOKEN",
unwrapped_key="YWJjZGVmZ2hpamtsbW5vcA==",
):
"""Uses the Data Loss Prevention API to reidentify sensitive data in a
string that was encrypted by Format Preserving Encryption (FPE) with
surrogate type. The encryption is performed with an unwrapped key.
Args:
project: The Google Cloud project id to use as a parent resource.
input_str: The string to deidentify (will be treated as text).
alphabet: The set of characters to replace sensitive ones with. For
more information, see https://cloud.google.com/dlp/docs/reference/
rest/v2beta2/organizations.deidentifyTemplates#ffxcommonnativealphabet
surrogate_type: The name of the surrogate custom info type to used
during the encryption process.
unwrapped_key: The base64-encoded AES-256 key to use.
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()

# Convert the project id into a full resource id.
parent = dlp.project_path(project)

# The unwrapped key is base64-encoded, but the library expects a binary
# string, so decode it here.
import base64

unwrapped_key = base64.b64decode(unwrapped_key)

# Construct Deidentify Config
transformation = {
"primitive_transformation": {
"crypto_replace_ffx_fpe_config": {
"crypto_key": {
"unwrapped": {"key": unwrapped_key}
},
"common_alphabet": alphabet,
"surrogate_info_type": {"name": surrogate_type},
}
}
}

reidentify_config = {
"info_type_transformations": {
"transformations": [transformation]
}
}

inspect_config = {
"custom_info_types": [
{"info_type": {"name": surrogate_type}, "surrogate_type": {}}
]
}

# Convert string to item
item = {"value": input_str}

# Call the API
response = dlp.reidentify_content(
parent,
inspect_config=inspect_config,
reidentify_config=reidentify_config,
item=item,
)

# Print results
print(response.item.value)


# [END dlp_reidentify_free_text_with_fpe_using_surrogate]


# [START dlp_deidentify_date_shift]
def deidentify_with_date_shift(
Expand Down
19 changes: 19 additions & 0 deletions dlp/deid_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
HARMFUL_STRING = "My SSN is 372819127"
HARMLESS_STRING = "My favorite color is blue"
GCLOUD_PROJECT = os.getenv("GOOGLE_CLOUD_PROJECT")
UNWRAPPED_KEY = "YWJjZGVmZ2hpamtsbW5vcA=="
WRAPPED_KEY = (
"CiQAz0hX4+go8fJwn80Fr8pVImwx+tmZdqU7JL+7TN/S5JxBU9gSSQDhFHpFVy"
"uzJps0YH9ls480mU+JLG7jI/0lL04i6XJRWqmI6gUSZRUtECYcLH5gXK4SXHlL"
Expand Down Expand Up @@ -197,6 +198,24 @@ def test_reidentify_with_fpe(capsys):
assert "731997681" not in out


def test_reidentify_free_text_with_fpe_using_surrogate(capsys):
labeled_fpe_string = "My phone number is PHONE_TOKEN(10):9617256398"

deid.reidentify_free_text_with_fpe_using_surrogate(
GCLOUD_PROJECT,
labeled_fpe_string,
surrogate_type="PHONE_TOKEN",
unwrapped_key=UNWRAPPED_KEY,
alphabet="NUMERIC",
)

out, _ = capsys.readouterr()

assert "PHONE_TOKEN" not in out
assert "9617256398" not in out
assert "My phone number is" in out


def test_deidentify_with_replace_infotype(capsys):
url_to_redact = "https://cloud.google.com"
deid.deidentify_with_replace_infotype(
Expand Down