import mimetypes
from typing import List
import google.cloud.dlp
def redact_image(
project: str,
filename: str,
output_filename: str,
info_types: List[str],
min_likelihood: str = None,
mime_type: str = None,
) -> None:
"""Uses the Data Loss Prevention API to redact protected data in an image.
Args:
project: The Google Cloud project id to use as a parent resource.
filename: The path to the file to inspect.
output_filename: The path to which the redacted image will be written.
info_types: A list of strings representing info types to look for.
A full list of info type categories can be fetched from the API.
min_likelihood: A string representing the minimum likelihood threshold
that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
mime_type: The MIME type of the file. If not specified, the type is
inferred via the Python standard library's mimetypes module.
Returns:
None; the response from the API is printed to the terminal.
"""
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Prepare info_types by converting the list of strings into a list of
# dictionaries (protos are also accepted).
info_types = [{"name": info_type} for info_type in info_types]
# Prepare image_redaction_configs, a list of dictionaries. Each dictionary
# contains an info_type and optionally the color used for the replacement.
# The color is omitted in this sample, so the default (black) will be used.
image_redaction_configs = []
if info_types is not None:
for info_type in info_types:
image_redaction_configs.append({"info_type": info_type})
# Construct the configuration dictionary. Keys which are None may
# optionally be omitted entirely.
inspect_config = {
"min_likelihood": min_likelihood,
"info_types": info_types,
}
# If mime_type is not specified, guess it from the filename.
if mime_type is None:
mime_guess = mimetypes.MimeTypes().guess_type(filename)
mime_type = mime_guess[0] or "application/octet-stream"
# Select the content type index from the list of supported types.
# https://github.com/googleapis/googleapis/blob/master/google/privacy/dlp/v2/dlp.proto / message ByteContentItem
supported_content_types = {
None: 0, # "Unspecified" or BYTES_TYPE_UNSPECIFIED
"image/jpeg": 1, # IMAGE_JPEG
"image/bmp": 2, # IMAGE_BMP
"image/png": 3, # IMAGE_PNG
"image/svg": 4, # IMAGE_SVG - Adjusted to "image/svg+xml" for correct MIME type
"text/plain": 5, # TEXT_UTF8
# Note: No specific MIME type for general "image", mapping to IMAGE for any image type not specified
"image": 6, # IMAGE - Any image type
"application/msword": 7, # WORD_DOCUMENT
"application/pdf": 8, # PDF
"application/powerpoint": 9, # POWERPOINT_DOCUMENT
"application/msexcel": 10, # EXCEL_DOCUMENT
"application/avro": 11, # AVRO
"text/csv": 12, # CSV
"text/tsv": 13, # TSV
}
content_type_index = supported_content_types.get(mime_type, 0)
# Construct the byte_item, containing the file's byte data.
with open(filename, mode="rb") as f:
byte_item = {"type_": content_type_index, "data": f.read()}
# Convert the project id into a full resource id.
parent = f"projects/{project}"
# Call the API.
response = dlp.redact_image(
request={
"parent": parent,
"inspect_config": inspect_config,
"image_redaction_configs": image_redaction_configs,
"byte_item": byte_item,
}
)
# Write out the results.
with open(output_filename, mode="wb") as f:
f.write(response.redacted_image)
print(
"Wrote {byte_count} to {filename}".format(
byte_count=len(response.redacted_image), filename=output_filename
)
)
