def sendToDLP(transcript, projectID):
dlpClient = dlp.DlpServiceClient()
parent = dlpClient.project_path(projectID)
# Prepare info_types by converting the list of strings into a list of
info_types = [
'PHONE_NUMBER', 'EMAIL_ADDRESS', 'CREDIT_CARD_NUMBER',
'US_SOCIAL_SECURITY_NUMBER'
]
# dictionaries (protos are also accepted).
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': {
'replace_with_info_type_config': {}
}
}]
}
}
regex = r".([A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+)*)(\sat\s+)((?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9]))"
updatedTranscript = re.sub(regex, r" \1@\3", transcript)
item = {'value': updatedTranscript}
# Call the API
dlpResponse = dlpClient.deidentify_content(
parent,
inspect_config=inspect_config,
deidentify_config=deidentify_config,
item=item)
# Print out the results.
print(dlpResponse.item.value)
"""The maximum number of findings to report (0 = server maximum)"""
MAX_FINDINGS = 0
"""The infoTypes of information to match"""
"""For more info visit: https://cloud.google.com/dlp/docs/concepts-infotypes"""
INFO_TYPES = [
'FIRST_NAME', 'PHONE_NUMBER', 'EMAIL_ADDRESS', 'US_SOCIAL_SECURITY_NUMBER'
]
PROJECT_ID = '[PROJECT_ID_FOR_DLP_FINDINGS]'
DATASET_ID = '[DATASET_ID_FOR_DLP_FINDINGS]'
TABLE_ID = '[TABLE_ID_FOR_DLP_FINDINGS]'
# End of User-configurable Constants
# ----------------------------------
# Initialize the Google Cloud client libraries
dlp = dlp.DlpServiceClient()
storage_client = storage.Client()
publisher = pubsub.PublisherClient()
subscriber = pubsub.SubscriberClient()
def create_DLP_job(data, done):
"""This function is triggered by new files uploaded to the designated Cloud Storage quarantine/staging bucket.
It creates a dlp job for the uploaded file.
Arg:
data: The Cloud Storage Event
Returns:
None. Debug information is printed to the log.
"""
# Get the targeted file in the quarantine bucket
def deidentify(file_name, projectID):
# Instantiates a client
speechClient = speech.SpeechClient()
dlpClient = dlp.DlpServiceClient()
parent = dlpClient.project_path(projectID)
# Prepare info_types by converting the list of strings into a list of
info_types = ['PHONE_NUMBER', 'EMAIL_ADDRESS', 'CREDIT_CARD_NUMBER', 'US_SOCIAL_SECURITY_NUMBER']
# dictionaries (protos are also accepted).
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': {
'replace_with_info_type_config': {
}
}
}
]
}
}
# The name of the audio file and path to transcribe
#file_name = Path('./resources/sallybrown.flac')
# Loads the audio into memory
with io.open(file_name, 'rb') as audio_file:
content = audio_file.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
sample_rate_hertz=16000,
language_code='en-US')
# Detects speech in the audio file
response = speechClient.recognize(config, audio)
transcript = ""
for result in response.results:
transcript = transcript + result.alternatives[0].transcript;
print('Original Transcript: {}'.format(transcript))
# Check transcription for email address, since speech-to-text returns " at " instead of "@"
# Format with regex before sending to DLP api
# Currently social security numbers and credit card numbers are interpreted as phone numbers
regex = r".([A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+)*)(\sat\s+)((?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9]))"
updatedTranscript = re.sub(regex, r" \1@\3", transcript)
print('Email addresses reformatted: {}'.format(updatedTranscript))
# Construct item
item = {'value': updatedTranscript}
# Call the API
dlpResponse = dlpClient.deidentify_content(
parent, inspect_config=inspect_config,
deidentify_config=deidentify_config, item=item)
# Print out the results.
print('Final Result with sensitive content redacted: {}'.format(dlpResponse.item.value))
