Matches against a custom simple word list to de-identify sensitive data.
Explore further
For detailed documentation that includes this code sample, see the following:
Code sample
C#
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
using
System
;
using
Google.Api.Gax.ResourceNames
;
using
Google.Cloud.Dlp.V2
;
public
class
DeidentifyWithSimpleWordList
{
public
static
DeidentifyContentResponse
Deidentify
(
string
projectId
,
string
text
)
{
// Instantiate a client.
var
dlp
=
DlpServiceClient
.
Create
();
var
contentItem
=
new
ContentItem
{
Value
=
text
};
var
wordList
=
new
CustomInfoType
.
Types
.
Dictionary
.
Types
.
WordList
{
Words
=
{
new
string
[]
{
"RM-GREEN"
,
"RM-YELLOW"
,
"RM-ORANGE"
}
}
};
var
infoType
=
new
InfoType
{
Name
=
"CUSTOM_ROOM_ID"
};
var
customInfoType
=
new
CustomInfoType
{
InfoType
=
infoType
,
Dictionary
=
new
CustomInfoType
.
Types
.
Dictionary
{
WordList
=
wordList
}
};
var
inspectConfig
=
new
InspectConfig
{
CustomInfoTypes
=
{
customInfoType
,
}
};
var
primitiveTransformation
=
new
PrimitiveTransformation
{
ReplaceWithInfoTypeConfig
=
new
ReplaceWithInfoTypeConfig
{
}
};
var
transformation
=
new
InfoTypeTransformations
.
Types
.
InfoTypeTransformation
{
InfoTypes
=
{
infoType
},
PrimitiveTransformation
=
primitiveTransformation
};
var
deidentifyConfig
=
new
DeidentifyConfig
{
InfoTypeTransformations
=
new
InfoTypeTransformations
{
Transformations
=
{
transformation
}
}
};
var
request
=
new
DeidentifyContentRequest
{
Parent
=
new
LocationName
(
projectId
,
"global"
).
ToString
(),
InspectConfig
=
inspectConfig
,
DeidentifyConfig
=
deidentifyConfig
,
Item
=
contentItem
};
// Call the API.
var
response
=
dlp
.
DeidentifyContent
(
request
);
// Inspect the results.
Console
.
WriteLine
(
$"Deidentified content: {response.Item. Value
}"
);
return
response
;
}
}
Go
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
import
(
"context"
"fmt"
"io"
dlp
"cloud.google.com/go/dlp/apiv2"
"cloud.google.com/go/dlp/apiv2/dlppb"
)
// deidentifyWithWordList matches against a custom simple word list to de-identify sensitive
// data based on the input
func
deidentifyWithWordList
(
w
io
.
Writer
,
projectID
,
input
string
,
infoTypeName
string
,
wordList
[]
string
)
error
{
// projectID := "my-project-id"
// input := "Patient was seen in RM-YELLOW then transferred to rm green."
// wordList := []string{"RM-GREEN", "RM-YELLOW", "RM-ORANGE"}
ctx
:=
context
.
Background
()
// Initialize a client once and reuse it to send multiple requests. Clients
// are safe to use across goroutines. When the client is no longer needed,
// call the Close method to cleanup its resources.
client
,
err
:=
dlp
.
NewClient
(
ctx
)
if
err
!=
nil
{
return
err
}
// Closing the client safely cleans up background resources.
defer
client
.
Close
()
// Specify what content you want the service to DeIdentify.
item
:=
& dlppb
.
ContentItem
{
DataItem
:
& dlppb
.
ContentItem_Value
{
Value
:
input
,
},
}
// Specify the word list custom info type the inspection will look for.
infoType
:=
& dlppb
.
InfoType
{
Name
:
infoTypeName
,
}
var
customInfoType
=
& dlppb
.
CustomInfoType
{
InfoType
:
infoType
,
Type
:
& dlppb
.
CustomInfoType_Dictionary_
{
Dictionary
:
& dlppb
.
CustomInfoType_Dictionary
{
Source
:
& dlppb
.
CustomInfoType_Dictionary_WordList_
{
// Construct the word list to be detected
WordList
:
& dlppb
.
CustomInfoType_Dictionary_WordList
{
Words
:
wordList
,
},
},
},
},
}
// Define type of de-identification as replacement.
primitiveTransformation
:=
& dlppb
.
PrimitiveTransformation
{
Transformation
:
& dlppb
.
PrimitiveTransformation_ReplaceWithInfoTypeConfig
{
ReplaceWithInfoTypeConfig
:
& dlppb
.
ReplaceWithInfoTypeConfig
{},
},
}
infoTypeTransformation
:=
& dlppb
.
InfoTypeTransformations_InfoTypeTransformation
{
InfoTypes
:
[]
*
dlppb
.
InfoType
{
infoType
},
PrimitiveTransformation
:
primitiveTransformation
,
}
infoTypeTransformations
:=
& dlppb
.
InfoTypeTransformations
{
// Associate de-identification type with info type.
Transformations
:
[]
*
dlppb
.
InfoTypeTransformations_InfoTypeTransformation
{
infoTypeTransformation
,
},
}
// Create a configured request.
req
:=
& dlppb
.
DeidentifyContentRequest
{
Parent
:
fmt
.
Sprintf
(
"projects/%s/locations/global"
,
projectID
),
InspectConfig
:
& dlppb
.
InspectConfig
{
CustomInfoTypes
:
[]
*
dlppb
.
CustomInfoType
{
customInfoType
,
},
},
// Construct the configuration for the de-identify request and list all desired transformations.
DeidentifyConfig
:
& dlppb
.
DeidentifyConfig
{
Transformation
:
& dlppb
.
DeidentifyConfig_InfoTypeTransformations
{
InfoTypeTransformations
:
infoTypeTransformations
,
},
},
// The item to analyze.
Item
:
item
,
}
// Send the request.
resp
,
err
:=
client
.
DeidentifyContent
(
ctx
,
req
)
if
err
!=
nil
{
return
err
}
// Print the result.
fmt
.
Fprintf
(
w
,
"output : %v"
,
resp
.
GetItem
().
GetValue
())
return
nil
}
Java
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
import
com.google.cloud.dlp.v2. DlpServiceClient
;
import
com.google.privacy.dlp.v2. ContentItem
;
import
com.google.privacy.dlp.v2. CustomInfoType
;
import
com.google.privacy.dlp.v2. CustomInfoType
. Dictionary
;
import
com.google.privacy.dlp.v2. CustomInfoType
. Dictionary
. WordList
;
import
com.google.privacy.dlp.v2. DeidentifyConfig
;
import
com.google.privacy.dlp.v2. DeidentifyContentRequest
;
import
com.google.privacy.dlp.v2. DeidentifyContentResponse
;
import
com.google.privacy.dlp.v2. InfoType
;
import
com.google.privacy.dlp.v2. InfoTypeTransformations
;
import
com.google.privacy.dlp.v2. InfoTypeTransformations
. InfoTypeTransformation
;
import
com.google.privacy.dlp.v2. InspectConfig
;
import
com.google.privacy.dlp.v2. LocationName
;
import
com.google.privacy.dlp.v2. PrimitiveTransformation
;
import
com.google.privacy.dlp.v2. ReplaceWithInfoTypeConfig
;
import
java.io.IOException
;
public
class
DeIdentifyWithSimpleWordList
{
public
static
void
main
(
String
[]
args
)
throws
Exception
{
// TODO(developer): Replace these variables before running the sample.
String
projectId
=
"your-project-id"
;
String
textToDeIdentify
=
"Patient was seen in RM-YELLOW then transferred to rm green."
;
deidentifyWithSimpleWordList
(
projectId
,
textToDeIdentify
);
}
public
static
void
deidentifyWithSimpleWordList
(
String
projectId
,
String
textToDeIdentify
)
throws
IOException
{
// Initialize client that will be used to send requests. This client only needs to be created
// once, and can be reused for multiple requests. After completing all of your requests, call
// the "close" method on the client to safely clean up any remaining background resources.
try
(
DlpServiceClient
dlp
=
DlpServiceClient
.
create
())
{
// Specify what content you want the service to DeIdentify.
ContentItem
contentItem
=
ContentItem
.
newBuilder
().
setValue
(
textToDeIdentify
).
build
();
// Construct the word list to be detected
Dictionary
wordList
=
Dictionary
.
newBuilder
()
.
setWordList
(
WordList
.
newBuilder
()
.
addWords
(
"RM-GREEN"
)
.
addWords
(
"RM-YELLOW"
)
.
addWords
(
"RM-ORANGE"
)
.
build
())
.
build
();
// Specify the word list custom info type the inspection will look for.
InfoType
infoType
=
InfoType
.
newBuilder
().
setName
(
"CUSTOM_ROOM_ID"
).
build
();
CustomInfoType
customInfoType
=
CustomInfoType
.
newBuilder
().
setInfoType
(
infoType
).
setDictionary
(
wordList
).
build
();
InspectConfig
inspectConfig
=
InspectConfig
.
newBuilder
().
addCustomInfoTypes
(
customInfoType
).
build
();
// Define type of deidentification as replacement.
PrimitiveTransformation
primitiveTransformation
=
PrimitiveTransformation
.
newBuilder
()
.
setReplaceWithInfoTypeConfig
(
ReplaceWithInfoTypeConfig
.
getDefaultInstance
())
.
build
();
// Associate deidentification type with info type.
InfoTypeTransformation
transformation
=
InfoTypeTransformation
.
newBuilder
()
.
addInfoTypes
(
infoType
)
.
setPrimitiveTransformation
(
primitiveTransformation
)
.
build
();
// Construct the configuration for the Redact request and list all desired transformations.
DeidentifyConfig
deidentifyConfig
=
DeidentifyConfig
.
newBuilder
()
.
setInfoTypeTransformations
(
InfoTypeTransformations
.
newBuilder
().
addTransformations
(
transformation
))
.
build
();
// Combine configurations into a request for the service.
DeidentifyContentRequest
request
=
DeidentifyContentRequest
.
newBuilder
()
.
setParent
(
LocationName
.
of
(
projectId
,
"global"
).
toString
())
.
setItem
(
contentItem
)
.
setInspectConfig
(
inspectConfig
)
.
setDeidentifyConfig
(
deidentifyConfig
)
.
build
();
// Send the request and receive response from the service
DeidentifyContentResponse
response
=
dlp
.
deidentifyContent
(
request
);
// Print the results
System
.
out
.
println
(
"Text after replace with infotype config: "
+
response
.
getItem
().
getValue
());
}
}
}
Node.js
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
// Imports the Google Cloud Data Loss Prevention library
const
DLP
=
require
(
' @google-cloud/dlp
'
);
// TODO(developer): Replace these variables before running the sample.
// const projectId = "your-project-id";
// The string to de-identify
// const textToInspect = 'Patient was seen in RM-YELLOW then transferred to rm green.';
// Words to look for during inspection
// const words = ['RM-GREEN', 'RM-YELLOW', 'RM-ORANGE'];
// Name of the custom info type
// const customInfoTypeName = 'CUSTOM_ROOM_ID';
async
function
deIdentifyWithSimpleWordList
()
{
// Initialize client that will be used to send requests. This client only needs to be created
// once, and can be reused for multiple requests. After completing all of your requests, call
// the "close" method on the client to safely clean up any remaining background resources.
const
dlp
=
new
DLP
.
DlpServiceClient
();
// Construct the word list to be detected
const
wordList
=
{
words
:
words
,
};
// Specify the word list custom info type the inspection will look for.
const
infoType
=
{
name
:
customInfoTypeName
,
};
const
customInfoType
=
{
infoType
,
dictionary
:
{
wordList
,
},
};
// Construct de-identify configuration
const
deidentifyConfig
=
{
infoTypeTransformations
:
{
transformations
:
[
{
primitiveTransformation
:
{
replaceWithInfoTypeConfig
:
{},
},
},
],
},
};
// Construct inspect configuration
const
inspectConfig
=
{
customInfoTypes
:
[
customInfoType
],
};
// Construct Item
const
item
=
{
value
:
textToInspect
,
};
// Combine configurations into a request for the service.
const
request
=
{
parent
:
`projects/
${
projectId
}
/locations/global`
,
item
,
deidentifyConfig
,
inspectConfig
,
};
// Send the request and receive response from the service
const
[
response
]
=
await
dlp
.
deidentifyContent
(
request
);
// Print the results
console
.
log
(
`Text after replace with infotype config:
${
response
.
item
.
value
}
`
);
}
deIdentifyWithSimpleWordList
();
PHP
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\CustomInfoType;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary\WordList;
use Google\Cloud\Dlp\V2\DeidentifyConfig;
use Google\Cloud\Dlp\V2\DeidentifyContentRequest;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InfoTypeTransformations;
use Google\Cloud\Dlp\V2\InfoTypeTransformations\InfoTypeTransformation;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\PrimitiveTransformation;
use Google\Cloud\Dlp\V2\ReplaceWithInfoTypeConfig;
/**
* De-identify sensitive data with a simple word list
* Matches against a custom simple word list to de-identify sensitive data.
*
* @param string $callingProjectId The Google Cloud project id to use as a parent resource.
* @param string $string The string to deidentify (will be treated as text).
*/
function deidentify_simple_word_list(
// TODO(developer): Replace sample parameters before running the code.
string $callingProjectId,
string $string = 'Patient was seen in RM-YELLOW then transferred to rm green.'
): void {
// Instantiate a client.
$dlp = new DlpServiceClient();
$parent = "projects/$callingProjectId/locations/global";
$content = (new ContentItem())
->setValue($string);
// Construct the word list to be detected
$wordList = (new Dictionary())
->setWordList((new WordList())
->setWords(['RM-GREEN', 'RM-YELLOW', 'RM-ORANGE']));
// The infoTypes of information to mask
$custoMRoomIdinfoType = (new InfoType())
->setName('CUSTOM_ROOM_ID');
$customInfoType = (new CustomInfoType())
->setInfoType($custoMRoomIdinfoType)
->setDictionary($wordList);
// Create the configuration object
$inspectConfig = (new InspectConfig())
->setCustomInfoTypes([$customInfoType]);
// Create the information transform configuration objects
$primitiveTransformation = (new PrimitiveTransformation())
->setReplaceWithInfoTypeConfig(new ReplaceWithInfoTypeConfig());
$infoTypeTransformation = (new InfoTypeTransformation())
->setPrimitiveTransformation($primitiveTransformation)
->setInfoTypes([$custoMRoomIdinfoType]);
$infoTypeTransformations = (new InfoTypeTransformations())
->setTransformations([$infoTypeTransformation]);
// Create the deidentification configuration object
$deidentifyConfig = (new DeidentifyConfig())
->setInfoTypeTransformations($infoTypeTransformations);
// Run request
$deidentifyContentRequest = (new DeidentifyContentRequest())
->setParent($parent)
->setDeidentifyConfig($deidentifyConfig)
->setItem($content)
->setInspectConfig($inspectConfig);
$response = $dlp->deidentifyContent($deidentifyContentRequest);
// Print the results
printf('Deidentified content: %s', $response->getItem()->getValue());
}
Python
To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .
To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .
import
google.cloud.dlp
def
deidentify_with_simple_word_list
(
project
:
str
,
input_str
:
str
,
custom_info_type_name
:
str
,
word_list
:
list
[
str
],
)
-
> None
:
"""Uses the Data Loss Prevention API to de-identify sensitive data in a
string by matching against custom word list.
Args:
project: The Google Cloud project id to use as a parent resource.
input_str: The string to deidentify (will be treated as text).
custom_info_type_name: The name of the custom info type to use.
word_list: The list of strings to match against.
"""
# Instantiate a client.
dlp
=
google
.
cloud
.
dlp_v2
.
DlpServiceClient
()
# Prepare custom_info_types by parsing word lists
word_list
=
{
"words"
:
word_list
}
custom_info_types
=
[
{
"info_type"
:
{
"name"
:
custom_info_type_name
},
"dictionary"
:
{
"word_list"
:
word_list
},
}
]
# Construct the configuration dictionary
inspect_config
=
{
"custom_info_types"
:
custom_info_types
,
}
# Construct deidentify configuration dictionary
deidentify_config
=
{
"info_type_transformations"
:
{
"transformations"
:
[
{
"primitive_transformation"
:
{
"replace_with_info_type_config"
:
{}}}
]
}
}
# Construct the `item`.
item
=
{
"value"
:
input_str
}
# Convert the project id into a full resource id.
parent
=
f
"projects/
{
project
}
/locations/global"
# Call the API
response
=
dlp
.
deidentify_content
(
request
=
{
"parent"
:
parent
,
"deidentify_config"
:
deidentify_config
,
"inspect_config"
:
inspect_config
,
"item"
:
item
,
}
)
print
(
f
"De-identified Content:
{
response
.
item
.
value
}
"
)
What's next
To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser .
