Feature/#168 redaction ruleset

examples/redaction-ruleset-project/.gitignore

@@ -0,0 +1,6 @@
+/bin
+.classpath
+.project
+/build
+.gradle
+.settings

examples/redaction-ruleset-project/README.md

@@ -0,0 +1,15 @@
+This project shows an example of how MarkLogic 9 Redaction Rulesets can be loaded into a schemas
+database from src/main/ml-schemas (the default path - this can be overridden via 
+mlSchemasPath). 
+
+Note that in order for this to work, the content-database.json file must specify the schema
+database that it's associated with. And in most cases, you'll want your own schemas database - not the default Schemas one - so schemas-database.json can be used to create own with a name based on mlAppName.
+
+Within each folder containing one or more Redaction Rulesets, you must provide a **collections.properties** and (optionally) a **permissions.properties** file.
+These files contain the definitions for the applicable collections to be applied to the rulesets as well as the document permissions (if included).
+
+***Note***: Rulesets must have a .json or .xml file extension.
+
+See [Specifying collections and permissions](https://github.com/marklogic-community/ml-javaclient-util/wiki/Loading-files#specifying-collections-and-permissions) for information on how to apply the collections and permission when the rulesets are loaded
+
+See [Redacting Document Content](http://docs.marklogic.com/guide/app-dev/redaction) for more information on redacting content

examples/redaction-ruleset-project/build.gradle

@@ -0,0 +1,87 @@
+buildscript {
+	repositories {
+		jcenter()
+		// Needed for mlcp dependency: XCC
+		maven { url "http://developer.marklogic.com/maven2/" }
+	}
+	dependencies {
+		classpath "com.marklogic:marklogic-contentpump:9.0.3"
+		classpath "com.marklogic:ml-gradle:3.0.0"
+	}
+}
+
+apply plugin: "com.marklogic.ml-gradle"
+
+repositories {
+	jcenter()
+	// Needed for mlcp dependency
+	maven { url "http://developer.marklogic.com/maven2/" }
+	maven { url "http://repository.cloudera.com/artifactory/cloudera-repos/" }
+}
+
+configurations {
+	mlcp {
+		resolutionStrategy {
+			force "xml-apis:xml-apis:1.4.01"
+		}
+	}
+}
+
+
+dependencies {
+	mlcp "com.marklogic:mlcp:9.0.3"
+	mlcp files("lib")
+}
+
+/***************************************************************
+					Optional tasks to test redaction of data
+***************************************************************/
+
+/*
+* The import task below is an example of using the built-in MLCP Task in ml-gradle and will import sample JSON
+* documents to the specified content database while applying the applicable collections to the content so that
+* the redaction rules can be applied
+* */
+task importSampleRedactionData(type: com.marklogic.gradle.task.MlcpTask) {
+	description = "Example of using mlcp and MlcpTask to import documents to test redaction rules"
+	classpath = configurations.mlcp
+	command = "IMPORT"
+	database = mlAppConfig.contentDatabaseName
+	input_file_path = "data/import"
+	output_collections = "security-rules,pii-rules,email-rules"
+	output_permissions = "rest-reader,read,rest-writer,update"
+	output_uri_replace = ".*import,'/import'"
+	logOutputUri = "/redaction.txt"
+}
+
+
+/*
+* The export task below shows an example of using JavaExec inside Gradle to invoke MLCP to export the documents.
+* This task, while a useful example, must be invoked this way because the built-in MLCP task does not yet recognize
+* the "redaction" option being passed. This will be addressed in a future release.
+* Exported documents will be within this project folder under /data/export
+* */
+task exportSampleRedactionData(type: JavaExec) {
+	classpath = configurations.mlcp
+	main = 'com.marklogic.contentpump.ContentPump'
+
+	args = [
+		"EXPORT",
+		"-host", "${mlHost}",
+		"-port", "8130",
+		"-username", "${mlUsername}",
+		"-password", "${mlPassword}",
+		"-database", mlAppConfig.contentDatabaseName,
+		"-output_file_path", "data/export",
+		"-collection_filter", "security-rules",
+		"-redaction", "security-rules"]
+	/*
+	* Applying "security-rules" as the redaction collection will redact both email and SSN fields in the documents
+	* You may also redact just the email or ths SSN fields individually by applying only those specific collections
+	* i.e. "pii-rules" OR "email-rules"
+
+ */
+
+}
+
+

examples/redaction-ruleset-project/gradle.properties

@@ -0,0 +1,5 @@
+mlHost=localhost
+mlAppName=redaction-project
+mlRestPort=8130
+mlUsername=admin
+mlPassword=admin

examples/redaction-ruleset-project/lib/log4j.properties

@@ -0,0 +1,8 @@
+# Root logger option
+log4j.rootLogger=INFO, stdout
+
+# Direct log messages to stdout
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.Target=System.out
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p %c{1}:%L - %m%n

examples/redaction-ruleset-project/src/main/ml-config/databases/content-database.json

@@ -0,0 +1,4 @@
+{
+  "database-name": "%%DATABASE%%",
+  "schema-database": "%%SCHEMAS_DATABASE%%"
+}

examples/redaction-ruleset-project/src/main/ml-config/databases/schemas-database.json

@@ -0,0 +1,3 @@
+{
+  "database-name": "%%SCHEMAS_DATABASE%%"
+}

examples/redaction-ruleset-project/src/main/ml-schemas/redactionRules/collections.properties

@@ -0,0 +1,5 @@
+#Add one or more collections to add the ruleset to (comma separated)
+# Example: file.json=collection1,collection2
+
+ssn.json=security-rules,pii-rules
+email.json=security-rules,email-rules

examples/redaction-ruleset-project/src/main/ml-schemas/redactionRules/email.json

@@ -0,0 +1,12 @@
+{
+	"rule": {
+		"description": "hide email addresses",
+		"path": "//email",
+		"method": {
+			"function": "redact-email"
+		},
+		"options": {
+			"pattern": "partial"
+		}
+	}
+}

examples/redaction-ruleset-project/src/main/ml-schemas/redactionRules/ssn.json

@@ -0,0 +1,12 @@
+{
+	"rule": {
+		"description": "hide SSNs",
+		"path": "//ssn",
+		"method": {
+			"function": "redact-us-ssn"
+		},
+		"options": {
+			"pattern": "partial"
+		}
+	}
+}