feat: add SHA256-HMAC for use in build-in pseudonym generator (#324)

4 files changed, 58 insertions, 3 deletions

diff --git a/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfigProperties.kt b/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfigProperties.kt
index fb93618..f0766a4 100644
--- a/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfigProperties.kt
+++ b/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfigProperties.kt
@@ -41,6 +41,7 @@ data class AppConfigProperties(
 data class PseudonymizeConfigProperties(
     var generator: PseudonymGenerator = PseudonymGenerator.BUILDIN,
     val prefix: String = "UNKNOWN",
+    val hmacKey: String? = null,
 ) {
     companion object {
         const val NAME = "app.pseudonymize"
diff --git a/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfiguration.kt b/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfiguration.kt
index d780642..54f4c6f 100644
--- a/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfiguration.kt
+++ b/src/main/kotlin/dev/dnpm/etl/processor/config/AppConfiguration.kt
@@ -155,7 +155,11 @@ class AppConfiguration {
         matchIfMissing = true,
     )
     @Bean
-    fun buildinPseudonymGenerator(): Generator {
+    fun buildinPseudonymGenerator(pseudonymizeConfigProperties: PseudonymizeConfigProperties): Generator {
+        if (null != pseudonymizeConfigProperties.hmacKey) {
+            logger.info("Selected 'BUILDIN Pseudonym Generator' using HMAC")
+            return AnonymizingHmacGenerator(pseudonymizeConfigProperties)
+        }
         logger.info("Selected 'BUILDIN Pseudonym Generator'")
         return AnonymizingGenerator()
     }
diff --git a/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingGenerator.kt b/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingGenerator.kt
index b3c80e2..5e97568 100644
--- a/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingGenerator.kt
+++ b/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingGenerator.kt
@@ -25,8 +25,6 @@ import org.apache.commons.codec.digest.DigestUtils
 import java.security.SecureRandom
 
 class AnonymizingGenerator : Generator {
-    companion object
-
     fun getSecureRandom(): SecureRandom = SecureRandom()
 
     override fun generate(id: String): String = Base32().encodeAsString(DigestUtils.sha256(id)).substring(0..41).lowercase()
diff --git a/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingHmacGenerator.kt b/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingHmacGenerator.kt
new file mode 100644
index 0000000..646f6d3
--- /dev/null
+++ b/src/main/kotlin/dev/dnpm/etl/processor/pseudonym/AnonymizingHmacGenerator.kt
@@ -0,0 +1,52 @@
+/*
+ * This file is part of ETL-Processor
+ *
+ * Copyright (c) 2023       Comprehensive Cancer Center Mainfranken
+ * Copyright (c) 2023-2026  Paul-Christian Volkmer
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+package dev.dnpm.etl.processor.pseudonym
+
+import dev.dnpm.etl.processor.config.AppConfigProperties
+import dev.dnpm.etl.processor.config.PseudonymizeConfigProperties
+import org.apache.commons.codec.binary.Base32
+import org.apache.commons.codec.digest.DigestUtils
+import org.apache.commons.codec.digest.HmacAlgorithms
+import org.apache.commons.codec.digest.HmacUtils
+import java.security.SecureRandom
+
+/**
+ * Variant of AnonymizingGenerator that uses app.pseudonymize.prefix as HMAC-SHA256 key
+ */
+class AnonymizingHmacGenerator(
+    private val pseudonymizeConfigProperties: PseudonymizeConfigProperties,
+) : Generator {
+    fun getSecureRandom(): SecureRandom = SecureRandom()
+
+    override fun generate(id: String): String =
+        Base32()
+            .encodeAsString(HmacUtils(HmacAlgorithms.HMAC_SHA_256, pseudonymizeConfigProperties.hmacKey).hmac(id))
+            .substring(0..41)
+            .lowercase()
+
+    @OptIn(ExperimentalStdlibApi::class)
+    override fun generateGenomDeTan(id: String): String {
+        val bytes = ByteArray(64 / 2)
+        getSecureRandom().nextBytes(bytes)
+
+        return bytes.joinToString("") { "%02x".format(it) }
+    }
+}