build: Eliminate most Hadoop dependencies

This change eliminates all Hadoop dependencies that are not necessary
for Parquet to work correctly. As a result, the number of dependencies
should now be greatly reduced, which in turn leads to less artifacts
that need to be retrieved at build time.

5 files changed, 16 insertions, 21 deletions

diff --git a/gradle/libs.versions.toml b/gradle/libs.versions.toml
index 4faa0476..22f713f6 100644
--- a/gradle/libs.versions.toml
+++ b/gradle/libs.versions.toml
@@ -46,6 +46,5 @@ kotlinx-benchmark-runtime-jvm = { module = "org.jetbrains.kotlinx:kotlinx-benchm
 # Other
 mongodb = { module = "org.mongodb:mongodb-driver-sync", version = "4.2.3" }
 classgraph = { module = "io.github.classgraph:classgraph", version = "4.8.105" }
-hadoop-client = { module = "org.apache.hadoop:hadoop-client", version.ref = "hadoop" }
 hadoop-common = { module = "org.apache.hadoop:hadoop-common", version.ref = "hadoop" }
 hadoop-mapreduce-client-core = { module = "org.apache.hadoop:hadoop-mapreduce-client-core", version.ref = "hadoop" }
diff --git a/opendc-experiments/opendc-experiments-capelin/build.gradle.kts b/opendc-experiments/opendc-experiments-capelin/build.gradle.kts
index 0dade513..324cae3e 100644
--- a/opendc-experiments/opendc-experiments-capelin/build.gradle.kts
+++ b/opendc-experiments/opendc-experiments-capelin/build.gradle.kts
@@ -44,10 +44,5 @@ dependencies {
     implementation(libs.clikt)
 
     implementation(libs.parquet)
-    implementation(libs.hadoop.client) {
-        exclude(group = "org.slf4j", module = "slf4j-log4j12")
-        exclude(group = "log4j")
-    }
-
     testImplementation(libs.log4j.slf4j)
 }
diff --git a/opendc-experiments/opendc-experiments-serverless20/build.gradle.kts b/opendc-experiments/opendc-experiments-serverless20/build.gradle.kts
index 88479765..7d68cb3a 100644
--- a/opendc-experiments/opendc-experiments-serverless20/build.gradle.kts
+++ b/opendc-experiments/opendc-experiments-serverless20/build.gradle.kts
@@ -37,10 +37,4 @@ dependencies {
     implementation(projects.opendcTelemetry.opendcTelemetrySdk)
     implementation(libs.kotlin.logging)
     implementation(libs.config)
-
-    implementation(libs.parquet)
-    implementation(libs.hadoop.client) {
-        exclude(group = "org.slf4j", module = "slf4j-log4j12")
-        exclude(group = "log4j")
-    }
 }
diff --git a/opendc-experiments/opendc-experiments-tf20/build.gradle.kts b/opendc-experiments/opendc-experiments-tf20/build.gradle.kts
index 64483bd4..b088045b 100644
--- a/opendc-experiments/opendc-experiments-tf20/build.gradle.kts
+++ b/opendc-experiments/opendc-experiments-tf20/build.gradle.kts
@@ -38,9 +38,4 @@ dependencies {
     implementation(projects.opendcUtils)
 
     implementation(libs.kotlin.logging)
-    implementation(libs.parquet)
-    implementation(libs.hadoop.client) {
-        exclude(group = "org.slf4j", module = "slf4j-log4j12")
-        exclude(group = "log4j")
-    }
 }
diff --git a/opendc-format/build.gradle.kts b/opendc-format/build.gradle.kts
index d3c1a59a..e19e0ec8 100644
--- a/opendc-format/build.gradle.kts
+++ b/opendc-format/build.gradle.kts
@@ -40,16 +40,28 @@ dependencies {
     }
     implementation(kotlin("reflect"))
 
+    /* This configuration is necessary for a slim dependency on Apache Parquet */
     implementation(libs.parquet) {
         exclude(group = "org.apache.hadoop")
     }
-    implementation(libs.hadoop.common) {
+    runtimeOnly(libs.hadoop.common) {
         exclude(group = "org.slf4j", module = "slf4j-log4j12")
         exclude(group = "log4j")
+        exclude(group = "org.apache.hadoop")
+        exclude(group = "org.apache.curator")
+        exclude(group = "org.apache.zookeeper")
+        exclude(group = "org.apache.kerby")
+        exclude(group = "org.apache.httpcomponents")
+        exclude(group = "org.apache.htrace")
+        exclude(group = "commons-cli")
+        exclude(group = "javax.servlet")
+        exclude(group = "org.eclipse.jetty")
+        exclude(group = "com.sun.jersey")
+        exclude(group = "com.jcraft")
+        exclude(group = "dnsjava")
     }
-    implementation(libs.hadoop.mapreduce.client.core) {
-        exclude(group = "org.slf4j", module = "slf4j-log4j12")
-        exclude(group = "log4j")
+    runtimeOnly(libs.hadoop.mapreduce.client.core) {
+        isTransitive = false
     }
 
     testRuntimeOnly(libs.slf4j.simple)