From 71ced9120a9a6c8e27dd14c265875dd391441965 Mon Sep 17 00:00:00 2001
From: Logan Riggs <logan.riggs@dremio.com>
Date: Mon, 9 Mar 2026 15:36:56 -0700
Subject: [PATCH 1/5] GH-1061 Add codegen classifier jar for arrow-vector.

---
 vector/pom.xml | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/vector/pom.xml b/vector/pom.xml
index b24f37d5f..6a349db97 100644
--- a/vector/pom.xml
+++ b/vector/pom.xml
@@ -194,6 +194,28 @@ under the License.
           </execution>
         </executions>
       </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-jar-plugin</artifactId>
+        <executions>
+          <execution>
+            <id>codegen-jar</id>
+            <goals>
+              <goal>jar</goal>
+            </goals>
+            <phase>package</phase>
+            <configuration>
+              <classifier>codegen</classifier>
+              <classesDirectory>${basedir}/src/main/codegen</classesDirectory>
+              <includes>
+                <include>**/*.tdd</include>
+                <include>**/*.fmpp</include>
+                <include>**/*.ftl</include>
+              </includes>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
 

From 8f7c595d9c4a7c510e81c5c92c1272a2f62ca56f Mon Sep 17 00:00:00 2001
From: Logan Riggs <logan.riggs@dremio.com>
Date: Mon, 9 Mar 2026 18:19:06 -0700
Subject: [PATCH 2/5] Added comment about the usefullness of the codegen files.

---
 vector/src/main/codegen/config.fmpp | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/vector/src/main/codegen/config.fmpp b/vector/src/main/codegen/config.fmpp
index ef5a5072a..d2473ea96 100644
--- a/vector/src/main/codegen/config.fmpp
+++ b/vector/src/main/codegen/config.fmpp
@@ -13,6 +13,14 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+# Arrow's type system has many types, and projects building operations across Arrow data
+# (comparisons, casts, aggregations) benefit from generating type-specialized code rather
+# than hand-writing implementations for each type.
+
+# The TDD files provide a machine-readable definition of Arrow's types that enables this. 
+# Including them in the distribution allows downstream projects to generate code that 
+# stays in sync as Arrow's type system evolves.
+
 data: {
     # TODO:  Rename to ~valueVectorModesAndTypes for clarity.
     vv:                       tdd(../data/ValueVectorTypes.tdd),

From cc77c5ebbd4d18b81025e19eaabb7b4bfd2cac30 Mon Sep 17 00:00:00 2001
From: Logan Riggs <logan.riggs@dremio.com>
Date: Tue, 10 Mar 2026 10:14:42 -0700
Subject: [PATCH 3/5] Revert "Added comment about the usefullness of the
 codegen files."

This reverts commit 8f7c595d9c4a7c510e81c5c92c1272a2f62ca56f.
---
 vector/src/main/codegen/config.fmpp | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/vector/src/main/codegen/config.fmpp b/vector/src/main/codegen/config.fmpp
index d2473ea96..ef5a5072a 100644
--- a/vector/src/main/codegen/config.fmpp
+++ b/vector/src/main/codegen/config.fmpp
@@ -13,14 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Arrow's type system has many types, and projects building operations across Arrow data
-# (comparisons, casts, aggregations) benefit from generating type-specialized code rather
-# than hand-writing implementations for each type.
-
-# The TDD files provide a machine-readable definition of Arrow's types that enables this. 
-# Including them in the distribution allows downstream projects to generate code that 
-# stays in sync as Arrow's type system evolves.
-
 data: {
     # TODO:  Rename to ~valueVectorModesAndTypes for clarity.
     vv:                       tdd(../data/ValueVectorTypes.tdd),

From 89658c74cdc184e2bdf0673a5343438d1c56bb8d Mon Sep 17 00:00:00 2001
From: Logan Riggs <logan.riggs@dremio.com>
Date: Tue, 10 Mar 2026 10:15:07 -0700
Subject: [PATCH 4/5] Documentation

---
 docs/source/overview.rst | 3 +++
 vector/pom.xml           | 6 ++++++
 2 files changed, 9 insertions(+)

diff --git a/docs/source/overview.rst b/docs/source/overview.rst
index be579c149..118805411 100644
--- a/docs/source/overview.rst
+++ b/docs/source/overview.rst
@@ -45,6 +45,9 @@ but some modules are JNI bindings to the C++ library.
    * - arrow-vector
      - An off-heap reference implementation for Arrow columnar data format.
      - Native
+   * - arrow-vector-codegen
+     - Template files for Arrow datatypes suitable for code generation.
+     - Native
    * - arrow-tools
      - Java applications for working with Arrow ValueVectors.
      - Native
diff --git a/vector/pom.xml b/vector/pom.xml
index 6a349db97..6391aafc5 100644
--- a/vector/pom.xml
+++ b/vector/pom.xml
@@ -205,6 +205,12 @@ under the License.
             </goals>
             <phase>package</phase>
             <configuration>
+              <!-- Arrow's type system has many types, and projects building operations across Arrow data
+              (comparisons, casts, aggregations) benefit from generating type-specialized code rather
+              than hand-writing implementations for each type.
+              The TDD files provide a machine-readable definition of Arrow's types that enables this.
+              Including them in the distribution allows downstream projects to generate code that 
+              stays in sync as Arrow's type system evolves.-->
               <classifier>codegen</classifier>
               <classesDirectory>${basedir}/src/main/codegen</classesDirectory>
               <includes>

From fd0ec69bd2dc828b6bde6aec3eeab50b4da62e7d Mon Sep 17 00:00:00 2001
From: Logan Riggs <logan.riggs@dremio.com>
Date: Tue, 10 Mar 2026 10:48:47 -0700
Subject: [PATCH 5/5] Remove a space

---
 vector/pom.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vector/pom.xml b/vector/pom.xml
index 6391aafc5..f46bd0e7b 100644
--- a/vector/pom.xml
+++ b/vector/pom.xml
@@ -209,7 +209,7 @@ under the License.
               (comparisons, casts, aggregations) benefit from generating type-specialized code rather
               than hand-writing implementations for each type.
               The TDD files provide a machine-readable definition of Arrow's types that enables this.
-              Including them in the distribution allows downstream projects to generate code that 
+              Including them in the distribution allows downstream projects to generate code that
               stays in sync as Arrow's type system evolves.-->
               <classifier>codegen</classifier>
               <classesDirectory>${basedir}/src/main/codegen</classesDirectory>