From bd378b118a0123c563671958d90a79e4471e0f62 Mon Sep 17 00:00:00 2001
From: "David E. Wheeler" <david.wheeler@tembo.io>
Date: Wed, 22 Jan 2025 18:20:29 -0500
Subject: [PATCH] Add tembo_parquet_s3_fdw.git to Analytics (#81)

In order to the data warehouse stack into Analytics, add Tembo's fork of
`tembo_parquet_s3_fdw` to the Analytics stack as required by support
pg_tier. Build the extension in its on `FROM` target and just copy its
files, to avoid installing unnecessary dependencies.

Exclude Postgres 17 from the build, since `parquet_s3_fdw` doesn't
support it yet, and the Analytics stack depends on on Hydra columnar
anyway, and it doesn't support Postgres 17, either.

Also remove pg_duckdb, as it is now available as a Trunk extension.
---
 .github/workflows/build_tembo_pg_slim.yaml |  7 +++
 analytics-cnpg/Dockerfile                  | 52 ++++++++++++++--------
 2 files changed, 40 insertions(+), 19 deletions(-)

diff --git a/.github/workflows/build_tembo_pg_slim.yaml b/.github/workflows/build_tembo_pg_slim.yaml
index b2b5b26..c6a2b99 100644
--- a/.github/workflows/build_tembo_pg_slim.yaml
+++ b/.github/workflows/build_tembo_pg_slim.yaml
@@ -388,7 +388,9 @@ jobs:
       CONTAINER_NAME: "analytics-cnpg"
     steps:
       - uses: actions/checkout@v4
+        if: ${{ matrix.pg_version != '17' }}
       - name: Build Docker images based on conditions
+        if: ${{ matrix.pg_version != '17' }}
         run: |
           if [[ "${{ matrix.pg_version }}" == "14" || "${{ matrix.pg_version }}" == "15" ]]; then
             echo "Skipping Analytics build for Postgres 14 or 15"
@@ -398,12 +400,14 @@ jobs:
           docker build ./$CONTAINER_NAME --build-arg PG_VERSION=${{ matrix.pg_version }} --build-arg TAG=${{ needs.pre-build.outputs.short_sha }} -t $IMAGE_NAME
         shell: bash
       - name: Login to Tembo Quay
+        if: ${{ matrix.pg_version != '17' }}
         uses: docker/login-action@v2
         with:
           registry: ${{ secrets.QUAY_REPOSITORY }}
           username: ${{ secrets.QUAY_USER_TEMBO }}
           password: ${{ secrets.QUAY_PASSWORD_TEMBO }}
       - name: Push to Quay
+        if: ${{ matrix.pg_version != '17' }}
         shell: bash
         run: |
           if [[ "${{ matrix.pg_version }}" == "14" || "${{ matrix.pg_version }}" == "15" ]]; then
@@ -418,14 +422,17 @@ jobs:
             docker push ${{ secrets.QUAY_REPOSITORY }}/$IMAGE_NAME-$tag
           done
       - name: Configure AWS credentials for ECR
+        if: ${{ matrix.pg_version != '17' }}
         uses: aws-actions/configure-aws-credentials@v4
         with:
           role-to-assume: ${{ secrets.GHA_IAM_ROLE }}
           role-session-name: images-gha-docker-build-and-push
           aws-region: "us-east-1"
       - name: Install awscli
+        if: ${{ matrix.pg_version != '17' }}
         uses: unfor19/install-aws-cli-action@v1
       - name: Push to ECR
+        if: ${{ matrix.pg_version != '17' }}
         shell: bash
         run: |
           if [[ "${{ matrix.pg_version }}" == "14" || "${{ matrix.pg_version }}" == "15" ]]; then
diff --git a/analytics-cnpg/Dockerfile b/analytics-cnpg/Dockerfile
index ff10288..ddedc61 100644
--- a/analytics-cnpg/Dockerfile
+++ b/analytics-cnpg/Dockerfile
@@ -1,36 +1,50 @@
 ARG PG_VERSION=16
-ARG TAG=c19d507
+ARG TAG=86080de
 
-FROM quay.io/tembo/standard-cnpg:${PG_VERSION}-${TAG}
+FROM quay.io/tembo/standard-cnpg:${PG_VERSION}-${TAG} AS build
 USER root
-
-WORKDIR /
+WORKDIR /work
 
 # Install build dependencies for parquet_s3_fdw and its dependent libraries
 RUN apt-get update && apt-get install -y \
-    git \
-    g++ \
+    automake \
+    bison \
+    build-essential \
+    ccache \
     cmake \
-    ninja-build \
+    flex \
+    git \
+    libboost-all-dev \
+    libcurl4-openssl-dev \
+    libevent-dev \
+    libprotobuf-dev \
+    libprotoc-dev \
+    libreadline-dev \
     libssl-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Clone and build parquet_s3_fdw
-RUN git clone https://github.com/duckdb/duckdb && \
-    cd duckdb && \
-    GEN=ninja make
-
-RUN git clone https://github.com/duckdb/pg_duckdb.git && \
-    cd pg_duckdb && \
-    make install
+    libtool \
+    libxml2-dev \
+    libxml2-utils \
+    libxslt-dev \
+    pkg-config \
+    protobuf-compiler \
+    xsltproc \
+    zlib1g-dev
+
+# Clone and build Tembo's fork of parquet_s3_fdw (required for pg_tier).
+RUN git clone https://github.com/tembo-io/tembo_parquet_s3_fdw.git \
+    && (cd tembo_parquet_s3_fdw && git checkout v1.1.4) \
+    && make -C tembo_parquet_s3_fdw USE_PGXS=1 install DESTDIR="$PWD/target"
+
+# Copy the files to the final image.
+FROM quay.io/tembo/standard-cnpg:${PG_VERSION}-${TAG}
+USER root
+COPY --from=build /work/target/./ /
 
 # cache all extensions
 RUN set -eux; \
       cp -r $(pg_config --pkglibdir)/* /tmp/pg_pkglibdir; \
       cp -r $(pg_config --sharedir)/* /tmp/pg_sharedir;
 
-ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
-
 # Revert the postgres user to id 26
 RUN usermod -u 26 postgres
 USER 26