Build PostgreSQL from source for pg_lake internal headers

pg_lake requires PostgreSQL internal headers (like server/rewrite/rewriteManip.h)
that are not available in pre-built packages. This follows pg_lake's official
Dockerfile approach of building PostgreSQL from source.

Changes:
- Use debian:bookworm-slim as base instead of postgres:17-bookworm
- Build PostgreSQL 17.2 from source with required configure flags
- Include simple entrypoint script for database initialization
- Add all required runtime dependencies

Author: pyramation

Dockerfile.pg_lake

@@ -1,89 +1,118 @@
 # PostgreSQL image with pgvector, PostGIS, pg_textsearch, pgsodium, and pg_lake
-# Uses Debian base for pg_lake compatibility (requires full PostgreSQL server headers)
+# Uses Debian base with PostgreSQL built from source (required for pg_lake internal headers)
 # Multi-stage build - all toolchains discarded, only artifacts kept
 
-ARG PG_VERSION=17
+ARG PG_VERSION=17.2
 ARG PGVECTOR_VERSION=0.8.0
 ARG POSTGIS_VERSION=3.5.1
 ARG PG_TEXTSEARCH_VERSION=0.2.0
 ARG PGSODIUM_VERSION=3.1.9
 ARG PG_LAKE_VERSION=main
 
 #############################################
-# Stage 1: Build extensions
+# Stage 1: Build PostgreSQL and extensions
 #############################################
-FROM postgres:${PG_VERSION}-bookworm AS builder
+FROM debian:bookworm-slim AS builder
 
+ARG PG_VERSION
 ARG PGVECTOR_VERSION
 ARG POSTGIS_VERSION
 ARG PG_TEXTSEARCH_VERSION
 ARG PGSODIUM_VERSION
 ARG PG_LAKE_VERSION
 
+# Install build dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     git \
     build-essential \
-    postgresql-server-dev-17 \
-    llvm-16-dev \
-    clang-16 \
     curl \
     ca-certificates \
+    wget \
+    # PostgreSQL build dependencies
+    libreadline-dev \
+    zlib1g-dev \
+    libssl-dev \
+    libxml2-dev \
+    libxslt1-dev \
+    libicu-dev \
+    uuid-dev \
+    liblz4-dev \
+    flex \
+    bison \
+    pkg-config \
     # PostGIS dependencies
     libgeos-dev \
     libproj-dev \
     libgdal-dev \
     libjson-c-dev \
     libprotobuf-c-dev \
     protobuf-c-compiler \
-    libxml2-dev \
     libpcre2-dev \
-    libsodium-dev \
-    # PostGIS build tools
     perl \
-    flex \
-    bison \
+    # pgsodium dependencies
+    libsodium-dev \
     # pg_lake dependencies
     cmake \
     ninja-build \
-    pkg-config \
-    libssl-dev \
     libsnappy-dev \
     libjansson-dev \
-    liblz4-dev \
     liblzma-dev \
     libzstd-dev \
-    libpq-dev \
     libkrb5-dev \
+    libcurl4-openssl-dev \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /build
 
+# Build PostgreSQL from source (required for pg_lake internal headers)
+ENV PGBASEDIR=/usr/local/pgsql
+RUN wget https://ftp.postgresql.org/pub/source/v${PG_VERSION}/postgresql-${PG_VERSION}.tar.gz && \
+    tar -xzf postgresql-${PG_VERSION}.tar.gz && \
+    cd postgresql-${PG_VERSION} && \
+    ./configure --prefix=${PGBASEDIR} \
+        --with-openssl \
+        --with-libxml \
+        --with-libxslt \
+        --with-icu \
+        --with-uuid=ossp \
+        --with-lz4 && \
+    make -j$(nproc) && \
+    make install && \
+    cd contrib && make -j$(nproc) install && \
+    cd ../.. && rm -rf postgresql-${PG_VERSION}*
+
+# Set PATH for pg_config
+ENV PATH="${PGBASEDIR}/bin:${PATH}"
+
 # pgvector
 RUN git clone --branch v${PGVECTOR_VERSION} --depth 1 https://github.com/pgvector/pgvector.git && \
     cd pgvector && \
     make OPTFLAGS="" -j$(nproc) && \
-    make install
+    make install && \
+    cd .. && rm -rf pgvector
 
 # PostGIS (without raster and topology for smaller build)
 RUN curl -L https://download.osgeo.org/postgis/source/postgis-${POSTGIS_VERSION}.tar.gz | tar xz && \
     cd postgis-${POSTGIS_VERSION} && \
-    ./configure --without-raster --without-topology && \
+    ./configure --without-raster --without-topology --with-pgconfig=${PGBASEDIR}/bin/pg_config && \
     make && \
-    make install
+    make install && \
+    cd .. && rm -rf postgis-${POSTGIS_VERSION}
 
 # pg_textsearch (BM25)
 RUN git clone --branch v${PG_TEXTSEARCH_VERSION} --depth 1 https://github.com/timescale/pg_textsearch.git && \
     cd pg_textsearch && \
-    # Fix missing math.h include (upstream bug)
     sed -i '1i #include <math.h>' src/am/build.c && \
     make -j$(nproc) && \
-    make install
+    make install && \
+    cd .. && rm -rf pg_textsearch
 
 # pgsodium
 RUN git clone --branch v${PGSODIUM_VERSION} --depth 1 https://github.com/michelp/pgsodium.git && \
     cd pgsodium && \
     make -j$(nproc) && \
-    make install
+    make install && \
+    cd .. && rm -rf pgsodium
 
 # pg_lake - Postgres with Iceberg and data lake access
 RUN git clone --branch ${PG_LAKE_VERSION} --depth 1 --recurse-submodules https://github.com/Snowflake-Labs/pg_lake.git && \
@@ -102,40 +131,101 @@ RUN git clone --branch ${PG_LAKE_VERSION} --depth 1 --recurse-submodules https:/
     make -C pg_lake_copy && make -C pg_lake_copy install && \
     make -C pg_lake_iceberg && make -C pg_lake_iceberg install && \
     make -C pg_lake_table && make -C pg_lake_table install && \
-    make -C pg_lake && make -C pg_lake install
+    make -C pg_lake && make -C pg_lake install && \
+    cd .. && rm -rf pg_lake
 
 #############################################
 # Stage 2: Final runtime image
 #############################################
-FROM postgres:${PG_VERSION}-bookworm
+FROM debian:bookworm-slim
 
 # Runtime deps only
 RUN apt-get update && apt-get install -y --no-install-recommends \
+    libreadline8 \
+    zlib1g \
+    libssl3 \
+    libxml2 \
+    libxslt1.1 \
+    libicu72 \
+    libossp-uuid16 \
+    liblz4-1 \
+    # PostGIS runtime
     libgeos-c1v5 \
     libproj25 \
     libgdal32 \
     libjson-c5 \
     libprotobuf-c1 \
-    libxml2 \
     libpcre2-8-0 \
+    # pgsodium runtime
     libsodium23 \
     # pg_lake runtime dependencies
     libsnappy1v5 \
     libjansson4 \
-    liblz4-1 \
     liblzma5 \
     libzstd1 \
-    libpq5 \
-    && rm -rf /var/lib/apt/lists/*
+    libkrb5-3 \
+    libcurl4 \
+    gosu \
+    locales \
+    && rm -rf /var/lib/apt/lists/* \
+    && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
+
+ENV LANG en_US.utf8
+
+# Create postgres user
+RUN groupadd -r postgres --gid=999 && \
+    useradd -r -g postgres --uid=999 --home-dir=/var/lib/postgresql --shell=/bin/bash postgres && \
+    mkdir -p /var/lib/postgresql && \
+    chown -R postgres:postgres /var/lib/postgresql
+
+# Copy PostgreSQL installation from builder
+COPY --from=builder /usr/local/pgsql /usr/local/pgsql
 
-# Copy compiled extensions from builder
-COPY --from=builder /usr/lib/postgresql/17/lib/ /usr/lib/postgresql/17/lib/
-COPY --from=builder /usr/share/postgresql/17/extension/ /usr/share/postgresql/17/extension/
 # Copy avro library for pg_lake
 COPY --from=builder /usr/local/lib/libavro* /usr/local/lib/
 
+# Set up paths and environment
+ENV PATH="/usr/local/pgsql/bin:${PATH}"
+ENV PGDATA=/var/lib/postgresql/data
+ENV LD_LIBRARY_PATH="/usr/local/lib"
+
 # Update library cache
 RUN ldconfig
 
+# Create data directory
+RUN mkdir -p "$PGDATA" && chown -R postgres:postgres "$PGDATA" && chmod 1777 "$PGDATA"
+
+# Create run directory for socket
+RUN mkdir -p /var/run/postgresql && chown -R postgres:postgres /var/run/postgresql && chmod 3777 /var/run/postgresql
+
+VOLUME /var/lib/postgresql/data
+
+EXPOSE 5432
+
+# Simple entrypoint that initializes DB if needed and starts postgres
+COPY --chmod=755 <<'EOF' /usr/local/bin/docker-entrypoint.sh
+#!/bin/bash
+set -e
+
+# If PGDATA is empty, initialize the database
+if [ -z "$(ls -A "$PGDATA" 2>/dev/null)" ]; then
+    gosu postgres initdb --username=postgres --pwfile=<(echo "${POSTGRES_PASSWORD:-postgres}")
+    
+    # Allow connections from anywhere
+    echo "host all all 0.0.0.0/0 md5" >> "$PGDATA/pg_hba.conf"
+    echo "listen_addresses = '*'" >> "$PGDATA/postgresql.conf"
+fi
+
+# If first arg is postgres or not provided, run postgres
+if [ "$1" = 'postgres' ] || [ -z "$1" ]; then
+    exec gosu postgres postgres -D "$PGDATA"
+fi
+
+exec "$@"
+EOF
+
+ENTRYPOINT ["docker-entrypoint.sh"]
+CMD ["postgres"]
+
 LABEL org.opencontainers.image.source="https://github.com/constructive-io/docker"
-LABEL org.opencontainers.image.description="PostgreSQL 17 with pgvector, PostGIS, pg_textsearch, pgsodium, and pg_lake (Debian-based)"
+LABEL org.opencontainers.image.description="PostgreSQL 17 with pgvector, PostGIS, pg_textsearch, pgsodium, and pg_lake (Debian-based, built from source)"