From 0f2f3b3ae09e8f2baf28c7b2c9002ae1117daa92 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Wed, 6 Aug 2025 23:08:47 -0700
Subject: [PATCH 01/11] ubuntu 24.04 scripts

---
 scripts/ubuntu2404/Dockerfile              |  70 ++++++
 scripts/ubuntu2404/install_requirements.sh | 265 +++++++++++++++++++++
 2 files changed, 335 insertions(+)
 create mode 100644 scripts/ubuntu2404/Dockerfile
 create mode 100755 scripts/ubuntu2404/install_requirements.sh

diff --git a/scripts/ubuntu2404/Dockerfile b/scripts/ubuntu2404/Dockerfile
new file mode 100644
index 000000000..e3cab66cc
--- /dev/null
+++ b/scripts/ubuntu2404/Dockerfile
@@ -0,0 +1,70 @@
+# Tuplex ubuntu 24.04 image, holds code in /code directory and allows to build tuplex easily.
+# create with docker build -t tuplex/ubuntu:24.04 .
+# Run with docker run -it tuplex/ubuntu:24.04 bash
+FROM ubuntu:24.04
+LABEL authors="leonhards"
+
+# Versions, environment variables.
+# Needs to be a pyenv supported version: pyenv install --list.
+ENV PYTHON_VERSION=3.13.5
+ENV GITHUB_BRANCH=master
+
+WORKDIR /tmp
+
+# Install python version
+# set the variables as per $(pyenv init -)
+ENV LANG="C.UTF-8" \
+    LC_ALL="C.UTF-8" \
+    PATH="/opt/pyenv/shims:/opt/pyenv/bin:$PATH" \
+    PYENV_ROOT="/opt/pyenv" \
+    PYENV_SHELL="bash"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        build-essential \
+        ca-certificates \
+        curl \
+        git \
+        libbz2-dev \
+        libffi-dev \
+        libncurses5-dev \
+        libncursesw5-dev \
+        libreadline-dev \
+        libsqlite3-dev \
+        liblzma-dev \
+        libssl-dev \
+        make \
+        netbase \
+        pkg-config \
+        tk-dev \
+        wget \
+        xz-utils \
+        zlib1g-dev \
+ && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+
+RUN git clone --single-branch --depth 1 https://github.com/pyenv/pyenv.git $PYENV_ROOT \
+    && pyenv install $PYTHON_VERSION \
+    && pyenv global $PYTHON_VERSION \
+    && find $PYENV_ROOT/versions -type d '(' -name '__pycache__' -o -name 'test' -o -name 'tests' ')' -exec rm -rf '{}' + \
+    && find $PYENV_ROOT/versions -type f '(' -name '*.pyo' -o -name '*.exe' ')' -exec rm -f '{}' + \
+    && rm -rf /tmp/*
+
+
+# --- install requirements ---
+
+ADD install_requirements.sh /tmp/install_requirements.sh
+
+RUN /tmp/install_requirements.sh
+
+# installs tuplex-specific dependencies into /opt
+RUN mkdir -p /opt
+
+# downloads/clones tuplex into /code directory
+RUN mkdir -p /code
+
+RUN rm -rf /tmp/*
+
+WORKDIR /code
+
+# Clone tuplex, and build initial version as well as install in python.
+RUN git clone -b ${GITHUB_BRANCH} --single-branch https://github.com/tuplex/tuplex.git
\ No newline at end of file
diff --git a/scripts/ubuntu2404/install_requirements.sh b/scripts/ubuntu2404/install_requirements.sh
new file mode 100755
index 000000000..107af2aa0
--- /dev/null
+++ b/scripts/ubuntu2404/install_requirements.sh
@@ -0,0 +1,265 @@
+#!/usr/bin/env bash
+# (c) Tuplex team 2017-2023
+# Installs all tuplex dependencies required to build tuplex.
+
+# Variables needed incl. defaults.
+PREFIX=${PREFIX:-/opt}
+WORKDIR=${WORKDIR:-/tmp}
+PYTHON_EXECUTABLE=${PYTHON_EXECUTABLE:-python3}
+CMAKE_VERSION="3.27.5"
+BOOST_VERSION="1.79.0"
+LLVM_VERSION="16.0.6"
+AWSSDK_CPP_VERSION=1.11.524
+ANTLR4_VERSION=4.13.1
+YAML_CPP_VERSION=0.8.0
+AWS_LAMBDA_CPP_VERSION=0.2.10
+PCRE2_VERSION=10.45
+PROTOBUF_VERSION=24.3
+CELERO_VERSION=2.8.3
+CC=gcc
+CXX=g++
+
+CPU_COUNT=$(( 1 * $( egrep '^processor[[:space:]]+:' /proc/cpuinfo | wc -l ) ))
+
+PYTHON_VERSION=$(echo $(python3 --version) | cut -d ' ' -f2)
+PYTHON_MAJMIN_VERSION=${PYTHON_VERSION%.*}
+echo ">> Installing dependencies for Python version ${PYTHON_VERSION}"
+
+function version { echo "$@" | awk -F. '{ printf("%d%03d%03d%03d\n", $1,$2,$3,$4); }'; }
+
+# Start script.
+set -euxo pipefail
+
+# need to run this with root privileges
+if [[ $(id -u) -ne 0 ]]; then
+  echo "Please run this script with root privileges"
+  exit 1
+fi
+
+# --- helper functions ---
+# Parse the major, minor and patch versions.
+# You use it like this:
+#    semver="3.4.5+xyz"
+#    a=($(parse_semver "$semver"))
+#    major=${a[0]}
+#    minor=${a[1]}
+#    patch=${a[2]}
+#    printf "%-32s %4d %4d %4d\n" "$semver" $major $minor $patch
+function parse_semver() {
+    local token="$1"
+    local major=0
+    local minor=0
+    local patch=0
+
+    if egrep '^[0-9]+\.[0-9]+\.[0-9]+' <<<"$token" >/dev/null 2>&1 ; then
+        # It has the correct syntax.
+        local n=${token//[!0-9]/ }
+        local a=(${n//\./ })
+        major=${a[0]}
+        minor=${a[1]}
+        patch=${a[2]}
+    fi
+
+    echo "$major $minor $patch"
+}
+
+function install_llvm {
+   LLVM_VERSION=$1
+   LLVM_MAJOR_VERSION=`echo ${LLVM_VERSION} | cut -d. -f1`
+   LLVM_MINOR_VERSION=`echo ${LLVM_VERSION} | cut -d. -f2`
+   LLVM_MAJMIN_VERSION="${LLVM_MAJOR_VERSION}.${LLVM_MINOR_VERSION}"
+
+   # list of targets available to build: AArch64;AMDGPU;ARM;AVR;BPF;Hexagon;Lanai;LoongArch;Mips;MSP430;NVPTX;PowerPC;RISCV;Sparc;SystemZ;VE;WebAssembly;X86;XCore
+   # in order to cross-compile, should use targets:
+
+
+   echo ">> building LLVM ${LLVM_VERSION}"
+   LLVM_URL=https://github.com/llvm/llvm-project/releases/download/llvmorg-${LLVM_VERSION}/llvm-${LLVM_VERSION}.src.tar.xz
+   CLANG_URL=https://github.com/llvm/llvm-project/releases/download/llvmorg-${LLVM_VERSION}/clang-${LLVM_VERSION}.src.tar.xz
+   # required when LLVM version > 15
+   LLVM_CMAKE_URL=https://github.com/llvm/llvm-project/releases/download/llvmorg-${LLVM_VERSION}/cmake-${LLVM_VERSION}.src.tar.xz
+
+   PYTHON_EXECUTABLE=${PYTHON_EXECUTABLE:-python3}
+   PYTHON_BASENAME="$(basename -- $PYTHON_EXECUTABLE)"
+   PYTHON_VERSION=$(${PYTHON_EXECUTABLE} --version)
+   echo ">> Building dependencies for ${PYTHON_VERSION}"
+
+   echo ">> Downloading prerequisites for llvm ${LLVM_VERSION}}"
+   LLVM_WORKDIR=${WORKDIR}/llvm${LLVM_VERSION}
+   mkdir -p ${LLVM_WORKDIR}
+   pushd "${LLVM_WORKDIR}" || exit 1
+
+   wget ${LLVM_URL} && tar xf llvm-${LLVM_VERSION}.src.tar.xz
+   wget ${CLANG_URL} && tar xf clang-${LLVM_VERSION}.src.tar.xz && mv clang-${LLVM_VERSION}.src llvm-${LLVM_VERSION}.src/../clang
+
+   if (( LLVM_MAJOR_VERSION >= 15 )); then
+      wget ${LLVM_CMAKE_URL} && tar xf cmake-${LLVM_VERSION}.src.tar.xz && mv cmake-${LLVM_VERSION}.src cmake
+   fi
+
+  mkdir -p llvm-${LLVM_VERSION}.src/build && cd llvm-${LLVM_VERSION}.src/build
+
+   cmake -GNinja -DLLVM_ENABLE_RTTI=ON -DLLVM_ENABLE_EH=ON -DLLVM_ENABLE_PROJECTS="clang" -DLLVM_TARGETS_TO_BUILD="X86;AArch64" \
+         -DCMAKE_BUILD_TYPE=Release -DLLVM_INCLUDE_TESTS=OFF -DLLVM_INCLUDE_BENCHMARKS=OFF  \
+         -DCMAKE_INSTALL_PREFIX=/opt/llvm-${LLVM_VERSION} ..
+   ninja install
+  popd
+}
+
+export DEBIAN_FRONTEND=noninteractive
+
+
+
+echo ">> Installing packages into ${PREFIX}"
+mkdir -p $PREFIX && chmod 0755 $PREFIX
+mkdir -p $PREFIX/sbin
+mkdir -p $PREFIX/bin
+mkdir -p $PREFIX/share
+mkdir -p $PREFIX/include
+mkdir -p $PREFIX/lib
+
+echo ">> Files will be downloaded to ${WORKDIR}/tuplex-downloads"
+WORKDIR=$WORKDIR/tuplex-downloads
+mkdir -p $WORKDIR
+
+PYTHON_BASENAME="$(basename -- $PYTHON_EXECUTABLE)"
+PYTHON_VERSION=$(${PYTHON_EXECUTABLE} --version)
+echo ">> Building dependencies for ${PYTHON_VERSION}"
+echo ">> Installing all build dependencies for Tuplex under Ubuntu 22.04"
+
+echo ">> Installing apt dependencies"
+apt update -y
+
+apt-get install -y apt-utils dh-autoreconf libmagic-dev curl libxml2-dev vim build-essential libssl-dev zlib1g-dev libncurses5-dev \
+libncursesw5-dev libreadline-dev libsqlite3-dev libgdbm-dev libdb5.3-dev openssh-client \
+libbz2-dev libexpat1-dev liblzma-dev tk-dev libffi-dev wget git libcurl4-openssl-dev python3-dev python3-pip openjdk-11-jdk ninja-build
+
+ldconfig
+export CC=${CC}
+export CXX=${CXX}
+
+echo ">> Installing recent cmake"
+# fetch recent cmake & install
+URL=https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz
+mkdir -p ${WORKDIR}/cmake && cd ${WORKDIR}/cmake &&
+  curl -sSL $URL -o cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz &&
+  tar -v -zxf cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz &&
+  rm -f cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz &&
+  cd cmake-${CMAKE_VERSION}-linux-x86_64 &&
+  cp -rp bin/* ${PREFIX}/bin/ &&
+  cp -rp share/* ${PREFIX}/share/ &&
+  cd / && rm -rf ${WORKDIR}/cmake
+
+export PATH=$PREFIX/bin:$PATH
+cmake --version
+
+
+echo ">> Installing Boost"
+mkdir -p ${WORKDIR}/boost
+
+# -- Install Boost.
+# create underscored version
+# e.g. 1.79.0 -> 1_79_0
+BOOST_UNDERSCORED_VERSION=$(echo ${BOOST_VERSION} | tr . _)
+
+# build incl. boost python
+cd ${WORKDIR}/boost && curl -L -O https://github.com/boostorg/boost/releases/download/boost-${BOOST_VERSION}/boost-${BOOST_VERSION}-b2-nodocs.tar.gz && tar xf boost-${BOOST_VERSION}-b2-nodocs.tar.gz && cd ${WORKDIR}/boost/boost-${BOOST_VERSION} \
+           && ./bootstrap.sh --with-python=${PYTHON_EXECUTABLE} --prefix=${PREFIX} --with-libraries="thread,iostreams,regex,system,filesystem,python,stacktrace,atomic,chrono,date_time" \
+            && ./b2 cxxflags="-fPIC" link=static -j "$(nproc)" \
+            && ./b2 cxxflags="-fPIC" link=static install && sed -i 's/#if PTHREAD_STACK_MIN > 0/#ifdef PTHREAD_STACK_MIN/g' ${PREFIX}/include/boost/thread/pthread/thread_data.hpp
+
+cd $WORKDIR
+rm -rf ${WORKDIR}/boost
+
+# -- install llvm
+install_llvm $LLVM_VERSION
+
+
+echo ">>> Installing tuplex dependencies."
+# install recent zlib version (1.2.11) fork from cloudflare
+# https://github.com/aws/aws-graviton-getting-started#zlib-on-linux
+LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}
+export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64:$LD_LIBRARY_PATH
+
+# Cloudflare fork is too old
+#mkdir -p $WORKDIR/zlib && cd $WORKDIR && git clone https://github.com/cloudflare/zlib.git && cd zlib && ./configure --prefix=$PREFIX && make -j ${CPU_COUNT} && make install
+
+# note that zlib defines Z_NULL=0 whereas zlib-ng defines it as NULL, patch aws sdk accordingly
+git clone https://github.com/zlib-ng/zlib-ng.git && cd zlib-ng && git checkout tags/2.1.3 && mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_FLAGS="-fPIC" -DZLIB_COMPAT=ON .. && make -j ${CPU_COUNT} && make install
+
+git clone https://github.com/google/googletest.git -b v1.14.0 && cd googletest && mkdir build && cd build && cmake -DBUILD_SHARED_LIBS=ON -DCMAKE_CXX_FLAGS="-fPIC" -DCMAKE_BUILD_TYPE=Release .. && make -j ${CPU_COUNT} && make install
+
+# build snappy as static lib
+git clone https://github.com/google/snappy.git -b 1.1.10 && cd snappy && git submodule update --init && mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF -DCMAKE_CXX_FLAGS="-fPIC" .. && make -j ${CPU_COUNT} && make install
+
+# add github to known hosts
+mkdir -p /root/.ssh/ &&
+  touch /root/.ssh/known_hosts &&
+  ssh-keyscan github.com >> /root/.ssh/known_hosts
+
+
+echo ">> Installing YAMLCPP"
+mkdir -p ${WORKDIR}/yamlcpp && cd ${WORKDIR}/yamlcpp \
+&& git clone https://github.com/jbeder/yaml-cpp.git yaml-cpp \
+&& cd yaml-cpp \
+&& git checkout tags/${YAML_CPP_VERSION} \
+&& mkdir build && cd build \
+&& cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=${PREFIX} -DYAML_CPP_BUILD_TESTS=OFF -DBUILD_SHARED_LIBS=OFF -DCMAKE_CXX_FLAGS="-fPIC" .. \
+&& make -j ${CPU_COUNT} && make install
+
+echo ">> Installing Celero"
+mkdir -p ${WORKDIR}/celero && cd ${WORKDIR}/celero \
+&&  git clone https://github.com/DigitalInBlue/Celero.git celero && cd celero \
+&& git checkout tags/v${CELERO_VERSION} \
+&& mkdir build && cd build \
+&& cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=${PREFIX} -DBUILD_SHARED_LIBS=OFF -DCMAKE_CXX_FLAGS="-fPIC -std=c++11" .. \
+&& make -j ${CPU_COUNT} && make install
+
+echo ">> Installing ANTLR"
+mkdir -p ${WORKDIR}/antlr && cd ${WORKDIR}/antlr \
+&& curl -O https://www.antlr.org/download/antlr-${ANTLR4_VERSION}-complete.jar \
+&& cp antlr-${ANTLR4_VERSION}-complete.jar ${PREFIX}/lib/ \
+&& curl -O https://www.antlr.org/download/antlr4-cpp-runtime-${ANTLR4_VERSION}-source.zip \
+&& unzip antlr4-cpp-runtime-${ANTLR4_VERSION}-source.zip -d antlr4-cpp-runtime \
+&& rm antlr4-cpp-runtime-${ANTLR4_VERSION}-source.zip \
+&& cd antlr4-cpp-runtime \
+&& mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=${PREFIX} .. \
+&& make -j ${CPU_COUNT}&& make install
+
+echo ">> Installing AWS SDK"
+# Note the z-lib patch here.
+mkdir -p ${WORKDIR}/aws && cd ${WORKDIR}/aws \
+&& git clone --recurse-submodules https://github.com/aws/aws-sdk-cpp.git \
+&& cd aws-sdk-cpp && git checkout tags/${AWSSDK_CPP_VERSION} && sed -i 's/int ret = Z_NULL;/int ret = static_cast<int>(Z_NULL);/g' src/aws-cpp-sdk-core/source/client/RequestCompression.cpp && mkdir build && cd build \
+&& cmake -DCMAKE_BUILD_TYPE=Release -DUSE_OPENSSL=ON -DENABLE_TESTING=OFF -DUSE_CRT_HTTP_CLIENT=ON -DENABLE_UNITY_BUILD=ON -DCPP_STANDARD=17 -DBUILD_SHARED_LIBS=OFF -DBUILD_ONLY="s3;s3-crt;core;lambda;transfer" -DCMAKE_INSTALL_PREFIX=${PREFIX} .. \
+&& make -j ${CPU_COUNT} \
+&& make install
+
+# Installing AWS Lambda C++ runtime.
+cd ${WORKDIR}/aws \
+&& git clone https://github.com/awslabs/aws-lambda-cpp.git \
+&& cd aws-lambda-cpp \
+&& git fetch && git fetch --tags \
+&& git checkout v${AWS_LAMBDA_CPP_VERSION} \
+&& mkdir build \
+&& cd build \
+&& cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=${PREFIX} .. \
+&& make -j$(nproc) && make install
+
+echo ">> Installing PCRE2"
+mkdir -p ${WORKDIR}/pcre2 && cd ${WORKDIR}/pcre2 \
+&& curl -LO https://github.com/PhilipHazel/pcre2/releases/download/pcre2-${PCRE2_VERSION}/pcre2-${PCRE2_VERSION}.zip \
+&& unzip pcre2-${PCRE2_VERSION}.zip \
+&& rm pcre2-${PCRE2_VERSION}.zip \
+&& cd pcre2-${PCRE2_VERSION} \
+&& ./configure CFLAGS="-O2 -fPIC" --prefix=${PREFIX} --enable-jit=auto --disable-shared \
+&& make -j$(nproc) && make install
+
+echo ">> Installing protobuf"
+mkdir -p ${WORKDIR}/protobuf && cd ${WORKDIR}/protobuf \
+&& git clone -b v${PROTOBUF_VERSION} https://github.com/protocolbuffers/protobuf.git && cd protobuf && git submodule update --init --recursive && mkdir build && cd build && cmake -DCMAKE_CXX_FLAGS="-fPIC" -DCMAKE_CXX_STANDARD=17 -Dprotobuf_BUILD_TESTS=OFF .. && make -j ${CPU_COUNT} && make install
+
+
+# delete workdir (downloads dir) to clean up space
+rm -rf ${WORKDIR}
+
+echo "-- Done, all Tuplex requirements installed to /opt --"

From a8c18da61bf33f37b9eb50d0261d2546457c419d Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Wed, 6 Aug 2025 23:33:46 -0700
Subject: [PATCH 02/11] boost fix

---
 scripts/ubuntu2404/install_requirements.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/ubuntu2404/install_requirements.sh b/scripts/ubuntu2404/install_requirements.sh
index 107af2aa0..8dce6efb6 100755
--- a/scripts/ubuntu2404/install_requirements.sh
+++ b/scripts/ubuntu2404/install_requirements.sh
@@ -7,7 +7,7 @@ PREFIX=${PREFIX:-/opt}
 WORKDIR=${WORKDIR:-/tmp}
 PYTHON_EXECUTABLE=${PYTHON_EXECUTABLE:-python3}
 CMAKE_VERSION="3.27.5"
-BOOST_VERSION="1.79.0"
+BOOST_VERSION="1.88.0"
 LLVM_VERSION="16.0.6"
 AWSSDK_CPP_VERSION=1.11.524
 ANTLR4_VERSION=4.13.1

From bf94c6d1f51a88b732a873d028b8479c42767243 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Thu, 7 Aug 2025 15:19:26 -0700
Subject: [PATCH 03/11] fixes

---
 scripts/ubuntu2404/Dockerfile              | 7 ++++++-
 scripts/ubuntu2404/install_requirements.sh | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/scripts/ubuntu2404/Dockerfile b/scripts/ubuntu2404/Dockerfile
index e3cab66cc..7a8f516a2 100644
--- a/scripts/ubuntu2404/Dockerfile
+++ b/scripts/ubuntu2404/Dockerfile
@@ -67,4 +67,9 @@ RUN rm -rf /tmp/*
 WORKDIR /code
 
 # Clone tuplex, and build initial version as well as install in python.
-RUN git clone -b ${GITHUB_BRANCH} --single-branch https://github.com/tuplex/tuplex.git
\ No newline at end of file
+RUN git clone -b ${GITHUB_BRANCH} --single-branch https://github.com/tuplex/tuplex.git
+
+# Install python dependencies
+RUN python3 -m pip install cloudpickle numpy pandas
+
+#
\ No newline at end of file
diff --git a/scripts/ubuntu2404/install_requirements.sh b/scripts/ubuntu2404/install_requirements.sh
index 8dce6efb6..5175a1fc2 100755
--- a/scripts/ubuntu2404/install_requirements.sh
+++ b/scripts/ubuntu2404/install_requirements.sh
@@ -130,7 +130,7 @@ echo ">> Installing apt dependencies"
 apt update -y
 
 apt-get install -y apt-utils dh-autoreconf libmagic-dev curl libxml2-dev vim build-essential libssl-dev zlib1g-dev libncurses5-dev \
-libncursesw5-dev libreadline-dev libsqlite3-dev libgdbm-dev libdb5.3-dev openssh-client \
+libncursesw5-dev libreadline-dev libsqlite3-dev libgdbm-dev libdb5.3-dev openssh-client unzip \
 libbz2-dev libexpat1-dev liblzma-dev tk-dev libffi-dev wget git libcurl4-openssl-dev python3-dev python3-pip openjdk-11-jdk ninja-build
 
 ldconfig

From 6aa2aef4835aa25d098be261a2dbb3f8db40a7da Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 15:56:52 -0700
Subject: [PATCH 04/11] fixes

---
 tuplex/CMakeLists.txt       | 2 ++
 tuplex/utils/include/Base.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/tuplex/CMakeLists.txt b/tuplex/CMakeLists.txt
index 8abb640d0..7adf4b7ef 100755
--- a/tuplex/CMakeLists.txt
+++ b/tuplex/CMakeLists.txt
@@ -6,6 +6,8 @@ cmake_minimum_required(VERSION 3.16 FATAL_ERROR)
 set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 message(STATUS "Using language version: C++${CMAKE_CXX_STANDARD}")
+set(CMAKE_C_STANDARD 17)
+set(CMAKE_C_STANDARD_REQUIRED ON)
 
 # add cmake modules from cmake folder
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake/")
diff --git a/tuplex/utils/include/Base.h b/tuplex/utils/include/Base.h
index 2475a9514..da3db47b7 100644
--- a/tuplex/utils/include/Base.h
+++ b/tuplex/utils/include/Base.h
@@ -13,6 +13,7 @@
 
 #include <string>
 #include <cstring>
+#include <cstdint>
 #include <unordered_set>
 #include <algorithm>
 

From 158b3b42618f2cdd8f3ccd7c985417c467e61fd7 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 16:00:53 -0700
Subject: [PATCH 05/11] fix

---
 tuplex/utils/include/Field.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tuplex/utils/include/Field.h b/tuplex/utils/include/Field.h
index fef968870..0ecb2d896 100644
--- a/tuplex/utils/include/Field.h
+++ b/tuplex/utils/include/Field.h
@@ -12,6 +12,7 @@
 #define TUPLEX_FIELD_H
 
 #include <tuple>
+#include <cstdint>
 #include <TypeSystem.h>
 #include <Tuple.h>
 #include <List.h>

From f7fd585eae90d1809626adf15dd1f08ac8db01e5 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 16:18:55 -0700
Subject: [PATCH 06/11] missing includes

---
 tuplex/io/include/VirtualMappedFile.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tuplex/io/include/VirtualMappedFile.h b/tuplex/io/include/VirtualMappedFile.h
index e7c65f374..0d21f30da 100644
--- a/tuplex/io/include/VirtualMappedFile.h
+++ b/tuplex/io/include/VirtualMappedFile.h
@@ -11,6 +11,9 @@
 #ifndef TUPLEX_VIRTUALMAPPEDFILE_H
 #define TUPLEX_VIRTUALMAPPEDFILE_H
 
+#include <cstdint>
+#include <URI.h>
+
 namespace tuplex {
     class VirtualMappedFile;
     class VirtualFileSystem;

From dd7cb1c6093b3e3637da25260e3105366c41fbdf Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 16:19:52 -0700
Subject: [PATCH 07/11] include fix

---
 tuplex/io/include/VirtualFileSystemBase.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tuplex/io/include/VirtualFileSystemBase.h b/tuplex/io/include/VirtualFileSystemBase.h
index 31b0087a6..d9c1c50f6 100644
--- a/tuplex/io/include/VirtualFileSystemBase.h
+++ b/tuplex/io/include/VirtualFileSystemBase.h
@@ -11,6 +11,8 @@
 #ifndef TUPLEX_VIRTUALFILESYSTEMBASE_H
 #define TUPLEX_VIRTUALFILESYSTEMBASE_H
 
+#include <cstdint>
+
 namespace tuplex {
     enum class VirtualFileSystemStatus {
         VFS_OK = 0,

From 79da010e6ed788a35e1647912d55adcf00cfadd8 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 16:20:33 -0700
Subject: [PATCH 08/11] fix

---
 tuplex/codegen/include/Token.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tuplex/codegen/include/Token.h b/tuplex/codegen/include/Token.h
index 7688a4dbe..b6ca1b713 100644
--- a/tuplex/codegen/include/Token.h
+++ b/tuplex/codegen/include/Token.h
@@ -13,6 +13,7 @@
 
 #include <TokenType.h>
 #include <string>
+#include <cstdint>
 #include <unordered_map>
 #include <iostream>
 #include <TypeSystem.h>

From d7a2973c0ec980f102602b7158f8cec5d41e2303 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 16:21:23 -0700
Subject: [PATCH 09/11] fix

---
 tuplex/core/include/RESTInterface.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tuplex/core/include/RESTInterface.h b/tuplex/core/include/RESTInterface.h
index ddf2d9bb8..ba1358250 100644
--- a/tuplex/core/include/RESTInterface.h
+++ b/tuplex/core/include/RESTInterface.h
@@ -13,6 +13,7 @@
 
 #include <curl/curl.h>
 #include <cstdlib>
+#include <cstdint>
 #include <string>
 #include <functional>
 

From 1ebca33b5215a5a26169e61396bc8e38dcc3e9c2 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 20:43:28 -0700
Subject: [PATCH 10/11] fixes

---
 scripts/ubuntu2404/Dockerfile              | 9 ++++++++-
 scripts/ubuntu2404/install_requirements.sh | 2 +-
 tuplex/codegen/include/CodegenHelper.h     | 6 ++++++
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/scripts/ubuntu2404/Dockerfile b/scripts/ubuntu2404/Dockerfile
index 7a8f516a2..716f4c9ae 100644
--- a/scripts/ubuntu2404/Dockerfile
+++ b/scripts/ubuntu2404/Dockerfile
@@ -72,4 +72,11 @@ RUN git clone -b ${GITHUB_BRANCH} --single-branch https://github.com/tuplex/tupl
 # Install python dependencies
 RUN python3 -m pip install cloudpickle numpy pandas
 
-#
\ No newline at end of file
+# Add paths to compile,
+RUN echo "export PATH=/opt/bin:${PATH}" >> /root/.bashrc
+RUN echo "export LLVM_ROOT=/opt/llvm-16.0.6" >> /root/.bashrc
+
+# Within the docker container, compile tuplex with
+# cd /code/tuplex/tuplex && mkdir -p build && cd build && cmake -DLLVM_ROOT=/opt/llvm-16.0.6/ -DBUILD_WITH_AWS=ON -DBUILD_WITH_ORC=ON .. && make
+# You can test via ctest
+# or follow instructions to test the python package.
\ No newline at end of file
diff --git a/scripts/ubuntu2404/install_requirements.sh b/scripts/ubuntu2404/install_requirements.sh
index 5175a1fc2..3937a5056 100755
--- a/scripts/ubuntu2404/install_requirements.sh
+++ b/scripts/ubuntu2404/install_requirements.sh
@@ -124,7 +124,7 @@ mkdir -p $WORKDIR
 PYTHON_BASENAME="$(basename -- $PYTHON_EXECUTABLE)"
 PYTHON_VERSION=$(${PYTHON_EXECUTABLE} --version)
 echo ">> Building dependencies for ${PYTHON_VERSION}"
-echo ">> Installing all build dependencies for Tuplex under Ubuntu 22.04"
+echo ">> Installing all build dependencies for Tuplex under Ubuntu 24.04"
 
 echo ">> Installing apt dependencies"
 apt update -y
diff --git a/tuplex/codegen/include/CodegenHelper.h b/tuplex/codegen/include/CodegenHelper.h
index 63af95f38..9649dc9d7 100644
--- a/tuplex/codegen/include/CodegenHelper.h
+++ b/tuplex/codegen/include/CodegenHelper.h
@@ -763,7 +763,13 @@ namespace tuplex {
                 llvm::Instruction& inst = *firstBlock.getFirstInsertionPt();
                 ctorBuilder.SetInsertPoint(&inst);
             }
+
+            // llvm IR builder has some issues with copy disallowed. C++ compilers will issue -Wreturn-local-addr.
+            // Disable warning here.
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wreturn-local-addr"
             return std::move(ctorBuilder);
+#pragma GCC diagnostic pop
         }
 
         // in order to serialize/deserialize data properly and deal with

From 712dc99d75bd2cd58076751c86750cb2daa32bc3 Mon Sep 17 00:00:00 2001
From: Leonhard Spiegelberg <leonhard@brown.edu>
Date: Fri, 8 Aug 2025 20:49:28 -0700
Subject: [PATCH 11/11] cancel previous runs

---
 .github/workflows/build_wheels.yml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/.github/workflows/build_wheels.yml b/.github/workflows/build_wheels.yml
index 682c184dc..f4dc95937 100644
--- a/.github/workflows/build_wheels.yml
+++ b/.github/workflows/build_wheels.yml
@@ -2,6 +2,11 @@ name: Build
 
 on: [push, pull_request, workflow_dispatch]
 
+# Cancel previous runs, i.e. run only latest push.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 # For macos, at least 10.13 is required
 # to avoid issues and since the runners are macos-13 and macos-14:
 #   -> use 13.6, which is Venture from 2022 and 14.0 on the arm runners.