From 59985538b4c67370b6aa5d9282bb1b896a2110bb Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 10:59:51 +0100
Subject: [PATCH 01/10] Add ADBC sqlite

---
 pixi.lock      | 199 ++++++++++++++++++++++++++++++++++++++++++++++++-
 pyproject.toml |  11 ++-
 2 files changed, 208 insertions(+), 2 deletions(-)

diff --git a/pixi.lock b/pixi.lock
index d5fd5a3..bea4c2a 100644
--- a/pixi.lock
+++ b/pixi.lock
@@ -12,6 +12,8 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/adbc-driver-manager-1.9.0-py312h1289d80_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/argon2-cffi-bindings-25.1.0-py312h4c3975b_2.conda
@@ -54,6 +56,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/linux-64/icu-75.1-he02047a_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/isoduration-20.11.0-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jinja2-3.1.6-pyhcf101f3_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jsonpointer-3.0.0-pyhcf101f3_3.conda
@@ -71,6 +74,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.45-default_hbd61a6d_104.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libabseil-20250127.1-cxx17_hbbce691_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libadbc-driver-sqlite-1.9.0-hcea63bf_1.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-20.0.0-h1b9301b_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-acero-20.0.0-hcb10f89_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-dataset-20.0.0-hcb10f89_8_cpu.conda
@@ -176,6 +180,8 @@ environments:
       - pypi: ./
       osx-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/adbc-driver-manager-1.9.0-py312h1eb2caf_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/argon2-cffi-bindings-25.1.0-py312h80b0991_2.conda
@@ -218,6 +224,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-64/icu-75.1-h120a0e1_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/isoduration-20.11.0-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jinja2-3.1.6-pyhcf101f3_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jsonpointer-3.0.0-pyhcf101f3_3.conda
@@ -233,6 +240,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-64/krb5-1.21.3-h37d8d59_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libabseil-20250127.1-cxx17_h0e468a2_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/libadbc-driver-sqlite-1.9.0-h4340512_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-20.0.0-h7601d43_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-acero-20.0.0-hdc53af8_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-dataset-20.0.0-hdc53af8_8_cpu.conda
@@ -333,6 +341,8 @@ environments:
       - pypi: ./
       osx-arm64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/adbc-driver-manager-1.9.0-py312h455b684_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/argon2-cffi-bindings-25.1.0-py312h4409184_2.conda
@@ -375,6 +385,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/icu-75.1-hfee45f7_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/isoduration-20.11.0-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jinja2-3.1.6-pyhcf101f3_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jsonpointer-3.0.0-pyhcf101f3_3.conda
@@ -390,6 +401,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/krb5-1.21.3-h237132a_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libabseil-20250127.1-cxx17_h07bc746_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libadbc-driver-sqlite-1.9.0-hdd8eb12_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-20.0.0-hd5f8272_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-acero-20.0.0-hf07054f_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-dataset-20.0.0-hf07054f_8_cpu.conda
@@ -490,6 +502,8 @@ environments:
       - pypi: ./
       win-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/adbc-driver-manager-1.9.0-py312hbb81ca0_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/argon2-cffi-bindings-25.1.0-py312he06e257_2.conda
@@ -524,6 +538,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/fqdn-1.5.1-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/isoduration-20.11.0-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jinja2-3.1.6-pyhcf101f3_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/jsonpointer-3.0.0-pyhcf101f3_3.conda
@@ -539,6 +554,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/win-64/krb5-1.21.3-hdf4eb48_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libabseil-20250127.1-cxx17_h4eb7d71_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libadbc-driver-sqlite-1.9.0-h18ee088_1.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-20.0.0-h3e40a90_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-acero-20.0.0-h7d8d6a5_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-dataset-20.0.0-h7d8d6a5_8_cpu.conda
@@ -639,6 +655,8 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/adbc-driver-manager-1.9.0-py312h1289d80_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/argon2-cffi-bindings-25.1.0-py312h4c3975b_2.conda
@@ -716,6 +734,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/identify-2.6.15-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/iniconfig-2.3.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyha191276_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
@@ -744,6 +763,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.45-default_hbd61a6d_104.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libabseil-20250127.1-cxx17_hbbce691_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libadbc-driver-sqlite-1.9.0-hcea63bf_1.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-20.0.0-h1b9301b_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-acero-20.0.0-hcb10f89_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-dataset-20.0.0-hcb10f89_8_cpu.conda
@@ -907,6 +927,8 @@ environments:
       - pypi: ./
       osx-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/adbc-driver-manager-1.9.0-py312h1eb2caf_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/appnope-0.1.4-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
@@ -985,6 +1007,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/identify-2.6.15-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/iniconfig-2.3.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh5552912_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
@@ -1011,6 +1034,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-64/krb5-1.21.3-h37d8d59_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libabseil-20250127.1-cxx17_h0e468a2_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/libadbc-driver-sqlite-1.9.0-h4340512_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-20.0.0-h7601d43_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-acero-20.0.0-hdc53af8_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-dataset-20.0.0-hdc53af8_8_cpu.conda
@@ -1168,6 +1192,8 @@ environments:
       - pypi: ./
       osx-arm64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/adbc-driver-manager-1.9.0-py312h455b684_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/appnope-0.1.4-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
@@ -1246,6 +1272,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/identify-2.6.15-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/iniconfig-2.3.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh5552912_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
@@ -1272,6 +1299,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/krb5-1.21.3-h237132a_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libabseil-20250127.1-cxx17_h07bc746_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libadbc-driver-sqlite-1.9.0-hdd8eb12_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-20.0.0-hd5f8272_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-acero-20.0.0-hf07054f_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-dataset-20.0.0-hf07054f_8_cpu.conda
@@ -1429,6 +1457,8 @@ environments:
       - pypi: ./
       win-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/adbc-driver-manager-1.9.0-py312hbb81ca0_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/argon2-cffi-bindings-25.1.0-py312he06e257_2.conda
@@ -1498,6 +1528,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/identify-2.6.15-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/iniconfig-2.3.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh6dadd2b_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyhe2676ad_0.conda
@@ -1524,6 +1555,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/win-64/krb5-1.21.3-hdf4eb48_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libabseil-20250127.1-cxx17_h4eb7d71_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libadbc-driver-sqlite-1.9.0-h18ee088_1.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-20.0.0-h3e40a90_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-acero-20.0.0-h7d8d6a5_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-dataset-20.0.0-h7d8d6a5_8_cpu.conda
@@ -1682,6 +1714,8 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/adbc-driver-manager-1.9.0-py312h1289d80_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/argon2-cffi-bindings-25.1.0-py312h4c3975b_2.conda
@@ -1745,6 +1779,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/linux-64/icu-75.1-he02047a_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyha191276_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython_pygments_lexers-1.1.1-pyhd8ed1ab_0.conda
@@ -1770,6 +1805,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.45-default_hbd61a6d_104.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libabseil-20250127.1-cxx17_hbbce691_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libadbc-driver-sqlite-1.9.0-hcea63bf_1.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-20.0.0-h1b9301b_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-acero-20.0.0-hcb10f89_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-dataset-20.0.0-hcb10f89_8_cpu.conda
@@ -1898,6 +1934,8 @@ environments:
       - pypi: ./
       osx-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/adbc-driver-manager-1.9.0-py312h1eb2caf_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/appnope-0.1.4-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
@@ -1962,6 +2000,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-64/icu-75.1-h120a0e1_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh5552912_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython_pygments_lexers-1.1.1-pyhd8ed1ab_0.conda
@@ -1985,6 +2024,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-64/krb5-1.21.3-h37d8d59_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libabseil-20250127.1-cxx17_h0e468a2_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-64/libadbc-driver-sqlite-1.9.0-h4340512_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-20.0.0-h7601d43_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-acero-20.0.0-hdc53af8_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-64/libarrow-dataset-20.0.0-hdc53af8_8_cpu.conda
@@ -2107,6 +2147,8 @@ environments:
       - pypi: ./
       osx-arm64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/adbc-driver-manager-1.9.0-py312h455b684_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/appnope-0.1.4-pyhd8ed1ab_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
@@ -2171,6 +2213,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/icu-75.1-hfee45f7_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh5552912_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyh53cf698_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython_pygments_lexers-1.1.1-pyhd8ed1ab_0.conda
@@ -2194,6 +2237,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/krb5-1.21.3-h237132a_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libabseil-20250127.1-cxx17_h07bc746_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libadbc-driver-sqlite-1.9.0-hdd8eb12_1.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-20.0.0-hd5f8272_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-acero-20.0.0-hf07054f_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/osx-arm64/libarrow-dataset-20.0.0-hf07054f_8_cpu.conda
@@ -2316,6 +2360,8 @@ environments:
       - pypi: ./
       win-64:
       - conda: https://conda.anaconda.org/conda-forge/noarch/_python_abi3_support-1.0-hd8ed1ab_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/adbc-driver-manager-1.9.0-py312hbb81ca0_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/argon2-cffi-25.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/argon2-cffi-bindings-25.1.0-py312he06e257_2.conda
@@ -2371,6 +2417,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/noarch/hyperframe-6.1.0-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/idna-3.11-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/importlib-metadata-8.7.0-pyhe01879c_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipykernel-7.1.0-pyh6dadd2b_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython-9.8.0-pyhe2676ad_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/ipython_pygments_lexers-1.1.1-pyhd8ed1ab_0.conda
@@ -2394,6 +2441,7 @@ environments:
       - conda: https://conda.anaconda.org/conda-forge/win-64/krb5-1.21.3-hdf4eb48_0.conda
       - conda: https://conda.anaconda.org/conda-forge/noarch/lark-1.3.1-pyhd8ed1ab_0.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libabseil-20250127.1-cxx17_h4eb7d71_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libadbc-driver-sqlite-1.9.0-h18ee088_1.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-20.0.0-h3e40a90_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-acero-20.0.0-h7d8d6a5_8_cpu.conda
       - conda: https://conda.anaconda.org/conda-forge/win-64/libarrow-dataset-20.0.0-h7d8d6a5_8_cpu.conda
@@ -2538,6 +2586,89 @@ packages:
   purls: []
   size: 8191
   timestamp: 1744137672556
+- conda: https://conda.anaconda.org/conda-forge/linux-64/adbc-driver-manager-1.9.0-py312h1289d80_1.conda
+  sha256: cee0eb8a92563267ded63f61901922fe8e115cf0b694bfd39548fee59d25ff2f
+  md5: 04f547f5f1f2022bdb0a556dcc566d5a
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=14
+  - libstdcxx >=14
+  - python >=3.12,<3.13.0a0
+  - python_abi 3.12.* *_cp312
+  constrains:
+  - pyarrow >=8.0.0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/adbc-driver-manager?source=hash-mapping
+  size: 346251
+  timestamp: 1764031540423
+- conda: https://conda.anaconda.org/conda-forge/osx-64/adbc-driver-manager-1.9.0-py312h1eb2caf_1.conda
+  sha256: 88fa88081d6376152383c7964340403f6a6e998212cddc87965c2e55957dcb96
+  md5: 83a2664f12bfc21d7f2a21e312472935
+  depends:
+  - __osx >=11.0
+  - libcxx >=19
+  - python >=3.12,<3.13.0a0
+  - python_abi 3.12.* *_cp312
+  constrains:
+  - pyarrow >=8.0.0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/adbc-driver-manager?source=hash-mapping
+  size: 311547
+  timestamp: 1764031904949
+- conda: https://conda.anaconda.org/conda-forge/osx-arm64/adbc-driver-manager-1.9.0-py312h455b684_1.conda
+  sha256: f4e18f38f7d1b8c569c83cd4caff30ffeb3949d99b6f3718685d47bf201c3916
+  md5: 220b002cc30013d69b584b64ff82113a
+  depends:
+  - __osx >=11.0
+  - libcxx >=19
+  - python >=3.12,<3.13.0a0
+  - python >=3.12,<3.13.0a0 *_cpython
+  - python_abi 3.12.* *_cp312
+  constrains:
+  - pyarrow >=8.0.0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/adbc-driver-manager?source=hash-mapping
+  size: 298419
+  timestamp: 1764031973405
+- conda: https://conda.anaconda.org/conda-forge/win-64/adbc-driver-manager-1.9.0-py312hbb81ca0_1.conda
+  sha256: 0613da8a43fb4f7b0b15604e2acbfcf8084bce3c2725df89b983156f525fb0bf
+  md5: 16a774881beceaa6f3dd41da99dec7b5
+  depends:
+  - python >=3.12,<3.13.0a0
+  - python_abi 3.12.* *_cp312
+  - ucrt >=10.0.20348.0
+  - vc >=14.3,<15
+  - vc14_runtime >=14.44.35208
+  constrains:
+  - pyarrow >=8.0.0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/adbc-driver-manager?source=hash-mapping
+  size: 430584
+  timestamp: 1764031648991
+- conda: https://conda.anaconda.org/conda-forge/noarch/adbc-driver-sqlite-1.9.0-pyha770c72_1.conda
+  sha256: 83c209bb144840e3375b2b525a4ed2dd7fc0e3c6a8da7273b122b08c29c8f567
+  md5: 80c8e7a339ad9423faa0b515ec0ea0a2
+  depends:
+  - adbc-driver-manager >=1.9.0,<2.0a0
+  - importlib_resources
+  - libadbc-driver-sqlite >=1.9.0,<1.9.1.0a0
+  - python >=3.10
+  constrains:
+  - pyarrow >=8.0.0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/adbc-driver-sqlite?source=hash-mapping
+  size: 24709
+  timestamp: 1764032240842
 - conda: https://conda.anaconda.org/conda-forge/noarch/anyio-4.12.0-pyhcf101f3_0.conda
   sha256: 830fc81970cd9d19869909b9b16d241f4d557e4f201a1030aa6ed87c6aa8b930
   md5: 9958d4a1ee7e9c768fe8f4fb51bd07ea
@@ -2570,8 +2701,10 @@ packages:
 - pypi: ./
   name: arbalister
   version: 0.1.0
-  sha256: b3c23e0901a5247469d7f00a61e13669ae82d954e1ae19f5074a2678a84efb23
+  sha256: 64957ee8a9f7ed7c972b982dae789b32d263bdafc5aaa9cdce14d6524831ae7b
   requires_dist:
+  - adbc-driver-manager
+  - adbc-driver-sqlite
   - datafusion>=40.0
   - jupyter-server>=2.4.0,<3
   - pyarrow>=20.0
@@ -4883,6 +5016,20 @@ packages:
   - pkg:pypi/importlib-metadata?source=hash-mapping
   size: 34641
   timestamp: 1747934053147
+- conda: https://conda.anaconda.org/conda-forge/noarch/importlib_resources-6.5.2-pyhd8ed1ab_0.conda
+  sha256: acc1d991837c0afb67c75b77fdc72b4bf022aac71fedd8b9ea45918ac9b08a80
+  md5: c85c76dc67d75619a92f51dfbce06992
+  depends:
+  - python >=3.9
+  - zipp >=3.1.0
+  constrains:
+  - importlib-resources >=6.5.2,<6.5.3.0a0
+  license: Apache-2.0
+  license_family: APACHE
+  purls:
+  - pkg:pypi/importlib-resources?source=hash-mapping
+  size: 33781
+  timestamp: 1736252433366
 - conda: https://conda.anaconda.org/conda-forge/noarch/iniconfig-2.3.0-pyhd8ed1ab_0.conda
   sha256: e1a9e3b1c8fe62dc3932a616c284b5d8cbe3124bbfbedcf4ce5c828cb166ee19
   md5: 9614359868482abba1bd15ce465e3c42
@@ -5504,6 +5651,56 @@ packages:
   purls: []
   size: 1836732
   timestamp: 1742370096247
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libadbc-driver-sqlite-1.9.0-hcea63bf_1.conda
+  sha256: 313d4ab39d50036b0816b01b290174d591e342f83b18eaaa6d21073f408b83e8
+  md5: 053a42e10fba063db539a8116d251a44
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=14
+  - libsqlite >=3.51.0,<4.0a0
+  - libstdcxx >=14
+  license: Apache-2.0
+  license_family: APACHE
+  purls: []
+  size: 194057
+  timestamp: 1764032114809
+- conda: https://conda.anaconda.org/conda-forge/osx-64/libadbc-driver-sqlite-1.9.0-h4340512_1.conda
+  sha256: 098a1ebc11cd605c128cd32434b21d57b0d87777b0a4b7becb120995d1ec7f97
+  md5: e243907376ea9c4ad3fb1c1c99baee6f
+  depends:
+  - __osx >=11.0
+  - libcxx >=19
+  - libsqlite >=3.51.0,<4.0a0
+  license: Apache-2.0
+  license_family: APACHE
+  purls: []
+  size: 204299
+  timestamp: 1764032925091
+- conda: https://conda.anaconda.org/conda-forge/osx-arm64/libadbc-driver-sqlite-1.9.0-hdd8eb12_1.conda
+  sha256: 1e40620e0ba150615708143d95c88923614173eb0ebacdf1db7312a9abd8fa74
+  md5: db776abb92bddec261c64bf3bc760d26
+  depends:
+  - __osx >=11.0
+  - libcxx >=19
+  - libsqlite >=3.51.0,<4.0a0
+  license: Apache-2.0
+  license_family: APACHE
+  purls: []
+  size: 189010
+  timestamp: 1764033020392
+- conda: https://conda.anaconda.org/conda-forge/win-64/libadbc-driver-sqlite-1.9.0-h18ee088_1.conda
+  sha256: e2f593e5c80c8959a090fd90adca0962927878fe9d392d5db58e30737796be4c
+  md5: d46c2a845fd78d99872a8bcefa2b217c
+  depends:
+  - libsqlite >=3.51.0,<4.0a0
+  - ucrt >=10.0.20348.0
+  - vc >=14.3,<15
+  - vc14_runtime >=14.44.35208
+  license: Apache-2.0
+  license_family: APACHE
+  purls: []
+  size: 164032
+  timestamp: 1764032117306
 - conda: https://conda.anaconda.org/conda-forge/linux-64/libarrow-20.0.0-h1b9301b_8_cpu.conda
   build_number: 8
   sha256: e218ae6165e6243d8850352640cee57f06a8d05743647918a0370cc5fcc8b602
diff --git a/pyproject.toml b/pyproject.toml
index 778a04f..3fe3977 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -24,8 +24,15 @@ classifiers = [
   "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: 3.14",
 ]
-dependencies = ["jupyter_server>=2.4.0,<3", "pyarrow>=20.0", "datafusion>=40.0"]
 dynamic = ["version", "description", "authors", "urls", "keywords"]
+dependencies = [
+  "jupyter_server>=2.4.0,<3",
+  "pyarrow>=20.0",
+  "datafusion>=40.0",
+  # Optional dependencies
+  "adbc_driver_manager",
+  "adbc_driver_sqlite",
+]
 
 [tool.hatch.version]
 source = "nodejs"
@@ -115,6 +122,8 @@ nodejs = "*"
 jupyter_server = "*"
 pyarrow = "*"
 datafusion = "*"
+adbc-driver-manager = "*"
+adbc-driver-sqlite = "*"
 
 [tool.pixi.pypi-dependencies]
 arbalister = { path = ".", editable = true }

From cf51cbb15ddccd53049867c938be40855cec7d63 Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 11:17:49 +0100
Subject: [PATCH 02/10] Add sqlite file type

---
 arbalister/__init__.py          |  1 +
 arbalister/arrow.py             | 61 ++++++++++-----------------------
 arbalister/file_format.py       | 35 +++++++++++++++++++
 arbalister/routes.py            |  3 +-
 arbalister/tests/test_routes.py | 11 +++---
 data/generate.py                | 13 +++----
 6 files changed, 70 insertions(+), 54 deletions(-)
 create mode 100644 arbalister/file_format.py

diff --git a/arbalister/__init__.py b/arbalister/__init__.py
index 1c93ea4..51ae515 100644
--- a/arbalister/__init__.py
+++ b/arbalister/__init__.py
@@ -15,6 +15,7 @@
 import jupyterlab.labapp
 
 from . import arrow as arrow
+from . import file_format as file_format
 from . import params as params
 from . import routes as routes
 
diff --git a/arbalister/arrow.py b/arbalister/arrow.py
index 3157b36..ec1c42a 100644
--- a/arbalister/arrow.py
+++ b/arbalister/arrow.py
@@ -1,39 +1,10 @@
-import enum
 import pathlib
-from typing import Any, Callable, Self
+from typing import Any, Callable
 
 import datafusion as dn
 import pyarrow as pa
 
-
-class FileFormat(enum.StrEnum):
-    """Known file format that we can read into an Arrow format.
-
-    Todo:
-    - ADBC (Sqlite/Postgres)
-
-    """
-
-    Avro = "avro"
-    Csv = "csv"
-    Ipc = "ipc"
-    Orc = "orc"
-    Parquet = "parquet"
-
-    @classmethod
-    def from_filename(cls, file: pathlib.Path | str) -> Self:
-        """Get the file format from a filename extension."""
-        file_type = pathlib.Path(file).suffix.removeprefix(".").strip().lower()
-
-        # Match again their default value
-        if ft := next((ft for ft in FileFormat if str(ft) == file_type), None):
-            return ft
-        # Match other known values
-        match file_type:
-            case "ipc" | "feather":
-                return cls.Ipc
-        raise ValueError(f"Unknown file type {file_type}")
-
+from . import file_format as ff
 
 ReadCallable = Callable[..., dn.DataFrame]
 
@@ -84,7 +55,7 @@ def _write_avro(
         writer.close()
 
 
-def get_table_reader(format: FileFormat) -> ReadCallable:
+def get_table_reader(format: ff.FileFormat) -> ReadCallable:
     """Get the datafusion reader factory function for the given format."""
     # TODO: datafusion >= 50.0
     #  def read(ctx: dtfn.SessionContext, path: str | pathlib.Path, *args, **kwargs) -> dtfn.DataFrame:
@@ -92,13 +63,13 @@ def get_table_reader(format: FileFormat) -> ReadCallable:
     #      return ctx.read_table(ds, *args, **kwargs)
     out: ReadCallable
     match format:
-        case FileFormat.Avro:
+        case ff.FileFormat.Avro:
             out = dn.SessionContext.read_avro
-        case FileFormat.Csv:
+        case ff.FileFormat.Csv:
             out = dn.SessionContext.read_csv
-        case FileFormat.Parquet:
+        case ff.FileFormat.Parquet:
             out = dn.SessionContext.read_parquet
-        case FileFormat.Ipc:
+        case ff.FileFormat.Ipc:
             import pyarrow.feather
 
             def read_ipc(
@@ -109,7 +80,7 @@ def read_ipc(
                 return ctx.from_arrow(table)
 
             out = read_ipc
-        case FileFormat.Orc:
+        case ff.FileFormat.Orc:
             # Watch for https://github.com/datafusion-contrib/datafusion-orc
             # Evolution for native datafusion reader
             import pyarrow.orc
@@ -121,6 +92,8 @@ def read_orc(
                 return ctx.from_arrow(table)
 
             out = read_orc
+        case ff.FileFormat.Sqlite:
+            raise NotImplementedError("Sqlite not available in Python Datafusion")
 
     return out
 
@@ -128,26 +101,28 @@ def read_orc(
 WriteCallable = Callable[..., None]
 
 
-def get_table_writer(format: FileFormat) -> WriteCallable:
+def get_table_writer(format: ff.FileFormat) -> WriteCallable:
     """Get the arrow writer factory function for the given format."""
     out: WriteCallable
     match format:
-        case FileFormat.Avro:
+        case ff.FileFormat.Avro:
             out = _write_avro
-        case FileFormat.Csv:
+        case ff.FileFormat.Csv:
             import pyarrow.csv
 
             out = pyarrow.csv.write_csv
-        case FileFormat.Parquet:
+        case ff.FileFormat.Parquet:
             import pyarrow.parquet
 
             out = pyarrow.parquet.write_table
-        case FileFormat.Ipc:
+        case ff.FileFormat.Ipc:
             import pyarrow.feather
 
             out = pyarrow.feather.write_feather
-        case FileFormat.Orc:
+        case ff.FileFormat.Orc:
             import pyarrow.orc
 
             out = pyarrow.orc.write_table
+        case ff.FileFormat.Sqlite:
+            raise NotImplementedError("Sqlite not available in Python Datafusion")
     return out
diff --git a/arbalister/file_format.py b/arbalister/file_format.py
new file mode 100644
index 0000000..f265b99
--- /dev/null
+++ b/arbalister/file_format.py
@@ -0,0 +1,35 @@
+import enum
+import pathlib
+from typing import Self
+
+
+class FileFormat(enum.StrEnum):
+    """Known file format that we can read into an Arrow format.
+
+    Todo:
+    - ADBC (Sqlite/Postgres)
+
+    """
+
+    Avro = "avro"
+    Csv = "csv"
+    Ipc = "ipc"
+    Orc = "orc"
+    Parquet = "parquet"
+    Sqlite = "sqlite"
+
+    @classmethod
+    def from_filename(cls, file: pathlib.Path | str) -> Self:
+        """Get the file format from a filename extension."""
+        file_type = pathlib.Path(file).suffix.removeprefix(".").strip().lower()
+
+        # Match again their default value
+        if ft := next((ft for ft in FileFormat if str(ft) == file_type), None):
+            return ft
+        # Match other known values
+        match file_type:
+            case "ipc" | "feather":
+                return cls.Ipc
+            case "sqlite3" | "db":
+                return cls.Sqlite
+        raise ValueError(f"Unknown file type {file_type}")
diff --git a/arbalister/routes.py b/arbalister/routes.py
index 4d12ddf..aaf8098 100644
--- a/arbalister/routes.py
+++ b/arbalister/routes.py
@@ -11,6 +11,7 @@
 from jupyter_server.utils import url_path_join
 
 from . import arrow as abw
+from . import file_format as ff
 from . import params as params
 
 
@@ -33,7 +34,7 @@ def dataframe(self, path: str) -> dn.DataFrame:
         Note: On some file type, the file is read eagerly when calling this method.
         """
         file = self.data_file(path)
-        read_table = abw.get_table_reader(format=abw.FileFormat.from_filename(file))
+        read_table = abw.get_table_reader(format=ff.FileFormat.from_filename(file))
         return read_table(self.context, file)
 
     def get_query_params_as[T](self, dataclass_type: type[T]) -> T:
diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index 90c1cf0..c851498 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -12,10 +12,13 @@
 import arbalister as arb
 
 
-@pytest.fixture(params=list(arb.arrow.FileFormat), scope="session")
-def file_format(request: pytest.FixtureRequest) -> arb.arrow.FileFormat:
+@pytest.fixture(
+    params=[f for f in arb.file_format.FileFormat if f != arb.file_format.FileFormat.Sqlite],
+    scope="session",
+)
+def file_format(request: pytest.FixtureRequest) -> arb.file_format.FileFormat:
     """Parametrize the file format used in the test."""
-    out: arb.arrow.FileFormat = request.param
+    out: arb.file_format.FileFormat = request.param
     return out
 
 
@@ -39,7 +42,7 @@ def dummy_table() -> pa.Table:
 
 @pytest.fixture
 def dummy_table_file(
-    jp_root_dir: pathlib.Path, dummy_table: pa.Table, file_format: arb.arrow.FileFormat
+    jp_root_dir: pathlib.Path, dummy_table: pa.Table, file_format: arb.file_format.FileFormat
 ) -> pathlib.Path:
     """Write the dummy table to file."""
     write_table = arb.arrow.get_table_writer(file_format)
diff --git a/data/generate.py b/data/generate.py
index b14e24e..ec8f2be 100644
--- a/data/generate.py
+++ b/data/generate.py
@@ -9,6 +9,7 @@
 import pyarrow.parquet as paq
 
 import arbalister.arrow as aa
+from arbalister import file_format as ff
 
 MAX_FAKER_ROWS = 100_000
 
@@ -81,7 +82,7 @@ def sink_coordinate_table(
     num_rows: int, num_cols: int, path: pathlib.Path, chunk_size: int = 1_000_000
 ) -> None:
     """Write iteratively a table where each cell has its coordinates."""
-    assert aa.FileFormat.from_filename(path) == aa.FileFormat.Parquet
+    assert ff.FileFormat.from_filename(path) == ff.FileFormat.Parquet
     print("Initializing session context", flush=True)
     ctx = dn.SessionContext()
     print("Generating schema", flush=True)
@@ -97,7 +98,7 @@ def configure_command_single(cmd: argparse.ArgumentParser) -> argparse.ArgumentP
     cmd.add_argument(
         "--output-type",
         "-t",
-        choices=[t.name.lower() for t in aa.FileFormat],
+        choices=[t.name.lower() for t in ff.FileFormat],
         default=None,
         help="Output file type",
     )
@@ -149,7 +150,7 @@ def shuffle_table(table: pa.Table, seed: int | None = None) -> pa.Table:
     return table.select(col_order).take(row_indices)
 
 
-def save_table(table: pa.Table, path: pathlib.Path, file_type: aa.FileFormat) -> None:
+def save_table(table: pa.Table, path: pathlib.Path, file_type: ff.FileFormat) -> None:
     """Save a table to file with the given file type."""
     path.parent.mkdir(exist_ok=True, parents=True)
     write_table = aa.get_table_writer(file_type)
@@ -165,13 +166,13 @@ def main() -> None:
 
     match args.command:
         case "single":
-            ft = next((t for t in aa.FileFormat if t.name.lower() == args.output_type), None)
+            ft = next((t for t in ff.FileFormat if t.name.lower() == args.output_type), None)
             if ft is None:
-                ft = aa.FileFormat.from_filename(args.output_file)
+                ft = ff.FileFormat.from_filename(args.output_file)
             save_table(shuffle_table(table), args.output_file, ft)
         case "batch":
             for p in args.output_file:
-                ft = aa.FileFormat.from_filename(p)
+                ft = ff.FileFormat.from_filename(p)
                 save_table(shuffle_table(table), p, ft)
         case "coordinate":
             sink_coordinate_table(num_rows=args.num_rows, num_cols=args.num_cols, path=args.output_file)

From 894d379bfb5f8d9a83b0a80a6e658fc06f52cdbc Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 16:34:47 +0100
Subject: [PATCH 03/10] Add Sqlite single table support in server

---
 arbalister/adbc.py              | 84 +++++++++++++++++++++++++++++++++
 arbalister/arrow.py             | 11 ++++-
 arbalister/tests/test_routes.py |  5 +-
 3 files changed, 94 insertions(+), 6 deletions(-)
 create mode 100644 arbalister/adbc.py

diff --git a/arbalister/adbc.py b/arbalister/adbc.py
new file mode 100644
index 0000000..c07b8fe
--- /dev/null
+++ b/arbalister/adbc.py
@@ -0,0 +1,84 @@
+import dataclasses
+import pathlib
+from typing import Any, Self
+
+import adbc_driver_sqlite.dbapi as adbc_sqlite
+import pyarrow as pa
+
+
+def write_sqlite(
+    table: pa.Table,
+    path: str | pathlib.Path,
+    table_name: str = "Table",
+    catalog_name: str | None = None,
+) -> None:
+    """Write a table as an Sqlite file."""
+    with adbc_sqlite.connect(str(path)) as connection:
+        with connection.cursor() as cursor:
+            cursor.adbc_ingest(table_name=table_name, data=table, mode="create", catalog_name=catalog_name)
+        connection.commit()
+
+
+@dataclasses.dataclass
+class SqliteDataFrame:
+    """A DataFrame plan on a Sqlite file.
+
+    This plan is made to resemble a Apache Datafusion DataFrame despite some performances penalty.
+    This is because in the Rust Datafusion implementation of as a Sqlite contrib which we would
+    like to eventually use so this class is only filling in temporarily.
+    """
+
+    _path: str
+    _table_name: str
+    _schema: pa.Schema
+    _num_rows: int
+    _limit: int | None = None
+    _offset: int | None = None
+    _select: list[str] | None = None
+
+    @classmethod
+    def read_sqlite(cls, context: Any, path: pathlib.Path | str, table_name: str | None = None) -> Self:
+        """Read an Sqlite file metadata and start a new DataFrame plan."""
+        with adbc_sqlite.connect(str(path)) as connection:
+            tables = connection.adbc_get_table_types()
+            if table_name is None and len(tables) > 0:
+                table_name = tables[0]
+            elif table_name not in tables:
+                raise ValueError(f"Invalid table name {table_name}")
+            schema = connection.adbc_get_table_schema(table_name)
+
+            with connection.cursor() as cursor:
+                cursor.execute(f'SELECT COUNT(*) FROM "{table_name}"')
+                num_rows = cursor.fetchone()[0]  # type: ignore[index]
+
+            return cls(_path=str(path), _table_name=table_name, _schema=schema, _num_rows=num_rows)
+
+    def schema(self) -> pa.Schema:
+        """Return the :py:class:`pyarrow.Schema` of this DataFrame."""
+        return self._schema
+
+    def limit(self, count: int, offset: int = 0) -> Self:
+        """Return a new DataFrame with a limited number of rows."""
+        return dataclasses.replace(self, _limit=count, _offset=offset)
+
+    def select(self, *columns: str) -> Self:
+        """Project arbitrary expressions into a new `DataFrame`."""
+        return dataclasses.replace(self, _select=list(columns))
+
+    def count(self) -> int:
+        """Return the total number of rows in this DataFrame."""
+        return self._num_rows
+
+    def to_arrow_table(self) -> pa.Table:
+        """Execute the DataFrame and convert it into an Arrow Table."""
+        limit = (
+            f"LIMIT {self._limit} OFFSET {self._offset}"
+            if self._limit is not None and self._offset is not None
+            else ""
+        )
+        columns = self._select if self._select is not None else ["*"]
+
+        with adbc_sqlite.connect(self._path) as connection:
+            with connection.cursor() as cursor:
+                cursor.execute(f'SELECT {",".join(columns)} FROM "{self._table_name}" {limit}')
+                return cursor.fetch_arrow_table()
diff --git a/arbalister/arrow.py b/arbalister/arrow.py
index ec1c42a..d24882d 100644
--- a/arbalister/arrow.py
+++ b/arbalister/arrow.py
@@ -93,7 +93,12 @@ def read_orc(
 
             out = read_orc
         case ff.FileFormat.Sqlite:
-            raise NotImplementedError("Sqlite not available in Python Datafusion")
+            from . import adbc as adbc
+
+            # FIXME: For now we just pretend SqliteDataFrame is a datafision DataFrame
+            # Either we integrate it properly into Datafusion, or we create a DataFrame as a
+            # typing.protocol.
+            out = adbc.SqliteDataFrame.read_sqlite  # type: ignore[assignment]
 
     return out
 
@@ -124,5 +129,7 @@ def get_table_writer(format: ff.FileFormat) -> WriteCallable:
 
             out = pyarrow.orc.write_table
         case ff.FileFormat.Sqlite:
-            raise NotImplementedError("Sqlite not available in Python Datafusion")
+            from . import adbc as adbc
+
+            out = adbc.write_sqlite
     return out
diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index c851498..e7922b8 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -12,10 +12,7 @@
 import arbalister as arb
 
 
-@pytest.fixture(
-    params=[f for f in arb.file_format.FileFormat if f != arb.file_format.FileFormat.Sqlite],
-    scope="session",
-)
+@pytest.fixture(params=list(arb.file_format.FileFormat), scope="session")
 def file_format(request: pytest.FixtureRequest) -> arb.file_format.FileFormat:
     """Parametrize the file format used in the test."""
     out: arb.file_format.FileFormat = request.param

From 37d21c5433b49022ae33226b52677e424fd7a99d Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 17:43:30 +0100
Subject: [PATCH 04/10] Test different sqlite table names

---
 arbalister/adbc.py              | 22 ++++++----
 arbalister/routes.py            | 28 ++++++++++++-
 arbalister/tests/test_routes.py | 73 +++++++++++++++++++++++----------
 3 files changed, 91 insertions(+), 32 deletions(-)

diff --git a/arbalister/adbc.py b/arbalister/adbc.py
index c07b8fe..54579d7 100644
--- a/arbalister/adbc.py
+++ b/arbalister/adbc.py
@@ -1,6 +1,6 @@
 import dataclasses
 import pathlib
-from typing import Any, Self
+from typing import Any, Literal, Self
 
 import adbc_driver_sqlite.dbapi as adbc_sqlite
 import pyarrow as pa
@@ -11,11 +11,12 @@ def write_sqlite(
     path: str | pathlib.Path,
     table_name: str = "Table",
     catalog_name: str | None = None,
+    mode: Literal["append", "create", "replace", "create_append"] = "create",
 ) -> None:
     """Write a table as an Sqlite file."""
     with adbc_sqlite.connect(str(path)) as connection:
         with connection.cursor() as cursor:
-            cursor.adbc_ingest(table_name=table_name, data=table, mode="create", catalog_name=catalog_name)
+            cursor.adbc_ingest(table_name=table_name, data=table, mode=mode, catalog_name=catalog_name)
         connection.commit()
 
 
@@ -40,17 +41,20 @@ class SqliteDataFrame:
     def read_sqlite(cls, context: Any, path: pathlib.Path | str, table_name: str | None = None) -> Self:
         """Read an Sqlite file metadata and start a new DataFrame plan."""
         with adbc_sqlite.connect(str(path)) as connection:
-            tables = connection.adbc_get_table_types()
-            if table_name is None and len(tables) > 0:
-                table_name = tables[0]
-            elif table_name not in tables:
-                raise ValueError(f"Invalid table name {table_name}")
-            schema = connection.adbc_get_table_schema(table_name)
-
             with connection.cursor() as cursor:
+                cursor.execute("SELECT name FROM sqlite_master WHERE type='table'")
+                tables = [row for (row,) in cursor.fetchall()]
+
+                if table_name is None and len(tables) > 0:
+                    table_name = tables[0]
+                if table_name not in tables or table_name is None:
+                    raise ValueError(f"Invalid table name {table_name}")
+
                 cursor.execute(f'SELECT COUNT(*) FROM "{table_name}"')
                 num_rows = cursor.fetchone()[0]  # type: ignore[index]
 
+            schema = connection.adbc_get_table_schema(table_name)
+
             return cls(_path=str(path), _table_name=table_name, _schema=schema, _num_rows=num_rows)
 
     def schema(self) -> pa.Schema:
diff --git a/arbalister/routes.py b/arbalister/routes.py
index aaf8098..0cb2ce1 100644
--- a/arbalister/routes.py
+++ b/arbalister/routes.py
@@ -15,6 +15,21 @@
 from . import params as params
 
 
+@dataclasses.dataclass(frozen=True, slots=True)
+class SqliteReadParams:
+    """Query parameter for the Sqlite reader."""
+
+    table_name: str | None = None
+
+
+@dataclasses.dataclass(frozen=True, slots=True)
+class NoReadParams:
+    """Query parameter for readers with no parameters."""
+
+
+FileReadParams = SqliteReadParams | NoReadParams
+
+
 class BaseRouteHandler(jupyter_server.base.handlers.APIHandler):
     """A base handler to share common methods."""
 
@@ -34,13 +49,22 @@ def dataframe(self, path: str) -> dn.DataFrame:
         Note: On some file type, the file is read eagerly when calling this method.
         """
         file = self.data_file(path)
-        read_table = abw.get_table_reader(format=ff.FileFormat.from_filename(file))
-        return read_table(self.context, file)
+        file_format = ff.FileFormat.from_filename(file)
+        file_params = self.get_file_read_params(file_format)
+        read_table = abw.get_table_reader(format=file_format)
+        return read_table(self.context, file, **dataclasses.asdict(file_params))
 
     def get_query_params_as[T](self, dataclass_type: type[T]) -> T:
         """Extract query parameters into a dataclass type."""
         return params.build_dataclass(dataclass_type, self.get_query_argument)
 
+    def get_file_read_params(self, file_format: ff.FileFormat) -> FileReadParams:
+        """Read the parameters associated with the relevant file format."""
+        match file_format:
+            case ff.FileFormat.Sqlite:
+                return self.get_query_params_as(SqliteReadParams)
+        return NoReadParams()
+
 
 @dataclasses.dataclass(frozen=True, slots=True)
 class IpcParams:
diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index e7922b8..dd42aa8 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -19,32 +19,61 @@ def file_format(request: pytest.FixtureRequest) -> arb.file_format.FileFormat:
     return out
 
 
-DUMMY_TABLE_ROW_COUNT: Final = 10
-DUMMY_TABLE_COL_COUNT: Final = 4
+DUMMY_TABLE_1_ROW_COUNT: Final = 10
+DUMMY_TABLE_1_COL_COUNT: Final = 4
 
 
 @pytest.fixture(scope="module")
-def dummy_table() -> pa.Table:
+def dummy_table_1() -> pa.Table:
     """Generate a table with fake data."""
     data = {
-        "lower": random.choices(string.ascii_lowercase, k=DUMMY_TABLE_ROW_COUNT),
-        "sequence": list(range(DUMMY_TABLE_ROW_COUNT)),
-        "upper": random.choices(string.ascii_uppercase, k=DUMMY_TABLE_ROW_COUNT),
-        "number": [random.random() for _ in range(DUMMY_TABLE_ROW_COUNT)],
+        "lower": random.choices(string.ascii_lowercase, k=DUMMY_TABLE_1_ROW_COUNT),
+        "sequence": list(range(DUMMY_TABLE_1_ROW_COUNT)),
+        "upper": random.choices(string.ascii_uppercase, k=DUMMY_TABLE_1_ROW_COUNT),
+        "number": [random.random() for _ in range(DUMMY_TABLE_1_ROW_COUNT)],
     }
     table = pa.table(data)
-    assert len(table.schema) == DUMMY_TABLE_COL_COUNT
+    assert len(table.schema) == DUMMY_TABLE_1_COL_COUNT
+    return table
+
+
+DUMMY_TABLE_2_ROW_COUNT = 13
+DUMMY_TABLE_2_COL_COUNT = 5
+
+
+@pytest.fixture(scope="module")
+def dummy_table_2() -> pa.Table:
+    """Generate a table with different fake data."""
+    data = {
+        "id": list(range(DUMMY_TABLE_2_ROW_COUNT)),
+        "flag": [random.choice([True, False]) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
+        "letter": random.choices(string.ascii_letters, k=DUMMY_TABLE_2_ROW_COUNT),
+        "score": [random.randint(0, 100) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
+        "timestamp": [random.randint(1_600_000_000, 1_700_000_000) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
+    }
+    table = pa.table(data)
+    assert len(table.schema) == DUMMY_TABLE_2_COL_COUNT
     return table
 
 
 @pytest.fixture
 def dummy_table_file(
-    jp_root_dir: pathlib.Path, dummy_table: pa.Table, file_format: arb.file_format.FileFormat
+    jp_root_dir: pathlib.Path,
+    dummy_table_1: pa.Table,
+    dummy_table_2: pa.Table,
+    file_format: arb.file_format.FileFormat,
 ) -> pathlib.Path:
     """Write the dummy table to file."""
     write_table = arb.arrow.get_table_writer(file_format)
     table_path = jp_root_dir / f"test.{str(file_format).lower()}"
-    write_table(dummy_table, table_path)
+
+    match file_format:
+        case arb.file_format.FileFormat.Sqlite:
+            write_table(dummy_table_1, table_path, table_name="dummy_table_1", mode="create_append")
+            write_table(dummy_table_2, table_path, table_name="dummy_table_2", mode="create_append")
+        case _:
+            write_table(dummy_table_1, table_path)
+
     return table_path.relative_to(jp_root_dir)
 
 
@@ -58,23 +87,23 @@ def dummy_table_file(
         # Limit only number of rows
         arb.routes.IpcParams(row_chunk=0, row_chunk_size=3),
         arb.routes.IpcParams(row_chunk=1, row_chunk_size=2),
-        arb.routes.IpcParams(row_chunk=0, row_chunk_size=DUMMY_TABLE_ROW_COUNT),
-        arb.routes.IpcParams(row_chunk=1, row_chunk_size=DUMMY_TABLE_ROW_COUNT // 2 + 1),
+        arb.routes.IpcParams(row_chunk=0, row_chunk_size=DUMMY_TABLE_1_ROW_COUNT),
+        arb.routes.IpcParams(row_chunk=1, row_chunk_size=DUMMY_TABLE_1_ROW_COUNT // 2 + 1),
         # Limit only number of cols
         arb.routes.IpcParams(col_chunk=0, col_chunk_size=3),
         arb.routes.IpcParams(col_chunk=1, col_chunk_size=2),
-        arb.routes.IpcParams(col_chunk=0, col_chunk_size=DUMMY_TABLE_COL_COUNT),
-        arb.routes.IpcParams(col_chunk=1, col_chunk_size=DUMMY_TABLE_COL_COUNT // 2 + 1),
+        arb.routes.IpcParams(col_chunk=0, col_chunk_size=DUMMY_TABLE_1_COL_COUNT),
+        arb.routes.IpcParams(col_chunk=1, col_chunk_size=DUMMY_TABLE_1_COL_COUNT // 2 + 1),
         # Limit both
         arb.routes.IpcParams(
             row_chunk=0,
             row_chunk_size=3,
             col_chunk=1,
-            col_chunk_size=DUMMY_TABLE_COL_COUNT // 2 + 1,
+            col_chunk_size=DUMMY_TABLE_1_COL_COUNT // 2 + 1,
         ),
         arb.routes.IpcParams(
             row_chunk=0,
-            row_chunk_size=DUMMY_TABLE_ROW_COUNT,
+            row_chunk_size=DUMMY_TABLE_1_ROW_COUNT,
             col_chunk=1,
             col_chunk_size=2,
         ),
@@ -87,7 +116,7 @@ def dummy_table_file(
 )
 async def test_ipc_route_limit_row(
     jp_fetch: JpFetch,
-    dummy_table: pa.Table,
+    dummy_table_1: pa.Table,
     dummy_table_file: pathlib.Path,
     params: arb.routes.IpcParams,
 ) -> None:
@@ -102,7 +131,7 @@ async def test_ipc_route_limit_row(
     assert response.headers["Content-Type"] == "application/vnd.apache.arrow.stream"
     payload = pa.ipc.open_stream(response.body).read_all()
 
-    expected = dummy_table
+    expected = dummy_table_1
 
     # Row slicing
     if (size := params.row_chunk_size) is not None and (cidx := params.row_chunk) is not None:
@@ -122,7 +151,9 @@ async def test_ipc_route_limit_row(
     assert expected.cast(payload.schema) == payload
 
 
-async def test_stats_route(jp_fetch: JpFetch, dummy_table: pa.Table, dummy_table_file: pathlib.Path) -> None:
+async def test_stats_route(
+    jp_fetch: JpFetch, dummy_table_1: pa.Table, dummy_table_file: pathlib.Path
+) -> None:
     """Test fetching a file returns the correct metadata in Json."""
     response = await jp_fetch("arrow/stats/", str(dummy_table_file))
 
@@ -130,5 +161,5 @@ async def test_stats_route(jp_fetch: JpFetch, dummy_table: pa.Table, dummy_table
     assert response.headers["Content-Type"] == "application/json; charset=UTF-8"
 
     payload = json.loads(response.body)
-    assert payload["num_cols"] == len(dummy_table.schema)
-    assert payload["num_rows"] == dummy_table.num_rows
+    assert payload["num_cols"] == len(dummy_table_1.schema)
+    assert payload["num_rows"] == dummy_table_1.num_rows

From bfed3505359514e0d914e822d71add44518f378a Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 18:13:39 +0100
Subject: [PATCH 05/10] Refactor ipc_param fixture

---
 arbalister/tests/test_routes.py | 52 ++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 23 deletions(-)

diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index dd42aa8..83a182b 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -80,51 +80,57 @@ def dummy_table_file(
 JpFetch = Callable[..., Awaitable[tornado.httpclient.HTTPResponse]]
 
 
-@pytest.mark.parametrize(
-    "params",
-    [
-        arb.routes.IpcParams(),
+@pytest.fixture(
+    params=[
+        # No limits
+        lambda table: arb.routes.IpcParams(),
         # Limit only number of rows
-        arb.routes.IpcParams(row_chunk=0, row_chunk_size=3),
-        arb.routes.IpcParams(row_chunk=1, row_chunk_size=2),
-        arb.routes.IpcParams(row_chunk=0, row_chunk_size=DUMMY_TABLE_1_ROW_COUNT),
-        arb.routes.IpcParams(row_chunk=1, row_chunk_size=DUMMY_TABLE_1_ROW_COUNT // 2 + 1),
+        lambda table: arb.routes.IpcParams(row_chunk=0, row_chunk_size=3),
+        lambda table: arb.routes.IpcParams(row_chunk=1, row_chunk_size=2),
+        lambda table: arb.routes.IpcParams(row_chunk=0, row_chunk_size=table.num_rows),
+        lambda table: arb.routes.IpcParams(row_chunk=1, row_chunk_size=table.num_rows // 2 + 1),
         # Limit only number of cols
-        arb.routes.IpcParams(col_chunk=0, col_chunk_size=3),
-        arb.routes.IpcParams(col_chunk=1, col_chunk_size=2),
-        arb.routes.IpcParams(col_chunk=0, col_chunk_size=DUMMY_TABLE_1_COL_COUNT),
-        arb.routes.IpcParams(col_chunk=1, col_chunk_size=DUMMY_TABLE_1_COL_COUNT // 2 + 1),
+        lambda table: arb.routes.IpcParams(col_chunk=0, col_chunk_size=3),
+        lambda table: arb.routes.IpcParams(col_chunk=1, col_chunk_size=2),
+        lambda table: arb.routes.IpcParams(col_chunk=0, col_chunk_size=table.num_columns),
+        lambda table: arb.routes.IpcParams(col_chunk=1, col_chunk_size=table.num_columns // 2 + 1),
         # Limit both
-        arb.routes.IpcParams(
+        lambda table: arb.routes.IpcParams(
             row_chunk=0,
             row_chunk_size=3,
             col_chunk=1,
-            col_chunk_size=DUMMY_TABLE_1_COL_COUNT // 2 + 1,
+            col_chunk_size=table.num_columns // 2 + 1,
         ),
-        arb.routes.IpcParams(
+        lambda table: arb.routes.IpcParams(
             row_chunk=0,
-            row_chunk_size=DUMMY_TABLE_1_ROW_COUNT,
+            row_chunk_size=table.num_rows,
             col_chunk=1,
             col_chunk_size=2,
         ),
         # Schema only
-        arb.routes.IpcParams(
+        lambda table: arb.routes.IpcParams(
             row_chunk=0,
             row_chunk_size=0,
         ),
-    ],
+    ]
 )
-async def test_ipc_route_limit_row(
+def ipc_params(request: pytest.FixtureRequest, dummy_table_1: pa.Table) -> arb.routes.IpcParams:
+    """Parameters used to select the IPC data in the response."""
+    make_table: Callable[[pa.Table], arb.routes.IpcParams] = request.param
+    return make_table(dummy_table_1)
+
+
+async def test_ipc_route_limit(
     jp_fetch: JpFetch,
     dummy_table_1: pa.Table,
     dummy_table_file: pathlib.Path,
-    params: arb.routes.IpcParams,
+    ipc_params: arb.routes.IpcParams,
 ) -> None:
     """Test fetching a file returns the limited rows and columns in IPC."""
     response = await jp_fetch(
         "arrow/stream",
         str(dummy_table_file),
-        params={k: v for k, v in dataclasses.asdict(params).items() if v is not None},
+        params={k: v for k, v in dataclasses.asdict(ipc_params).items() if v is not None},
     )
 
     assert response.code == 200
@@ -134,13 +140,13 @@ async def test_ipc_route_limit_row(
     expected = dummy_table_1
 
     # Row slicing
-    if (size := params.row_chunk_size) is not None and (cidx := params.row_chunk) is not None:
+    if (size := ipc_params.row_chunk_size) is not None and (cidx := ipc_params.row_chunk) is not None:
         expected_num_rows = min((size * (cidx + 1)), expected.num_rows) - (size * cidx)
         assert payload.num_rows == expected_num_rows
         expected = expected.slice(cidx * size, size)
 
     # Col slicing
-    if (size := params.col_chunk_size) is not None and (cidx := params.col_chunk) is not None:
+    if (size := ipc_params.col_chunk_size) is not None and (cidx := ipc_params.col_chunk) is not None:
         expected_num_cols = min((size * (cidx + 1)), len(expected.schema)) - (size * cidx)
         assert len(payload.schema) == expected_num_cols
         col_names = expected.schema.names

From 251a12631b8ab23c41d5adb7c3fd81704c43c4c9 Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 18:19:54 +0100
Subject: [PATCH 06/10] Refactor constants

---
 arbalister/tests/test_routes.py | 34 ++++++++++++---------------------
 1 file changed, 12 insertions(+), 22 deletions(-)

diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index 83a182b..b711653 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -3,7 +3,7 @@
 import pathlib
 import random
 import string
-from typing import Awaitable, Callable, Final
+from typing import Awaitable, Callable
 
 import pyarrow as pa
 import pytest
@@ -19,40 +19,30 @@ def file_format(request: pytest.FixtureRequest) -> arb.file_format.FileFormat:
     return out
 
 
-DUMMY_TABLE_1_ROW_COUNT: Final = 10
-DUMMY_TABLE_1_COL_COUNT: Final = 4
-
-
 @pytest.fixture(scope="module")
-def dummy_table_1() -> pa.Table:
+def dummy_table_1(num_rows: int = 10) -> pa.Table:
     """Generate a table with fake data."""
     data = {
-        "lower": random.choices(string.ascii_lowercase, k=DUMMY_TABLE_1_ROW_COUNT),
-        "sequence": list(range(DUMMY_TABLE_1_ROW_COUNT)),
-        "upper": random.choices(string.ascii_uppercase, k=DUMMY_TABLE_1_ROW_COUNT),
-        "number": [random.random() for _ in range(DUMMY_TABLE_1_ROW_COUNT)],
+        "lower": random.choices(string.ascii_lowercase, k=num_rows),
+        "sequence": list(range(num_rows)),
+        "upper": random.choices(string.ascii_uppercase, k=num_rows),
+        "number": [random.random() for _ in range(num_rows)],
     }
     table = pa.table(data)
-    assert len(table.schema) == DUMMY_TABLE_1_COL_COUNT
     return table
 
 
-DUMMY_TABLE_2_ROW_COUNT = 13
-DUMMY_TABLE_2_COL_COUNT = 5
-
-
 @pytest.fixture(scope="module")
-def dummy_table_2() -> pa.Table:
+def dummy_table_2(num_rows: int = 13) -> pa.Table:
     """Generate a table with different fake data."""
     data = {
-        "id": list(range(DUMMY_TABLE_2_ROW_COUNT)),
-        "flag": [random.choice([True, False]) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
-        "letter": random.choices(string.ascii_letters, k=DUMMY_TABLE_2_ROW_COUNT),
-        "score": [random.randint(0, 100) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
-        "timestamp": [random.randint(1_600_000_000, 1_700_000_000) for _ in range(DUMMY_TABLE_2_ROW_COUNT)],
+        "id": list(range(num_rows)),
+        "flag": [random.choice([True, False]) for _ in range(num_rows)],
+        "letter": random.choices(string.ascii_letters, k=num_rows),
+        "score": [random.randint(0, 100) for _ in range(num_rows)],
+        "timestamp": [random.randint(1_600_000_000, 1_700_000_000) for _ in range(num_rows)],
     }
     table = pa.table(data)
-    assert len(table.schema) == DUMMY_TABLE_2_COL_COUNT
     return table
 
 

From 91b2b4003d4fe77e61216b72c81eeee43bb2976d Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 18:52:05 +0100
Subject: [PATCH 07/10] Test sqlite table_name in request

---
 arbalister/tests/test_routes.py | 79 +++++++++++++++++++++++++++------
 1 file changed, 66 insertions(+), 13 deletions(-)

diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index b711653..182c108 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -10,15 +10,46 @@
 import tornado
 
 import arbalister as arb
+import arbalister.file_format as ff
 
 
-@pytest.fixture(params=list(arb.file_format.FileFormat), scope="session")
-def file_format(request: pytest.FixtureRequest) -> arb.file_format.FileFormat:
-    """Parametrize the file format used in the test."""
-    out: arb.file_format.FileFormat = request.param
+@pytest.fixture(
+    params=[
+        (ff.FileFormat.Avro, arb.routes.NoReadParams()),
+        (ff.FileFormat.Csv, arb.routes.NoReadParams()),
+        (ff.FileFormat.Ipc, arb.routes.NoReadParams()),
+        (ff.FileFormat.Orc, arb.routes.NoReadParams()),
+        (ff.FileFormat.Parquet, arb.routes.NoReadParams()),
+        (ff.FileFormat.Sqlite, arb.routes.NoReadParams()),
+        (ff.FileFormat.Sqlite, arb.routes.SqliteReadParams(table_name="SuperData")),
+    ],
+    ids=lambda f_p: f"{f_p[0].value}-{dataclasses.asdict(f_p[1])}",
+    scope="module",
+)
+def file_format_and_params(request: pytest.FixtureRequest) -> tuple[ff.FileFormat, arb.routes.FileReadParams]:
+    """Parametrize the file format and file parameters used in the tests.
+
+    This is used to to build test cases with a give set of parameters since each file format may be tested
+    with a different number of parameters.
+    """
+    out: tuple[ff.FileFormat, arb.routes.FileReadParams] = request.param
     return out
 
 
+@pytest.fixture(scope="module")
+def file_format(file_format_and_params: tuple[ff.FileFormat, arb.routes.FileReadParams]) -> ff.FileFormat:
+    """Extract the the file format fixture value used in the tests."""
+    return file_format_and_params[0]
+
+
+@pytest.fixture(scope="module")
+def file_params(
+    file_format_and_params: tuple[ff.FileFormat, arb.routes.FileReadParams],
+) -> arb.routes.FileReadParams:
+    """Extract the the file parameters fixture value used in the tests."""
+    return file_format_and_params[1]
+
+
 @pytest.fixture(scope="module")
 def dummy_table_1(num_rows: int = 10) -> pa.Table:
     """Generate a table with fake data."""
@@ -51,16 +82,22 @@ def dummy_table_file(
     jp_root_dir: pathlib.Path,
     dummy_table_1: pa.Table,
     dummy_table_2: pa.Table,
-    file_format: arb.file_format.FileFormat,
+    file_format: ff.FileFormat,
+    file_params: arb.routes.FileReadParams,
 ) -> pathlib.Path:
     """Write the dummy table to file."""
     write_table = arb.arrow.get_table_writer(file_format)
     table_path = jp_root_dir / f"test.{str(file_format).lower()}"
 
     match file_format:
-        case arb.file_format.FileFormat.Sqlite:
+        case ff.FileFormat.Sqlite:
             write_table(dummy_table_1, table_path, table_name="dummy_table_1", mode="create_append")
-            write_table(dummy_table_2, table_path, table_name="dummy_table_2", mode="create_append")
+            table_2_name = (
+                file_params.table_name
+                if isinstance(file_params, arb.routes.SqliteReadParams)
+                else "dummy_table_2"
+            )
+            write_table(dummy_table_2, table_path, table_name=table_2_name, mode="create_append")
         case _:
             write_table(dummy_table_1, table_path)
 
@@ -113,21 +150,27 @@ def ipc_params(request: pytest.FixtureRequest, dummy_table_1: pa.Table) -> arb.r
 async def test_ipc_route_limit(
     jp_fetch: JpFetch,
     dummy_table_1: pa.Table,
+    dummy_table_2: pa.Table,
     dummy_table_file: pathlib.Path,
     ipc_params: arb.routes.IpcParams,
+    file_params: arb.routes.SqliteReadParams,
 ) -> None:
     """Test fetching a file returns the limited rows and columns in IPC."""
     response = await jp_fetch(
         "arrow/stream",
         str(dummy_table_file),
-        params={k: v for k, v in dataclasses.asdict(ipc_params).items() if v is not None},
+        params={
+            k: v
+            for k, v in {**dataclasses.asdict(ipc_params), **dataclasses.asdict(file_params)}.items()
+            if v is not None
+        },
     )
 
     assert response.code == 200
     assert response.headers["Content-Type"] == "application/vnd.apache.arrow.stream"
     payload = pa.ipc.open_stream(response.body).read_all()
 
-    expected = dummy_table_1
+    expected = dummy_table_2 if isinstance(file_params, arb.routes.SqliteReadParams) else dummy_table_1
 
     # Row slicing
     if (size := ipc_params.row_chunk_size) is not None and (cidx := ipc_params.row_chunk) is not None:
@@ -148,14 +191,24 @@ async def test_ipc_route_limit(
 
 
 async def test_stats_route(
-    jp_fetch: JpFetch, dummy_table_1: pa.Table, dummy_table_file: pathlib.Path
+    jp_fetch: JpFetch,
+    dummy_table_1: pa.Table,
+    dummy_table_2: pa.Table,
+    dummy_table_file: pathlib.Path,
+    file_params: arb.routes.SqliteReadParams,
 ) -> None:
     """Test fetching a file returns the correct metadata in Json."""
-    response = await jp_fetch("arrow/stats/", str(dummy_table_file))
+    response = await jp_fetch(
+        "arrow/stats/",
+        str(dummy_table_file),
+        params={k: v for k, v in dataclasses.asdict(file_params).items() if v is not None},
+    )
 
     assert response.code == 200
     assert response.headers["Content-Type"] == "application/json; charset=UTF-8"
 
+    expected = dummy_table_2 if isinstance(file_params, arb.routes.SqliteReadParams) else dummy_table_1
+
     payload = json.loads(response.body)
-    assert payload["num_cols"] == len(dummy_table_1.schema)
-    assert payload["num_rows"] == dummy_table_1.num_rows
+    assert payload["num_cols"] == len(expected.schema)
+    assert payload["num_rows"] == expected.num_rows

From c77999fbc024169b6f65ee8024eb564848858ec8 Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 18:59:35 +0100
Subject: [PATCH 08/10] Refactor target table fixture in test

---
 arbalister/tests/test_routes.py | 44 +++++++++++++++++----------------
 1 file changed, 23 insertions(+), 21 deletions(-)

diff --git a/arbalister/tests/test_routes.py b/arbalister/tests/test_routes.py
index 182c108..9b571b0 100644
--- a/arbalister/tests/test_routes.py
+++ b/arbalister/tests/test_routes.py
@@ -21,7 +21,7 @@
         (ff.FileFormat.Orc, arb.routes.NoReadParams()),
         (ff.FileFormat.Parquet, arb.routes.NoReadParams()),
         (ff.FileFormat.Sqlite, arb.routes.NoReadParams()),
-        (ff.FileFormat.Sqlite, arb.routes.SqliteReadParams(table_name="SuperData")),
+        (ff.FileFormat.Sqlite, arb.routes.SqliteReadParams(table_name="dummy_table_2")),
     ],
     ids=lambda f_p: f"{f_p[0].value}-{dataclasses.asdict(f_p[1])}",
     scope="module",
@@ -77,8 +77,19 @@ def dummy_table_2(num_rows: int = 13) -> pa.Table:
     return table
 
 
+@pytest.fixture(scope="module")
+def full_table(file_params: ff.FileFormat, dummy_table_1: pa.Table, dummy_table_2: pa.Table) -> pa.Table:
+    """Return the full table on which we are executed queries."""
+    if isinstance(file_params, arb.routes.SqliteReadParams):
+        return {
+            "dummy_table_1": dummy_table_1,
+            "dummy_table_2": dummy_table_2,
+        }[file_params.table_name]
+    return dummy_table_1
+
+
 @pytest.fixture
-def dummy_table_file(
+def table_file(
     jp_root_dir: pathlib.Path,
     dummy_table_1: pa.Table,
     dummy_table_2: pa.Table,
@@ -92,12 +103,7 @@ def dummy_table_file(
     match file_format:
         case ff.FileFormat.Sqlite:
             write_table(dummy_table_1, table_path, table_name="dummy_table_1", mode="create_append")
-            table_2_name = (
-                file_params.table_name
-                if isinstance(file_params, arb.routes.SqliteReadParams)
-                else "dummy_table_2"
-            )
-            write_table(dummy_table_2, table_path, table_name=table_2_name, mode="create_append")
+            write_table(dummy_table_2, table_path, table_name="dummy_table_2", mode="create_append")
         case _:
             write_table(dummy_table_1, table_path)
 
@@ -149,16 +155,15 @@ def ipc_params(request: pytest.FixtureRequest, dummy_table_1: pa.Table) -> arb.r
 
 async def test_ipc_route_limit(
     jp_fetch: JpFetch,
-    dummy_table_1: pa.Table,
-    dummy_table_2: pa.Table,
-    dummy_table_file: pathlib.Path,
+    full_table: pa.Table,
+    table_file: pathlib.Path,
     ipc_params: arb.routes.IpcParams,
     file_params: arb.routes.SqliteReadParams,
 ) -> None:
     """Test fetching a file returns the limited rows and columns in IPC."""
     response = await jp_fetch(
         "arrow/stream",
-        str(dummy_table_file),
+        str(table_file),
         params={
             k: v
             for k, v in {**dataclasses.asdict(ipc_params), **dataclasses.asdict(file_params)}.items()
@@ -170,7 +175,7 @@ async def test_ipc_route_limit(
     assert response.headers["Content-Type"] == "application/vnd.apache.arrow.stream"
     payload = pa.ipc.open_stream(response.body).read_all()
 
-    expected = dummy_table_2 if isinstance(file_params, arb.routes.SqliteReadParams) else dummy_table_1
+    expected = full_table
 
     # Row slicing
     if (size := ipc_params.row_chunk_size) is not None and (cidx := ipc_params.row_chunk) is not None:
@@ -192,23 +197,20 @@ async def test_ipc_route_limit(
 
 async def test_stats_route(
     jp_fetch: JpFetch,
-    dummy_table_1: pa.Table,
-    dummy_table_2: pa.Table,
-    dummy_table_file: pathlib.Path,
+    full_table: pa.Table,
+    table_file: pathlib.Path,
     file_params: arb.routes.SqliteReadParams,
 ) -> None:
     """Test fetching a file returns the correct metadata in Json."""
     response = await jp_fetch(
         "arrow/stats/",
-        str(dummy_table_file),
+        str(table_file),
         params={k: v for k, v in dataclasses.asdict(file_params).items() if v is not None},
     )
 
     assert response.code == 200
     assert response.headers["Content-Type"] == "application/json; charset=UTF-8"
 
-    expected = dummy_table_2 if isinstance(file_params, arb.routes.SqliteReadParams) else dummy_table_1
-
     payload = json.loads(response.body)
-    assert payload["num_cols"] == len(expected.schema)
-    assert payload["num_rows"] == expected.num_rows
+    assert payload["num_cols"] == len(full_table.schema)
+    assert payload["num_rows"] == full_table.num_rows

From 5e1d5d8530cde953e4654418df422276c5c468cf Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 19:13:23 +0100
Subject: [PATCH 09/10] Add more file extensions

---
 arbalister/file_format.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arbalister/file_format.py b/arbalister/file_format.py
index f265b99..d2d687a 100644
--- a/arbalister/file_format.py
+++ b/arbalister/file_format.py
@@ -30,6 +30,6 @@ def from_filename(cls, file: pathlib.Path | str) -> Self:
         match file_type:
             case "ipc" | "feather":
                 return cls.Ipc
-            case "sqlite3" | "db":
+            case "sqlite3" | "db" | ".db3", ".s3db", ".sl3":
                 return cls.Sqlite
         raise ValueError(f"Unknown file type {file_type}")

From 36242b11f8b99ac663f255fb56fddf32475faf72 Mon Sep 17 00:00:00 2001
From: AntoinePrv <AntoinePrv@users.noreply.github.com>
Date: Mon, 15 Dec 2025 19:19:12 +0100
Subject: [PATCH 10/10] Add generation of sqlite file

---
 pixi.lock      | 2 +-
 pyproject.toml | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/pixi.lock b/pixi.lock
index bea4c2a..8d20e59 100644
--- a/pixi.lock
+++ b/pixi.lock
@@ -2701,7 +2701,7 @@ packages:
 - pypi: ./
   name: arbalister
   version: 0.1.0
-  sha256: 64957ee8a9f7ed7c972b982dae789b32d263bdafc5aaa9cdce14d6524831ae7b
+  sha256: 3173db325467de56d1c311749ceec1fa1e50196d0cdd0a6bb5d201ee2ed9c8c7
   requires_dist:
   - adbc-driver-manager
   - adbc-driver-sqlite
diff --git a/pyproject.toml b/pyproject.toml
index 3fe3977..8d9dafc 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -229,6 +229,7 @@ python data/generate.py batch \
     -o data/gen/test.ipc \
     -o data/gen/test.orc \
     -o data/gen/test.parquet \
+    -o data/gen/test.sqlite \
 """
 outputs = ["data/gen/**/test.*"]
 description = """Generate different data files to use in development in data/gen."""