From 3da49783a8889ed9d57796265caaa3fdeaad9a10 Mon Sep 17 00:00:00 2001
From: Takuya Ueshin <ueshin@happy-camper.st>
Date: Mon, 3 Aug 2026 15:42:12 -0700
Subject: [PATCH] Make dependency group names compliant with the PyPA
 specification

---
 pyproject.toml | 78 +++++++++++++++++++++++++-------------------------
 1 file changed, 39 insertions(+), 39 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 790a3268daf80..d761759bb1991 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -64,14 +64,14 @@ ignore = [
     "python/pyspark/sql/tests/df_golden/scripts/**/*.py" = ["F821"]
 
 [dependency-groups]
-_py4j = ["py4j>=0.10.9.9"]
+internal_py4j = ["py4j>=0.10.9.9"]
 
-_numpy = ["numpy>=1.23.2"]
-_pandas = ["pandas>=2.2.0,<3.0.0"]
-_protobuf = ["protobuf==6.33.5"]
-_pyarrow = ["pyarrow>=18.0.0"]
+internal_numpy = ["numpy>=1.23.2"]
+internal_pandas = ["pandas>=2.2.0,<3.0.0"]
+internal_protobuf = ["protobuf==6.33.5"]
+internal_pyarrow = ["pyarrow>=18.0.0"]
 
-_pyspark_devtool = [
+internal_pyspark_devtool = [
     # Optional tools that are used by pyspark directly.
     "memory-profiler>=0.61.0",
     "flameprof==0.4",
@@ -80,10 +80,10 @@ _pyspark_devtool = [
 ]
 
 connect = [
-    {include-group = "_py4j"},
-    {include-group = "_pandas"},
-    {include-group = "_protobuf"},
-    {include-group = "_pyarrow"},
+    {include-group = "internal_py4j"},
+    {include-group = "internal_pandas"},
+    {include-group = "internal_protobuf"},
+    {include-group = "internal_pyarrow"},
     "grpcio>=1.76.0",
     "grpcio-status>=1.76.0",
     "googleapis-common-protos>=1.71.0",
@@ -92,15 +92,15 @@ connect = [
 ]
 
 sql = [
-    {include-group = "_py4j"},
-    {include-group = "_pandas"},
-    {include-group = "_pyarrow"},
+    {include-group = "internal_py4j"},
+    {include-group = "internal_pandas"},
+    {include-group = "internal_pyarrow"},
 ]
 
 pandas_on_spark = [
-    {include-group = "_py4j"},
-    {include-group = "_pandas"},
-    {include-group = "_pyarrow"},
+    {include-group = "internal_py4j"},
+    {include-group = "internal_pandas"},
+    {include-group = "internal_pyarrow"},
 ]
 
 pandas_on_spark_extra = [
@@ -111,13 +111,13 @@ pandas_on_spark_extra = [
 ]
 
 ml = [
-    {include-group = "_py4j"},
-    {include-group = "_numpy"},
+    {include-group = "internal_py4j"},
+    {include-group = "internal_numpy"},
 ]
 
 mllib = [
-    {include-group = "_py4j"},
-    {include-group = "_numpy"},
+    {include-group = "internal_py4j"},
+    {include-group = "internal_numpy"},
 ]
 
 ml_extra_base = [
@@ -145,7 +145,7 @@ pipelines = [
     "pyyaml>=3.11",
 ]
 
-_lint = [
+internal_lint = [
     "ruff==0.14.8",
     "mypy==1.19.1",
     "pytest",
@@ -159,7 +159,7 @@ _lint = [
     "types-PyYAML"
 ]
 
-_test = [
+internal_test = [
     # Dependency for running tests
     "unittest-xml-reporting",
     # Coverage tool
@@ -175,7 +175,7 @@ _test = [
     "hypothesis>=6,<7",
 ]
 
-_docs = [
+internal_docs = [
     "sphinx==8.2.3",
     "sphinx-plotly-directive",
     "sphinx-copybutton",
@@ -188,7 +188,7 @@ _docs = [
     "mkdocs",
 ]
 
-_devtools = [
+internal_devtools = [
     # Devtools that are used by pyspark developers.
     "debugpy",
     "viztracer",
@@ -198,11 +198,11 @@ _devtools = [
 ]
 
 dev = [
-    {include-group = "_pyspark_devtool"},
-    {include-group = "_lint"},
-    {include-group = "_test"},
-    {include-group = "_docs"},
-    {include-group = "_devtools"},
+    {include-group = "internal_pyspark_devtool"},
+    {include-group = "internal_lint"},
+    {include-group = "internal_test"},
+    {include-group = "internal_docs"},
+    {include-group = "internal_devtools"},
     {include-group = "sql"},
     {include-group = "connect"},
     {include-group = "ml"},
@@ -213,7 +213,7 @@ dev = [
     {include-group = "pipelines"},
 ]
 
-_ci_connect = [
+internal_ci_connect = [
     {include-group = "connect"},
     "grpcio==1.76.0",
     "grpcio-status==1.76.0",
@@ -223,24 +223,24 @@ _ci_connect = [
 ]
 
 ci_connect_standard = [
-    {include-group = "_ci_connect"},
+    {include-group = "internal_ci_connect"},
     "graphviz==0.20.3",
 ]
 
 ci_connect_minimum = [
-    {include-group = "_ci_connect"},
+    {include-group = "internal_ci_connect"},
     "graphviz==0.20",
 ]
 
 ci_classic_standard = [
-    {include-group = "_pyspark_devtool"},
+    {include-group = "internal_pyspark_devtool"},
     {include-group = "sql"},
     {include-group = "pandas_on_spark"},
     {include-group = "pandas_on_spark_extra"},
     {include-group = "ml"},
     # torch should be installed with ml_torch group
     {include-group = "ml_extra_base"},
-    {include-group = "_test"},
+    {include-group = "internal_test"},
     "pyarrow>=23.0.0",
     "pandas==2.3.3",
 ]
@@ -260,10 +260,10 @@ ci_classic_minimum = [
 ]
 
 ci_lint = [
-    {include-group = "_lint"},
+    {include-group = "internal_lint"},
     {include-group = "ml_extra_base"},
     {include-group = "pandas_on_spark_extra"},
-    {include-group = "_ci_connect"},
+    {include-group = "internal_ci_connect"},
     "pyarrow>=23.0.0",
     "pandas==2.3.3",
     "pandas-stubs==2.3.3.260113",
@@ -271,9 +271,9 @@ ci_lint = [
 ]
 
 ci_docs = [
-    {include-group = "_docs"},
-    {include-group = "_ci_connect"},
-    {include-group = "_numpy"},
+    {include-group = "internal_docs"},
+    {include-group = "internal_ci_connect"},
+    {include-group = "internal_numpy"},
     # These are required for sphinx to introspect the code
     "pyarrow>=23.0.0",
     "pandas==2.3.3",