BEAM-9626: Move out optional packages from core dependencies - 20259

sdks/python/setup.py

@@ -378,7 +378,6 @@ def get_portability_package_data():
           'numpy>=1.14.3,<2.3.0',  # Update pyproject.toml as well.
           'objsize>=0.6.1,<0.8.0',
           'packaging>=22.0',
-          'pymongo>=3.8.0,<5.0.0',
           'proto-plus>=1.7.1,<2',
           # 1. Use a tighter upper bound in protobuf dependency to make sure
           # the minor version at job submission
@@ -560,6 +559,9 @@ def get_portability_package_data():
               # `--update` / `-U` flag to replace the dask release brought in
               # by distributed.
           ],
+          'mongodb': [
+              'pymongo>=3.8.0,<5.0.0'
+          ],
           'yaml': [
               'docstring-parser>=0.15,<1.0',
               'jinja2>=3.0,<3.2',

sdks/python/tox.ini

@@ -33,7 +33,7 @@ pip_pre = True
 # allow apps that support color to use it.
 passenv=TERM,CLOUDSDK_CONFIG
 # Set [] options for pip installation of apache-beam tarball.
-extras = test,dataframe
+extras = test,dataframe,mongodb
 # Don't warn that these commands aren't installed.
 allowlist_externals =
   false
@@ -98,7 +98,7 @@ list_dependencies_command = {envbindir}/python.exe {envbindir}/pip.exe freeze
 
 [testenv:py{39,310,311,312,313}-cloud]
 ; extras = test,gcp,interactive,dataframe,aws,azure
-extras = test,gcp,interactive,dataframe,aws,azure
+extras = test,gcp,interactive,dataframe,aws,azure,mongodb
 commands =
   python apache_beam/examples/complete/autocomplete_test.py
   bash {toxinidir}/scripts/run_pytest.sh {envname} "{posargs}"
@@ -109,7 +109,7 @@ deps =
   pip==25.0.1
   accelerate>=1.6.0
 setenv =
-extras = test,gcp,dataframe,ml_test
+extras = test,gcp,dataframe,ml_test, mongodb
 commands =
   # Log tensorflow version for debugging
   /bin/sh -c "pip freeze | grep -E tensorflow"
@@ -121,14 +121,15 @@ commands =
 deps =
   accelerate>=1.6.0
 setenv =
-extras = test,gcp,dataframe,p312_ml_test
+extras = test,gcp,dataframe,p312_ml_test,mongodb
 commands =
   # Log tensorflow version for debugging
   /bin/sh -c "pip freeze | grep -E tensorflow"
   bash {toxinidir}/scripts/run_pytest.sh {envname} "{posargs}"
 
+
 [testenv:py{39,310,311,31,313}-dask]
-extras = test,dask,dataframes
+extras = test,dask,dataframes,mongodb
 commands_pre =
   pip install 'distributed>=2024.4.2' 'dask>=2024.4.2'
 commands =
@@ -153,7 +154,7 @@ setenv =
 platform = linux
 passenv = GIT_*,BUILD_*,ghprb*,CHANGE_ID,BRANCH_NAME,JENKINS_*,CODECOV_*,GITHUB_*
 # NOTE: we could add ml_test to increase the collected code coverage metrics, but it would make the suite slower.
-extras = test,gcp,interactive,dataframe,aws
+extras = test,gcp,interactive,dataframe,aws,mongodb
 commands =
   bash {toxinidir}/scripts/run_pytest.sh {envname} "{posargs}" "--cov-report=xml --cov=. --cov-append"
 
@@ -186,13 +187,14 @@ deps =
 # make extras available in case any of these libs are typed
 extras =
   gcp
+  mongodb
 commands =
   mypy --version
   python setup.py mypy
 
 
 [testenv:docs]
-extras = test,gcp,docs,interactive,dataframe,dask
+extras = test,gcp,docs,interactive,dataframe,dask,mongodb
 deps =
   Sphinx==7.4.7
   sphinx_rtd_theme==3.0.1