GH-41480: [Python] Building PyArrow: enable/disable python components by default based on availability in Arrow C++ #41494
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -152,48 +152,27 @@ def initialize_options(self): | |
| if not hasattr(sys, 'gettotalrefcount'): | ||
| self.build_type = 'release' | ||
|
|
||
| self.with_azure = None | ||
|
There was a problem hiding this comment. Do we still need There was a problem hiding this comment. Yes, they are still used in case someone is passing that to setup.py. See #41494 (comment) I think that's something we should deprecate, though. But planning to do a separate follow-up PR to that, since it's not actually related to this PR (it's just another way that someone can right now override the default, just as setting an environment variable) There was a problem hiding this comment. Ah, we need them for |
||
| self.with_gcs = None | ||
| self.with_s3 = None | ||
| self.with_hdfs = None | ||
| self.with_cuda = None | ||
| self.with_substrait = None | ||
| self.with_flight = None | ||
| self.with_acero = None | ||
| self.with_dataset = None | ||
| self.with_parquet = None | ||
| self.with_parquet_encryption = None | ||
| self.with_orc = None | ||
| self.with_gandiva = None | ||
|
|
||
| self.generate_coverage = strtobool( | ||
| os.environ.get('PYARROW_GENERATE_COVERAGE', '0')) | ||
| self.bundle_arrow_cpp = strtobool( | ||
| os.environ.get('PYARROW_BUNDLE_ARROW_CPP', '0')) | ||
| self.bundle_cython_cpp = strtobool( | ||
| os.environ.get('PYARROW_BUNDLE_CYTHON_CPP', '0')) | ||
|
|
||
| CYTHON_MODULE_NAMES = [ | ||
| 'lib', | ||
| '_fs', | ||
|
|
@@ -270,23 +249,30 @@ def append_cmake_bool(value, varname): | |
| cmake_options.append('-D{0}={1}'.format( | ||
| varname, 'on' if value else 'off')) | ||
|
|
||
| def append_cmake_component(flag, varname): | ||
| # only pass this to cmake is the user pass the --with-component | ||
| # flag to setup.py build_ext | ||
| if flag is not None: | ||
| append_cmake_bool(flag, varname) | ||
|
|
||
| if self.cmake_generator: | ||
| cmake_options += ['-G', self.cmake_generator] | ||
|
|
||
| append_cmake_component(self.with_cuda, 'PYARROW_CUDA') | ||
| append_cmake_component(self.with_substrait, 'PYARROW_SUBSTRAIT') | ||
| append_cmake_component(self.with_flight, 'PYARROW_FLIGHT') | ||
| append_cmake_component(self.with_gandiva, 'PYARROW_GANDIVA') | ||
| append_cmake_component(self.with_acero, 'PYARROW_ACERO') | ||
| append_cmake_component(self.with_dataset, 'PYARROW_DATASET') | ||
| append_cmake_component(self.with_orc, 'PYARROW_ORC') | ||
| append_cmake_component(self.with_parquet, 'PYARROW_PARQUET') | ||
| append_cmake_component(self.with_parquet_encryption, | ||
| 'PYARROW_PARQUET_ENCRYPTION') | ||
| append_cmake_component(self.with_azure, 'PYARROW_AZURE') | ||
| append_cmake_component(self.with_gcs, 'PYARROW_GCS') | ||
| append_cmake_component(self.with_s3, 'PYARROW_S3') | ||
| append_cmake_component(self.with_hdfs, 'PYARROW_HDFS') | ||
|
|
||
| append_cmake_bool(self.bundle_arrow_cpp, | ||
| 'PYARROW_BUNDLE_ARROW_CPP') | ||
| append_cmake_bool(self.bundle_cython_cpp, | ||
|
|
@@ -329,54 +315,8 @@ def append_cmake_bool(value, varname): | |
| self._found_names = [] | ||
| for name in self.CYTHON_MODULE_NAMES: | ||
| built_path = pjoin(install_prefix, name + ext_suffix) | ||
| if os.path.exists(built_path): | ||
| self._found_names.append(name) | ||
|
There was a problem hiding this comment. Do we need to prepare There was a problem hiding this comment. It's used in There was a problem hiding this comment. Hmm. It seems that the setuptools There was a problem hiding this comment. It does have |
||
|
|
||
| def _get_build_dir(self): | ||
| # Get the package directory from build_py | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is to ensure we keep the same logic as we have now in setup.py, but we could in theory also leave this out (and ensure the scripts don't explicitly disable Acero when enabling Dataset)