-
Notifications
You must be signed in to change notification settings - Fork 3.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Fix](Outfile) upgrade apache-arrow version to 13.0.0 #35142
Draft
BePPPower
wants to merge
3
commits into
apache:branch-2.0
Choose a base branch
from
BePPPower:upgrade-arrow
base: branch-2.0
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
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
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 |
|---|---|---|
| @@ -0,0 +1,120 @@ | ||
| diff --git a/cpp/src/arrow/adapters/orc/adapter.cc b/cpp/src/arrow/adapters/orc/adapter.cc | ||
| index 2466e7433..46b4402d4 100644 | ||
| --- a/cpp/src/arrow/adapters/orc/adapter.cc | ||
| +++ b/cpp/src/arrow/adapters/orc/adapter.cc | ||
| @@ -47,9 +47,6 @@ | ||
| #include "arrow/util/visibility.h" | ||
| #include "orc/Exceptions.hh" | ||
|
|
||
| -// alias to not interfere with nested orc namespace | ||
| -namespace liborc = orc; | ||
| - | ||
| #define ORC_THROW_NOT_OK(s) \ | ||
| do { \ | ||
| Status _s = (s); \ | ||
| @@ -202,6 +199,8 @@ class ORCFileReader::Impl { | ||
| return Init(); | ||
| } | ||
|
|
||
| + virtual liborc::Reader* GetRawORCReader() { return reader_.get(); } | ||
| + | ||
| Status Init() { | ||
| int64_t nstripes = reader_->getNumberOfStripes(); | ||
| stripes_.resize(nstripes); | ||
| @@ -479,6 +478,31 @@ class ORCFileReader::Impl { | ||
| return Status::OK(); | ||
| } | ||
|
|
||
| + Result<std::shared_ptr<RecordBatchReader>> NextStripeReader( | ||
| + int64_t batch_size, const std::vector<std::string>& include_names) { | ||
| + if (current_row_ >= NumberOfRows()) { | ||
| + return nullptr; | ||
| + } | ||
| + | ||
| + liborc::RowReaderOptions opts = default_row_reader_options(); | ||
| + if (!include_names.empty()) { | ||
| + RETURN_NOT_OK(SelectNames(&opts, include_names)); | ||
| + } | ||
| + StripeInformation stripe_info({0, 0, 0, 0}); | ||
| + RETURN_NOT_OK(SelectStripeWithRowNumber(&opts, current_row_, &stripe_info)); | ||
| + ARROW_ASSIGN_OR_RAISE(auto schema, ReadSchema(opts)); | ||
| + std::unique_ptr<liborc::RowReader> row_reader; | ||
| + | ||
| + ORC_BEGIN_CATCH_NOT_OK | ||
| + row_reader = reader_->createRowReader(opts); | ||
| + row_reader->seekToRow(current_row_); | ||
| + current_row_ = stripe_info.first_row_id + stripe_info.num_rows; | ||
| + ORC_END_CATCH_NOT_OK | ||
| + | ||
| + return std::make_shared<OrcStripeReader>(std::move(row_reader), schema, batch_size, | ||
| + pool_); | ||
| + } | ||
| + | ||
| Result<std::shared_ptr<RecordBatchReader>> NextStripeReader( | ||
| int64_t batch_size, const std::vector<int>& include_indices) { | ||
| if (current_row_ >= NumberOfRows()) { | ||
| @@ -544,6 +568,8 @@ Result<std::unique_ptr<ORCFileReader>> ORCFileReader::Open( | ||
| return std::move(result); | ||
| } | ||
|
|
||
| +liborc::Reader* ORCFileReader::GetRawORCReader() { return impl_->GetRawORCReader(); } | ||
| + | ||
| Result<std::shared_ptr<const KeyValueMetadata>> ORCFileReader::ReadMetadata() { | ||
| return impl_->ReadMetadata(); | ||
| } | ||
| @@ -605,6 +631,11 @@ Result<std::shared_ptr<RecordBatchReader>> ORCFileReader::NextStripeReader( | ||
| return impl_->NextStripeReader(batch_size, include_indices); | ||
| } | ||
|
|
||
| +Result<std::shared_ptr<RecordBatchReader>> ORCFileReader::NextStripeReader( | ||
| + int64_t batch_size, const std::vector<std::string>& include_names) { | ||
| + return impl_->NextStripeReader(batch_size, include_names); | ||
| +} | ||
| + | ||
| int64_t ORCFileReader::NumberOfStripes() { return impl_->NumberOfStripes(); } | ||
|
|
||
| int64_t ORCFileReader::NumberOfRows() { return impl_->NumberOfRows(); } | ||
| diff --git a/cpp/src/arrow/adapters/orc/adapter.h b/cpp/src/arrow/adapters/orc/adapter.h | ||
| index 013be7860..7fd06bcb8 100644 | ||
| --- a/cpp/src/arrow/adapters/orc/adapter.h | ||
| +++ b/cpp/src/arrow/adapters/orc/adapter.h | ||
| @@ -30,6 +30,10 @@ | ||
| #include "arrow/type_fwd.h" | ||
| #include "arrow/util/macros.h" | ||
| #include "arrow/util/visibility.h" | ||
| +#include "orc/Reader.hh" | ||
| + | ||
| +// alias to not interfere with nested orc namespace | ||
| +namespace liborc = orc; | ||
|
|
||
| namespace arrow { | ||
| namespace adapters { | ||
| @@ -53,6 +57,9 @@ class ARROW_EXPORT ORCFileReader { | ||
| public: | ||
| ~ORCFileReader(); | ||
|
|
||
| + /// \brief Get ORC reader from inside. | ||
| + liborc::Reader* GetRawORCReader(); | ||
| + | ||
| /// \brief Creates a new ORC reader | ||
| /// | ||
| /// \param[in] file the data source | ||
| @@ -174,6 +181,19 @@ class ARROW_EXPORT ORCFileReader { | ||
| Result<std::shared_ptr<RecordBatchReader>> GetRecordBatchReader( | ||
| int64_t batch_size, const std::vector<std::string>& include_names); | ||
|
|
||
| + /// \brief Get a stripe level record batch iterator with specified row count | ||
| + /// in each record batch. NextStripeReader serves as a fine grain | ||
| + /// alternative to ReadStripe which may cause OOM issue by loading | ||
| + /// the whole stripes into memory. | ||
| + /// | ||
| + /// \param[in] batch_size Get a stripe level record batch iterator with specified row | ||
| + /// count in each record batch. | ||
| + /// | ||
| + /// \param[in] include_names the selected field names to read | ||
| + /// \return the returned stripe reader | ||
| + Result<std::shared_ptr<RecordBatchReader>> NextStripeReader( | ||
| + int64_t batch_size, const std::vector<std::string>& include_names); | ||
| + | ||
| /// \brief The number of stripes in the file | ||
| int64_t NumberOfStripes(); |
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
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.
change comment
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.
done