This is an automated email from the ASF dual-hosted git repository.
kszucs pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new f7bc27132e GH-46132: [C++][Parquet] Remove deprecated parquet APIs
from 19.0.0 (#46133)
f7bc27132e is described below
commit f7bc27132ea84c4639528d73a9c289c7a1db154f
Author: Alenka Frim <[email protected]>
AuthorDate: Tue Apr 15 15:29:39 2025 +0200
GH-46132: [C++][Parquet] Remove deprecated parquet APIs from 19.0.0 (#46133)
### Rationale for this change
`GetRecordBatchReader` in reader.h and `NewRowGroup` with `chunk_size` in
writer.h have been deprecated in 19.0.0.
### What changes are included in this PR?
Deprecated functions are removed.
### Are these changes tested?
Existing tests should pass.
### Are there any user-facing changes?
No, deprecated functionality is removed.
* GitHub Issue: #46132
Authored-by: AlenkaF <[email protected]>
Signed-off-by: Krisztian Szucs <[email protected]>
---
cpp/examples/arrow/parquet_read_write.cc | 2 +-
cpp/src/arrow/filesystem/s3fs_benchmark.cc | 4 +--
cpp/src/parquet/arrow/reader.cc | 40 --------------------------
cpp/src/parquet/arrow/reader.h | 45 ------------------------------
cpp/src/parquet/arrow/writer.h | 7 -----
5 files changed, 3 insertions(+), 95 deletions(-)
diff --git a/cpp/examples/arrow/parquet_read_write.cc
b/cpp/examples/arrow/parquet_read_write.cc
index b952f925c6..2465018966 100644
--- a/cpp/examples/arrow/parquet_read_write.cc
+++ b/cpp/examples/arrow/parquet_read_write.cc
@@ -67,7 +67,7 @@ arrow::Status ReadInBatches(std::string path_to_file) {
ARROW_ASSIGN_OR_RAISE(arrow_reader, reader_builder.Build());
std::shared_ptr<::arrow::RecordBatchReader> rb_reader;
- ARROW_RETURN_NOT_OK(arrow_reader->GetRecordBatchReader(&rb_reader));
+ ARROW_ASSIGN_OR_RAISE(rb_reader, arrow_reader->GetRecordBatchReader());
for (arrow::Result<std::shared_ptr<arrow::RecordBatch>> maybe_batch :
*rb_reader) {
// Operate on each batch...
diff --git a/cpp/src/arrow/filesystem/s3fs_benchmark.cc
b/cpp/src/arrow/filesystem/s3fs_benchmark.cc
index b7b6dda641..0cdcb03702 100644
--- a/cpp/src/arrow/filesystem/s3fs_benchmark.cc
+++ b/cpp/src/arrow/filesystem/s3fs_benchmark.cc
@@ -318,8 +318,8 @@ static void ParquetRead(benchmark::State& st, S3FileSystem*
fs, const std::strin
std::shared_ptr<Table> table;
ASSERT_OK(reader->ReadTable(column_indices, &table));
} else {
- std::shared_ptr<RecordBatchReader> rb_reader;
- ASSERT_OK(reader->GetRecordBatchReader({0}, column_indices, &rb_reader));
+ ASSERT_OK_AND_ASSIGN(auto rb_reader, reader->GetRecordBatchReader(
+ std::vector<int>{0},
column_indices));
ASSERT_OK(rb_reader->ToTable());
}
diff --git a/cpp/src/parquet/arrow/reader.cc b/cpp/src/parquet/arrow/reader.cc
index a6294cb1b6..bc0b7aa51c 100644
--- a/cpp/src/parquet/arrow/reader.cc
+++ b/cpp/src/parquet/arrow/reader.cc
@@ -1300,46 +1300,6 @@ std::shared_ptr<RowGroupReader>
FileReaderImpl::RowGroup(int row_group_index) {
// ----------------------------------------------------------------------
// Public factory functions
-Status FileReader::GetRecordBatchReader(std::unique_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(*out, GetRecordBatchReader());
- return Status::OK();
-}
-
-Status FileReader::GetRecordBatchReader(const std::vector<int>&
row_group_indices,
- std::unique_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(*out, GetRecordBatchReader(row_group_indices));
- return Status::OK();
-}
-
-Status FileReader::GetRecordBatchReader(const std::vector<int>&
row_group_indices,
- const std::vector<int>& column_indices,
- std::unique_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(*out, GetRecordBatchReader(row_group_indices,
column_indices));
- return Status::OK();
-}
-
-Status FileReader::GetRecordBatchReader(std::shared_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(auto tmp, GetRecordBatchReader());
- out->reset(tmp.release());
- return Status::OK();
-}
-
-Status FileReader::GetRecordBatchReader(const std::vector<int>&
row_group_indices,
- std::shared_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(auto tmp, GetRecordBatchReader(row_group_indices));
- out->reset(tmp.release());
- return Status::OK();
-}
-
-Status FileReader::GetRecordBatchReader(const std::vector<int>&
row_group_indices,
- const std::vector<int>& column_indices,
- std::shared_ptr<RecordBatchReader>*
out) {
- ARROW_ASSIGN_OR_RAISE(auto tmp,
- GetRecordBatchReader(row_group_indices,
column_indices));
- out->reset(tmp.release());
- return Status::OK();
-}
-
Status FileReader::Make(::arrow::MemoryPool* pool,
std::unique_ptr<ParquetFileReader> reader,
const ArrowReaderProperties& properties,
diff --git a/cpp/src/parquet/arrow/reader.h b/cpp/src/parquet/arrow/reader.h
index 476a940bf1..4a01d7c4e4 100644
--- a/cpp/src/parquet/arrow/reader.h
+++ b/cpp/src/parquet/arrow/reader.h
@@ -154,29 +154,10 @@ class PARQUET_EXPORT FileReader {
virtual ::arrow::Status ReadColumn(int i,
std::shared_ptr<::arrow::ChunkedArray>*
out) = 0;
- /// \brief Return a RecordBatchReader of all row groups and columns.
- ///
- /// \deprecated Deprecated in 19.0.0. Use arrow::Result version instead.
- ARROW_DEPRECATED("Deprecated in 19.0.0. Use arrow::Result version instead.")
- ::arrow::Status
GetRecordBatchReader(std::unique_ptr<::arrow::RecordBatchReader>* out);
-
/// \brief Return a RecordBatchReader of all row groups and columns.
virtual ::arrow::Result<std::unique_ptr<::arrow::RecordBatchReader>>
GetRecordBatchReader() = 0;
- /// \brief Return a RecordBatchReader of row groups selected from
row_group_indices.
- ///
- /// Note that the ordering in row_group_indices matters. FileReaders must
outlive
- /// their RecordBatchReaders.
- ///
- /// \returns error Status if row_group_indices contains an invalid index
- ///
- /// \deprecated Deprecated in 19.0.0. Use arrow::Result version instead.
- ARROW_DEPRECATED("Deprecated in 19.0.0. Use arrow::Result version instead.")
- virtual ::arrow::Status GetRecordBatchReader(
- const std::vector<int>& row_group_indices,
- std::unique_ptr<::arrow::RecordBatchReader>* out);
-
/// \brief Return a RecordBatchReader of row groups selected from
row_group_indices.
///
/// Note that the ordering in row_group_indices matters. FileReaders must
outlive
@@ -186,21 +167,6 @@ class PARQUET_EXPORT FileReader {
virtual ::arrow::Result<std::unique_ptr<::arrow::RecordBatchReader>>
GetRecordBatchReader(const std::vector<int>& row_group_indices) = 0;
- /// \brief Return a RecordBatchReader of row groups selected from
- /// row_group_indices, whose columns are selected by column_indices.
- ///
- /// Note that the ordering in row_group_indices and column_indices
- /// matter. FileReaders must outlive their RecordBatchReaders.
- ///
- /// \returns error Status if either row_group_indices or column_indices
- /// contains an invalid index
- ///
- /// \deprecated Deprecated in 19.0.0. Use arrow::Result version instead.
- ARROW_DEPRECATED("Deprecated in 19.0.0. Use arrow::Result version instead.")
- virtual ::arrow::Status GetRecordBatchReader(
- const std::vector<int>& row_group_indices, const std::vector<int>&
column_indices,
- std::unique_ptr<::arrow::RecordBatchReader>* out);
-
/// \brief Return a RecordBatchReader of row groups selected from
/// row_group_indices, whose columns are selected by column_indices.
///
@@ -387,17 +353,6 @@ class PARQUET_EXPORT FileReaderBuilder {
///
/// @{
-/// \brief Build FileReader from Arrow file and MemoryPool
-///
-/// Advanced settings are supported through the FileReaderBuilder class.
-///
-/// \deprecated Deprecated in 19.0.0. Use arrow::Result version instead.
-ARROW_DEPRECATED("Deprecated in 19.0.0. Use arrow::Result version instead.")
-PARQUET_EXPORT
-::arrow::Status OpenFile(std::shared_ptr<::arrow::io::RandomAccessFile>,
- ::arrow::MemoryPool* allocator,
- std::unique_ptr<FileReader>* reader);
-
/// \brief Build FileReader from Arrow file and MemoryPool
///
/// Advanced settings are supported through the FileReaderBuilder class.
diff --git a/cpp/src/parquet/arrow/writer.h b/cpp/src/parquet/arrow/writer.h
index e36b8f252c..8ec8796ffd 100644
--- a/cpp/src/parquet/arrow/writer.h
+++ b/cpp/src/parquet/arrow/writer.h
@@ -89,13 +89,6 @@ class PARQUET_EXPORT FileWriter {
/// Returns an error if not all columns have been written.
virtual ::arrow::Status NewRowGroup() = 0;
- /// \brief Start a new row group.
- ///
- /// \deprecated Deprecated in 19.0.0.
- ARROW_DEPRECATED(
- "Deprecated in 19.0.0. Use NewRowGroup() without the `chunk_size`
argument.")
- virtual ::arrow::Status NewRowGroup(int64_t chunk_size) { return
NewRowGroup(); }
-
/// \brief Write ColumnChunk in row group using an array.
virtual ::arrow::Status WriteColumnChunk(const ::arrow::Array& data) = 0;
