This is an automated email from the ASF dual-hosted git repository.
zeroshade 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 1ff43ab5ee GH-38516: [Go][Parquet] Increment the number of rows
written when appending a new row group (#38517)
1ff43ab5ee is described below
commit 1ff43ab5ee13de5c3130acf10c7aa8eb9680baab
Author: Tim Schaub <[email protected]>
AuthorDate: Mon Nov 13 10:01:01 2023 -0700
GH-38516: [Go][Parquet] Increment the number of rows written when appending
a new row group (#38517)
### Rationale for this change
This makes it so the `NumRows` method on the `file.Writer` reports the
total number of rows written across multiple row groups.
### Are these changes tested?
A regression test is added that asserts that the total number of rows
written matches expectations.
* Closes: #38516
Authored-by: Tim Schaub <[email protected]>
Signed-off-by: Matt Topol <[email protected]>
---
go/parquet/file/file_writer.go | 1 +
go/parquet/file/file_writer_test.go | 2 ++
2 files changed, 3 insertions(+)
diff --git a/go/parquet/file/file_writer.go b/go/parquet/file/file_writer.go
index 48eb8f44d1..1d7f7840da 100644
--- a/go/parquet/file/file_writer.go
+++ b/go/parquet/file/file_writer.go
@@ -121,6 +121,7 @@ func (fw *Writer) AppendRowGroup() SerialRowGroupWriter {
func (fw *Writer) appendRowGroup(buffered bool) *rowGroupWriter {
if fw.rowGroupWriter != nil {
+ fw.nrows += fw.rowGroupWriter.nrows
fw.rowGroupWriter.Close()
}
fw.rowGroups++
diff --git a/go/parquet/file/file_writer_test.go
b/go/parquet/file/file_writer_test.go
index beceff9732..f32e403a8d 100644
--- a/go/parquet/file/file_writer_test.go
+++ b/go/parquet/file/file_writer_test.go
@@ -97,6 +97,8 @@ func (t *SerializeTestSuite) fileSerializeTest(codec
compress.Compression, expec
writer.Close()
nrows := t.numRowGroups * t.rowsPerRG
+ t.EqualValues(nrows, writer.NumRows())
+
reader, err := file.NewParquetReader(bytes.NewReader(sink.Bytes()))
t.NoError(err)
t.Equal(t.numCols, reader.MetaData().Schema.NumColumns())
