Skip to content
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.

Sign up for GitHub

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

Bugfix/parquet inventory failure #1979

Merged
merged 4 commits into from
May 23, 2021
Merged

Bugfix/parquet inventory failure #1979

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b9ba9b6
fix manifest sort bug
johnnyaug May 20, 2021
92f100a
remove logging
johnnyaug May 20, 2021
a993a50
Merge branch 'master' into bugfix/parquet_inventory_failure
johnnyaug May 23, 2021
3aea463
cr fixes
johnnyaug May 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 15 additions & 6 deletions pkg/cloud/aws/s3inventory/parquet_reader.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,20 +35,29 @@ func (p *ParquetInventoryFileReader) Close() error {
return p.PFile.Close()
}

func (p *ParquetInventoryFileReader) getKeyColumnStatistics() *parquet.Statistics {
for i, c := range p.Footer.RowGroups[0].Columns {
func (p *ParquetInventoryFileReader) getKeyColumnStatistics(rowGroupIdx int) *parquet.Statistics {
for i, c := range p.Footer.RowGroups[rowGroupIdx].Columns {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

simplify by replacing all occurrences:

	columns := p.Footer.RowGroups[rowGroupIdx].Columns

and inside the loop:

	metaData := c.GetMetaData()

if c.MetaData.PathInSchema[len(c.GetMetaData().GetPathInSchema())-1] == "Key" {
return p.Footer.RowGroups[0].Columns[i].GetMetaData().GetStatistics()
return p.Footer.RowGroups[rowGroupIdx].Columns[i].GetMetaData().GetStatistics()
}
}
return p.Footer.RowGroups[0].Columns[1].GetMetaData().GetStatistics()
return p.Footer.RowGroups[rowGroupIdx].Columns[1].GetMetaData().GetStatistics()
}

func (p *ParquetInventoryFileReader) FirstObjectKey() string {
return string(p.getKeyColumnStatistics().GetMin())
statistics := p.getKeyColumnStatistics(0)
if len(statistics.GetMin()) > 0 {
return string(statistics.GetMin())
}
return string(statistics.GetMinValue())
}

func (p *ParquetInventoryFileReader) LastObjectKey() string {
return string(p.getKeyColumnStatistics().GetMax())
statistics := p.getKeyColumnStatistics(len(p.Footer.RowGroups) - 1)
if len(statistics.GetMax()) > 0 {
return string(statistics.GetMax())
}
return string(statistics.GetMinValue())
}

func (p *ParquetInventoryFileReader) Read(n int) ([]*InventoryObject, error) {
Expand Down