Skip to content

fix: Optimized CSV writing #579

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

Merged
merged 2 commits into from
Oct 3, 2024
Merged

fix: Optimized CSV writing #579

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ba50dca
fix: Optimized CSV writing
disq Oct 3, 2024
56c4670
Undo go.mod change
disq Oct 3, 2024
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
17 changes: 9 additions & 8 deletions csv/write.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@ import (
)

type Handle struct {
w *csv.Writer
w *csv.Writer
schema *arrow.Schema
}

var _ types.Handle = (*Handle)(nil)
Expand All @@ -30,13 +31,14 @@ func (cl *Client) WriteHeader(w io.Writer, t *schema.Table) (types.Handle, error
)

return &Handle{
w: writer,
w: writer,
schema: newSchema,
}, nil
}

func (h *Handle) WriteContent(records []arrow.Record) error {
for _, record := range records {
castRec := castToString(record)
castRec := h.castToString(record)
if err := h.w.Write(castRec); err != nil {
return fmt.Errorf("failed to write record to csv: %w", err)
}
Expand Down Expand Up @@ -89,10 +91,9 @@ func isTypeSupported(t arrow.DataType) bool {
}

// castToString casts extension columns or unsupported columns to string. It does not release the original record.
func castToString(rec arrow.Record) arrow.Record {
newSchema := convertSchema(rec.Schema())
cols := make([]arrow.Array, rec.NumCols())
for c := 0; c < int(rec.NumCols()); c++ {
func (h *Handle) castToString(rec arrow.Record) arrow.Record {
cols := make([]arrow.Array, h.schema.NumFields())
for c := 0; c < h.schema.NumFields(); c++ {
col := rec.Column(c)
if isTypeSupported(col.DataType()) {
cols[c] = col
Expand All @@ -109,7 +110,7 @@ func castToString(rec arrow.Record) arrow.Record {
}
cols[c] = sb.NewArray()
}
return array.NewRecord(newSchema, cols, rec.NumRows())
return array.NewRecord(h.schema, cols, rec.NumRows())
}

func stripCQExtensionMetadata(md arrow.Metadata) arrow.Metadata {
Expand Down
Loading