Files
s3/weed/mq/schema/write_parquet_test.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

175 lines
4.4 KiB
Go

package schema
import (
"fmt"
"io"
"os"
"testing"
"github.com/parquet-go/parquet-go"
"github.com/parquet-go/parquet-go/compress/zstd"
"github.com/seaweedfs/seaweedfs/weed/pb/schema_pb"
)
func TestWriteReadParquet(t *testing.T) {
// create a schema_pb.RecordType
recordType := RecordTypeBegin().
WithField("ID", TypeInt64).
WithField("CreatedAt", TypeInt64).
WithRecordField("Person",
RecordTypeBegin().
WithField("zName", TypeString).
WithField("emails", ListOf(TypeString)).
RecordTypeEnd()).
WithField("Company", TypeString).
WithRecordField("Address",
RecordTypeBegin().
WithField("Street", TypeString).
WithField("City", TypeString).
RecordTypeEnd()).
RecordTypeEnd()
fmt.Printf("RecordType: %v\n", recordType)
// create a parquet schema
parquetSchema, err := ToParquetSchema("example", recordType)
if err != nil {
t.Fatalf("ToParquetSchema failed: %v", err)
}
fmt.Printf("ParquetSchema: %v\n", parquetSchema)
fmt.Printf("Go Type: %+v\n", parquetSchema.GoType())
filename := "example.parquet"
count := 3
testWritingParquetFile(t, count, filename, parquetSchema, recordType)
total := testReadingParquetFile(t, filename, parquetSchema, recordType)
if total != count {
t.Fatalf("total != 128*1024: %v", total)
}
if err = os.Remove(filename); err != nil {
t.Fatalf("os.Remove failed: %v", err)
}
}
func testWritingParquetFile(t *testing.T, count int, filename string, parquetSchema *parquet.Schema, recordType *schema_pb.RecordType) {
parquetLevels, err := ToParquetLevels(recordType)
if err != nil {
t.Fatalf("ToParquetLevels failed: %v", err)
}
// create a parquet file
file, err := os.OpenFile(filename, os.O_CREATE|os.O_TRUNC|os.O_WRONLY, 0664)
if err != nil {
t.Fatalf("os.Open failed: %v", err)
}
defer file.Close()
writer := parquet.NewWriter(file, parquetSchema, parquet.Compression(&zstd.Codec{Level: zstd.DefaultLevel}))
rowBuilder := parquet.NewRowBuilder(parquetSchema)
for i := 0; i < count; i++ {
rowBuilder.Reset()
// generate random data
recordValue := RecordBegin().
SetInt64("ID", 1+int64(i)).
SetInt64("CreatedAt", 2+2*int64(i)).
SetRecord("Person",
RecordBegin().
SetString("zName", fmt.Sprintf("john_%d", i)).
SetStringList("emails",
fmt.Sprintf("john_%[email protected]", i),
fmt.Sprintf("john_%[email protected]", i),
fmt.Sprintf("john_%[email protected]", i),
fmt.Sprintf("john_%[email protected]", i),
fmt.Sprintf("john_%[email protected]", i)).
RecordEnd()).
SetString("Company", fmt.Sprintf("company_%d", i)).
RecordEnd()
AddRecordValue(rowBuilder, recordType, parquetLevels, recordValue)
if count < 10 {
fmt.Printf("Write RecordValue: %v\n", recordValue)
}
row := rowBuilder.Row()
if count < 10 {
fmt.Printf("Build Row: %+v\n", row)
}
if err != nil {
t.Fatalf("rowBuilder.Build failed: %v", err)
}
if _, err = writer.WriteRows([]parquet.Row{row}); err != nil {
t.Fatalf("writer.Write failed: %v", err)
}
}
if err = writer.Close(); err != nil {
t.Fatalf("writer.WriteStop failed: %v", err)
}
}
func testReadingParquetFile(t *testing.T, filename string, parquetSchema *parquet.Schema, recordType *schema_pb.RecordType) (total int) {
parquetLevels, err := ToParquetLevels(recordType)
if err != nil {
t.Fatalf("ToParquetLevels failed: %v", err)
}
// read the parquet file
file, err := os.Open(filename)
if err != nil {
t.Fatalf("os.Open failed: %v", err)
}
defer file.Close()
// Get file info to determine size
fileInfo, err := file.Stat()
if err != nil {
t.Fatalf("file.Stat failed: %v", err)
}
// Create a parquet file from the opened file
parquetFile, err := parquet.OpenFile(file, fileInfo.Size())
if err != nil {
t.Fatalf("parquet.OpenFile failed: %v", err)
}
reader := parquet.NewReader(parquetFile)
rows := make([]parquet.Row, 128)
for {
rowCount, err := reader.ReadRows(rows)
// Process the rows first, even if EOF is returned
for i := 0; i < rowCount; i++ {
row := rows[i]
// convert parquet row to schema_pb.RecordValue
recordValue, err := ToRecordValue(recordType, parquetLevels, row)
if err != nil {
t.Fatalf("ToRecordValue failed: %v", err)
}
if rowCount < 10 {
fmt.Printf("Read RecordValue: %v\n", recordValue)
}
}
total += rowCount
// Check for end conditions after processing rows
if err != nil {
if err == io.EOF {
break
}
t.Fatalf("reader.Read failed: %v", err)
}
if rowCount == 0 {
break
}
}
fmt.Printf("total: %v\n", total)
return
}