badalprasadsingh commented on code in PR #524:
URL: https://github.com/apache/iceberg-go/pull/524#discussion_r2324013619
##########
manifest.go:
##########
@@ -1461,33 +1598,114 @@ func mapToAvroColMap[K comparable, V any](m map[K]V)
*[]colMap[K, V] {
return &out
}
-func avroPartitionData(input map[int]any, logicalTypes
map[int]avro.LogicalType) map[int]any {
+func avroPartitionData(input map[int]any, logicalTypes
map[int]avro.LogicalType, fixedSizes map[int]int) map[int]any {
out := make(map[int]any)
for k, v := range input {
if logical, ok := logicalTypes[k]; ok {
- switch logical {
- case avro.Date:
- out[k] =
Date(v.(time.Time).Truncate(24*time.Hour).Unix() / int64((time.Hour *
24).Seconds()))
- case avro.TimeMillis:
- out[k] = Time(v.(time.Duration).Milliseconds())
- case avro.TimeMicros:
- out[k] = Time(v.(time.Duration).Microseconds())
- case avro.TimestampMillis:
- out[k] =
Timestamp(v.(time.Time).UTC().UnixMilli())
- case avro.TimestampMicros:
- out[k] =
Timestamp(v.(time.Time).UTC().UnixMicro())
- default:
- out[k] = v
- }
-
- continue
+ out[k] = convertLogicalTypeValue(v, logical,
fixedSizes[k])
+ } else {
+ out[k] = convertDefaultValue(v, fixedSizes[k])
}
- out[k] = v
}
return out
}
+func convertLogicalTypeValue(v any, logicalType avro.LogicalType, fixedSize
int) any {
+ switch logicalType {
+ case avro.Date:
+ return convertDateValue(v)
+ case avro.TimeMicros:
+ return convertTimeMicrosValue(v)
+ case avro.TimestampMicros:
+ return convertTimestampMicrosValue(v)
+ case avro.Decimal:
+ return convertDecimalValue(v, fixedSize)
+ default:
+ return v
+ }
+}
+
+func convertDateValue(v any) any {
+ if t, ok := v.(time.Time); ok {
+ return map[string]any{"int.date":
int32(t.Truncate(24*time.Hour).Unix() / int64((time.Hour * 24).Seconds()))}
+ }
+ if d, ok := v.(Date); ok {
+ return map[string]any{"int.date": int32(d)}
+ }
+
+ return v
+}
+
+func convertTimeMicrosValue(v any) any {
+ if t, ok := v.(Time); ok {
+ return map[string]any{"long.time-micros": int64(t)}
+ }
+ if d, ok := v.(time.Duration); ok {
+ return map[string]any{"long.time-micros": d.Microseconds()}
+ }
+
+ return v
+}
+
+func convertTimestampMicrosValue(v any) any {
+ if t, ok := v.(time.Time); ok {
+ return map[string]any{"long.timestamp-micros":
t.UTC().UnixMicro()}
+ }
+ if ts, ok := v.(Timestamp); ok {
+ return map[string]any{"long.timestamp-micros": int64(ts)}
+ }
+
+ return v
+}
+
+func convertDecimalValue(v any, fixedSize int) any {
+ if v == nil {
+ return map[string]any{"null": nil}
+ }
+
+ dec, ok := v.(Decimal)
+ if !ok {
+ return v
+ }
+
+ bytes, err := DecimalLiteral(dec).MarshalBinary()
+ if err != nil {
+ return v
+ }
+ fixedArray := convertToFixedArray(padOrTruncateBytes(bytes, fixedSize),
fixedSize)
+
+ return map[string]any{"fixed": fixedArray}
+}
+
+func convertDefaultValue(v any, fixedSize int) any {
+ if uuidVal, ok := v.(uuid.UUID); ok {
+ return uuidVal.String()
+ }
+
+ if bytes, ok := v.([]byte); ok && fixedSize > 0 {
+ return convertToFixedArray(padOrTruncateBytes(bytes,
fixedSize), fixedSize)
Review Comment:
well, for the nullable uuid schema, it is defined as a fixed-length schema
expecting exactly 16 bytes.
```json
["null",{"name":"uuid","type":"fixed","size":16,"logicalType":"uuid"}]
```
further on passing it like:
```go
return map[string]any{"uuid": fixedArray}
```
we explicitly telling `avro` to use the union branch named `uuid` and the
value for that branch is `fixedArray`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
