zeroshade commented on code in PR #872:
URL: https://github.com/apache/arrow-go/pull/872#discussion_r3502096949
##########
arrow/array/data.go:
##########
@@ -270,12 +268,59 @@ func NewSliceData(data arrow.ArrayData, i, j int64)
arrow.ArrayData {
func Hash(h *maphash.MapHash, data arrow.ArrayData) {
a := data.(*Data)
- h.Write((*[bits.UintSize / 8]byte)(unsafe.Pointer(&a.length))[:])
- h.Write((*[bits.UintSize / 8]byte)(unsafe.Pointer(&a.length))[:])
- if len(a.buffers) > 0 && a.buffers[0] != nil {
- h.Write(a.buffers[0].Bytes())
+ hashString(h, a.dtype.Fingerprint())
+ hashInt(h, a.length)
+ hashInt(h, a.offset)
+
+ hashInt(h, len(a.buffers))
+ for _, b := range a.buffers {
+ if b == nil {
+ hashByte(h, 0)
+ continue
+ }
+
+ hashByte(h, 1)
+ hashBytes(h, b.Bytes())
}
+
+ hashInt(h, len(a.childData))
for _, c := range a.childData {
+ if c == nil {
+ hashByte(h, 0)
+ continue
+ }
+
+ hashByte(h, 1)
Hash(h, c)
}
+
+ if a.dictionary == nil {
+ hashByte(h, 0)
+ return
+ }
+
+ hashByte(h, 1)
+ Hash(h, a.dictionary)
+}
+
+func hashByte(h *maphash.MapHash, v byte) {
+ var b [1]byte
+ b[0] = v
+ h.Write(b[:])
+}
+
+func hashInt(h *maphash.MapHash, v int) {
+ var b [8]byte
+ binary.LittleEndian.PutUint64(b[:], uint64(int64(v)))
+ h.Write(b[:])
+}
+
+func hashBytes(h *maphash.MapHash, b []byte) {
+ hashInt(h, len(b))
Review Comment:
why do we need to separately hash the length? isn't `h.Write(b)` sufficient?
##########
arrow/array/data.go:
##########
@@ -270,12 +268,59 @@ func NewSliceData(data arrow.ArrayData, i, j int64)
arrow.ArrayData {
func Hash(h *maphash.MapHash, data arrow.ArrayData) {
a := data.(*Data)
- h.Write((*[bits.UintSize / 8]byte)(unsafe.Pointer(&a.length))[:])
- h.Write((*[bits.UintSize / 8]byte)(unsafe.Pointer(&a.length))[:])
- if len(a.buffers) > 0 && a.buffers[0] != nil {
- h.Write(a.buffers[0].Bytes())
+ hashString(h, a.dtype.Fingerprint())
+ hashInt(h, a.length)
+ hashInt(h, a.offset)
+
+ hashInt(h, len(a.buffers))
+ for _, b := range a.buffers {
+ if b == nil {
+ hashByte(h, 0)
+ continue
+ }
+
+ hashByte(h, 1)
+ hashBytes(h, b.Bytes())
}
+
+ hashInt(h, len(a.childData))
for _, c := range a.childData {
+ if c == nil {
+ hashByte(h, 0)
+ continue
+ }
+
+ hashByte(h, 1)
Hash(h, c)
}
+
+ if a.dictionary == nil {
+ hashByte(h, 0)
+ return
+ }
+
+ hashByte(h, 1)
+ Hash(h, a.dictionary)
+}
+
+func hashByte(h *maphash.MapHash, v byte) {
+ var b [1]byte
+ b[0] = v
+ h.Write(b[:])
+}
+
+func hashInt(h *maphash.MapHash, v int) {
+ var b [8]byte
+ binary.LittleEndian.PutUint64(b[:], uint64(int64(v)))
+ h.Write(b[:])
+}
+
+func hashBytes(h *maphash.MapHash, b []byte) {
+ hashInt(h, len(b))
+ h.Write(b)
+}
+
+func hashString(h *maphash.MapHash, s string) {
+ hashInt(h, len(s))
+ h.WriteString(s)
Review Comment:
same question as above, isn't `h.WriteString(s)` sufficient?
--
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]
