Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
37 changes: 37 additions & 0 deletions be/src/exprs/hybrid_set.h
Original file line number Diff line number Diff line change
Expand Up @@ -257,6 +257,7 @@ class HybridSetBase : public FilterBase {
doris::vectorized::ColumnUInt8::Container& results) = 0;

virtual void to_pb(PInFilter* filter) = 0;
virtual uint64_t get_digest(uint64_t seed) = 0;

class IteratorBase {
public:
Expand Down Expand Up @@ -412,6 +413,21 @@ class HybridSet : public HybridSetBase {

void to_pb(PInFilter* filter) override { set_pb(filter, get_convertor<ElementType>()); }

uint64_t get_digest(uint64_t seed) override {
std::vector<ElementType> elems(_set.begin(), _set.end());
std::sort(elems.begin(), elems.end());
if constexpr (std::is_same<ElementType, bool>::value) {
for (const auto& v : elems) {
seed = HashUtil::crc_hash64(&v, sizeof(v), seed);
}
} else {
seed = HashUtil::crc_hash64(elems.data(),
(uint32_t)(elems.size() * sizeof(ElementType)), seed);
}

return HashUtil::crc_hash64(&_contain_null, sizeof(_contain_null), seed);
}

private:
ContainerType _set;
ObjectPool _pool;
Expand Down Expand Up @@ -589,6 +605,16 @@ class StringSet : public HybridSetBase {

void to_pb(PInFilter* filter) override { set_pb(filter, get_convertor<std::string>()); }

uint64_t get_digest(uint64_t seed) override {
std::vector<StringRef> elems(_set.begin(), _set.end());
std::sort(elems.begin(), elems.end());

for (const auto& v : elems) {
seed = HashUtil::crc_hash64(v.data, (uint32_t)v.size, seed);
}
return HashUtil::crc_hash64(&_contain_null, sizeof(_contain_null), seed);
}

private:
ContainerType _set;
ObjectPool _pool;
Expand Down Expand Up @@ -767,6 +793,17 @@ class StringValueSet : public HybridSetBase {
throw Exception(ErrorCode::INTERNAL_ERROR, "StringValueSet do not support to_pb");
}

uint64_t get_digest(uint64_t seed) override {
std::vector<StringRef> elems(_set.begin(), _set.end());
std::sort(elems.begin(), elems.end());

for (const auto& v : elems) {
seed = HashUtil::crc_hash64(v.data, (uint32_t)v.size, seed);
}

return HashUtil::crc_hash64(&_contain_null, sizeof(_contain_null), seed);
}

private:
ContainerType _set;
ObjectPool _pool;
Expand Down
2 changes: 1 addition & 1 deletion be/src/vec/exprs/vdirect_in_predicate.h
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,7 @@ class VDirectInPredicate final : public VExpr {
return true;
}

uint64_t get_digest(uint64_t seed) const override { return 0; }
uint64_t get_digest(uint64_t seed) const override { return _filter->get_digest(seed); }

private:
Status _do_execute(VExprContext* context, const Block* block, ColumnPtr& result_column,
Expand Down
Loading