bkietz commented on a change in pull request #9621:
URL: https://github.com/apache/arrow/pull/9621#discussion_r599007804
##########
File path: cpp/src/arrow/compute/api_aggregate.h
##########
@@ -306,5 +306,100 @@ Result<Datum> TDigest(const Datum& value,
const TDigestOptions& options =
TDigestOptions::Defaults(),
ExecContext* ctx = NULLPTR);
+namespace internal {
+
+/// Internal use only: streaming group identifier.
+/// Consumes batches of keys and yields batches of the group ids.
+class ARROW_EXPORT Grouper {
+ public:
+ virtual ~Grouper() = default;
+
+ /// Construct a Grouper which receives the specified key types
+ static Result<std::unique_ptr<Grouper>> Make(const std::vector<ValueDescr>&
descrs,
+ ExecContext* ctx =
default_exec_context());
+
+ /// Consume a batch of keys, producing the corresponding group ids as an
integer array.
+ virtual Result<Datum> Consume(const ExecBatch& batch) = 0;
+
+ /// Get current unique keys. May be called multiple times.
+ virtual Result<ExecBatch> GetUniques() = 0;
+
+ /// Get the current number of groups.
+ virtual uint32_t num_groups() const = 0;
+
+ /// \brief Assemble lists of indices of identical elements.
+ ///
+ /// \param[in] ids An unsigned, all-valid integral array which will be
+ /// used as grouping criteria.
+ /// \param[in] num_groups An upper bound for the elements of ids
Review comment:
Ah, that's a typo. There should be an 8 instead of a 7 below
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
