isin init

R-JunmingChen · Aug 18, 2023 · b79a4dc · b79a4dc
1 parent 60bbb14
commit b79a4dc
Show file tree

Hide file tree

Showing 3 changed files with 80 additions and 207 deletions.
diff --git a/cpp/src/arrow/compute/api_scalar.cc b/cpp/src/arrow/compute/api_scalar.cc
@@ -344,7 +344,8 @@ static auto kRoundToMultipleOptionsType = GetFunctionOptionsType<RoundToMultiple
     DataMember("round_mode", &RoundToMultipleOptions::round_mode));
 static auto kSetLookupOptionsType = GetFunctionOptionsType<SetLookupOptions>(
     DataMember("value_set", &SetLookupOptions::value_set),
-    DataMember("skip_nulls", &SetLookupOptions::skip_nulls));
+    DataMember("skip_nulls", &SetLookupOptions::skip_nulls),
+    DataMember("null_matching_behavior", &SetLookupOptions::null_matching_behavior));
 static auto kSliceOptionsType = GetFunctionOptionsType<SliceOptions>(
     DataMember("start", &SliceOptions::start), DataMember("stop", &SliceOptions::stop),
     DataMember("step", &SliceOptions::step));
@@ -540,8 +541,29 @@ constexpr char RoundToMultipleOptions::kTypeName[];
 SetLookupOptions::SetLookupOptions(Datum value_set, bool skip_nulls)
     : FunctionOptions(internal::kSetLookupOptionsType),
       value_set(std::move(value_set)),
-      skip_nulls(skip_nulls) {}
-SetLookupOptions::SetLookupOptions() : SetLookupOptions({}, false) {}
+      skip_nulls(skip_nulls) {
+  if (skip_nulls) {
+    this->null_matching_behavior = SetLookupOptions::NullMatchingBehavior::SKIP;
+  } else {
+    this->null_matching_behavior = SetLookupOptions::NullMatchingBehavior::MATCH;
+  }
+}
+SetLookupOptions::SetLookupOptions(
+    Datum value_set, SetLookupOptions::NullMatchingBehavior null_matching_behavior)
+    : FunctionOptions(internal::kSetLookupOptionsType),
+      value_set(std::move(value_set)),
+      null_matching_behavior(std::move(null_matching_behavior)) {}
+SetLookupOptions::SetLookupOptions()
+    : SetLookupOptions({}, SetLookupOptions::NullMatchingBehavior::MATCH) {}
+SetLookupOptions::NullMatchingBehavior SetLookupOptions::getNullMatchingBehavior() {
+  if (this->skip_nulls == std::nullopt) {
+    return this->null_matching_behavior;
+  } else if (this->skip_nulls) {
+    return SetLookupOptions::NullMatchingBehavior::SKIP;
+  } else {
+    return SetLookupOptions::NullMatchingBehavior::MATCH;
+  }
+}
 constexpr char SetLookupOptions::kTypeName[];
 
 SliceOptions::SliceOptions(int64_t start, int64_t stop, int64_t step)
@@ -745,14 +767,6 @@ Result<Datum> MinElementWise(const std::vector<Datum>& args,
 // ----------------------------------------------------------------------
 // Set-related operations
 
-Result<Datum> In(const Datum& values, const SetLookupOptions& options, ExecContext* ctx) {
-  return CallFunction("in", {values}, &options, ctx);
-}
-
-Result<Datum> In(const Datum& values, const Datum& value_set, ExecContext* ctx) {
-  return In(values, SetLookupOptions{value_set}, ctx);
-}
-
 Result<Datum> IsIn(const Datum& values, const SetLookupOptions& options,
                    ExecContext* ctx) {
   return CallFunction("is_in", {values}, &options, ctx);

diff --git a/cpp/src/arrow/compute/api_scalar.h b/cpp/src/arrow/compute/api_scalar.h
@@ -268,19 +268,28 @@ class ARROW_EXPORT ExtractRegexOptions : public FunctionOptions {
 /// Options for IsIn and IndexIn functions
 class ARROW_EXPORT SetLookupOptions : public FunctionOptions {
  public:
-  explicit SetLookupOptions(Datum value_set, bool skip_nulls = false);
-  SetLookupOptions();
+  enum NullMatchingBehavior { MATCH, SKIP, EMIT_NULL, INCONCLUSIVE };
+
+  explicit SetLookupOptions(Datum value_set, NullMatchingBehavior = MATCH);
+  explicit SetLookupOptions(Datum value_set, bool skip_nulls);  SetLookupOptions();
   static constexpr char const kTypeName[] = "SetLookupOptions";
 
   /// The set of values to look up input values into.
   Datum value_set;
+
+  NullMatchingBehavior null_matching_behavior;
+
+  // DEPRECATED(will be removed after removing of skip_nulls)
+   NullMatchingBehavior const getNullMatchingBehavior();
+
+  // DEPRECATED(use null_matching_behavior instead)
   /// Whether nulls in `value_set` count for lookup.
   ///
   /// If true, any null in `value_set` is ignored and nulls in the input
   /// produce null (IndexIn) or false (IsIn) values in the output.
   /// If false, any null in `value_set` is successfully matched in
   /// the input.
-  bool skip_nulls;
+  std::optional<bool> skip_nulls;
 };
 
 /// Options for struct_field function
@@ -1089,28 +1098,6 @@ ARROW_EXPORT
 Result<Datum> KleeneAndNot(const Datum& left, const Datum& right,
                            ExecContext* ctx = NULLPTR);
 
-/// \brief In returns true for each element of `values` that is contained in
-/// `value_set`.
-///  In is sql-compatible, null in `values` will directly output null,
-///  each elelement of `values` that isn't contained in `value_set`
-///  will output null if the `value_set` contains null and output
-///  false if the `value_set` doesn't contain null.
-///
-/// In ignore the parameter skip_nulls in SetLookupOptions.
-///
-/// \param[in] values array-like input to look up in value_set
-/// \param[in] options SetLookupOptions
-/// \param[in] ctx the function execution context, optional
-/// \return the resulting datum
-///
-/// \since 12.0.1
-/// \note API not yet finalized
-ARROW_EXPORT
-Result<Datum> In(const Datum& values, const SetLookupOptions& options,
-                 ExecContext* ctx = NULLPTR);
-ARROW_EXPORT
-Result<Datum> In(const Datum& values, const Datum& value_set, ExecContext* ctx = NULLPTR);
-
 /// \brief IsIn returns true for each element of `values` that is contained in
 /// `value_set`
 ///