ARROW-9116: [C++] Add BaseBinaryArray::total_values_length

Closes #7426 from wesm/ARROW-9116 Authored-by: Wes McKinney <[email protected]> Signed-off-by: Sutou Kouhei <[email protected]>
apache · Jun 14, 2020 · 657d9c6 · 657d9c6
1 parent 2e977a2
commit 657d9c6
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 1 deletion.
diff --git a/cpp/src/arrow/array/array_binary.h b/cpp/src/arrow/array/array_binary.h
@@ -85,15 +85,30 @@ class BaseBinaryArray : public FlatArray {
     return raw_value_offsets_ + data_->offset;
   }
 
-  // Neither of these functions will perform boundschecking
+  /// \brief Return the data buffer absolute offset of the data for the value
+  /// at the passed index.
+  ///
+  /// Does not perform boundschecking
   offset_type value_offset(int64_t i) const {
     return raw_value_offsets_[i + data_->offset];
   }
+
+  /// \brief Return the length of the data for the value at the passed index.
+  ///
+  /// Does not perform boundschecking
   offset_type value_length(int64_t i) const {
     i += data_->offset;
     return raw_value_offsets_[i + 1] - raw_value_offsets_[i];
   }
 
+  /// \brief Return the total length of the memory in the data buffer
+  /// referenced by this array. If the array has been sliced then this may be
+  /// less than the size of the data buffer (data_->buffers[2]).
+  offset_type total_values_length() const {
+    return raw_value_offsets_[data_->length + data_->offset] -
+           raw_value_offsets_[data_->offset];
+  }
+
  protected:
   // For subclasses
   BaseBinaryArray() : raw_value_offsets_(NULLPTR), raw_data_(NULLPTR) {}

diff --git a/cpp/src/arrow/array/array_binary_test.cc b/cpp/src/arrow/array/array_binary_test.cc
@@ -109,6 +109,18 @@ class TestStringArray : public ::testing::Test {
     AssertZeroPadded(*strings_);
   }
 
+  void TestTotalValuesLength() {
+    auto ty = TypeTraits<T>::type_singleton();
+    auto arr = ArrayFromJSON(ty, R"(["a", null, "bbb", "cccc", "ddddd"])");
+
+    offset_type values_length = arr.total_values_length();
+    ASSERT_EQ(values_length, static_cast<offset_type>(13));
+
+    offset_type sliced_values_length =
+        checked_cast<const ArrayType&>(*arr.Slice(3)).total_values_length();
+    ASSERT_EQ(sliced_values_length, static_cast<offset_type>(9));
+  }
+
   void TestType() {
     std::shared_ptr<DataType> type = this->strings_->type();