This is an automated email from the ASF dual-hosted git repository.
westonpace pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 3e123ad6e5 GH-38960: [C++] Fix spelling (acero) (#38961)
3e123ad6e5 is described below
commit 3e123ad6e503b486cc95503827099ec11b17132c
Author: Josh Soref <[email protected]>
AuthorDate: Tue Dec 5 13:57:41 2023 -0500
GH-38960: [C++] Fix spelling (acero) (#38961)
### Rationale for this change
### What changes are included in this PR?
Spelling fixes to cpp/src/arrow/acero/
### Are these changes tested?
### Are there any user-facing changes?
* Closes: #38960
Authored-by: Josh Soref <[email protected]>
Signed-off-by: Weston Pace <[email protected]>
---
cpp/src/arrow/acero/accumulation_queue.h | 2 +-
cpp/src/arrow/acero/aggregate_internal.h | 2 +-
cpp/src/arrow/acero/asof_join_node.cc | 4 ++--
cpp/src/arrow/acero/asof_join_node_test.cc | 4 ++--
cpp/src/arrow/acero/expression_benchmark.cc | 4 ++--
cpp/src/arrow/acero/hash_aggregate_test.cc | 2 +-
cpp/src/arrow/acero/partition_util.h | 4 ++--
cpp/src/arrow/acero/pivot_longer_node.cc | 2 +-
cpp/src/arrow/acero/sorted_merge_node.cc | 2 +-
cpp/src/arrow/acero/swiss_join.cc | 8 ++++----
cpp/src/arrow/acero/swiss_join_internal.h | 4 ++--
11 files changed, 19 insertions(+), 19 deletions(-)
diff --git a/cpp/src/arrow/acero/accumulation_queue.h
b/cpp/src/arrow/acero/accumulation_queue.h
index 285790207f..a27b8b399c 100644
--- a/cpp/src/arrow/acero/accumulation_queue.h
+++ b/cpp/src/arrow/acero/accumulation_queue.h
@@ -82,7 +82,7 @@ class SequencingQueue {
/// This method will be called on each batch in order. Calls to this
method
/// will be serialized and it will not be called reentrantly. This makes
it
/// safe to do things that rely on order but minimal time should be spent
here
- /// to avoid becoming a bottlneck.
+ /// to avoid becoming a bottleneck.
///
/// \return a follow-up task that will be scheduled. The follow-up
task(s) are
/// is not guaranteed to run in any particular order. If nullopt
is
diff --git a/cpp/src/arrow/acero/aggregate_internal.h
b/cpp/src/arrow/acero/aggregate_internal.h
index 72537a7f7e..5730d99f93 100644
--- a/cpp/src/arrow/acero/aggregate_internal.h
+++ b/cpp/src/arrow/acero/aggregate_internal.h
@@ -224,7 +224,7 @@ class ScalarAggregateNode : public ExecNode, public
TracedNode {
// Field indices corresponding to the segment-keys
const std::vector<int> segment_field_ids_;
// Holds the value of segment keys of the most recent input batch
- // The values are updated everytime an input batch is processed
+ // The values are updated every time an input batch is processed
std::vector<Datum> segmenter_values_;
const std::vector<std::vector<int>> target_fieldsets_;
diff --git a/cpp/src/arrow/acero/asof_join_node.cc
b/cpp/src/arrow/acero/asof_join_node.cc
index 4a3b6b199c..2609905a0b 100644
--- a/cpp/src/arrow/acero/asof_join_node.cc
+++ b/cpp/src/arrow/acero/asof_join_node.cc
@@ -472,7 +472,7 @@ class BackpressureController : public BackpressureControl {
};
class InputState {
- // InputState correponds to an input
+ // InputState corresponds to an input
// Input record batches are queued up in InputState until processed and
// turned into output record batches.
@@ -1453,7 +1453,7 @@ class AsofJoinNode : public ExecNode {
bool must_hash_;
bool may_rehash_;
// InputStates
- // Each input state correponds to an input table
+ // Each input state corresponds to an input table
std::vector<std::unique_ptr<InputState>> state_;
std::mutex gate_;
TolType tolerance_;
diff --git a/cpp/src/arrow/acero/asof_join_node_test.cc
b/cpp/src/arrow/acero/asof_join_node_test.cc
index df3172b2a0..e400cc0316 100644
--- a/cpp/src/arrow/acero/asof_join_node_test.cc
+++ b/cpp/src/arrow/acero/asof_join_node_test.cc
@@ -604,7 +604,7 @@ struct BasicTest {
auto r0_types = init_types(all_types, [](T& t) { return t->byte_width() >
1; });
auto r1_types = init_types(all_types, [](T& t) { return t->byte_width() >
1; });
- // sample a limited number of type-combinations to keep the runnning time
reasonable
+ // sample a limited number of type-combinations to keep the running time
reasonable
// the scoped-traces below help reproduce a test failure, should it happen
auto start_time = std::chrono::system_clock::now();
auto seed = start_time.time_since_epoch().count();
@@ -1279,7 +1279,7 @@ TRACED_TEST(AsofJoinTest, TestUnsupportedOntype, {
field("r0_v0", float32())}));
})
-TRACED_TEST(AsofJoinTest, TestUnsupportedBytype, {
+TRACED_TEST(AsofJoinTest, TestUnsupportedByType, {
DoRunInvalidTypeTest(schema({field("time", int64()), field("key",
list(int32())),
field("l_v0", float64())}),
schema({field("time", int64()), field("key",
list(int32())),
diff --git a/cpp/src/arrow/acero/expression_benchmark.cc
b/cpp/src/arrow/acero/expression_benchmark.cc
index 9799446ed6..a57dd6b9e3 100644
--- a/cpp/src/arrow/acero/expression_benchmark.cc
+++ b/cpp/src/arrow/acero/expression_benchmark.cc
@@ -107,7 +107,7 @@ static void
ExecuteScalarExpressionOverhead(benchmark::State& state, Expression
}
/// \brief Baseline benchmarks are implemented in pure C++ without arrow for
performance
-/// comparision.
+/// comparison.
template <typename BenchmarkType>
void ExecuteScalarExpressionBaseline(benchmark::State& state) {
const auto rows_per_batch = static_cast<int32_t>(state.range(0));
@@ -193,7 +193,7 @@ BENCHMARK_CAPTURE(BindAndEvaluate, nested_scalar,
struct ComplexExpressionBaseline {
public:
ComplexExpressionBaseline(size_t input_size) {
- /* hack - cuts off a few elemets if the input size is not a multiple of 64
for
+ /* hack - cuts off a few elements if the input size is not a multiple of
64 for
* simplicity. We can't use std::vector<bool> here since it slows down
things
* massively */
less_20.resize(input_size / 64);
diff --git a/cpp/src/arrow/acero/hash_aggregate_test.cc
b/cpp/src/arrow/acero/hash_aggregate_test.cc
index 02e67927cc..a4874f3581 100644
--- a/cpp/src/arrow/acero/hash_aggregate_test.cc
+++ b/cpp/src/arrow/acero/hash_aggregate_test.cc
@@ -261,7 +261,7 @@ Result<Datum> MakeGroupByOutput(const
std::vector<ExecBatch>& output_batches,
return struct_arr;
}
- // The exec plan may reorder the output rows. The tests are all setup to
expect ouptut
+ // The exec plan may reorder the output rows. The tests are all setup to
expect output
// in ascending order of keys. So we need to sort the result by the key
columns. To do
// that we create a table using the key columns, calculate the sort indices
from that
// table (sorting on all fields) and then use those indices to calculate our
result.
diff --git a/cpp/src/arrow/acero/partition_util.h
b/cpp/src/arrow/acero/partition_util.h
index 27cde61d58..1413a8326a 100644
--- a/cpp/src/arrow/acero/partition_util.h
+++ b/cpp/src/arrow/acero/partition_util.h
@@ -33,11 +33,11 @@ class PartitionSort {
public:
/// \brief Bucket sort rows on partition ids in O(num_rows) time.
///
- /// Include in the output exclusive cummulative sum of bucket sizes.
+ /// Include in the output exclusive cumulative sum of bucket sizes.
/// This corresponds to ranges in the sorted array containing all row ids for
/// each of the partitions.
///
- /// prtn_ranges must be initailized and have at least prtn_ranges + 1
elements
+ /// prtn_ranges must be initialized and have at least prtn_ranges + 1
elements
/// when this method returns prtn_ranges[i] will contains the total number of
/// elements in partitions 0 through i. prtn_ranges[0] will be 0.
///
diff --git a/cpp/src/arrow/acero/pivot_longer_node.cc
b/cpp/src/arrow/acero/pivot_longer_node.cc
index e54f00a20b..ea5ca44baa 100644
--- a/cpp/src/arrow/acero/pivot_longer_node.cc
+++ b/cpp/src/arrow/acero/pivot_longer_node.cc
@@ -135,7 +135,7 @@ class PivotLongerNode : public ExecNode, public TracedNode {
for (std::size_t i = 0; i < measurement_types.size(); i++) {
if (!measurement_types[i]) {
return Status::Invalid(
- "All row templates had nullopt for the meausrement column at index
", i, " (",
+ "All row templates had nullopt for the measurement column at index
", i, " (",
options.measurement_field_names[i], ")");
}
fields.push_back(
diff --git a/cpp/src/arrow/acero/sorted_merge_node.cc
b/cpp/src/arrow/acero/sorted_merge_node.cc
index f3b934eda1..4d4565a6bb 100644
--- a/cpp/src/arrow/acero/sorted_merge_node.cc
+++ b/cpp/src/arrow/acero/sorted_merge_node.cc
@@ -95,7 +95,7 @@ class BackpressureController : public BackpressureControl {
std::atomic<int32_t>& backpressure_counter_;
};
-/// InputState correponds to an input. Input record batches are queued up in
InputState
+/// InputState corresponds to an input. Input record batches are queued up in
InputState
/// until processed and turned into output record batches.
class InputState {
public:
diff --git a/cpp/src/arrow/acero/swiss_join.cc
b/cpp/src/arrow/acero/swiss_join.cc
index 3f11b89af3..2f79ed299b 100644
--- a/cpp/src/arrow/acero/swiss_join.cc
+++ b/cpp/src/arrow/acero/swiss_join.cc
@@ -1433,16 +1433,16 @@ void SwissTableForJoinBuild::PrtnMerge(int prtn_id) {
if (!no_payload_) {
// Count sort payloads on key id
//
- // Start by computing inclusive cummulative sum of counters.
+ // Start by computing inclusive cumulative sum of counters.
//
uint32_t sum = 0;
for (int64_t i = 0; i < num_keys; ++i) {
sum += counters[i];
counters[i] = sum;
}
- // Now use cummulative sum of counters to obtain the target position in
+ // Now use cumulative sum of counters to obtain the target position in
// the sorted order for each row. At the end of this process the counters
- // will contain exclusive cummulative sum (instead of inclusive that is
+ // will contain exclusive cumulative sum (instead of inclusive that is
// there at the beginning).
//
source_payload_ids.resize(prtn_state.key_ids.size());
@@ -1458,7 +1458,7 @@ void SwissTableForJoinBuild::PrtnMerge(int prtn_id) {
}
} else {
// When there is no payload to process, we just need to compute exclusive
- // cummulative sum of counters and add the base payload id to all of
them.
+ // cumulative sum of counters and add the base payload id to all of them.
//
uint32_t sum = 0;
for (int64_t i = 0; i < num_keys; ++i) {
diff --git a/cpp/src/arrow/acero/swiss_join_internal.h
b/cpp/src/arrow/acero/swiss_join_internal.h
index 88b80f06f5..6403b7a655 100644
--- a/cpp/src/arrow/acero/swiss_join_internal.h
+++ b/cpp/src/arrow/acero/swiss_join_internal.h
@@ -156,7 +156,7 @@ class RowArrayMerge {
// All input sources must be initialized, but they can contain zero rows.
//
// Output in vector the first target row id for each source (exclusive
- // cummulative sum of number of rows in sources). This output is optional,
+ // cumulative sum of number of rows in sources). This output is optional,
// caller can pass in nullptr to indicate that it is not needed.
//
static Status PrepareForMerge(RowArray* target, const
std::vector<RowArray*>& sources,
@@ -235,7 +235,7 @@ class SwissTableMerge {
// All input sources must be initialized, but they can be empty.
//
// Output in a vector the first target group id for each source (exclusive
- // cummulative sum of number of groups in sources). This output is optional,
+ // cumulative sum of number of groups in sources). This output is optional,
// caller can pass in nullptr to indicate that it is not needed.
//
static Status PrepareForMerge(SwissTable* target,
