AlvinJ15 commented on code in PR #13009:
URL: https://github.com/apache/arrow/pull/13009#discussion_r865043510
##########
cpp/src/arrow/stl_iterator.h:
##########
@@ -128,6 +132,153 @@ class ArrayIterator {
int64_t index_;
};
+template <typename ArrayType,
+ typename ValueAccessor = detail::DefaultValueAccessor<ArrayType>>
+class ChunkedArrayIterator {
+ public:
+ using value_type = arrow::util::optional<typename ValueAccessor::ValueType>;
+ using difference_type = int64_t;
+ using pointer = value_type*;
+ using reference = value_type&;
+ using iterator_category = std::random_access_iterator_tag;
+
+ // Some algorithms need to default-construct an iterator
+ ChunkedArrayIterator() : chunked_array_(NULLPTR), index_(0),
current_chunk_index_(0) {}
+
+ explicit ChunkedArrayIterator(const ChunkedArray& chunked_array, int64_t
index = 0)
+ : chunked_array_(&chunked_array), index_(index) {
+ auto chunk_location = GetChunkLocation(this->index_);
+ if (chunked_array.length()) {
+ current_array_iterator_ = ArrayIterator<ArrayType>(
+ *arrow::internal::checked_pointer_cast<ArrayType>(
+
chunked_array_->chunk(static_cast<int>(chunk_location.chunk_index))),
+ index_);
+ } else {
+ current_array_iterator_ = {};
+ }
+
+ this->current_chunk_index_ = chunk_location.chunk_index;
+ current_array_iterator_ -= this->index() - chunk_location.index_in_chunk;
+ }
+
+ // Value access
+ value_type operator*() const { return *current_array_iterator_; }
+
+ value_type operator[](difference_type n) const {
+ auto chunk_location = GetChunkLocation(index_ + n);
+ if (current_chunk_index_ == chunk_location.chunk_index) {
+ return current_array_iterator_[chunk_location.index_in_chunk -
+ current_array_iterator_.index()];
+ } else {
+ ArrayIterator<ArrayType> target_iterator{
+ *arrow::internal::checked_pointer_cast<ArrayType>(
+
chunked_array_->chunk(static_cast<int>(chunk_location.chunk_index)))};
+ return target_iterator[chunk_location.index_in_chunk];
+ }
+ }
+
+ int64_t index() const { return index_; }
+
+ // Forward / backward
+ ChunkedArrayIterator& operator++() {
+ (*this) += 1;
+ return *this;
+ }
+ ChunkedArrayIterator& operator--() {
+ (*this) -= 1;
+ return *this;
+ }
Review Comment:
Extra conditions would have to be added to control overflows, so I better
call the `operator +=` which already has the necessary conditions, and also the
ChunkResolver implementation managing a cache which avoids repeated searches
when it is in the same chunk
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
