pitrou commented on code in PR #50422:
URL: https://github.com/apache/arrow/pull/50422#discussion_r3553322318
##########
cpp/src/arrow/util/rle_encoding_internal.h:
##########
@@ -515,6 +573,85 @@ class RleBitPackedDecoder {
int64_t valid_bits_offset, rle_size_t
null_count);
};
+/// Minimal decoder for legacy bit packed encoding (BIT_PACKED = 4).
+///
+/// The number of values that the decoder can represent is up to 2^31 - 1.
+template <typename T>
+class BitPackedDecoder : private BitPackedRunDecoder<T> {
+ private:
+ using Base = BitPackedRunDecoder<T>;
+
+ public:
+ /// The type in which the data should be decoded.
+ using value_type = T;
+
+ using Base::Advance;
+
+ BitPackedDecoder() noexcept = default;
+
+ /// Create a decoder object.
+ ///
+ /// Unless explicitly given, then number of values is deduced from the data
size,
+ /// in which case it may read more values from the input stream than the user
+ /// intended (to reach final byte alignment). This option is mandatory if the
+ /// `value_bit_width` is zero.
+ ///
+ /// @param data and data_size are the raw bytes to decode.
+ /// @param value_bit_width is the size in bits of each encoded value.
+ /// @param value_count is an optional number of values in the run.
+ BitPackedDecoder(const uint8_t* data, rle_size_t data_size, rle_size_t
value_bit_width,
+ rle_size_t value_count = -1) noexcept {
+ Reset(data, data_size, value_bit_width, value_count);
+ }
+
+ void Reset(const uint8_t* data, rle_size_t data_size, rle_size_t
value_bit_width,
+ rle_size_t value_count = -1) noexcept {
+ ARROW_DCHECK_GE(value_bit_width, 0);
+ ARROW_DCHECK_LE(value_bit_width, 64);
+
+ value_bit_width_ = value_bit_width;
+ if (value_count < 0) {
+ ARROW_DCHECK_GT(value_bit_width, 0);
+ const int64_t data_bit_size = static_cast<int64_t>(data_size) * 8;
+ value_count = static_cast<rle_size_t>(data_bit_size / value_bit_width);
+ }
+
+ ARROW_DCHECK_LE(value_count, std::numeric_limits<rle_size_t>::max());
+ const auto run = BitPackedRun{
+ /* data= */ data,
+ /* value_count= */ value_count,
+ /* value_bit_width= */ value_bit_width,
Review Comment:
`max_read_bytes` in the `BitPackedRun` constructor signature (see the
comment I just posted)
--
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]
