Undo debug additions

Author: pitrou

.github/workflows/cpp_windows.yml

@@ -43,16 +43,16 @@ jobs:
       ARROW_BUILD_SHARED: ON
       ARROW_BUILD_STATIC: OFF
       ARROW_BUILD_TESTS: ON
-      ARROW_DATASET: OFF
+      ARROW_DATASET: ON
       ARROW_FLIGHT: OFF
       ARROW_HDFS: ON
       ARROW_HOME: /usr
       ARROW_JEMALLOC: OFF
       ARROW_MIMALLOC: ON
-      ARROW_ORC: OFF
-      ARROW_PARQUET: OFF
+      ARROW_ORC: ON
+      ARROW_PARQUET: ON
       ARROW_SIMD_LEVEL: ${{ inputs.simd-level }}
-      ARROW_SUBSTRAIT: OFF
+      ARROW_SUBSTRAIT: ON
       ARROW_USE_GLOG: OFF
       ARROW_VERBOSE_THIRDPARTY_BUILD: OFF
       ARROW_WITH_BROTLI: OFF

cpp/src/arrow/util/rle_encoding_internal.h

@@ -532,6 +532,10 @@ class RleBitPackedEncoder {
   }
 
   /// Returns the maximum byte size it could take to encode 'num_values'.
+  ///
+  /// Note: because of the way CheckBufferFull() is called, you have to
+  /// reserve an extra "RleEncoder::MinBufferSize" bytes. These extra bytes
+  /// won't be used but not reserving them can cause the encoder to fail.
   static int64_t MaxBufferSize(int bit_width, int64_t num_values) {
     // For a bit_width > 1, the worst case is the repetition of "literal run of length 8
     // and then a repeated run of length 8".

cpp/src/arrow/util/rle_encoding_test.cc

@@ -993,24 +993,15 @@ void CheckRoundTrip(const Array& data, int bit_width, bool spaced, int32_t parts
   const int data_size = static_cast<int>(data.length());
   const int data_values_count =
       static_cast<int>(data.length() - spaced * data.null_count());
-      // Note: because of the way RleEncoder::CheckBufferFull()
-  // is called, we have to reserve an extra "RleEncoder::MinBufferSize"
-  // bytes. These extra bytes won't be used but not reserving them
-  // would cause the encoder to fail.
-  const int buffer_size =
-      static_cast<int>(
-  ::arrow::util::RleBitPackedEncoder::MaxBufferSize(bit_width, data_values_count) +
-         ::arrow::util::RleBitPackedEncoder::MinBufferSize(bit_width));
+  const int buffer_size = static_cast<int>(
+      ::arrow::util::RleBitPackedEncoder::MaxBufferSize(bit_width, data_values_count) +
+      ::arrow::util::RleBitPackedEncoder::MinBufferSize(bit_width));
 
   ASSERT_GE(parts, 1);
   ASSERT_LE(parts, data_size);
 
-  ARROW_SCOPED_TRACE("bit_width = ", bit_width, ", spaced = ", spaced, ", data_size = ", data_size,
-                     ", buffer_size = ", buffer_size);
-  ARROW_LOG(INFO) << "bit_width = " <<bit_width << ", data_size = " << data_size
-      << ", buffer size = " << buffer_size
-      << ", min buffer size = " << RleBitPackedEncoder::MinBufferSize(bit_width);
-
+  ARROW_SCOPED_TRACE("bit_width = ", bit_width, ", spaced = ", spaced,
+                     ", data_size = ", data_size, ", buffer_size = ", buffer_size);
   const value_type* data_values = static_cast<const ArrayType&>(data).raw_values();
 
   // Encode the data into `buffer` using the encoder.
@@ -1021,15 +1012,14 @@ void CheckRoundTrip(const Array& data, int bit_width, bool spaced, int32_t parts
     // Depending on `spaced` we treat nulls as regular values.
     if (data.IsValid(i) || !spaced) {
       bool success = encoder.Put(static_cast<uint64_t>(data_values[i]));
-      ASSERT_TRUE(success) << "Encoding failed in pos " << i << ", current encoder len: " << encoder.len();
+      ASSERT_TRUE(success) << "Encoding failed in pos " << i
+                           << ", current encoder len: " << encoder.len();
       ++encoded_values_size;
     }
   }
   int encoded_byte_size = encoder.Flush();
   ASSERT_EQ(encoded_values_size, data_values_count)
       << "All values input were not encoded successfully by the encoder";
-  // ARROW_LOG(INFO) << "bit_width = " <<bit_width << ", data_size = " << data_size
-  //     << ", buffer size = " << buffer_size << ", encoded_byte_size = " << encoded_byte_size;
 
   // Now we verify batch read
   RleBitPackedDecoder<value_type> decoder(buffer.data(), encoded_byte_size, bit_width);