fix comment

mapleFU · Nov 15, 2024 · d892819 · d892819
1 parent 23fb3fa
commit d892819
Show file tree

Hide file tree

Showing 5 changed files with 12 additions and 9 deletions.
diff --git a/cpp/src/parquet/bloom_filter_reader.h b/cpp/src/parquet/bloom_filter_reader.h
@@ -17,7 +17,7 @@
 
 #pragma once
 
-#include "arrow/io/type_fwd.h"
+#include "arrow/io/interfaces.h"
 #include "parquet/properties.h"
 #include "parquet/type_fwd.h"
 

diff --git a/cpp/src/parquet/column_writer.cc b/cpp/src/parquet/column_writer.cc
@@ -1701,6 +1701,7 @@ Status TypedColumnWriterImpl<DType>::WriteArrowDictionary(
 
   auto update_stats = [&](int64_t num_chunk_levels,
                           const std::shared_ptr<Array>& chunk_indices) {
+    DCHECK(page_statistics_ != nullptr || bloom_filter_ != nullptr);
     // TODO(PARQUET-2068) This approach may make two copies.  First, a copy of the
     // indices array to a (hopefully smaller) referenced indices array.  Second, a copy
     // of the values array to a (probably not smaller) referenced values array.
@@ -1725,9 +1726,8 @@ Status TypedColumnWriterImpl<DType>::WriteArrowDictionary(
                                  &exec_ctx));
       referenced_dictionary = referenced_dictionary_datum.make_array();
     }
-
-    int64_t non_null_count = chunk_indices->length() - chunk_indices->null_count();
     if (page_statistics_ != nullptr) {
+      int64_t non_null_count = chunk_indices->length() - chunk_indices->null_count();
       page_statistics_->IncrementNullCount(num_chunk_levels - non_null_count);
       page_statistics_->IncrementNumValues(non_null_count);
       page_statistics_->Update(*referenced_dictionary, /*update_counts=*/false);
@@ -2426,7 +2426,9 @@ void TypedColumnWriterImpl<FLBAType>::UpdateBloomFilter(const FLBA* values,
 
 template <>
 void TypedColumnWriterImpl<BooleanType>::UpdateBloomFilter(const bool*, int64_t) {
-  DCHECK(bloom_filter_ == nullptr);
+  if (ARROW_PREDICT_FALSE(bloom_filter_ != nullptr)) {
+    throw ParquetException("BooleanType does not support bloom filters");
+  }
 }
 
 template <typename DType>

diff --git a/cpp/src/parquet/metadata.h b/cpp/src/parquet/metadata.h
@@ -516,9 +516,10 @@ class PARQUET_EXPORT RowGroupMetaDataBuilder {
 using RowGroupIndexLocation = std::vector<std::optional<IndexLocation>>;
 
 /// Alias type of bloom filter location of a row group. The filter location
-/// is located by column ordinal. Number of columns with a bloom filter to
-/// be relatively small compared to the number of overall columns, so
-/// map is used.
+/// is located by column ordinal.
+///
+/// Number of columns with a bloom filter to be relatively small compared to
+/// the number of overall columns, so map is used.
 using RowGroupBloomFilterLocation = std::map<int32_t, IndexLocation>;
 
 /// Alias type of page index and location of a parquet file. The

diff --git a/cpp/src/parquet/page_index.h b/cpp/src/parquet/page_index.h
@@ -17,7 +17,7 @@
 
 #pragma once
 
-#include "arrow/io/type_fwd.h"
+#include "arrow/io/interfaces.h"
 #include "parquet/encryption/type_fwd.h"
 #include "parquet/types.h"
 

diff --git a/cpp/src/parquet/properties.h b/cpp/src/parquet/properties.h
@@ -599,7 +599,7 @@ class PARQUET_EXPORT WriterProperties {
     }
 
     /// Disable bloom filter for the column specified by `path`.
-    /// Default enabled.
+    /// Default disabled.
     Builder* disable_bloom_filter(const std::shared_ptr<schema::ColumnPath>& path) {
       return this->disable_bloom_filter(path->ToDotString());
     }