apacheGH-38090: [C++][Emscripten][Parquet] Suppress shorten-64-to-32 …

…warnings (apache#38129) ### Rationale for this change We need explicit cast to use `int64_t` for `size_t` on Emscripten. ### What changes are included in this PR? Explicit casts. ### Are these changes tested? Yes. ### Are there any user-facing changes? No. * Closes: apache#38090 Authored-by: Sutou Kouhei <[email protected]> Signed-off-by: Sutou Kouhei <[email protected]>
loicalleyne · Nov 13, 2023 · 8a73c09 · 8a73c09
1 parent 0951455
commit 8a73c09
Show file tree

Hide file tree

Showing 10 changed files with 23 additions and 17 deletions.
diff --git a/cpp/src/parquet/arrow/reader.cc b/cpp/src/parquet/arrow/reader.cc
@@ -999,7 +999,8 @@ Status FileReaderImpl::GetRecordBatchReader(const std::vector<int>& row_groups,
     for (int row_group : row_groups) {
       int64_t num_rows = parquet_reader()->metadata()->RowGroup(row_group)->num_rows();
 
-      batches.insert(batches.end(), num_rows / batch_size, max_sized_batch);
+      batches.insert(batches.end(), static_cast<size_t>(num_rows / batch_size),
+                     max_sized_batch);
 
       if (int64_t trailing_rows = num_rows % batch_size) {
         batches.push_back(max_sized_batch->Slice(0, trailing_rows));

diff --git a/cpp/src/parquet/arrow/reader_internal.cc b/cpp/src/parquet/arrow/reader_internal.cc
@@ -365,7 +365,7 @@ Status TransferBool(RecordReader* reader, bool nullable, MemoryPool* pool, Datum
   // Transfer boolean values to packed bitmap
   auto values = reinterpret_cast<const bool*>(reader->values());
   uint8_t* data_ptr = data->mutable_data();
-  memset(data_ptr, 0, buffer_size);
+  memset(data_ptr, 0, static_cast<size_t>(buffer_size));
 
   for (int64_t i = 0; i < length; i++) {
     if (values[i]) {

diff --git a/cpp/src/parquet/bloom_filter.cc b/cpp/src/parquet/bloom_filter.cc
@@ -143,7 +143,7 @@ BlockSplitBloomFilter BlockSplitBloomFilter::Deserialize(
   const auto bloom_filter_bytes_in_header = header_buf->size() - header_size;
   if (bloom_filter_bytes_in_header > 0) {
     std::memcpy(buffer->mutable_data(), header_buf->data() + header_size,
-                bloom_filter_bytes_in_header);
+                static_cast<size_t>(bloom_filter_bytes_in_header));
   }
 
   const auto required_read_size = bloom_filter_size - bloom_filter_bytes_in_header;

diff --git a/cpp/src/parquet/column_reader.cc b/cpp/src/parquet/column_reader.cc
@@ -1792,7 +1792,7 @@ class TypedRecordReader : public TypedColumnReaderImpl<DType>,
 
         // Avoid valgrind warnings
         memset(valid_bits_->mutable_data() + valid_bytes_old, 0,
-               valid_bytes_new - valid_bytes_old);
+               static_cast<size_t>(valid_bytes_new - valid_bytes_old));
       }
     }
   }
@@ -1935,7 +1935,7 @@ class TypedRecordReader : public TypedColumnReaderImpl<DType>,
     // Conservative upper bound
     const int64_t possible_num_values =
         std::max<int64_t>(num_records, levels_written_ - levels_position_);
-    ReserveValues(possible_num_values);
+    ReserveValues(static_cast<size_t>(possible_num_values));
 
     const int64_t start_levels_position = levels_position_;
 

diff --git a/cpp/src/parquet/column_scanner.h b/cpp/src/parquet/column_scanner.h
@@ -48,8 +48,10 @@ class PARQUET_EXPORT Scanner {
         value_offset_(0),
         values_buffered_(0),
         reader_(std::move(reader)) {
-    def_levels_.resize(descr()->max_definition_level() > 0 ? batch_size_ : 0);
-    rep_levels_.resize(descr()->max_repetition_level() > 0 ? batch_size_ : 0);
+    def_levels_.resize(
+        descr()->max_definition_level() > 0 ? static_cast<size_t>(batch_size_) : 0);
+    rep_levels_.resize(
+        descr()->max_repetition_level() > 0 ? static_cast<size_t>(batch_size_) : 0);
   }
 
   virtual ~Scanner() {}

diff --git a/cpp/src/parquet/column_writer.cc b/cpp/src/parquet/column_writer.cc
@@ -895,11 +895,13 @@ class ColumnWriterImpl {
   void ConcatenateBuffers(int64_t definition_levels_rle_size,
                           int64_t repetition_levels_rle_size,
                           const std::shared_ptr<Buffer>& values, uint8_t* combined) {
-    memcpy(combined, repetition_levels_rle_->data(), repetition_levels_rle_size);
+    memcpy(combined, repetition_levels_rle_->data(),
+           static_cast<size_t>(repetition_levels_rle_size));
     combined += repetition_levels_rle_size;
-    memcpy(combined, definition_levels_rle_->data(), definition_levels_rle_size);
+    memcpy(combined, definition_levels_rle_->data(),
+           static_cast<size_t>(definition_levels_rle_size));
     combined += definition_levels_rle_size;
-    memcpy(combined, values->data(), values->size());
+    memcpy(combined, values->data(), static_cast<size_t>(values->size()));
   }
 };
 

diff --git a/cpp/src/parquet/encoding.cc b/cpp/src/parquet/encoding.cc
@@ -850,8 +850,8 @@ std::shared_ptr<Buffer> ByteStreamSplitEncoder<DType>::FlushValues() {
       AllocateBuffer(this->memory_pool(), EstimatedDataEncodedSize());
   uint8_t* output_buffer_raw = output_buffer->mutable_data();
   const uint8_t* raw_values = sink_.data();
-  ::arrow::util::internal::ByteStreamSplitEncode<T>(raw_values, num_values_in_buffer_,
-                                                    output_buffer_raw);
+  ::arrow::util::internal::ByteStreamSplitEncode<T>(
+      raw_values, static_cast<size_t>(num_values_in_buffer_), output_buffer_raw);
   sink_.Reset();
   num_values_in_buffer_ = 0;
   return std::move(output_buffer);
@@ -1018,7 +1018,7 @@ inline int DecodePlain(const uint8_t* data, int64_t data_size, int num_values,
   }
   // If bytes_to_decode == 0, data could be null
   if (bytes_to_decode > 0) {
-    memcpy(out, data, bytes_to_decode);
+    memcpy(out, data, static_cast<size_t>(bytes_to_decode));
   }
   return static_cast<int>(bytes_to_decode);
 }
@@ -1574,7 +1574,7 @@ class DictDecoderImpl : public DecoderImpl, virtual public DictDecoder<Type> {
 
     // XXX(wesm): Cannot append "valid bits" directly to the builder
     std::vector<uint8_t> valid_bytes(num_values, 0);
-    int64_t i = 0;
+    size_t i = 0;
     VisitNullBitmapInline(
         valid_bits, valid_bits_offset, num_values, null_count,
         [&]() { valid_bytes[i++] = 1; }, [&]() { ++i; });

diff --git a/cpp/src/parquet/file_reader.cc b/cpp/src/parquet/file_reader.cc
@@ -918,7 +918,7 @@ int64_t ScanFileContents(std::vector<int> columns, const int32_t column_batch_si
             ScanAllValues(column_batch_size, def_levels.data(), rep_levels.data(),
                           values.data(), &values_read, col_reader.get());
         if (col_reader->descr()->max_repetition_level() > 0) {
-          for (int64_t i = 0; i < levels_read; i++) {
+          for (size_t i = 0; i < static_cast<size_t>(levels_read); i++) {
             if (rep_levels[i] == 0) {
               total_rows[col]++;
             }

diff --git a/cpp/src/parquet/metadata.cc b/cpp/src/parquet/metadata.cc
@@ -1843,7 +1843,8 @@ class FileMetaDataBuilder::FileMetaDataBuilderImpl {
         key_value_metadata_ = key_value_metadata_->Merge(*key_value_metadata);
       }
       metadata_->key_value_metadata.clear();
-      metadata_->key_value_metadata.reserve(key_value_metadata_->size());
+      metadata_->key_value_metadata.reserve(
+          static_cast<size_t>(key_value_metadata_->size()));
       for (int64_t i = 0; i < key_value_metadata_->size(); ++i) {
         format::KeyValue kv_pair;
         kv_pair.__set_key(key_value_metadata_->key(i));

diff --git a/cpp/src/parquet/statistics.cc b/cpp/src/parquet/statistics.cc
@@ -771,7 +771,7 @@ void TypedStatisticsImpl<DType>::PlainEncode(const T& src, std::string* dst) con
   encoder->Put(&src, 1);
   auto buffer = encoder->FlushValues();
   auto ptr = reinterpret_cast<const char*>(buffer->data());
-  dst->assign(ptr, buffer->size());
+  dst->assign(ptr, static_cast<size_t>(buffer->size()));
 }
 
 template <typename DType>