Merge pull request #69 from ClickHouse/ncb/arrow-crash-fixes

pull in some fixes for possible crash in TableBatchReader

Author: alexey-milovidov

cpp/src/arrow/table.cc

@@ -619,6 +619,7 @@ TableBatchReader::TableBatchReader(const Table& table)
   for (int i = 0; i < table.num_columns(); ++i) {
     column_data_[i] = table.column(i).get();
   }
+  DCHECK(table_.Validate().ok());
 }
 
 TableBatchReader::TableBatchReader(std::shared_ptr<Table> table)
@@ -632,6 +633,7 @@ TableBatchReader::TableBatchReader(std::shared_ptr<Table> table)
   for (int i = 0; i < owned_table_->num_columns(); ++i) {
     column_data_[i] = owned_table_->column(i).get();
   }
+  DCHECK(table_.Validate().ok());
 }
 
 std::shared_ptr<Schema> TableBatchReader::schema() const { return table_.schema(); }

cpp/src/arrow/table.h

@@ -241,6 +241,8 @@ class ARROW_EXPORT Table {
 ///
 /// The conversion is zero-copy: each record batch is a view over a slice
 /// of the table's columns.
+///
+/// The table is expected to be valid prior to using it with the batch reader.
 class ARROW_EXPORT TableBatchReader : public RecordBatchReader {
  public:
   /// \brief Construct a TableBatchReader for the given table

cpp/src/parquet/arrow/reader.cc

@@ -1043,6 +1043,16 @@ Status FileReaderImpl::GetRecordBatchReader(const std::vector<int>& row_groups,
           }
         }
 
+        // Check all columns has same row-size
+        if (!columns.empty()) {
+          int64_t row_size = columns[0]->length();
+          for (size_t i = 1; i < columns.size(); ++i) {
+            if (columns[i]->length() != row_size) {
+              return ::arrow::Status::Invalid("columns do not have the same size");
+            }
+          }
+        }
+
         auto table = ::arrow::Table::Make(batch_schema, std::move(columns));
         auto table_reader = std::make_shared<::arrow::TableBatchReader>(*table);