decoder: handle empty non-string types

For legacy reasons, non-string types support "empty" values, e.g. you can have
an empty int, distinct from NULL. This case used to trigger deserialization errors,
so now it's simply a fallback to NULL. Another option is to introduce a new "empty"
state that a value can be in, but it's semantically no different from NULL,
even though it's serialized in a different way.

Ref: https://github.com/apache/cassandra/blob/7b58b79fe24c612f8bbf7984c325e88496f482d6/doc/native_protocol_v4.spec#L861-L863

Author: psarna

src/decoder.cpp

@@ -149,6 +149,16 @@ Value Decoder::decode_value(const DataType::ConstPtr& data_type) {
 
     int32_t count = 0;
     if (!data_type->is_collection()) {
+      if (!is_string_type(data_type->value_type()) && !is_bytes_type(data_type->value_type())
+          && size == 0) {
+        // For legacy reasons, non-string types support "empty" values, e.g. you can have
+        // an empty int, distinct from NULL. This case used to trigger deserialization errors,
+        // so now it's simply a fallback to NULL. Another option is to introduce a new "empty"
+        // state that a value can be in, but it's semantically no different from NULL,
+        // even though it's serialized in a different way.
+        // Ref: https://github.com/apache/cassandra/blob/7b58b79fe24c612f8bbf7984c325e88496f482d6/doc/native_protocol_v4.spec#L861-L863
+        return Value(data_type);
+      }
       return Value(data_type, decoder);
     } else if (decoder.decode_int32(count)) {
       return Value(data_type, count, decoder);

tests/src/unit/tests/test_decoder.cpp

@@ -17,6 +17,7 @@
 #include <gtest/gtest.h>
 
 #include "decoder.hpp"
+#include "value.hpp"
 #include "logger.hpp"
 
 using namespace datastax;
@@ -1002,3 +1003,48 @@ TEST_F(DecoderUnitTest, DecodeWarnings) {
   ASSERT_FALSE(decoder.decode_warnings(value));
   ASSERT_TRUE(failure_logged_);
 }
+
+TEST_F(DecoderUnitTest, DecodeEmpty) {
+  CassValueType nonzero_length_scalars[] = {
+    CASS_VALUE_TYPE_BIGINT, 
+    CASS_VALUE_TYPE_BOOLEAN,
+    CASS_VALUE_TYPE_COUNTER,
+    CASS_VALUE_TYPE_DECIMAL,  
+    CASS_VALUE_TYPE_DOUBLE,  
+    CASS_VALUE_TYPE_FLOAT,  
+    CASS_VALUE_TYPE_INT,  
+    CASS_VALUE_TYPE_TIMESTAMP, 
+    CASS_VALUE_TYPE_UUID,  
+    CASS_VALUE_TYPE_TIMEUUID,  
+    CASS_VALUE_TYPE_INET,  
+    CASS_VALUE_TYPE_DATE,  
+    CASS_VALUE_TYPE_TIME,  
+    CASS_VALUE_TYPE_SMALL_INT, 
+    CASS_VALUE_TYPE_TINY_INT,  
+    CASS_VALUE_TYPE_DURATION,
+  };
+  CassValueType variable_length_scalars[] = {
+    CASS_VALUE_TYPE_CUSTOM,
+    CASS_VALUE_TYPE_ASCII,
+    CASS_VALUE_TYPE_BLOB,
+    CASS_VALUE_TYPE_TEXT,
+    CASS_VALUE_TYPE_VARCHAR,
+    CASS_VALUE_TYPE_VARINT,
+  };
+  for (CassValueType t : nonzero_length_scalars) {
+    const char input[4] = { 0, 0, 0, 0 };
+    TestDecoder decoder((const char*)input, 4);
+    DataType::ConstPtr type_ptr(new DataType(t));
+    Value val = decoder.decode_value(type_ptr);
+    // Empty types are deserialized without errors and treated as null
+    ASSERT_TRUE(val.is_null());
+  }
+  for (CassValueType t : variable_length_scalars) {
+    const char input[4] = { 0, 0, 0, 0 };
+    TestDecoder decoder((const char*)input, 4);
+    DataType::ConstPtr type_ptr(new DataType(t));
+    Value val = decoder.decode_value(type_ptr);
+    // Empty types with variable size are simply empty, not null
+    ASSERT_FALSE(val.is_null());
+  }
+}