From 4c4953bcab4886be14fc9b7f95a77caa86a7629f Mon Sep 17 00:00:00 2001
From: Volodymyr Vysotskyi <vvovyk@gmail.com>
Date: Thu, 5 Apr 2018 15:35:42 +0300
Subject: DRILL-6094: Decimal data type enhancements

Add ExprVisitors for VARDECIMAL
Modify writers/readers to support VARDECIMAL
- Added usage of VarDecimal for parquet, hive, maprdb, jdbc;
- Added options to store decimals as int32 and int64 or fixed_len_byte_array or binary;
Add UDFs for VARDECIMAL data type
- modify type inference rules
- remove UDFs for obsolete DECIMAL types
Enable DECIMAL data type by default
Add unit tests for DECIMAL data type
Fix mapping for NLJ when literal with non-primitive type is used in join conditions
Refresh protobuf C++ source files
Changes in C++ files
Add support for decimal logical type in Avro.
Add support for date, time and timestamp logical types.
Update Avro version to 1.8.2.
---
 .../client/src/include/drill/decimalUtils.hpp      |  1 +
 .../client/src/include/drill/protobuf/Types.pb.h   |  5 +-
 .../client/src/include/drill/recordBatch.hpp       | 55 ++++++++++++++++++++--
 3 files changed, 54 insertions(+), 7 deletions(-)

(limited to 'contrib/native/client/src/include')

diff --git a/contrib/native/client/src/include/drill/decimalUtils.hpp b/contrib/native/client/src/include/drill/decimalUtils.hpp
index 2ace85772..5f9d37a99 100644
--- a/contrib/native/client/src/include/drill/decimalUtils.hpp
+++ b/contrib/native/client/src/include/drill/decimalUtils.hpp
@@ -41,6 +41,7 @@ struct DecimalValue
 
 // These functions need not be exported. They are used by the templates that return the DecimalValue class.
 DecimalValue getDecimalValueFromByteBuf(SlicedByteBuf& data, size_t startIndex, int nDecimalDigits, int scale, bool truncateScale);
+DecimalValue getDecimalValueFromByteBuf(SlicedByteBuf& data, size_t length, int scale);
 DecimalValue getDecimalValueFromDense(SlicedByteBuf& data, size_t startIndex, int nDecimalDigits, int scale, int maxPrecision, int width);
 
 inline DecimalValue getDecimalValueFromIntermediate(SlicedByteBuf& data, size_t startIndex, int nDecimalDigits, int scale)
diff --git a/contrib/native/client/src/include/drill/protobuf/Types.pb.h b/contrib/native/client/src/include/drill/protobuf/Types.pb.h
index f9200ec09..b1dec7bd6 100644
--- a/contrib/native/client/src/include/drill/protobuf/Types.pb.h
+++ b/contrib/native/client/src/include/drill/protobuf/Types.pb.h
@@ -74,11 +74,12 @@ enum MinorType {
   INTERVALDAY = 39,
   LIST = 40,
   GENERIC_OBJECT = 41,
-  UNION = 42
+  UNION = 42,
+  VARDECIMAL = 43
 };
 bool MinorType_IsValid(int value);
 const MinorType MinorType_MIN = LATE;
-const MinorType MinorType_MAX = UNION;
+const MinorType MinorType_MAX = VARDECIMAL;
 const int MinorType_ARRAYSIZE = MinorType_MAX + 1;
 
 const ::google::protobuf::EnumDescriptor* MinorType_descriptor();
diff --git a/contrib/native/client/src/include/drill/recordBatch.hpp b/contrib/native/client/src/include/drill/recordBatch.hpp
index 30287b6ad..435eb7715 100644
--- a/contrib/native/client/src/include/drill/recordBatch.hpp
+++ b/contrib/native/client/src/include/drill/recordBatch.hpp
@@ -346,7 +346,8 @@ template <int DECIMAL_DIGITS, int WIDTH_IN_BYTES, bool IS_SPARSE, int MAX_PRECIS
                     strncpy(buf, str.c_str(), nChars);
                 } else {
                     size_t idxDecimalMark = str.length() - m_scale;
-                    const std::string& decStr= str.substr(0, idxDecimalMark) + "." + str.substr(idxDecimalMark, m_scale);
+                    const std::string& decStr =
+                            (idxDecimalMark == 0 ? "0" : str.substr(0, idxDecimalMark)) + "." + str.substr(idxDecimalMark, m_scale);
                     strncpy(buf, decStr.c_str(), nChars);
                 }
                 return;
@@ -734,6 +735,49 @@ class DECLSPEC_DRILL_CLIENT ValueVectorVarChar:public ValueVectorVarWidth{
         }
 };
 
+class DECLSPEC_DRILL_CLIENT ValueVectorVarDecimal:public ValueVectorVarWidth{
+    public:
+        ValueVectorVarDecimal(SlicedByteBuf *b, size_t rowCount, size_t scale):
+            ValueVectorVarWidth(b, rowCount),
+            m_scale(scale)
+        {
+        }
+        DecimalValue get(size_t index) const {
+            size_t length = getSize(index);
+            ByteBuf_t buff = getRaw(index);
+            SlicedByteBuf intermediateData(&buff[0], 0, length);
+            return getDecimalValueFromByteBuf(intermediateData, length, this->m_scale);
+        }
+
+        void getValueAt(size_t index, char* buf, size_t nChars) const {
+            const DecimalValue& val = this->get(index);
+            std::string str = boost::lexical_cast<std::string>(val.m_unscaledValue);
+            if (str[0] == '-') {
+                str = str.substr(1);
+                while (str.length() < m_scale) {
+                    str = "0" + str;
+                }
+                str = "-" + str;
+            } else {
+                while (str.length() < m_scale) {
+                    str = "0" + str;
+                }
+            }
+            if (m_scale == 0) {
+                strncpy(buf, str.c_str(), nChars);
+            } else {
+                size_t idxDecimalMark = str.length() - m_scale;
+                const std::string& decStr =
+                        (idxDecimalMark == 0 ? "0" : str.substr(0, idxDecimalMark)) + "." + str.substr(idxDecimalMark, m_scale);
+                strncpy(buf, decStr.c_str(), nChars);
+            }
+            return;
+        }
+
+    private:
+        int32_t m_scale;
+};
+
 class DECLSPEC_DRILL_CLIENT ValueVectorVarBinary:public ValueVectorVarWidth{
     public:
         ValueVectorVarBinary(SlicedByteBuf *b, size_t rowCount):ValueVectorVarWidth(b, rowCount){
@@ -764,10 +808,11 @@ typedef ValueVectorDecimal<6, 24, true, 38>  ValueVectorDecimal38Sparse;
 
 typedef NullableValueVectorTyped<int32_t, ValueVectorDecimal9> NullableValueVectorDecimal9;
 typedef NullableValueVectorTyped<int64_t, ValueVectorDecimal18> NullableValueVectorDecimal18;
-typedef NullableValueVectorTyped<DecimalValue , ValueVectorDecimal28Dense> NullableValueVectorDecimal28Dense;
-typedef NullableValueVectorTyped<DecimalValue , ValueVectorDecimal38Dense> NullableValueVectorDecimal38Dense;
-typedef NullableValueVectorTyped<DecimalValue , ValueVectorDecimal28Sparse> NullableValueVectorDecimal28Sparse;
-typedef NullableValueVectorTyped<DecimalValue , ValueVectorDecimal38Sparse> NullableValueVectorDecimal38Sparse;
+typedef NullableValueVectorTyped<DecimalValue, ValueVectorDecimal28Dense> NullableValueVectorDecimal28Dense;
+typedef NullableValueVectorTyped<DecimalValue, ValueVectorDecimal38Dense> NullableValueVectorDecimal38Dense;
+typedef NullableValueVectorTyped<DecimalValue, ValueVectorDecimal28Sparse> NullableValueVectorDecimal28Sparse;
+typedef NullableValueVectorTyped<DecimalValue, ValueVectorDecimal38Sparse> NullableValueVectorDecimal38Sparse;
+typedef NullableValueVectorTyped<DecimalValue, ValueVectorVarDecimal> NullableValueVectorVarDecimal;
 
 typedef ValueVectorTyped<DateHolder, int64_t> ValueVectorDate;
 typedef ValueVectorTyped<DateTimeHolder, int64_t> ValueVectorTimestamp;
-- 
cgit v1.2.3