[CH-397] support posexplode/sequence functions (#399)

Co-authored-by: Robert Schulze <[email protected]>
Kyligence · Apr 12, 2023 · 0417ceb · 0417ceb
1 parent 876a30d
commit 0417ceb
Show file tree

Hide file tree

Showing 24 changed files with 350 additions and 137 deletions.
diff --git a/docs/en/sql-reference/functions/tuple-map-functions.md b/docs/en/sql-reference/functions/tuple-map-functions.md
@@ -66,6 +66,46 @@ Result:
 
 -   [Map(key, value)](../../sql-reference/data-types/map.md) data type
 
+## mapFromArrays
+
+Merges an [Array](../../sql-reference/data-types/array.md) of keys and an [Array](../../sql-reference/data-types/array.md) of values into a [Map(key, value)](../../sql-reference/data-types/map.md). Notice that the second argument could also be a [Map](../../sql-reference/data-types/map.md), thus it is casted to an Array when executing.
+
+The function is a more convenient alternative to `CAST((key_array, value_array_or_map), 'Map(key_type, value_type)')`. For example, instead of writing `CAST((['aa', 'bb'], [4, 5]), 'Map(String, UInt32)')`, you can write `mapFromArrays(['aa', 'bb'], [4, 5])`.
+
+**Syntax**
+
+```sql
+mapFromArrays(keys, values)
+```  
+
+Alias: `MAP_FROM_ARRAYS(keys, values)`
+
+**Parameters**
+-   `keys` — Given key array to create a map from. The nested type of array must be: [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md), [FixedString](../../sql-reference/data-types/fixedstring.md), [UUID](../../sql-reference/data-types/uuid.md), [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md), [Date32](../../sql-reference/data-types/date32.md), [Enum](../../sql-reference/data-types/enum.md)
+-   `values`  - Given value array or map to create a map from.
+
+**Returned value**
+
+- A map whose keys and values are constructed from the key array and value array/map.
+
+**Example**
+
+Query:
+
+```sql
+select mapFromArrays(['a', 'b', 'c'], [1, 2, 3])
+
+┌─mapFromArrays(['a', 'b', 'c'], [1, 2, 3])─┐
+│ {'a':1,'b':2,'c':3}                       │
+└───────────────────────────────────────────┘
+
+SELECT mapFromArrays([1, 2, 3], map('a', 1, 'b', 2, 'c', 3))
+
+┌─mapFromArrays([1, 2, 3], map('a', 1, 'b', 2, 'c', 3))─┐
+│ {1:('a',1),2:('b',2),3:('c',3)}                       │
+└───────────────────────────────────────────────────────┘
+```
+
 ## mapAdd
 
 Collect all the keys and sum corresponding values.
@@ -429,6 +469,8 @@ Result:
 │ {}                         │
 └────────────────────────────┘
 ```  
+
+
 
 ## mapApply  
 

diff --git a/src/AggregateFunctions/AggregateFunctionArray.h b/src/AggregateFunctions/AggregateFunctionArray.h
@@ -13,7 +13,7 @@ struct Settings;
 
 namespace ErrorCodes
 {
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
 }
 
@@ -129,7 +129,7 @@ class AggregateFunctionArray final : public IAggregateFunctionHelper<AggregateFu
             const IColumn::Offsets & ith_offsets = ith_column.getOffsets();
 
             if (ith_offsets[row_num] != end || (row_num != 0 && ith_offsets[row_num - 1] != begin))
-                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Arrays passed to {} aggregate function have different sizes", getName());
+                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Arrays passed to {} aggregate function have different sizes", getName());
         }
 
         for (size_t i = begin; i < end; ++i)

diff --git a/src/AggregateFunctions/AggregateFunctionForEach.h b/src/AggregateFunctions/AggregateFunctionForEach.h
@@ -19,7 +19,7 @@ namespace ErrorCodes
 {
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
 }
 
 
@@ -197,7 +197,7 @@ class AggregateFunctionForEach final : public IAggregateFunctionDataHelper<Aggre
             const IColumn::Offsets & ith_offsets = ith_column.getOffsets();
 
             if (ith_offsets[row_num] != end || (row_num != 0 && ith_offsets[row_num - 1] != begin))
-                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Arrays passed to {} aggregate function have different sizes", getName());
+                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Arrays passed to {} aggregate function have different sizes", getName());
         }
 
         AggregateFunctionForEachData & state = ensureAggregateData(place, end - begin, *arena);

diff --git a/src/Common/ErrorCodes.cpp b/src/Common/ErrorCodes.cpp
@@ -197,7 +197,7 @@
     M(187, COLLATION_COMPARISON_FAILED) \
     M(188, UNKNOWN_ACTION) \
     M(189, TABLE_MUST_NOT_BE_CREATED_MANUALLY) \
-    M(190, SIZES_OF_ARRAYS_DOESNT_MATCH) \
+    M(190, SIZES_OF_ARRAYS_DONT_MATCH) \
     M(191, SET_SIZE_LIMIT_EXCEEDED) \
     M(192, UNKNOWN_USER) \
     M(193, WRONG_PASSWORD) \

diff --git a/src/DataTypes/NestedUtils.cpp b/src/DataTypes/NestedUtils.cpp
@@ -25,7 +25,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int ILLEGAL_COLUMN;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
 }
 
 namespace Nested
@@ -242,7 +242,7 @@ void validateArraySizes(const Block & block)
                     const ColumnArray & another_array_column = assert_cast<const ColumnArray &>(*elem.column);
 
                     if (!first_array_column.hasEqualOffsets(another_array_column))
-                        throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                        throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                                         "Elements '{}' and '{}' "
                                         "of Nested data structure '{}' (Array columns) have different array sizes.",
                                         block.getByPosition(it->second).name, elem.name, split.first);

diff --git a/src/Functions/FunctionHelpers.cpp b/src/Functions/FunctionHelpers.cpp
@@ -16,7 +16,7 @@ namespace ErrorCodes
 {
     extern const int ILLEGAL_COLUMN;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
 }
 
@@ -213,7 +213,7 @@ checkAndGetNestedArrayOffset(const IColumn ** columns, size_t num_arguments)
         if (i == 0)
             offsets = offsets_i;
         else if (*offsets_i != *offsets)
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Lengths of all arrays passed to aggregate function must be equal.");
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Lengths of all arrays passed to aggregate function must be equal.");
     }
     return {nested_columns, offsets->data()};
 }

diff --git a/src/Functions/array/FunctionArrayMapped.h b/src/Functions/array/FunctionArrayMapped.h
@@ -36,7 +36,7 @@ namespace ErrorCodes
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
     extern const int LOGICAL_ERROR;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
 }
 
@@ -308,7 +308,7 @@ class FunctionArrayMapped : public IFunction
                     if (getOffsetsPtr(*column_array) != offsets_column
                         && getOffsets(*column_array) != typeid_cast<const ColumnArray::ColumnOffsets &>(*offsets_column).getData())
                         throw Exception(
-                            ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                            ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                             "{}s passed to {} must have equal size",
                             argument_type_name,
                             getName());

diff --git a/src/Functions/array/arrayDistance.cpp b/src/Functions/array/arrayDistance.cpp
@@ -16,7 +16,7 @@ namespace ErrorCodes
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
     extern const int LOGICAL_ERROR;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int ARGUMENT_OUT_OF_BOUND;
 }
 
@@ -356,7 +356,7 @@ class FunctionArrayDistance : public IFunction
             {
                 ColumnArray::Offset prev_offset = row > 0 ? offsets_x[row] : 0;
                 throw Exception(
-                    ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                    ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                     "Arguments of function {} have different array sizes: {} and {}",
                     getName(),
                     offsets_x[row] - prev_offset,
@@ -423,7 +423,7 @@ class FunctionArrayDistance : public IFunction
             if (unlikely(offsets_x[0] != offsets_y[row] - prev_offset))
             {
                 throw Exception(
-                    ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                    ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                     "Arguments of function {} have different array sizes: {} and {}",
                     getName(),
                     offsets_x[0],

diff --git a/src/Functions/array/arrayEnumerateExtended.h b/src/Functions/array/arrayEnumerateExtended.h
@@ -20,7 +20,7 @@ namespace ErrorCodes
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
 }
 
 class FunctionArrayEnumerateUniq;
@@ -153,7 +153,7 @@ ColumnPtr FunctionArrayEnumerateExtended<Derived>::executeImpl(const ColumnsWith
             offsets_column = array->getOffsetsPtr();
         }
         else if (offsets_i != *offsets)
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Lengths of all arrays passed to {} must be equal.",
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Lengths of all arrays passed to {} must be equal.",
                 getName());
 
         const auto * array_data = &array->getData();

diff --git a/src/Functions/array/arrayEnumerateRanked.h b/src/Functions/array/arrayEnumerateRanked.h
@@ -60,7 +60,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
 }
 
 class FunctionArrayEnumerateUniqRanked;
@@ -194,7 +194,7 @@ ColumnPtr FunctionArrayEnumerateRankedExtended<Derived>::executeImpl(
         {
             if (*offsets_by_depth[0] != array->getOffsets())
             {
-                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                                 "Lengths and effective depths of all arrays passed to {} must be equal.", getName());
             }
         }
@@ -217,15 +217,15 @@ ColumnPtr FunctionArrayEnumerateRankedExtended<Derived>::executeImpl(
             {
                 if (*offsets_by_depth[col_depth] != array->getOffsets())
                 {
-                    throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                    throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                                 "Lengths and effective depths of all arrays passed to {} must be equal.", getName());
                 }
             }
         }
 
         if (col_depth < arrays_depths.depths[array_num])
         {
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                             "{}: Passed array number {} depth ({}) is more than the actual array depth ({}).",
                             getName(), array_num, std::to_string(arrays_depths.depths[array_num]), col_depth);
         }

diff --git a/src/Functions/array/arrayReduce.cpp b/src/Functions/array/arrayReduce.cpp
@@ -19,7 +19,7 @@ namespace DB
 
 namespace ErrorCodes
 {
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
@@ -144,7 +144,7 @@ ColumnPtr FunctionArrayReduce::executeImpl(const ColumnsWithTypeAndName & argume
         if (i == 0)
             offsets = offsets_i;
         else if (*offsets_i != *offsets)
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Lengths of all arrays passed to {} must be equal.",
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Lengths of all arrays passed to {} must be equal.",
                 getName());
     }
     const IColumn ** aggregate_arguments = aggregate_arguments_vec.data();

diff --git a/src/Functions/array/arrayReduceInRanges.cpp b/src/Functions/array/arrayReduceInRanges.cpp
@@ -21,7 +21,7 @@ namespace DB
 
 namespace ErrorCodes
 {
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
@@ -190,7 +190,7 @@ ColumnPtr FunctionArrayReduceInRanges::executeImpl(
         if (i == 0)
             offsets = offsets_i;
         else if (*offsets_i != *offsets)
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Lengths of all arrays passed to {} must be equal.",
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Lengths of all arrays passed to {} must be equal.",
                 getName());
     }
     const IColumn ** aggregate_arguments = aggregate_arguments_vec.data();

diff --git a/src/Functions/array/arrayUniq.cpp b/src/Functions/array/arrayUniq.cpp
@@ -18,7 +18,7 @@ namespace DB
 
 namespace ErrorCodes
 {
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
     extern const int ILLEGAL_COLUMN;
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
@@ -151,7 +151,7 @@ ColumnPtr FunctionArrayUniq::executeImpl(const ColumnsWithTypeAndName & argument
         if (i == 0)
             offsets = &offsets_i;
         else if (offsets_i != *offsets)
-            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH, "Lengths of all arrays passed to {} must be equal.",
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Lengths of all arrays passed to {} must be equal.",
                 getName());
 
         const auto * array_data = &array->getData();

diff --git a/src/Functions/array/arrayZip.cpp b/src/Functions/array/arrayZip.cpp
@@ -13,7 +13,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int ILLEGAL_TYPE_OF_ARGUMENT;
-    extern const int SIZES_OF_ARRAYS_DOESNT_MATCH;
+    extern const int SIZES_OF_ARRAYS_DONT_MATCH;
     extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
     extern const int ILLEGAL_COLUMN;
 }
@@ -81,7 +81,7 @@ class FunctionArrayZip : public IFunction
             }
             else if (!column_array->hasEqualOffsets(static_cast<const ColumnArray &>(*first_array_column)))
             {
-                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DOESNT_MATCH,
+                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
                                 "The argument 1 and argument {} of function {} have different array sizes",
                                 i + 1, getName());
             }