pytrilogy 0.0.3.73__py3-none-any.whl → 0.0.3.75__py3-none-any.whl

{pytrilogy-0.0.3.73.dist-info → pytrilogy-0.0.3.75.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrilogy
-Version: 0.0.3.73
+Version: 0.0.3.75
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.3.73.dist-info → pytrilogy-0.0.3.75.dist-info}/RECORD

@@ -1,5 +1,5 @@
-pytrilogy-0.0.3.73.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
-trilogy/__init__.py,sha256=QMg3__Goia6PP_-WfMP9ZmROmpZ0XzX4rCz9MvpBb_w,303
+pytrilogy-0.0.3.75.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
+trilogy/__init__.py,sha256=MIf9sLTcNq9Rl4yjZRDALK9URcm1vSxXzixHDnfPJg0,303
 trilogy/compiler.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/constants.py,sha256=eKb_EJvSqjN9tGbdVEViwdtwwh8fZ3-jpOEDqL71y70,1691
 trilogy/engine.py,sha256=OK2RuqCIUId6yZ5hfF8J1nxGP0AJqHRZiafcowmW0xc,1728
@@ -8,25 +8,25 @@ trilogy/parser.py,sha256=o4cfk3j3yhUFoiDKq9ZX_GjBF3dKhDjXEwb63rcBkBM,293
 trilogy/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/render.py,sha256=qQWwduymauOlB517UtM-VGbVe8Cswa4UJub5aGbSO6c,1512
 trilogy/utility.py,sha256=euQccZLKoYBz0LNg5tzLlvv2YHvXh9HArnYp1V3uXsM,763
-trilogy/authoring/__init__.py,sha256=h-Ag7vT76tsjib9BfjOgI-yVpuJDgpn2TSps-ibRAj8,2593
+trilogy/authoring/__init__.py,sha256=e74k-Jep4DLYPQU_2m0aVsYlw5HKTOucAKtdTbd6f2g,2595
 trilogy/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/core/constants.py,sha256=nizWYDCJQ1bigQMtkNIEMNTcN0NoEAXiIHLzpelxQ24,201
-trilogy/core/enums.py,sha256=fog9j6YU22LXuoArKsNJn-UFIEAVk06LI_-Zdg2UDv0,7841
+trilogy/core/enums.py,sha256=--iG8Q1NJ9JBJe4IIdO37P2T3TOWn_CmqbagsQGfNf0,8050
 trilogy/core/env_processor.py,sha256=pFsxnluKIusGKx1z7tTnfsd_xZcPy9pZDungkjkyvI0,3170
 trilogy/core/environment_helpers.py,sha256=VvPIiFemqaLLpIpLIqprfu63K7muZ1YzNg7UZIUph8w,8267
 trilogy/core/ergonomics.py,sha256=e-7gE29vPLFdg0_A1smQ7eOrUwKl5VYdxRSTddHweRA,1631
 trilogy/core/exceptions.py,sha256=jYEduuMehcMkmCpf-OC_taELPZm7qNfeSNzIWkDYScs,707
-trilogy/core/functions.py,sha256=xT4DR6IRTt3N6TZ_LEcSV2nvLUWFGfajd5vQZd2Pw7k,29512
+trilogy/core/functions.py,sha256=wQ5yCvMKXSCkaSo7yiwlGY0wvqE4Sm2MI9e5NEr2ORw,30933
 trilogy/core/graph_models.py,sha256=BYhJzHKSgnZHVLJs1CfsgrxTPHqKqPNeA64RlozGY0A,3498
 trilogy/core/internal.py,sha256=iicDBlC6nM8d7e7jqzf_ZOmpUsW8yrr2AA8AqEiLx-s,1577
 trilogy/core/optimization.py,sha256=ojpn-p79lr03SSVQbbw74iPCyoYpDYBmj1dbZ3oXCjI,8860
 trilogy/core/query_processor.py,sha256=5aFgv-2LVM1Uku9cR_tFuTRDwyLnxc95bCMAHeFy2AY,20332
 trilogy/core/utility.py,sha256=3VC13uSQWcZNghgt7Ot0ZTeEmNqs__cx122abVq9qhM,410
 trilogy/core/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/core/models/author.py,sha256=Wz_6yEZS5EyXJ5wHHl-C44ikFka5XftBYOjNRK98Hfw,77790
-trilogy/core/models/build.py,sha256=59KmJDY1lzJMXuAZjxvT7K5IhIga9k2xwhzQBbx5zyo,65688
+trilogy/core/models/author.py,sha256=iCj5zQcBYB-4u93vM9OfX56-eqRcWQhKRAwrHXRsNGA,78046
+trilogy/core/models/build.py,sha256=UfWuG86O8yivqK4UhCOXk5IyHUw0vZPckcSljeCuK3o,65859
 trilogy/core/models/build_environment.py,sha256=s_C9xAHuD3yZ26T15pWVBvoqvlp2LdZ8yjsv2_HdXLk,5363
-trilogy/core/models/core.py,sha256=EMAuWTngoNVGCdfNrAY7_k6g528iodNQLwPRVip-8DA,10980
+trilogy/core/models/core.py,sha256=q-8ExAaSB3PoSDX2XOqfZ01HBBvT1pZFs7jGg1vZizc,11096
 trilogy/core/models/datasource.py,sha256=wogTevZ-9CyUW2a8gjzqMCieircxi-J5lkI7EOAZnck,9596
 trilogy/core/models/environment.py,sha256=TBbPfsXHpJK49QKuqHwhgZD4PwHiSAYjXmTTTomRE7o,27861
 trilogy/core/models/execute.py,sha256=Erufst3yroU3PgNJMWF5lICm14AkH02laYeesSB01UU,41705
@@ -41,7 +41,7 @@ trilogy/core/processing/discovery_node_factory.py,sha256=I3JJxoF-u8OVvqXXAOhvMg2
 trilogy/core/processing/discovery_utility.py,sha256=3xdd1ypKappSDm0SJs7WtW5YegL80SlYhDQlkNePp4E,4549
 trilogy/core/processing/discovery_validation.py,sha256=fGWJmKpgEd1f4RkK-fYOBUT1cwsJnahwXFAdRlou7MI,5365
 trilogy/core/processing/graph_utils.py,sha256=8QUVrkE9j-9C1AyrCb1nQEh8daCe0u1HuXl-Te85lag,1205
-trilogy/core/processing/utility.py,sha256=ChD1lP2iXtfsI1bS08OZsJ2o9t877OhNXrDvyEgYdmY,22581
+trilogy/core/processing/utility.py,sha256=xsuVMRFi2nY2So0yohhweI2D92wZVsTpHezS0giM4ck,22583
 trilogy/core/processing/node_generators/__init__.py,sha256=w8TQQgNhyAra6JQHdg1_Ags4BGyxjXYruu6UeC5yOkI,873
 trilogy/core/processing/node_generators/basic_node.py,sha256=luN8LftafZepoFgDRv4gmvEGFlOI2j0icJ5fz4UT7uo,5165
 trilogy/core/processing/node_generators/common.py,sha256=PdysdroW9DUADP7f5Wv_GKPUyCTROZV1g3L45fawxi8,9443
@@ -76,12 +76,12 @@ trilogy/core/statements/build.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 trilogy/core/statements/common.py,sha256=KxEmz2ySySyZ6CTPzn0fJl5NX2KOk1RPyuUSwWhnK1g,759
 trilogy/core/statements/execute.py,sha256=rqfuoMuXPcH7L7TmE1dSiZ_K_A1ohB8whVMfGimZBOk,1294
 trilogy/dialect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/dialect/base.py,sha256=5FI4_XDdSavdHeC3VhSI8xrvQagFyRRq6Ttsh70ajo4,45241
+trilogy/dialect/base.py,sha256=fEkPou4Eku7Un9NLZ6ya8OIVdaaV8ZJyZIbn56xOrVc,45829
 trilogy/dialect/bigquery.py,sha256=8xhEu0z_lKANjbvzvBbC7CeKrJf1iP8YyrHqNale-ug,4351
 trilogy/dialect/common.py,sha256=tSthIZOXXRPQ4KeMKnDDsH7KlTmf2EVqigVtLyoc4zc,6071
 trilogy/dialect/config.py,sha256=olnyeVU5W5T6b9-dMeNAnvxuPlyc2uefb7FRME094Ec,3834
 trilogy/dialect/dataframe.py,sha256=RUbNgReEa9g3pL6H7fP9lPTrAij5pkqedpZ99D8_5AE,1522
-trilogy/dialect/duckdb.py,sha256=gsXhPKX0D7ykJ9RFK9qx8uBTjLgtHu6PYv6GlBFtnJE,4448
+trilogy/dialect/duckdb.py,sha256=0qWQkyijz1_MnsVFyY_Iqqx0ba6E8o50s8pvLLpZH6g,5138
 trilogy/dialect/enums.py,sha256=FRNYQ5-w-B6-X0yXKNU5g9GowsMlERFogTC5u2nxL_s,4740
 trilogy/dialect/postgres.py,sha256=el2PKwfyvWGk5EZtLudqAH5ewLitY1sFHJiocBSyxyM,3393
 trilogy/dialect/presto.py,sha256=yzSF8SZ6o1dizj1UueAa7S3lR0qNYJdSXbF78EHyhY0,3668
@@ -97,9 +97,9 @@ trilogy/parsing/common.py,sha256=yV1AckK0h8u1OFeGQBTMu-wuW5m63c5CcZuPicsTH_w,306
 trilogy/parsing/config.py,sha256=Z-DaefdKhPDmSXLgg5V4pebhSB0h590vI0_VtHnlukI,111
 trilogy/parsing/exceptions.py,sha256=Xwwsv2C9kSNv2q-HrrKC1f60JNHShXcCMzstTSEbiCw,154
 trilogy/parsing/helpers.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-trilogy/parsing/parse_engine.py,sha256=YFIWTkWrUJ8l-KoCVwPs1hodj3BhqX-DHbBXWQN5akc,72776
-trilogy/parsing/render.py,sha256=gGCFj2ue0UoaU2MR6qHGMAHXkYRMkTmHjnBowdcgFMY,19603
-trilogy/parsing/trilogy.lark,sha256=1RIqA7zrGuqDJYSv9yHGSw0vdIfGOLPOnc4hSBRSTVU,14346
+trilogy/parsing/parse_engine.py,sha256=XQa8kSLiXd--MH89HvwlyNClQnFJ7ZLkm8PwxMsxHeY,74587
+trilogy/parsing/render.py,sha256=HSNntD82GiiwHT-TWPLXAaIMWLYVV5B5zQEsgwrHIBE,19605
+trilogy/parsing/trilogy.lark,sha256=v2UqMBhU9hn9km4mvQkk3E2wsEZjJ4cz4wU72NFFvU4,14993
 trilogy/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/scripts/trilogy.py,sha256=1L0XrH4mVHRt1C9T1HnaDv2_kYEfbWTb5_-cBBke79w,3774
 trilogy/std/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -110,8 +110,8 @@ trilogy/std/money.preql,sha256=XWwvAV3WxBsHX9zfptoYRnBigcfYwrYtBHXTME0xJuQ,2082
 trilogy/std/net.preql,sha256=7l7MqIjs6TDCpO6dBAoNJU81Ex255jZRK36kBgE1GDs,158
 trilogy/std/ranking.preql,sha256=LDoZrYyz4g3xsII9XwXfmstZD-_92i1Eox1UqkBIfi8,83
 trilogy/std/report.preql,sha256=LbV-XlHdfw0jgnQ8pV7acG95xrd1-p65fVpiIc-S7W4,202
-pytrilogy-0.0.3.73.dist-info/METADATA,sha256=hMwyLjCer0xl2zhn1XH4PijoJrNy7oXV9qKyHIDfUWA,9734
-pytrilogy-0.0.3.73.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pytrilogy-0.0.3.73.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
-pytrilogy-0.0.3.73.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
-pytrilogy-0.0.3.73.dist-info/RECORD,,
+pytrilogy-0.0.3.75.dist-info/METADATA,sha256=BiUDu-P-eT6dmtLstg2EmFFJ0Pc-eU6k17U--NmkXqU,9734
+pytrilogy-0.0.3.75.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pytrilogy-0.0.3.75.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
+pytrilogy-0.0.3.75.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
+pytrilogy-0.0.3.75.dist-info/RECORD,,

trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.dialect.enums import Dialects
 from trilogy.executor import Executor
 from trilogy.parser import parse
 
-__version__ = "0.0.3.73"
+__version__ = "0.0.3.75"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

trilogy/authoring/__init__.py

@@ -37,8 +37,8 @@ from trilogy.core.models.author import (
     WindowType,
 )
 from trilogy.core.models.core import (
+    ArrayType,
     DataType,
-    ListType,
     ListWrapper,
     MapType,
     StructType,
@@ -77,7 +77,7 @@ __all__ = [
     "WindowItemOver",
     "DataType",
     "StructType",
-    "ListType",
+    "ArrayType",
     "Grain",
     "RowsetDerivationStatement",
     "MapType",

trilogy/core/enums.py

@@ -149,6 +149,12 @@ class FunctionType(Enum):
     DATE_LITERAL = "date_literal"
     DATETIME_LITERAL = "datetime_literal"
 
+    # ARRAY
+    ARRAY_DISTINCT = "array_distinct"
+    ARRAY_SUM = "array_sum"
+    ARRAY_SORT = "array_sort"
+    ARRAY_TRANSFORM = "array_transform"
+
     # TEXT AND MAYBE MORE
     SPLIT = "split"
     LENGTH = "len"
@@ -177,6 +183,7 @@ class FunctionType(Enum):
     MAX = "max"
     MIN = "min"
     AVG = "avg"
+    ARRAY_AGG = "array_agg"
 
     # String
     LIKE = "like"
@@ -228,6 +235,7 @@ class FunctionClass(Enum):
         FunctionType.MIN,
         FunctionType.SUM,
         FunctionType.AVG,
+        FunctionType.ARRAY_AGG,
         FunctionType.COUNT,
         FunctionType.COUNT_DISTINCT,
     ]

trilogy/core/functions.py

@@ -25,8 +25,8 @@ from trilogy.core.models.author import (
 )
 from trilogy.core.models.core import (
     CONCRETE_TYPES,
+    ArrayType,
     DataType,
-    ListType,
     MapType,
     NumericType,
     StructType,
@@ -45,14 +45,14 @@ class FunctionConfig:
     valid_inputs: set[DataType] | list[set[DataType]] | None = None
     output_purpose: Purpose | None = None
     output_type: (
-        DataType | ListType | MapType | StructType | NumericType | TraitDataType | None
+        DataType | ArrayType | MapType | StructType | NumericType | TraitDataType | None
     ) = None
     output_type_function: Optional[Callable] = None
 
 
 def get_unnest_output_type(args: list[Any]) -> CONCRETE_TYPES:
     output = arg_to_datatype(args[0])
-    if isinstance(output, (ListType, MapType)):
+    if isinstance(output, (ArrayType, MapType)):
         output = output.value_data_type
     else:
         output = DataType.STRING
@@ -69,12 +69,16 @@ def get_coalesce_output_type(args: list[Any]) -> CONCRETE_TYPES:
     return processed[0]
 
 
+def get_transform_output_type(args: list[Any]) -> CONCRETE_TYPES:
+    return arg_to_datatype(args[2])
+
+
 def get_index_output_type(
     args: list[Any],
 ) -> CONCRETE_TYPES:
     arg = args[0]
     datatype = arg_to_datatype(arg)
-    if isinstance(datatype, ListType):
+    if isinstance(datatype, ArrayType):
         return datatype.value_data_type
     elif isinstance(datatype, MapType):
         return datatype.value_data_type
@@ -184,7 +188,6 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
     FunctionType.UNNEST: FunctionConfig(
         valid_inputs={
             DataType.ARRAY,
-            DataType.LIST,
         },
         output_purpose=Purpose.KEY,
         output_type_function=get_unnest_output_type,
@@ -235,13 +238,12 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
     FunctionType.SPLIT: FunctionConfig(
         valid_inputs={DataType.STRING},
         output_purpose=Purpose.PROPERTY,
-        output_type=ListType(type=DataType.STRING),
+        output_type=ArrayType(type=DataType.STRING),
         arg_count=2,
     ),
     FunctionType.INDEX_ACCESS: FunctionConfig(
         valid_inputs=[
             {
-                DataType.LIST,
                 DataType.ARRAY,
             },
             {
@@ -252,6 +254,43 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         output_type_function=get_index_output_type,
         arg_count=2,
     ),
+    FunctionType.ARRAY_DISTINCT: FunctionConfig(
+        valid_inputs={
+            DataType.ARRAY,
+        },
+        output_purpose=Purpose.PROPERTY,
+        output_type_function=lambda args: get_output_type_at_index(args, 0),
+        arg_count=1,
+    ),
+    FunctionType.ARRAY_SORT: FunctionConfig(
+        valid_inputs=[
+            {DataType.ARRAY},
+            {DataType.STRING},
+        ],
+        output_purpose=Purpose.PROPERTY,
+        output_type_function=lambda args: get_output_type_at_index(args, 0),
+        arg_count=2,
+    ),
+    FunctionType.ARRAY_TRANSFORM: FunctionConfig(
+        valid_inputs=[
+            {
+                DataType.ARRAY,
+            },
+            {*DataType},
+            {*DataType},
+        ],
+        output_purpose=Purpose.PROPERTY,
+        output_type_function=get_transform_output_type,
+        arg_count=3,
+    ),
+    FunctionType.ARRAY_SUM: FunctionConfig(
+        valid_inputs={
+            DataType.ARRAY,
+        },
+        output_purpose=Purpose.PROPERTY,
+        output_type_function=get_index_output_type,
+        arg_count=1,
+    ),
     FunctionType.MAP_ACCESS: FunctionConfig(
         valid_inputs=[
             {
@@ -722,7 +761,7 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
     FunctionType.ARRAY: FunctionConfig(
         output_purpose=Purpose.PROPERTY,
         arg_count=InfiniteFunctionArgs,
-        output_type=ListType(type=DataType.STRING),
+        output_type=ArrayType(type=DataType.STRING),
     ),
     FunctionType.LENGTH: FunctionConfig(
         valid_inputs={DataType.STRING, DataType.ARRAY, DataType.MAP},
@@ -740,6 +779,14 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         output_purpose=Purpose.METRIC,
         arg_count=1,
     ),
+    FunctionType.ARRAY_AGG: FunctionConfig(
+        valid_inputs={*DataType},
+        output_purpose=Purpose.METRIC,
+        output_type_function=lambda args: ArrayType(
+            type=merge_datatypes([arg_to_datatype(x) for x in args])
+        ),
+        arg_count=1,
+    ),
     FunctionType.AVG: FunctionConfig(
         valid_inputs={
             DataType.INTEGER,
@@ -837,7 +884,7 @@ def create_function_derived_concept(
     arguments: list[Concept],
     environment: Environment,
     output_type: Optional[
-        DataType | ListType | StructType | MapType | NumericType | TraitDataType
+        DataType | ArrayType | StructType | MapType | NumericType | TraitDataType
     ] = None,
     output_purpose: Optional[Purpose] = None,
 ) -> Concept:

trilogy/core/models/author.py

@@ -48,9 +48,9 @@ from trilogy.core.enums import (
 )
 from trilogy.core.models.core import (
     Addressable,
+    ArrayType,
     DataType,
     DataTyped,
-    ListType,
     ListWrapper,
     MapType,
     MapWrapper,
@@ -104,7 +104,7 @@ class HasUUID(ABC):
 class ConceptRef(Addressable, Namespaced, DataTyped, Mergeable, BaseModel):
     address: str
     datatype: (
-        DataType | TraitDataType | ListType | StructType | MapType | NumericType
+        DataType | TraitDataType | ArrayType | StructType | MapType | NumericType
     ) = DataType.UNKNOWN
     metadata: Optional["Metadata"] = None
 
@@ -646,7 +646,7 @@ class Comparison(ConceptArgs, Mergeable, DataTyped, Namespaced, BaseModel):
                 )
         elif self.operator in (ComparisonOperator.IN, ComparisonOperator.NOT_IN):
             right_type = arg_to_datatype(self.right)
-            if isinstance(right_type, ListType) and not is_compatible_datatype(
+            if isinstance(right_type, ArrayType) and not is_compatible_datatype(
                 arg_to_datatype(self.left), right_type.value_data_type
             ):
                 raise SyntaxError(
@@ -802,7 +802,7 @@ class Concept(Addressable, DataTyped, ConceptArgs, Mergeable, Namespaced, BaseMo
         extra="forbid",
     )
     name: str
-    datatype: DataType | TraitDataType | ListType | StructType | MapType | NumericType
+    datatype: DataType | TraitDataType | ArrayType | StructType | MapType | NumericType
     purpose: Purpose
     derivation: Derivation = Derivation.ROOT
     granularity: Granularity = Granularity.MULTI_ROW
@@ -1277,7 +1277,7 @@ class UndefinedConceptFull(Concept, Mergeable, Namespaced):
     name: str
     line_no: int | None = None
     datatype: (
-        DataType | TraitDataType | ListType | StructType | MapType | NumericType
+        DataType | TraitDataType | ArrayType | StructType | MapType | NumericType
     ) = DataType.UNKNOWN
     purpose: Purpose = Purpose.UNKNOWN
 
@@ -1437,10 +1437,10 @@ class WindowItem(DataTyped, ConceptArgs, Mergeable, Namespaced, BaseModel):
 
 
 def get_basic_type(
-    type: DataType | ListType | StructType | MapType | NumericType | TraitDataType,
+    type: DataType | ArrayType | StructType | MapType | NumericType | TraitDataType,
 ) -> DataType:
-    if isinstance(type, ListType):
-        return DataType.LIST
+    if isinstance(type, ArrayType):
+        return DataType.ARRAY
     if isinstance(type, StructType):
         return DataType.STRUCT
     if isinstance(type, MapType):
@@ -1609,7 +1609,7 @@ class Function(DataTyped, ConceptArgs, Mergeable, Namespaced, BaseModel):
     operator: FunctionType
     arg_count: int = Field(default=1)
     output_datatype: (
-        DataType | ListType | StructType | MapType | NumericType | TraitDataType
+        DataType | ArrayType | StructType | MapType | NumericType | TraitDataType
     )
     output_purpose: Purpose
     valid_inputs: Optional[
@@ -2358,9 +2358,10 @@ class Comment(BaseModel):
     text: str
 
 
-class ArgBinding(Namespaced, BaseModel):
+class ArgBinding(Namespaced, DataTyped, BaseModel):
     name: str
     default: Expr | None = None
+    datatype: DataType = DataType.UNKNOWN
 
     def with_namespace(self, namespace):
         return ArgBinding(
@@ -2372,6 +2373,12 @@ class ArgBinding(Namespaced, BaseModel):
             ),
         )
 
+    @property
+    def output_datatype(self):
+        if self.default is not None:
+            return arg_to_datatype(self.default)
+        return self.datatype
+
 
 class CustomType(BaseModel):
     name: str
@@ -2426,7 +2433,7 @@ FuncArgs = (
     | MapWrapper[Any, Any]
     | TraitDataType
     | DataType
-    | ListType
+    | ArrayType
     | MapType
     | NumericType
     | ListWrapper[Any]
@@ -2434,4 +2441,6 @@ FuncArgs = (
     | Comparison
     | Conditional
     | MagicConstants
+    | ArgBinding
+    | Ordering
 )

trilogy/core/models/build.py

@@ -45,6 +45,7 @@ from trilogy.core.models.author import (
     AggregateWrapper,
     AlignClause,
     AlignItem,
+    ArgBinding,
     CaseElse,
     CaseWhen,
     Comparison,
@@ -72,9 +73,9 @@ from trilogy.core.models.author import (
 )
 from trilogy.core.models.core import (
     Addressable,
+    ArrayType,
     DataType,
     DataTyped,
-    ListType,
     ListWrapper,
     MapType,
     MapWrapper,
@@ -791,7 +792,7 @@ class BuildSubselectComparison(BuildComparison):
 class BuildConcept(Addressable, BuildConceptArgs, DataTyped, BaseModel):
     model_config = ConfigDict(extra="forbid")
     name: str
-    datatype: DataType | ListType | StructType | MapType | NumericType
+    datatype: DataType | ArrayType | StructType | MapType | NumericType
     purpose: Purpose
     build_is_aggregate: bool
     derivation: Derivation = Derivation.ROOT
@@ -1083,7 +1084,7 @@ class BuildFunction(DataTyped, BuildConceptArgs, BaseModel):
     operator: FunctionType
     arg_count: int = Field(default=1)
     output_datatype: (
-        DataType | ListType | StructType | MapType | NumericType | TraitDataType
+        DataType | ArrayType | StructType | MapType | NumericType | TraitDataType
     )
     output_purpose: Purpose
     valid_inputs: Optional[
@@ -1102,7 +1103,7 @@ class BuildFunction(DataTyped, BuildConceptArgs, BaseModel):
             MapWrapper[Any, Any],
             TraitDataType,
             DataType,
-            ListType,
+            ArrayType,
             MapType,
             NumericType,
             DatePart,
@@ -2075,7 +2076,7 @@ class Factory:
         return base
 
     @build.register
-    def _(self, base: ListType):
+    def _(self, base: ArrayType):
         return base
 
     @build.register
@@ -2086,6 +2087,14 @@ class Factory:
     def _(self, base: MapType):
         return base
 
+    @build.register
+    def _(self, base: ArgBinding):
+        return base
+
+    @build.register
+    def _(self, base: Ordering):
+        return base
+
     @build.register
     def _(self, base: Datasource):
         local_cache: dict[str, BuildConcept] = {}

trilogy/core/models/core.py

@@ -27,6 +27,7 @@ from pydantic_core import core_schema
 from trilogy.constants import (
     MagicConstants,
 )
+from trilogy.core.enums import Ordering
 
 
 class DataTyped(ABC):
@@ -53,7 +54,7 @@ class Addressable(ABC):
 TYPEDEF_TYPES = Union[
     "DataType",
     "MapType",
-    "ListType",
+    "ArrayType",
     "NumericType",
     "StructType",
     "DataTyped",
@@ -63,7 +64,7 @@ TYPEDEF_TYPES = Union[
 CONCRETE_TYPES = Union[
     "DataType",
     "MapType",
-    "ListType",
+    "ArrayType",
     "NumericType",
     "StructType",
     "TraitDataType",
@@ -79,7 +80,6 @@ class DataType(Enum):
     STRING = "string"
     BOOL = "bool"
     MAP = "map"
-    LIST = "list"
     NUMBER = "number"
     FLOAT = "float"
     NUMERIC = "numeric"
@@ -105,7 +105,7 @@ class DataType(Enum):
 
 
 class TraitDataType(BaseModel):
-    type: DataType | NumericType | StructType | ListType | MapType
+    type: DataType | NumericType | StructType | ArrayType | MapType
     traits: list[str]
 
     def __hash__(self):
@@ -146,7 +146,7 @@ class NumericType(BaseModel):
         return self.data_type.value
 
 
-class ListType(BaseModel):
+class ArrayType(BaseModel):
     model_config = ConfigDict(frozen=True)
     type: TYPEDEF_TYPES
 
@@ -159,7 +159,7 @@ class ListType(BaseModel):
 
     @property
     def data_type(self):
-        return DataType.LIST
+        return DataType.ARRAY
 
     @property
     def value(self):
@@ -340,9 +340,9 @@ def dict_to_map_wrapper(arg):
 
 def merge_datatypes(
     inputs: list[
-        DataType | ListType | StructType | MapType | NumericType | TraitDataType
+        DataType | ArrayType | StructType | MapType | NumericType | TraitDataType
     ],
-) -> DataType | ListType | StructType | MapType | NumericType | TraitDataType:
+) -> DataType | ArrayType | StructType | MapType | NumericType | TraitDataType:
     """This is a temporary hack for doing between
     allowable datatype transformation matrix"""
     if len(inputs) == 1:
@@ -393,6 +393,8 @@ def arg_to_datatype(arg) -> CONCRETE_TYPES:
         raise ValueError(f"Cannot parse arg datatype for arg of type {arg}")
     elif isinstance(arg, bool):
         return DataType.BOOL
+    elif isinstance(arg, Ordering):
+        return DataType.STRING  # TODO: revisit
     elif isinstance(arg, int):
         return DataType.INTEGER
     elif isinstance(arg, str):
@@ -404,14 +406,14 @@ def arg_to_datatype(arg) -> CONCRETE_TYPES:
     elif isinstance(arg, TraitDataType):
         return arg
     elif isinstance(arg, ListWrapper):
-        return ListType(type=arg.type)
+        return ArrayType(type=arg.type)
     elif isinstance(arg, DataTyped):
         return arg.output_datatype
     elif isinstance(arg, TupleWrapper):
-        return ListType(type=arg.type)
+        return ArrayType(type=arg.type)
     elif isinstance(arg, list):
         wrapper = list_to_wrapper(arg)
-        return ListType(type=wrapper.type)
+        return ArrayType(type=wrapper.type)
     elif isinstance(arg, MapWrapper):
         return MapType(key_type=arg.key_type, value_type=arg.value_type)
     elif isinstance(arg, datetime):

trilogy/core/processing/utility.py

@@ -33,8 +33,8 @@ from trilogy.core.models.build import (
 )
 from trilogy.core.models.build_environment import BuildEnvironment
 from trilogy.core.models.core import (
+    ArrayType,
     DataType,
-    ListType,
     ListWrapper,
     MapType,
     MapWrapper,
@@ -471,7 +471,7 @@ def is_scalar_condition(
         | TraitDataType
         | DataType
         | MapWrapper[Any, Any]
-        | ListType
+        | ArrayType
         | MapType
         | NumericType
         | DatePart

trilogy/dialect/base.py

@@ -15,10 +15,12 @@ from trilogy.core.enums import (
     ComparisonOperator,
     DatePart,
     FunctionType,
+    Ordering,
     UnnestMode,
     WindowType,
 )
 from trilogy.core.internal import DEFAULT_CONCEPTS
+from trilogy.core.models.author import ArgBinding
 from trilogy.core.models.build import (
     BuildAggregateWrapper,
     BuildCaseElse,
@@ -37,8 +39,8 @@ from trilogy.core.models.build import (
     BuildWindowItem,
 )
 from trilogy.core.models.core import (
+    ArrayType,
     DataType,
-    ListType,
     ListWrapper,
     MapType,
     MapWrapper,
@@ -142,11 +144,11 @@ DATATYPE_MAP: dict[DataType, str] = {
     DataType.MAP: "map",
     DataType.DATE: "date",
     DataType.DATETIME: "datetime",
-    DataType.LIST: "list",
+    DataType.ARRAY: "list",
 }
 
 COMPLEX_DATATYPE_MAP = {
-    DataType.LIST: lambda x: f"{x}[]",
+    DataType.ARRAY: lambda x: f"{x}[]",
 }
 
 
@@ -182,6 +184,13 @@ FUNCTION_MAP = {
     FunctionType.ARRAY: lambda x: f"[{', '.join(x)}]",
     FunctionType.DATE_LITERAL: lambda x: f"date '{x}'",
     FunctionType.DATETIME_LITERAL: lambda x: f"datetime '{x}'",
+    # ARRAY
+    FunctionType.ARRAY_SUM: lambda x: f"array_sum({x[0]})",
+    FunctionType.ARRAY_DISTINCT: lambda x: f"array_distinct({x[0]})",
+    FunctionType.ARRAY_SORT: lambda x: f"array_sort({x[0]})",
+    FunctionType.ARRAY_TRANSFORM: lambda args: (
+        f"array_transform({args[0]}, {args[1]} -> {args[2]})"
+    ),
     # math
     FunctionType.ADD: lambda x: " + ".join(x),
     FunctionType.ABS: lambda x: f"abs({x[0]})",
@@ -198,6 +207,7 @@ FUNCTION_MAP = {
     FunctionType.COUNT_DISTINCT: lambda x: f"count(distinct {x[0]})",
     FunctionType.COUNT: lambda x: f"count({x[0]})",
     FunctionType.SUM: lambda x: f"sum({x[0]})",
+    FunctionType.ARRAY_AGG: lambda x: f"array_agg({x[0]})",
     FunctionType.LENGTH: lambda x: f"length({x[0]})",
     FunctionType.AVG: lambda x: f"avg({x[0]})",
     FunctionType.MAX: lambda x: f"max({x[0]})",
@@ -569,7 +579,7 @@ class BaseDialect:
             MapType,
             NumericType,
             StructType,
-            ListType,
+            ArrayType,
             ListWrapper[Any],
             TupleWrapper[Any],
             DatePart,
@@ -749,8 +759,12 @@ class BaseDialect:
             return self.FUNCTION_MAP[FunctionType.DATETIME_LITERAL](e)
         elif isinstance(e, TraitDataType):
             return self.render_expr(e.type, cte=cte, cte_map=cte_map)
-        elif isinstance(e, ListType):
-            return f"{self.COMPLEX_DATATYPE_MAP[DataType.LIST](self.render_expr(e.value_data_type, cte=cte, cte_map=cte_map))}"
+        elif isinstance(e, ArgBinding):
+            return e.name
+        elif isinstance(e, Ordering):
+            return str(e.value)
+        elif isinstance(e, ArrayType):
+            return f"{self.COMPLEX_DATATYPE_MAP[DataType.ARRAY](self.render_expr(e.value_data_type, cte=cte, cte_map=cte_map))}"
         elif isinstance(e, BuildParamaterizedConceptReference):
             if self.rendering.parameters:
                 if e.concept.namespace == DEFAULT_NAMESPACE:

trilogy/dialect/duckdb.py

@@ -23,6 +23,16 @@ def generate_regex_extract(x: list[str]) -> str:
     return f"REGEXP_EXTRACT({x[0]},{x[1]},{x[2]})"
 
 
+def render_sort(args):
+    if len(args) == 1:
+        return f"list_sort({args[0]})"
+    order = args[1].split(" ", 1)
+    if len(order) == 1:
+        return f"list_sort({args[0]}, '{order[0]}')"
+    elif len(order) == 2:
+        return f"list_sort({args[0]}, '{order[0]}', '{order[1]}')"
+
+
 FUNCTION_MAP = {
     FunctionType.COUNT: lambda args: f"count({args[0]})",
     FunctionType.SUM: lambda args: f"sum({args[0]})",
@@ -39,6 +49,14 @@ FUNCTION_MAP = {
     ),
     ## Duckdb indexes from 1, not 0
     FunctionType.INDEX_ACCESS: lambda args: (f"{args[0]}[{args[1]}]"),
+    ## Duckdb uses list for array
+    FunctionType.ARRAY_DISTINCT: lambda args: f"list_distinct({args[0]})",
+    FunctionType.ARRAY_SUM: lambda args: f"list_sum({args[0]})",
+    FunctionType.ARRAY_SORT: render_sort,
+    FunctionType.ARRAY_TRANSFORM: lambda args: (
+        f"list_transform({args[0]}, {args[1]} -> {args[2]})"
+    ),
+    FunctionType.ARRAY_AGG: lambda args: f"array_agg({args[0]})",
     # datetime is aliased
     FunctionType.CURRENT_DATETIME: lambda x: "cast(get_current_timestamp() as datetime)",
     FunctionType.DATE: lambda x: f"cast({x[0]} as date)",

trilogy/parsing/parse_engine.py

@@ -82,9 +82,9 @@ from trilogy.core.models.author import (
     WindowItemOver,
 )
 from trilogy.core.models.core import (
+    ArrayType,
     DataType,
     DataTyped,
-    ListType,
     ListWrapper,
     MapType,
     MapWrapper,
@@ -446,7 +446,7 @@ class ParseToObjects(Transformer):
     @v_args(meta=True)
     def struct_type(self, meta: Meta, args) -> StructType:
         final: list[
-            DataType | MapType | ListType | NumericType | StructType | Concept
+            DataType | MapType | ArrayType | NumericType | StructType | Concept
         ] = []
         for arg in args:
             new = self.environment.concepts.__getitem__(  # type: ignore
@@ -459,11 +459,11 @@ class ParseToObjects(Transformer):
             fields_map={x.name: x for x in final if isinstance(x, Concept)},
         )
 
-    def list_type(self, args) -> ListType:
+    def list_type(self, args) -> ArrayType:
         content = args[0]
         if isinstance(content, str):
             content = self.environment.concepts[content]
-        return ListType(type=content)
+        return ArrayType(type=content)
 
     def numeric_type(self, args) -> NumericType:
         return NumericType(precision=args[0], scale=args[1])
@@ -480,13 +480,13 @@ class ParseToObjects(Transformer):
     @v_args(meta=True)
     def data_type(
         self, meta: Meta, args
-    ) -> DataType | TraitDataType | ListType | StructType | MapType | NumericType:
+    ) -> DataType | TraitDataType | ArrayType | StructType | MapType | NumericType:
         resolved = args[0]
         traits = args[2:]
-        base: DataType | TraitDataType | ListType | StructType | MapType | NumericType
+        base: DataType | TraitDataType | ArrayType | StructType | MapType | NumericType
         if isinstance(resolved, StructType):
             base = resolved
-        elif isinstance(resolved, ListType):
+        elif isinstance(resolved, ArrayType):
             base = resolved
         elif isinstance(resolved, NumericType):
             base = resolved
@@ -524,8 +524,12 @@ class ParseToObjects(Transformer):
     @v_args(meta=True)
     def column_assignment(self, meta: Meta, args):
         modifiers = []
-        alias = args[0]
-        concept_list = args[1]
+        if len(args) == 2:
+            alias = args[0]
+            concept_list = args[1]
+        else:
+            alias = args[0][-1]
+            concept_list = args[0]
         # recursively collect modifiers
         if len(concept_list) > 1:
             modifiers += concept_list[:-1]
@@ -1737,6 +1741,10 @@ class ParseToObjects(Transformer):
     def sum(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.SUM, meta)
 
+    @v_args(meta=True)
+    def array_agg(self, meta, args):
+        return self.function_factory.create_function(args, FunctionType.ARRAY_AGG, meta)
+
     @v_args(meta=True)
     def avg(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.AVG, meta)
@@ -2002,6 +2010,51 @@ class ParseToObjects(Transformer):
     def fbool(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.BOOL, meta)
 
+    @v_args(meta=True)
+    def farray_sum(self, meta, args):
+        return self.function_factory.create_function(args, FunctionType.ARRAY_SUM, meta)
+
+    @v_args(meta=True)
+    def farray_distinct(self, meta, args):
+        return self.function_factory.create_function(
+            args, FunctionType.ARRAY_DISTINCT, meta
+        )
+
+    @v_args(meta=True)
+    def farray_sort(self, meta, args):
+        if len(args) == 1:
+            # this is a magic value to represent the default behavior
+            args = [args[0], Ordering.ASCENDING]
+        return self.function_factory.create_function(
+            args, FunctionType.ARRAY_SORT, meta
+        )
+
+    @v_args(meta=True)
+    def transform_lambda(self, meta, args):
+        return self.environment.functions[args[0]]
+
+    @v_args(meta=True)
+    def farray_transform(self, meta, args):
+        factory: CustomFunctionFactory = args[1]
+        if not len(factory.function_arguments) == 1:
+            raise InvalidSyntaxException(
+                "Array transform function must have exactly one argument;"
+            )
+        return self.function_factory.create_function(
+            [
+                args[0],
+                factory.function_arguments[0],
+                factory(
+                    ArgBinding(
+                        name=factory.function_arguments[0].name,
+                        datatype=arg_to_datatype(args[0]).value_data_type,
+                    )
+                ),
+            ],
+            FunctionType.ARRAY_TRANSFORM,
+            meta,
+        )
+
 
 def unpack_visit_error(e: VisitError, text: str | None = None):
     """This is required to get exceptions from imports, which would

trilogy/parsing/render.py

@@ -28,8 +28,8 @@ from trilogy.core.models.author import (
     WindowItem,
 )
 from trilogy.core.models.core import (
+    ArrayType,
     DataType,
-    ListType,
     ListWrapper,
     MapWrapper,
     NumericType,
@@ -332,7 +332,7 @@ class Renderer:
         return output
 
     @to_string.register
-    def _(self, arg: ListType):
+    def _(self, arg: ArrayType):
         return f"list<{self.to_string(arg.value_data_type)}>"
 
     @to_string.register

trilogy/parsing/trilogy.lark

@@ -51,7 +51,7 @@
     
     //column_assignment
     //figure out if we want static
-    column_assignment: (raw_column_assignment | IDENTIFIER | QUOTED_IDENTIFIER |  expr  ) ":" concept_assignment
+    column_assignment: ((raw_column_assignment | IDENTIFIER | QUOTED_IDENTIFIER |  expr  ) ":" concept_assignment) | concept_assignment
     
     RAW_ENTRY.1: /raw\s*\(/s
 
@@ -162,7 +162,7 @@
     
     between_comparison: "between"i expr "and"i expr
 
-    subselect_comparison: expr array_comparison (literal | _constant_functions | _string_functions | concept_lit | filter_item | window_item | unnest | fgroup |  expr_tuple | parenthetical )
+    subselect_comparison: expr array_comparison (literal | _constant_functions | _string_functions | _array_functions | concept_lit | filter_item | window_item | unnest | fgroup |  expr_tuple | parenthetical )
     
     expr_tuple: ("("  expr ("," expr)+ ","?  ")") | ("("  expr "," ")")
 
@@ -286,6 +286,19 @@
     fregexp_replace: _REGEXP_REPLACE expr "," expr "," expr   ")"
 
     _string_functions: like | ilike | upper | flower | fsplit | fstrpos | fsubstring | fcontains | fregexp_extract | fregexp_contains | fregexp_replace
+
+    //array_functions
+    _ARRAY_SUM.1: "array_sum("i
+    farray_sum: _ARRAY_SUM  expr  ")"
+    _ARRAY_DISTINCT.1: "array_distinct("i
+    farray_distinct: _ARRAY_DISTINCT expr ")"
+    _ARRAY_SORT.1: "array_sort("i
+    farray_sort: _ARRAY_SORT expr ("," ordering )? ")"
+    _ARRAY_TRANSFORM.1: "array_transform("i
+    transform_lambda: "@" IDENTIFIER
+    farray_transform: _ARRAY_TRANSFORM expr ","  transform_lambda   ")"
+
+    _array_functions: farray_sum | farray_distinct | farray_sort | farray_transform
     
     // special aggregate
     _GROUP.1: "group("i
@@ -309,11 +322,13 @@
     max: _MAX expr ")"
     _MIN.1: "min("i
     min: _MIN expr ")"
+    _ARRAY_AGG.1: "array_agg("i
+    array_agg: _ARRAY_AGG expr ")"
     
     //aggregates can force a grain
     aggregate_all: "*"
     aggregate_over: ("BY"i (aggregate_all | over_list))
-    aggregate_functions: (count | count_distinct | sum | avg | max | min) aggregate_over?
+    aggregate_functions: (count | count_distinct | sum | avg | max | min | array_agg) aggregate_over?
 
     // date functions
     _DATE.1: "date("i
@@ -355,7 +370,7 @@
     
     _date_functions: fdate | fdate_add | fdate_sub | fdate_diff | fdatetime | ftimestamp | fsecond | fminute | fhour | fday | fday_of_week | fweek | fmonth | fquarter | fyear | fdate_part | fdate_trunc
     
-    _static_functions:  _string_functions | _math_functions 
+    _static_functions:  _string_functions | _math_functions | _array_functions
 
     custom_function:  "@" IDENTIFIER  "(" (expr ",")* expr ")"