pytrilogy 0.0.2.22__py3-none-any.whl → 0.0.2.25__py3-none-any.whl

{pytrilogy-0.0.2.22.dist-info → pytrilogy-0.0.2.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.22
+Version: 0.0.2.25
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.2.22.dist-info → pytrilogy-0.0.2.25.dist-info}/RECORD

@@ -1,33 +1,33 @@
-trilogy/__init__.py,sha256=C9onmFcqcrpb9znQMhvQ84guVv4plpSoR0x6qC1SDs4,291
+trilogy/__init__.py,sha256=5XwNYAlRMOuSKIFUPwSVWUdNK1RpSEPCsc_H7W06R7w,291
 trilogy/compiler.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/constants.py,sha256=rHCe0Pe3LuB-VwCr2765QhzkUrTqZKEYPJ7rS0ykxYw,1273
 trilogy/engine.py,sha256=R5ubIxYyrxRExz07aZCUfrTsoXCHQ8DKFTDsobXdWdA,1102
-trilogy/executor.py,sha256=Sv623APcNOKScYTmiiSvDcSy_ZZiKa04Wtav6dO-TFs,11760
+trilogy/executor.py,sha256=b2pUL_Ha1H7pyhqssc2-hTd0OUO2KIcS0x6BLMPckZw,11822
 trilogy/parser.py,sha256=UtuqSiGiCjpMAYgo1bvNq-b7NSzCA5hzbUW31RXaMII,281
 trilogy/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/utility.py,sha256=zM__8r29EsyDW7K9VOHz8yvZC2bXFzh7xKy3cL7GKsk,707
 trilogy/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/core/constants.py,sha256=7XaCpZn5mQmjTobbeBn56SzPWq9eMNDfzfsRU-fP0VE,171
-trilogy/core/enums.py,sha256=W4ojA8xWRNh8frrTEYyJNLSm1rDA_O0uBL447USmF6c,6144
-trilogy/core/env_processor.py,sha256=z8pYgl5XpprA4ZzRvn7CVIG0hbMu04BlNkugKlT6i3o,2333
-trilogy/core/environment_helpers.py,sha256=1miP4is4FEoci01KSAy2VZVYmlmT5TOCOALBekd2muQ,7211
+trilogy/core/enums.py,sha256=y0Z0m-xtcVw1ktkQ5yD3fJYWfOa4ncN_MzCTpREAxy0,6374
+trilogy/core/env_processor.py,sha256=SHVB3nkidIlFc5dz-sofRMKXx66stpLQNuVdQSjC-So,2586
+trilogy/core/environment_helpers.py,sha256=DIsoo-GcXmXVPB1JbNh8Oku25Nyef9mexPIdy2ur_sk,7159
 trilogy/core/ergonomics.py,sha256=ASLDd0RqKWrZiG3XcKHo8nyTjaB_8xfE9t4NZ1UvGpc,1639
 trilogy/core/exceptions.py,sha256=NvV_4qLOgKXbpotgRf7c8BANDEvHxlqRPaA53IThQ2o,561
-trilogy/core/functions.py,sha256=ShFTStIKbgI-3EZIU0xTumI78AC5QlvARwnBM53P2O0,10677
+trilogy/core/functions.py,sha256=IhVpt3n6wEanKHnGu3oA2w6-hKIlxWpEyz7fHN66mpo,10720
 trilogy/core/graph_models.py,sha256=oJUMSpmYhqXlavckHLpR07GJxuQ8dZ1VbB1fB0KaS8c,2036
 trilogy/core/internal.py,sha256=jNGFHKENnbMiMCtAgsnLZYVSENDK4b5ALecXFZpTDzQ,1075
-trilogy/core/models.py,sha256=IzB_IYcNmEWLYdqgG6fbplM3tNQOOxhW9oBkLP4XYs4,153920
+trilogy/core/models.py,sha256=LUaoxk4twHRY9_Qatdbo1GjjCZRo_91Hql7BwKjLbfM,156934
 trilogy/core/optimization.py,sha256=od_60A9F8J8Nj24MHgrxl4vwRwmBFH13TMdoMQvgVKs,7717
-trilogy/core/query_processor.py,sha256=jTYYC0LjrC0ZSFNXSa26QUGsaImwdvWx2yHFFgWQZRU,16607
+trilogy/core/query_processor.py,sha256=sdG0XcHNBS0kuqUPztDZ1i-kpDV5LJLrO55Og2Y8hSg,17140
 trilogy/core/optimizations/__init__.py,sha256=bWQecbeiwiDx9LJnLsa7dkWxdbl2wcnkcTN69JyP8iI,356
 trilogy/core/optimizations/base_optimization.py,sha256=tWWT-xnTbnEU-mNi_isMNbywm8B9WTRsNFwGpeh3rqE,468
 trilogy/core/optimizations/inline_constant.py,sha256=kHNyc2UoaPVdYfVAPAFwnWuk4sJ_IF5faRtVcDOrBtw,1110
 trilogy/core/optimizations/inline_datasource.py,sha256=AATzQ6YrtW_1-aQFjQyTYqEYKBoMFhek7ADfBr4uUdQ,3634
 trilogy/core/optimizations/predicate_pushdown.py,sha256=1l9WnFOSv79e341typG3tTdk0XGl1J_ToQih3LYoGIY,8435
 trilogy/core/processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/core/processing/concept_strategies_v3.py,sha256=J4efhZCSGSo_CXVRObn7p3Lxr5Ry_G01265amsr2iIU,35294
+trilogy/core/processing/concept_strategies_v3.py,sha256=7MT_x6QFHrbSDmjz21pYdQB5ux419ES4QS-8lO16eyw,36091
 trilogy/core/processing/graph_utils.py,sha256=aq-kqk4Iado2HywDxWEejWc-7PGO6Oa-ZQLAM6XWPHw,1199
-trilogy/core/processing/utility.py,sha256=v06sqXpnuYct_MMZXxEaiP0WwkeblWpO81QG1Ns3yGc,19420
+trilogy/core/processing/utility.py,sha256=hzuEsNqP5dq1GBT96lWYX1UkakMl6XItp-nIKFH6wLg,19617
 trilogy/core/processing/node_generators/__init__.py,sha256=-mzYkRsaRNa_dfTckYkKVFSR8h8a3ihEiPJDU_tAmDo,672
 trilogy/core/processing/node_generators/basic_node.py,sha256=WQNgJ1MwrMS_BQ-b3XwGGB6eToDykelAVj_fesJuqe0,2069
 trilogy/core/processing/node_generators/common.py,sha256=LwDgPlhWeuw0t07f3kX9IE5LXBdZhXfh-aY0XGk50ak,8946
@@ -35,7 +35,7 @@ trilogy/core/processing/node_generators/filter_node.py,sha256=Vz9Rb67e1dfZgnliek
 trilogy/core/processing/node_generators/group_node.py,sha256=r54IVEhXW-tzod6uEHIQObrxgQt6aNySk5emWkWyqCU,4938
 trilogy/core/processing/node_generators/group_to_node.py,sha256=R9i_wHipxjXJyfYEwfeTw2EPpuanXVA327XyfcP2tBg,2537
 trilogy/core/processing/node_generators/multiselect_node.py,sha256=_KO9lqzHQoy4VAviO0ttQlmK0tjaqrJj4SJPhmoIYm8,6229
-trilogy/core/processing/node_generators/node_merge_node.py,sha256=ArwE7QoLgSoc2WUR_z9kyWJROxn9qq3KhMcdMZdH3k0,13977
+trilogy/core/processing/node_generators/node_merge_node.py,sha256=dIEv5P2MTViAES2MzqJgccYzM3HldjHrQYFwH00cqyc,14003
 trilogy/core/processing/node_generators/rowset_node.py,sha256=KtdN6t2xM8CJxobc4aQX4W8uX98U6IabeuBF_FtBLR4,4583
 trilogy/core/processing/node_generators/select_merge_node.py,sha256=MKjlXqFBSin6cTnS6n5lEcNBJsMvSefDIXOwYNVbM0s,10371
 trilogy/core/processing/node_generators/select_node.py,sha256=nwXHQF6C-aQUIelx9dyxN2pK3muL-4-6RIqnqQqNwtw,1808
@@ -50,7 +50,7 @@ trilogy/core/processing/nodes/select_node_v2.py,sha256=gS9OQgS2TSEK59BQ9R0i83pTH
 trilogy/core/processing/nodes/unnest_node.py,sha256=mAmFluzm2yeeiQ6NfIB7BU_8atRGh-UJfPf9ROwbhr8,2152
 trilogy/core/processing/nodes/window_node.py,sha256=ro0QfMFi4ZmIn5Q4D0M_vJWfnHH_C0MN7XkVkx8Gygg,1214
 trilogy/dialect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/dialect/base.py,sha256=9hT4adhR4NG98AnrSYnJ9wGN0xJvth53fd-xLuyw3nI,33151
+trilogy/dialect/base.py,sha256=zqPBWv5gsnk4KhyzHdxcpDkVXU7luEVvHepUWRzjUfo,34019
 trilogy/dialect/bigquery.py,sha256=15KJ-cOpBlk9O7FPviPgmg8xIydJeKx7WfmL3SSsPE8,2953
 trilogy/dialect/common.py,sha256=Hr0mxcNxjSvhpBM5Wvb_Q7aklAuYj5aBDrW433py0Zs,4403
 trilogy/dialect/config.py,sha256=tLVEMctaTDhUgARKXUNfHUcIolGaALkQ0RavUvXAY4w,2994
@@ -70,14 +70,14 @@ trilogy/parsing/common.py,sha256=kbqWy30nnVc7ID-sdSDwxYomnxd3guyuIJF3yvlpQwg,996
 trilogy/parsing/config.py,sha256=Z-DaefdKhPDmSXLgg5V4pebhSB0h590vI0_VtHnlukI,111
 trilogy/parsing/exceptions.py,sha256=92E5i2frv5hj9wxObJZsZqj5T6bglvPzvdvco_vW1Zk,38
 trilogy/parsing/helpers.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-trilogy/parsing/parse_engine.py,sha256=X1EFrHrc22dOsWHbk_5VVhViZZnF_SdmYlz_xksxplk,63751
-trilogy/parsing/render.py,sha256=FRC42ZV2Xg3P4pZ7dBMZCgRdFYf_QbN_CCOgnVMON_g,12395
-trilogy/parsing/trilogy.lark,sha256=3ElzcGWx8exOv9zJwxd_Vs_lau7g97QulwdfWldOLkA,11971
+trilogy/parsing/parse_engine.py,sha256=tcBgjfew0kAfSEt1aFo9Pu3yacEBB1KFm7v_Iobz52g,64467
+trilogy/parsing/render.py,sha256=7mEEe5DWVAafaGl__oQE7FPn_4QhcsGT2VVp-nk1Lr8,13078
+trilogy/parsing/trilogy.lark,sha256=ZP9USPgD8-Fq5UzIl4iGpAeGuh2JLGzSoYJhvEGOi2c,12188
 trilogy/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/scripts/trilogy.py,sha256=PHxvv6f2ODv0esyyhWxlARgra8dVhqQhYl0lTrSyVNo,3729
-pytrilogy-0.0.2.22.dist-info/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
-pytrilogy-0.0.2.22.dist-info/METADATA,sha256=KjHfUWqKMsWICew6drUKziQGGQINSUsrXIeggDK4CIw,8403
-pytrilogy-0.0.2.22.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-pytrilogy-0.0.2.22.dist-info/entry_points.txt,sha256=0petKryjvvtEfTlbZC1AuMFumH_WQ9v8A19LvoS6G6c,54
-pytrilogy-0.0.2.22.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
-pytrilogy-0.0.2.22.dist-info/RECORD,,
+pytrilogy-0.0.2.25.dist-info/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
+pytrilogy-0.0.2.25.dist-info/METADATA,sha256=GtN5gVcDusbMKaXTn5O_CLcZAk00h5Xe5df4i5QqZzs,8403
+pytrilogy-0.0.2.25.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+pytrilogy-0.0.2.25.dist-info/entry_points.txt,sha256=0petKryjvvtEfTlbZC1AuMFumH_WQ9v8A19LvoS6G6c,54
+pytrilogy-0.0.2.25.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
+pytrilogy-0.0.2.25.dist-info/RECORD,,

{pytrilogy-0.0.2.22.dist-info → pytrilogy-0.0.2.25.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.executor import Executor
 from trilogy.parser import parse
 from trilogy.constants import CONFIG
 
-__version__ = "0.0.2.22"
+__version__ = "0.0.2.25"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

trilogy/core/enums.py

@@ -292,3 +292,13 @@ class SelectFiltering(Enum):
     NONE = "none"
     EXPLICIT = "explicit"  # the filtering contains only selected values
     IMPLICIT = "implicit"  # the filtering contains unselected values
+
+
+class IOType(Enum):
+    CSV = "csv"
+
+    @classmethod
+    def _missing_(cls, value):
+        if isinstance(value, str) and value.lower() != value:
+            return IOType(value.lower())
+        return super()._missing_(value)

trilogy/core/env_processor.py

@@ -6,17 +6,20 @@ from trilogy.core.graph_models import (
 from trilogy.core.models import Environment, Concept, Datasource
 
 
-def add_concept(concept: Concept, g: ReferenceGraph):
+def add_concept(
+    concept: Concept, g: ReferenceGraph, concept_mapping: dict[str, Concept]
+):
     g.add_node(concept)
     # if we have sources, recursively add them
     node_name = concept_to_node(concept)
     if concept.concept_arguments:
         for source in concept.concept_arguments:
             generic = source.with_default_grain()
-            add_concept(generic, g)
+            add_concept(generic, g, concept_mapping)
 
             g.add_edge(generic, node_name)
-    for _, pseudonym in concept.pseudonyms.items():
+    for ps_address in concept.pseudonyms:
+        pseudonym = concept_mapping[ps_address]
         pseudonym = pseudonym.with_default_grain()
         pseudonym_node = concept_to_node(pseudonym)
         if (pseudonym_node, node_name) in g.edges and (
@@ -28,7 +31,7 @@ def add_concept(concept: Concept, g: ReferenceGraph):
             continue
         g.add_edge(pseudonym_node, node_name, pseudonym=True)
         g.add_edge(node_name, pseudonym_node, pseudonym=True)
-        add_concept(pseudonym, g)
+        add_concept(pseudonym, g, concept_mapping)
 
 
 def generate_adhoc_graph(
@@ -37,10 +40,11 @@ def generate_adhoc_graph(
     restrict_to_listed: bool = False,
 ) -> ReferenceGraph:
     g = ReferenceGraph()
+    concept_mapping = {x.address: x for x in concepts}
 
     # add all parsed concepts
     for concept in concepts:
-        add_concept(concept, g)
+        add_concept(concept, g, concept_mapping)
 
     for dataset in datasources:
         node = datasource_to_node(dataset)
@@ -66,5 +70,7 @@ def generate_graph(
 ) -> ReferenceGraph:
 
     return generate_adhoc_graph(
-        list(environment.concepts.values()), list(environment.datasources.values())
+        list(environment.concepts.values())
+        + list(environment.alias_origin_lookup.values()),
+        list(environment.datasources.values()),
     )

trilogy/core/environment_helpers.py

@@ -191,4 +191,3 @@ def generate_related_concepts(
             environment.add_concept(auto, meta=meta)
             if isinstance(value, Concept):
                 environment.merge_concept(auto, value, modifiers=[])
-                assert value.pseudonyms is not None

trilogy/core/functions.py

@@ -104,6 +104,8 @@ def Unnest(args: list[Concept]) -> Function:
     output = arg_to_datatype(args[0])
     if isinstance(output, (ListType)):
         output = output.value_data_type
+    else:
+        output = DataType.STRING
     return Function(
         operator=FunctionType.UNNEST,
         arguments=args,

trilogy/core/models.py

@@ -65,6 +65,7 @@ from trilogy.core.enums import (
     ShowCategory,
     Granularity,
     SelectFiltering,
+    IOType,
 )
 from trilogy.core.exceptions import UndefinedConceptException, InvalidSyntaxException
 from trilogy.utility import unique
@@ -81,6 +82,9 @@ LT = TypeVar("LT")
 
 
 def is_compatible_datatype(left, right):
+    # for unknown types, we can't make any assumptions
+    if right == DataType.UNKNOWN or left == DataType.UNKNOWN:
+        return True
     if left == right:
         return True
     if {left, right} == {DataType.NUMERIC, DataType.FLOAT}:
@@ -98,6 +102,12 @@ def get_version():
     return __version__
 
 
+def address_with_namespace(address: str, namespace: str) -> str:
+    if address.split(".", 1)[0] == DEFAULT_NAMESPACE:
+        return f"{namespace}.{address.split('.',1)[1]}"
+    return f"{namespace}.{address}"
+
+
 def get_concept_arguments(expr) -> List["Concept"]:
     output = []
     if isinstance(expr, Concept):
@@ -432,7 +442,7 @@ class Concept(Mergeable, Namespaced, SelectContext, BaseModel):
     keys: Optional[Tuple["Concept", ...]] = None
     grain: "Grain" = Field(default=None, validate_default=True)
     modifiers: Optional[List[Modifier]] = Field(default_factory=list)
-    pseudonyms: Dict[str, Concept] = Field(default_factory=dict)
+    pseudonyms: set[str] = Field(default_factory=set)
     _address_cache: str | None = None
 
     def __hash__(self):
@@ -458,7 +468,7 @@ class Concept(Mergeable, Namespaced, SelectContext, BaseModel):
     def with_merge(self, source: Concept, target: Concept, modifiers: List[Modifier]):
         if self.address == source.address:
             new = target.with_grain(self.grain.with_merge(source, target, modifiers))
-            new.pseudonyms[self.address] = self
+            new.pseudonyms.add(self.address)
             return new
         return self.__class__(
             name=self.name,
@@ -612,9 +622,7 @@ class Concept(Mergeable, Namespaced, SelectContext, BaseModel):
                 else None
             ),
             modifiers=self.modifiers,
-            pseudonyms={
-                k: v.with_namespace(namespace) for k, v in self.pseudonyms.items()
-            },
+            pseudonyms={address_with_namespace(v, namespace) for v in self.pseudonyms},
         )
 
     def with_select_context(
@@ -858,7 +866,7 @@ class Grain(Mergeable, BaseModel):
             )
         else:
             v2 = unique(v, "address")
-        final = []
+        final: List[Concept] = []
         for sub in v2:
             if sub.purpose in (Purpose.PROPERTY, Purpose.METRIC) and sub.keys:
                 if all([c in v2 for c in sub.keys]):
@@ -912,6 +920,20 @@ class Grain(Mergeable, BaseModel):
             [c.name == ALL_ROWS_CONCEPT for c in self.components]
         )
 
+    @property
+    def synonym_set(self) -> set[str]:
+        base = []
+        for x in self.components_copy:
+            if isinstance(x.lineage, RowsetItem):
+                base.append(x.lineage.content.address)
+                for c in x.lineage.content.pseudonyms:
+                    base.append(c)
+            else:
+                base.append(x.address)
+                for c in x.pseudonyms:
+                    base.append(c)
+        return set(base)
+
     @cached_property
     def set(self) -> set[str]:
         base = []
@@ -927,7 +949,11 @@ class Grain(Mergeable, BaseModel):
             return self.set == set([c.address for c in other])
         if not isinstance(other, Grain):
             return False
-        return self.set == other.set
+        if self.set == other.set:
+            return True
+        elif self.synonym_set == other.synonym_set:
+            return True
+        return False
 
     def issubset(self, other: "Grain"):
         return self.set.issubset(other.set)
@@ -1778,6 +1804,16 @@ class SelectStatement(Mergeable, Namespaced, SelectTypeMixin, BaseModel):
         )
 
 
+class CopyStatement(BaseModel):
+    target: str
+    target_type: IOType
+    meta: Optional[Metadata] = Field(default_factory=lambda: Metadata())
+    select: SelectStatement
+
+    def refresh_bindings(self, environment: Environment):
+        self.select.refresh_bindings(environment)
+
+
 class AlignItem(Namespaced, BaseModel):
     alias: str
     concepts: List[Concept]
@@ -2248,7 +2284,7 @@ class BaseJoin(BaseModel):
             for ds in [self.left_datasource, self.right_datasource]:
                 synonyms = []
                 for c in ds.output_concepts:
-                    synonyms += list(c.pseudonyms.keys())
+                    synonyms += list(c.pseudonyms)
                 if (
                     concept.address not in [c.address for c in ds.output_concepts]
                     and concept.address not in synonyms
@@ -2823,9 +2859,21 @@ class CTE(BaseModel):
             return self.parent_ctes[0].name
         return self.name
 
+    def get_concept(self, address: str) -> Concept | None:
+        for cte in self.parent_ctes:
+            if address in cte.output_columns:
+                match = [x for x in cte.output_columns if x.address == address].pop()
+                return match
+
+        for array in [self.source.input_concepts, self.source.output_concepts]:
+            match_list = [x for x in array if x.address == address]
+            if match_list:
+                return match_list.pop()
+        return None
+
     def get_alias(self, concept: Concept, source: str | None = None) -> str:
         for cte in self.parent_ctes:
-            if concept.address in [x.address for x in cte.output_columns]:
+            if concept.address in cte.output_columns:
                 if source and source != cte.name:
                     continue
                 return concept.safe_address
@@ -2977,7 +3025,7 @@ class UndefinedConcept(Concept, Mergeable, Namespaced):
     ) -> "UndefinedConcept" | Concept:
         if self.address == source.address:
             new = target.with_grain(self.grain.with_merge(source, target, modifiers))
-            new.pseudonyms[self.address] = self
+            new.pseudonyms.add(self.address)
             return new
         return self.__class__(
             name=self.name,
@@ -3509,6 +3557,7 @@ class Environment(BaseModel):
         self, source: Concept, target: Concept, modifiers: List[Modifier]
     ):
         replacements = {}
+
         # exit early if we've run this
         if source.address in self.alias_origin_lookup:
             if self.concepts[source.address] == target:
@@ -3517,11 +3566,11 @@ class Environment(BaseModel):
         for k, v in self.concepts.items():
 
             if v.address == target.address:
-                v.pseudonyms[source.address] = source
+                v.pseudonyms.add(source.address)
             if v.address == source.address:
                 replacements[k] = target
                 self.canonical_map[k] = target.address
-                v.pseudonyms[target.address] = target
+                v.pseudonyms.add(target.address)
             # we need to update keys and grains of all concepts
             else:
                 replacements[k] = v.with_merge(source, target, modifiers)
@@ -3599,6 +3648,7 @@ class Comparison(
         MagicConstants,
         WindowItem,
         AggregateWrapper,
+        TupleWrapper,
     ]
     operator: ComparisonOperator
 
@@ -4258,13 +4308,23 @@ class ProcessedQuery(BaseModel):
     order_by: Optional[OrderBy] = None
 
 
-class ProcessedQueryMixin(BaseModel):
+class PersistQueryMixin(BaseModel):
     output_to: MaterializedDataset
     datasource: Datasource
     # base:Dataset
 
 
-class ProcessedQueryPersist(ProcessedQuery, ProcessedQueryMixin):
+class ProcessedQueryPersist(ProcessedQuery, PersistQueryMixin):
+    pass
+
+
+class CopyQueryMixin(BaseModel):
+    target: str
+    target_type: IOType
+    # base:Dataset
+
+
+class ProcessedCopyStatement(ProcessedQuery, CopyQueryMixin):
     pass
 
 
@@ -4523,6 +4583,37 @@ class Parenthetical(
         return base
 
 
+class TupleWrapper(Generic[VT], tuple):
+    """Used to distinguish parsed tuple objects from other tuples"""
+
+    def __init__(self, val, type: DataType, **kwargs):
+        super().__init__()
+        self.type = type
+        self.val = val
+
+    def __getnewargs__(self):
+        return (self.val, self.type)
+
+    def __new__(cls, val, type: DataType, **kwargs):
+        return super().__new__(cls, tuple(val))
+        # self.type = type
+
+    @classmethod
+    def __get_pydantic_core_schema__(
+        cls, source_type: Any, handler: Callable[[Any], core_schema.CoreSchema]
+    ) -> core_schema.CoreSchema:
+        args = get_args(source_type)
+        if args:
+            schema = handler(Tuple[args])  # type: ignore
+        else:
+            schema = handler(Tuple)
+        return core_schema.no_info_after_validator_function(cls.validate, schema)
+
+    @classmethod
+    def validate(cls, v):
+        return cls(v, type=arg_to_datatype(v[0]))
+
+
 class PersistStatement(BaseModel):
     datasource: Datasource
     select: SelectStatement
@@ -4589,6 +4680,12 @@ def list_to_wrapper(args):
     return ListWrapper(args, type=types[0])
 
 
+def tuple_to_wrapper(args):
+    types = [arg_to_datatype(arg) for arg in args]
+    assert len(set(types)) == 1
+    return TupleWrapper(args, type=types[0])
+
+
 def dict_to_map_wrapper(arg):
     key_types = [arg_to_datatype(arg) for arg in arg.keys()]
 
@@ -4644,6 +4741,8 @@ def arg_to_datatype(arg) -> DataType | ListType | StructType | MapType | Numeric
         return arg.function.output_datatype
     elif isinstance(arg, Parenthetical):
         return arg_to_datatype(arg.content)
+    elif isinstance(arg, TupleWrapper):
+        return ListType(type=arg.type)
     elif isinstance(arg, WindowItem):
         if arg.type in (WindowType.RANK, WindowType.ROW_NUMBER):
             return DataType.INTEGER

trilogy/core/processing/concept_strategies_v3.py

@@ -455,7 +455,20 @@ def generate_node(
                         if x.address not in [y.address for y in root_targets]
                         and x not in ex_resolve.grain.components
                     ]
-                    expanded.set_output_concepts(root_targets)
+
+                    pseudonyms = [
+                        x
+                        for x in extra
+                        if any(x.address in y.pseudonyms for y in root_targets)
+                    ]
+                    # if we're only connected by a pseudonym, keep those in output
+                    expanded.set_output_concepts(root_targets + pseudonyms)
+                    # but hide them
+                    if pseudonyms:
+                        logger.info(
+                            f"{depth_to_prefix(depth)}{LOGGER_PREFIX} Hiding pseudonyms{[c.address for c in pseudonyms]}"
+                        )
+                        expanded.hide_output_concepts(pseudonyms)
 
                     logger.info(
                         f"{depth_to_prefix(depth)}{LOGGER_PREFIX} Found connections for {[c.address for c in root_targets]} via concept addition; removing extra {[c.address for c in extra]}"
@@ -480,6 +493,7 @@ def validate_concept(
     found_map: dict[str, set[Concept]],
     accept_partial: bool,
     seen: set[str],
+    environment: Environment,
 ):
 
     found_map[str(node)].add(concept)
@@ -500,10 +514,11 @@ def validate_concept(
         if accept_partial:
             found_addresses.add(concept.address)
             found_map[str(node)].add(concept)
-    for _, v in concept.pseudonyms.items():
-        if v.address == concept.address:
+    for v_address in concept.pseudonyms:
+        v = environment.concepts[v_address]
+        if v == concept.address:
             return
-        if v.address in seen:
+        if v in seen:
             return
         validate_concept(
             v,
@@ -515,10 +530,12 @@ def validate_concept(
             found_map,
             accept_partial,
             seen=seen,
+            environment=environment,
         )
 
 
 def validate_stack(
+    environment: Environment,
     stack: List[StrategyNode],
     concepts: List[Concept],
     mandatory_with_filter: List[Concept],
@@ -546,6 +563,7 @@ def validate_stack(
                 found_map,
                 accept_partial,
                 seen,
+                environment,
             )
         for concept in node.virtual_output_concepts:
             if concept.address in non_partial_addresses:
@@ -807,6 +825,7 @@ def _search_concepts(
                 break
         attempted.add(priority_concept.address)
         complete, found, missing, partial, virtual = validate_stack(
+            environment,
             stack,
             mandatory_list,
             completion_mandatory,

trilogy/core/processing/node_generators/node_merge_node.py

@@ -209,9 +209,9 @@ def resolve_weak_components(
         for c in all_concepts
         if "__preql_internal" not in c.address
     ]
-    synonyms: list[Concept] = []
+    synonyms: set[str] = set()
     for x in all_concepts:
-        synonyms += x.pseudonyms.values()
+        synonyms = synonyms.union(x.pseudonyms)
     while break_flag is not True:
         count += 1
         if count > AMBIGUITY_CHECK_LIMIT:
@@ -385,9 +385,9 @@ def gen_merge_node(
     # one concept handling may need to be kicked to alias
     if len(all_concepts) == 1:
         concept = all_concepts[0]
-        for k, v in concept.pseudonyms.items():
+        for v in concept.pseudonyms:
             test = subgraphs_to_merge_node(
-                [[concept, v]],
+                [[concept, environment.alias_origin_lookup[v]]],
                 g=g,
                 all_concepts=[concept],
                 environment=environment,

trilogy/core/processing/utility.py

@@ -28,6 +28,7 @@ from trilogy.core.models import (
     DatePart,
     NumericType,
     ListType,
+    TupleWrapper,
 )
 
 from trilogy.core.enums import Purpose, Granularity, BooleanOperator, Modifier
@@ -161,17 +162,21 @@ def add_node_join_concept(
     concept: Concept,
     datasource: Datasource | QueryDatasource,
     concepts: List[Concept],
+    environment: Environment,
 ):
 
     concepts.append(concept)
 
     graph.add_node(concept.address, type=NodeType.CONCEPT)
     graph.add_edge(datasource.identifier, concept.address)
-    for _, v in concept.pseudonyms.items():
+    for v_address in concept.pseudonyms:
+        v = environment.alias_origin_lookup.get(
+            v_address, environment.concepts[v_address]
+        )
         if v in concepts:
             continue
-        if v.address != concept.address:
-            add_node_join_concept(graph, v, datasource, concepts)
+        if v != concept.address:
+            add_node_join_concept(graph, v, datasource, concepts, environment)
 
 
 def get_node_joins(
@@ -185,7 +190,7 @@ def get_node_joins(
     for datasource in datasources:
         graph.add_node(datasource.identifier, type=NodeType.NODE)
         for concept in datasource.output_concepts:
-            add_node_join_concept(graph, concept, datasource, concepts)
+            add_node_join_concept(graph, concept, datasource, concepts, environment)
 
     # add edges for every constant to every datasource
     for datasource in datasources:
@@ -194,7 +199,6 @@ def get_node_joins(
                 for node in graph.nodes:
                     if graph.nodes[node]["type"] == NodeType.NODE:
                         graph.add_edge(node, concept.address)
-
     joins: defaultdict[str, set] = defaultdict(set)
     identifier_map: dict[str, Datasource | QueryDatasource] = {
         x.identifier: x for x in datasources
@@ -205,7 +209,7 @@ def get_node_joins(
         # if we're looking up a pseudonym, we would have gotten the remapped value
         # so double check we got what we were looking for
         if env_lookup.address == g.address:
-            grain_pseudonyms.update(env_lookup.pseudonyms.keys())
+            grain_pseudonyms.update(env_lookup.pseudonyms)
 
     node_list = sorted(
         [x for x in graph.nodes if graph.nodes[x]["type"] == NodeType.NODE],
@@ -422,6 +426,7 @@ def is_scalar_condition(
         | NumericType
         | DatePart
         | ListWrapper[Any]
+        | TupleWrapper[Any]
     ),
     materialized: set[str] | None = None,
 ) -> bool:

trilogy/core/query_processor.py

@@ -26,6 +26,8 @@ from trilogy.core.models import (
     BaseJoin,
     InstantiatedUnnestJoin,
     Conditional,
+    ProcessedCopyStatement,
+    CopyStatement,
 )
 
 from trilogy.utility import unique
@@ -418,6 +420,24 @@ def process_persist(
     )
 
 
+def process_copy(
+    environment: Environment,
+    statement: CopyStatement,
+    hooks: List[BaseHook] | None = None,
+) -> ProcessedCopyStatement:
+    select = process_query(
+        environment=environment, statement=statement.select, hooks=hooks
+    )
+
+    # build our object to return
+    arg_dict = {k: v for k, v in select.__dict__.items()}
+    return ProcessedCopyStatement(
+        **arg_dict,
+        target=statement.target,
+        target_type=statement.target_type,
+    )
+
+
 def process_query(
     environment: Environment,
     statement: SelectStatement | MultiSelectStatement,

trilogy/dialect/base.py

@@ -35,6 +35,7 @@ from trilogy.core.models import (
     Environment,
     RawColumnExpr,
     ListWrapper,
+    TupleWrapper,
     MapWrapper,
     ShowStatement,
     RowsetItem,
@@ -49,8 +50,10 @@ from trilogy.core.models import (
     StructType,
     MergeStatementV2,
     Datasource,
+    CopyStatement,
+    ProcessedCopyStatement,
 )
-from trilogy.core.query_processor import process_query, process_persist
+from trilogy.core.query_processor import process_query, process_persist, process_copy
 from trilogy.dialect.common import render_join, render_unnest
 from trilogy.hooks.base_hook import BaseHook
 from trilogy.core.enums import UnnestMode
@@ -260,7 +263,11 @@ class BaseDialect:
     ) -> str:
         result = None
         if c.pseudonyms:
-            for candidate in [c] + list(c.pseudonyms.values()):
+            candidates = [y for y in [cte.get_concept(x) for x in c.pseudonyms] if y]
+            logger.debug(
+                f"{LOGGER_PREFIX} [{c.address}] pseudonym candidates are {[x.address for x in candidates]}"
+            )
+            for candidate in [c] + candidates:
                 try:
                     logger.debug(
                         f"{LOGGER_PREFIX} [{c.address}] Attempting rendering w/ candidate {candidate.address}"
@@ -391,6 +398,7 @@ class BaseDialect:
             StructType,
             ListType,
             ListWrapper[Any],
+            TupleWrapper[Any],
             DatePart,
             CaseWhen,
             CaseElse,
@@ -430,7 +438,7 @@ class BaseDialect:
                         f"Missing source CTE for {e.right.address}"
                     )
                 return f"{self.render_expr(e.left, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid)} {e.operator.value} (select {target}.{self.QUOTE_CHARACTER}{e.right.safe_address}{self.QUOTE_CHARACTER} from {target} where {target}.{self.QUOTE_CHARACTER}{e.right.safe_address}{self.QUOTE_CHARACTER} is not null)"
-            elif isinstance(e.right, (ListWrapper, Parenthetical, list)):
+            elif isinstance(e.right, (ListWrapper, TupleWrapper, Parenthetical, list)):
                 return f"{self.render_expr(e.left, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid)} {e.operator.value} {self.render_expr(e.right, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid)}"
 
             elif isinstance(
@@ -511,6 +519,8 @@ class BaseDialect:
             return str(e)
         elif isinstance(e, ListWrapper):
             return f"[{','.join([self.render_expr(x, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid) for x in e])}]"
+        elif isinstance(e, TupleWrapper):
+            return f"({','.join([self.render_expr(x, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid) for x in e])})"
         elif isinstance(e, MapWrapper):
             return f"MAP {{{','.join([f'{self.render_expr(k, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid)}:{self.render_expr(v, cte=cte, cte_map=cte_map, raise_invalid=raise_invalid)}' for k, v in e.items()])}}}"
         elif isinstance(e, list):
@@ -662,6 +672,7 @@ class BaseDialect:
             | ImportStatement
             | RawSQLStatement
             | MergeStatementV2
+            | CopyStatement
         ],
         hooks: Optional[List[BaseHook]] = None,
     ) -> List[
@@ -675,6 +686,7 @@ class BaseDialect:
             | ProcessedQueryPersist
             | ProcessedShowStatement
             | ProcessedRawSQLStatement
+            | ProcessedCopyStatement
         ] = []
         for statement in statements:
             if isinstance(statement, PersistStatement):
@@ -683,6 +695,12 @@ class BaseDialect:
                         hook.process_persist_info(statement)
                 persist = process_persist(environment, statement, hooks=hooks)
                 output.append(persist)
+            elif isinstance(statement, CopyStatement):
+                if hooks:
+                    for hook in hooks:
+                        hook.process_select_info(statement.select)
+                copy = process_copy(environment, statement, hooks=hooks)
+                output.append(copy)
             elif isinstance(statement, SelectStatement):
                 if hooks:
                     for hook in hooks:

trilogy/executor.py

@@ -10,6 +10,7 @@ from trilogy.core.models import (
     ProcessedShowStatement,
     ProcessedQueryPersist,
     ProcessedRawSQLStatement,
+    ProcessedCopyStatement,
     RawSQLStatement,
     MultiSelectStatement,
     SelectStatement,
@@ -18,9 +19,11 @@ from trilogy.core.models import (
     Concept,
     ConceptDeclarationStatement,
     Datasource,
+    CopyStatement,
 )
 from trilogy.dialect.base import BaseDialect
 from trilogy.dialect.enums import Dialects
+from trilogy.core.enums import IOType
 from trilogy.parser import parse_text
 from trilogy.hooks.base_hook import BaseHook
 from pathlib import Path
@@ -94,7 +97,15 @@ class Executor(object):
         self.connection = self.engine.connect()
 
     def execute_statement(self, statement) -> Optional[CursorResult]:
-        if not isinstance(statement, (ProcessedQuery, ProcessedQueryPersist)):
+        if not isinstance(
+            statement,
+            (
+                ProcessedQuery,
+                ProcessedShowStatement,
+                ProcessedQueryPersist,
+                ProcessedCopyStatement,
+            ),
+        ):
             return None
         return self.execute_query(statement)
 
@@ -183,12 +194,33 @@ class Executor(object):
 
     @execute_query.register
     def _(self, query: ProcessedQueryPersist) -> CursorResult:
+
         sql = self.generator.compile_statement(query)
-        # connection = self.engine.connect()
+
         output = self.connection.execute(text(sql))
         self.environment.add_datasource(query.datasource)
         return output
 
+    @execute_query.register
+    def _(self, query: ProcessedCopyStatement) -> CursorResult:
+        sql = self.generator.compile_statement(query)
+        output: CursorResult = self.connection.execute(text(sql))
+        if query.target_type == IOType.CSV:
+            import csv
+
+            with open(query.target, "w", newline="", encoding="utf-8") as f:
+                outcsv = csv.writer(f)
+                outcsv.writerow(output.keys())
+                outcsv.writerows(output)
+        else:
+            raise NotImplementedError(f"Unsupported IOType {query.target_type}")
+        # now return the query we ran through IO
+        # TODO: instead return how many rows were written?
+        return generate_result_set(
+            query.output_columns,
+            [self.generator.compile_statement(query)],
+        )
+
     @singledispatchmethod
     def generate_sql(self, command) -> list[str]:
         raise NotImplementedError(
@@ -251,39 +283,17 @@ class Executor(object):
         | ProcessedQueryPersist
         | ProcessedShowStatement
         | ProcessedRawSQLStatement
+        | ProcessedCopyStatement
     ]:
-        """Process a preql text command"""
-        _, parsed = parse_text(command, self.environment)
-        generatable = [
-            x
-            for x in parsed
-            if isinstance(
-                x,
-                (
-                    SelectStatement,
-                    PersistStatement,
-                    MultiSelectStatement,
-                    ShowStatement,
-                    RawSQLStatement,
-                ),
-            )
-        ]
-        sql = []
-        while generatable:
-            t = generatable.pop(0)
-            x = self.generator.generate_queries(
-                self.environment, [t], hooks=self.hooks
-            )[0]
-            if persist and isinstance(x, ProcessedQueryPersist):
-                self.environment.add_datasource(x.datasource)
-            sql.append(x)
-        return sql
+
+        return list(self.parse_text_generator(command, persist=persist))
 
     def parse_text_generator(self, command: str, persist: bool = False) -> Generator[
         ProcessedQuery
         | ProcessedQueryPersist
         | ProcessedShowStatement
-        | ProcessedRawSQLStatement,
+        | ProcessedRawSQLStatement
+        | ProcessedCopyStatement,
         None,
         None,
     ]:
@@ -300,6 +310,7 @@ class Executor(object):
                     MultiSelectStatement,
                     ShowStatement,
                     RawSQLStatement,
+                    CopyStatement,
                 ),
             )
         ]
@@ -340,13 +351,7 @@ class Executor(object):
                     )
                 )
                 continue
-            compiled_sql = self.generator.compile_statement(statement)
-            logger.debug(compiled_sql)
-
-            output.append(self.connection.execute(text(compiled_sql)))
-            # generalize post-run success hooks
-            if isinstance(statement, ProcessedQueryPersist):
-                self.environment.add_datasource(statement.datasource)
+            output.append(self.execute_query(statement))
         return output
 
     def execute_file(self, file: str | Path) -> List[CursorResult]:

trilogy/parsing/parse_engine.py

@@ -1,7 +1,7 @@
 from os.path import dirname, join
 from typing import List, Optional, Tuple, Union
 from re import IGNORECASE
-from lark import Lark, Transformer, v_args
+from lark import Lark, Transformer, v_args, Tree
 from lark.exceptions import (
     UnexpectedCharacters,
     UnexpectedEOF,
@@ -31,6 +31,7 @@ from trilogy.core.enums import (
     DatePart,
     ShowCategory,
     FunctionClass,
+    IOType,
 )
 from trilogy.core.exceptions import InvalidSyntaxException, UndefinedConceptException
 from trilogy.core.functions import (
@@ -84,6 +85,7 @@ from trilogy.core.models import (
     PersistStatement,
     Query,
     RawSQLStatement,
+    CopyStatement,
     SelectStatement,
     SelectItem,
     WhereClause,
@@ -105,9 +107,11 @@ from trilogy.core.models import (
     ConceptDerivation,
     RowsetDerivationStatement,
     list_to_wrapper,
+    tuple_to_wrapper,
     dict_to_map_wrapper,
     NumericType,
     HavingClause,
+    TupleWrapper,
 )
 from trilogy.parsing.exceptions import ParseError
 from trilogy.parsing.common import (
@@ -748,13 +752,29 @@ class ParseToObjects(Transformer):
     def rawsql_statement(self, meta: Meta, args) -> RawSQLStatement:
         return RawSQLStatement(meta=Metadata(line_number=meta.line), text=args[0])
 
+    def COPY_TYPE(self, args) -> IOType:
+        return IOType(args.value)
+
+    @v_args(meta=True)
+    def copy_statement(self, meta: Meta, args) -> CopyStatement:
+
+        return CopyStatement(
+            target=args[1],
+            target_type=args[0],
+            meta=Metadata(line_number=meta.line),
+            select=args[-1],
+        )
+
     def resolve_import_address(self, address) -> str:
         with open(address, "r", encoding="utf-8") as f:
             text = f.read()
         return text
 
     def import_statement(self, args: list[str]) -> ImportStatement:
-        alias = args[-1]
+        if len(args) == 2:
+            alias = args[-1]
+        else:
+            alias = self.environment.namespace
         path = args[0].split(".")
 
         target = join(self.environment.working_path, *path) + ".preql"
@@ -1064,6 +1084,9 @@ class ParseToObjects(Transformer):
     def array_lit(self, args):
         return list_to_wrapper(args)
 
+    def tuple_lit(self, args):
+        return tuple_to_wrapper(args)
+
     def struct_lit(self, args):
 
         zipped = dict(zip(args[::2], args[1::2]))
@@ -1124,12 +1147,18 @@ class ParseToObjects(Transformer):
 
         while isinstance(right, Parenthetical) and isinstance(
             right.content,
-            (Concept, Function, FilterItem, WindowItem, AggregateWrapper, ListWrapper),
+            (
+                Concept,
+                Function,
+                FilterItem,
+                WindowItem,
+                AggregateWrapper,
+                ListWrapper,
+                TupleWrapper,
+            ),
         ):
             right = right.content
-        if isinstance(
-            right, (Function, FilterItem, WindowItem, AggregateWrapper, ListWrapper)
-        ):
+        if isinstance(right, (Function, FilterItem, WindowItem, AggregateWrapper)):
             right = arbitrary_to_concept(
                 right,
                 namespace=self.environment.namespace,
@@ -1142,7 +1171,7 @@ class ParseToObjects(Transformer):
         )
 
     def expr_tuple(self, args):
-        return Parenthetical(content=args)
+        return TupleWrapper(content=tuple(args))
 
     def parenthetical(self, args):
         return Parenthetical(content=args[0])
@@ -1840,10 +1869,12 @@ def unpack_visit_error(e: VisitError):
         unpack_visit_error(e.orig_exc)
     elif isinstance(e.orig_exc, (UndefinedConceptException, ImportError)):
         raise e.orig_exc
-    elif isinstance(e.orig_exc, SyntaxError):
-        raise InvalidSyntaxException(str(e.orig_exc) + str(e.rule) + str(e.obj))
-    elif isinstance(e.orig_exc, (ValidationError, TypeError)):
-        raise InvalidSyntaxException(str(e.orig_exc) + str(e.rule) + str(e.obj))
+    elif isinstance(e.orig_exc, (SyntaxError, TypeError)):
+        if isinstance(e.obj, Tree):
+            raise InvalidSyntaxException(
+                str(e.orig_exc) + " in " + str(e.rule) + f" Line: {e.obj.meta.line}"
+            )
+        raise InvalidSyntaxException(str(e.orig_exc))
     raise e
 
 

trilogy/parsing/render.py

@@ -32,6 +32,8 @@ from trilogy.core.models import (
     AggregateWrapper,
     PersistStatement,
     ListWrapper,
+    ListType,
+    TupleWrapper,
     RowsetDerivationStatement,
     MultiSelectStatement,
     OrderBy,
@@ -40,6 +42,7 @@ from trilogy.core.models import (
     RawSQLStatement,
     NumericType,
     MergeStatementV2,
+    CopyStatement,
 )
 from trilogy.core.enums import Modifier
 
@@ -180,6 +183,10 @@ class Renderer:
     def _(self, arg: ListWrapper):
         return "[" + ", ".join([self.to_string(x) for x in arg]) + "]"
 
+    @to_string.register
+    def _(self, arg: TupleWrapper):
+        return "(" + ", ".join([self.to_string(x) for x in arg]) + ")"
+
     @to_string.register
     def _(self, arg: DatePart):
         return arg.value
@@ -211,21 +218,30 @@ class Renderer:
             base_description = concept.metadata.description
         else:
             base_description = None
-        if concept.namespace:
+        if concept.namespace and concept.namespace != DEFAULT_NAMESPACE:
             namespace = f"{concept.namespace}."
         else:
             namespace = ""
         if not concept.lineage:
             if concept.purpose == Purpose.PROPERTY and concept.keys:
-                output = f"{concept.purpose.value} {namespace}{concept.keys[0].name}.{concept.name} {concept.datatype.value};"
+                keys = ",".join([self.to_string(key) for key in concept.keys])
+                output = f"{concept.purpose.value} <{keys}>.{namespace}{concept.name} {self.to_string(concept.datatype)};"
             else:
-                output = f"{concept.purpose.value} {namespace}{concept.name} {concept.datatype.value};"
+                output = f"{concept.purpose.value} {namespace}{concept.name} {self.to_string(concept.datatype)};"
         else:
             output = f"{concept.purpose.value} {namespace}{concept.name} <- {self.to_string(concept.lineage)};"
         if base_description:
             output += f" # {base_description}"
         return output
 
+    @to_string.register
+    def _(self, arg: ListType):
+        return f"list<{self.to_string(arg.value_data_type)}>"
+
+    @to_string.register
+    def _(self, arg: DataType):
+        return arg.value
+
     @to_string.register
     def _(self, arg: ConceptDerivation):
         # this is identical rendering;
@@ -271,6 +287,10 @@ class Renderer:
         base += "\n;"
         return base
 
+    @to_string.register
+    def _(self, arg: CopyStatement):
+        return f"COPY INTO {arg.target_type.value.upper()} '{arg.target}' FROM {self.to_string(arg.select)}"
+
     @to_string.register
     def _(self, arg: AlignClause):
         return "\nALIGN\n\t" + ",\n\t".join([self.to_string(c) for c in arg.items])

trilogy/parsing/trilogy.lark

@@ -8,7 +8,7 @@
     | persist_statement
     | rowset_derivation_statement
     | import_statement
-
+    | copy_statement
     | merge_statement_v2
     | rawsql_statement
     
@@ -57,7 +57,7 @@
     
     column_list : (IDENTIFIER "," )* IDENTIFIER ","?
     
-    import_statement: "import" (IDENTIFIER ".") * IDENTIFIER "as" IDENTIFIER
+    import_statement: "import" IDENTIFIER ("."  IDENTIFIER)* ("as" IDENTIFIER)?
 
     // persist_statement
     persist_statement: "persist"i IDENTIFIER "into"i IDENTIFIER "from"i select_statement grain_clause?
@@ -78,6 +78,12 @@
     // raw sql statement
     rawsql_statement: "raw_sql"i "(" MULTILINE_STRING ")"
 
+    // copy statement
+
+    COPY_TYPE: "csv"i
+
+    copy_statement: "copy"i "into"i COPY_TYPE _string_lit "from"i select_statement
+
     // FUNCTION blocks
     function: raw_function
     function_binding_item: IDENTIFIER ":" data_type
@@ -303,6 +309,8 @@
 
     array_lit: "[" (literal ",")* literal ","? "]"()
 
+    tuple_lit: "(" (literal ",")* literal ","? ")"
+
     map_lit: "{" (literal ":" literal ",")* literal ":" literal ","? "}"
 
     _STRUCT.1: "struct("i
@@ -312,7 +320,7 @@
 
     !null_lit.1: "null"i
     
-    literal: null_lit | _string_lit | int_lit | float_lit | bool_lit | array_lit | map_lit | struct_lit
+    literal: null_lit | _string_lit | int_lit | float_lit | bool_lit | array_lit | map_lit | struct_lit | tuple_lit
 
     MODIFIER: "Optional"i | "Partial"i | "Nullable"i