pytrilogy 0.0.3.67__tar.gz → 0.0.3.68__tar.gz

{pytrilogy-0.0.3.67/pytrilogy.egg-info → pytrilogy-0.0.3.68}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrilogy
-Version: 0.0.3.67
+Version: 0.0.3.68
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68/pytrilogy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrilogy
-Version: 0.0.3.67
+Version: 0.0.3.68
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/tests/test_statements.py

@@ -59,7 +59,7 @@ def test_io_statement():
 
 auto x <- unnest(array);
 
-copy into csv '{target}' from select x -> test;
+copy into csv '{target}' from select x -> test order by test asc;
 """
     exec = Dialects.DUCK_DB.default_executor()
     results = exec.parse_text(text)

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.dialect.enums import Dialects
 from trilogy.executor import Executor
 from trilogy.parser import parse
 
-__version__ = "0.0.3.67"
+__version__ = "0.0.3.68"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/core/processing/discovery_node_factory.py

@@ -307,16 +307,17 @@ class RootNodeHandler:
     def _resolve_root_concepts(
         self, root_targets: List[BuildConcept]
     ) -> Optional[StrategyNode]:
-        synonym_node = self._try_synonym_resolution(root_targets)
-        if synonym_node:
-            logger.info(
-                f"{depth_to_prefix(self.ctx.depth)}{LOGGER_PREFIX} "
-                f"resolved root concepts through synonyms"
-            )
-            return synonym_node
         expanded_node = self._try_merge_expansion(root_targets)
         if expanded_node:
             return expanded_node
+        if self.ctx.accept_partial:
+            synonym_node = self._try_synonym_resolution(root_targets)
+            if synonym_node:
+                logger.info(
+                    f"{depth_to_prefix(self.ctx.depth)}{LOGGER_PREFIX} "
+                    f"resolved root concepts through synonyms"
+                )
+                return synonym_node
 
         return None
 

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/core/processing/node_generators/select_merge_node.py

@@ -493,7 +493,7 @@ def create_select_node(
     else:
 
         candidate = bcandidate
-    assert candidate.resolve().output_concepts == all_concepts
+
     return candidate
 
 
@@ -536,7 +536,12 @@ def gen_select_merge_node(
             force_group=False,
             conditions=conditions.conditional if conditions else None,
         )
-    for attempt in [False, True]:
+    attempts = [
+        False,
+    ]
+    if accept_partial:
+        attempts.append(True)
+    for attempt in attempts:
         pruned_concept_graph = create_pruned_concept_graph(
             g,
             non_constant,

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/core/processing/node_generators/synonym_node.py

@@ -3,8 +3,8 @@ from collections import defaultdict
 from typing import List
 
 from trilogy.constants import logger
-from trilogy.core.enums import FunctionType
-from trilogy.core.models.build import BuildConcept, BuildFunction, BuildWhereClause
+from trilogy.core.enums import Derivation
+from trilogy.core.models.build import BuildConcept, BuildWhereClause
 from trilogy.core.models.build_environment import BuildEnvironment
 from trilogy.core.processing.nodes import History, StrategyNode
 from trilogy.core.processing.utility import padding
@@ -12,13 +12,6 @@ from trilogy.core.processing.utility import padding
 LOGGER_PREFIX = "[GEN_SYNONYM_NODE]"
 
 
-def is_union(c: BuildConcept):
-    return (
-        isinstance(c.lineage, BuildFunction)
-        and c.lineage.operator == FunctionType.UNION
-    )
-
-
 def gen_synonym_node(
     all_concepts: List[BuildConcept],
     environment: BuildEnvironment,
@@ -41,7 +34,6 @@ def gen_synonym_node(
                 synonyms[x.address].append(parent)
                 has_synonyms = True
         for y in x.pseudonyms:
-
             if y in environment.alias_origin_lookup:
                 synonyms[x.address].append(environment.alias_origin_lookup[y])
                 has_synonyms = True
@@ -59,11 +51,14 @@ def gen_synonym_node(
         itertools.product(*(synonyms[obj] for obj in sorted_keys))
     )
 
-    def similarity_sort_key(combo):
+    def similarity_sort_key(combo: tuple[BuildConcept, ...]):
         addresses = [x.address for x in combo]
 
         # Calculate similarity score - count how many pairs share prefixes
         similarity_score = 0
+        roots = sum(
+            [1 for x in combo if x.derivation in (Derivation.ROOT, Derivation.CONSTANT)]
+        )
         for i in range(len(addresses)):
             for j in range(i + 1, len(addresses)):
                 # Find common prefix length
@@ -77,8 +72,8 @@ def gen_synonym_node(
                         break
                 similarity_score += common_prefix_len
 
-        # Sort by similarity (descending), then by addresses (ascending) for ties
-        return (-similarity_score, addresses)
+        # Sort by roots, similarity (descending), then by addresses (ascending) for ties
+        return (-roots, -similarity_score, addresses)
 
     combinations_list.sort(key=similarity_sort_key)
     for combo in combinations_list:

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/core/processing/utility.py

@@ -322,8 +322,10 @@ def resolve_instantiated_concept(
     for k in concept.pseudonyms:
         if k in datasource.output_concepts:
             return [x for x in datasource.output_concepts if x.address == k].pop()
+        if any(k in x.pseudonyms for x in datasource.output_concepts):
+            return [x for x in datasource.output_concepts if k in x.pseudonyms].pop()
     raise SyntaxError(
-        f"Could not find {concept.address} in {datasource.identifier} output {[c.address for c in datasource.output_concepts]}"
+        f"Could not find {concept.address} in {datasource.identifier} output {[c.address for c in datasource.output_concepts]}, acceptable synonyms {concept.pseudonyms}"
     )
 
 
@@ -601,19 +603,28 @@ def find_nullable_concepts(
 
 
 def sort_select_output_processed(
-    cte: CTE | UnionCTE, query: ProcessedQuery
+    cte: CTE | UnionCTE, query: SelectStatement | MultiSelectStatement | ProcessedQuery
 ) -> CTE | UnionCTE:
-    output_addresses = [c.address for c in query.output_columns]
+    if isinstance(query, ProcessedQuery):
+        targets = query.output_columns
+        hidden = query.hidden_columns
+    else:
+        targets = query.output_components
+        hidden = query.hidden_components
+
+    output_addresses = [c.address for c in targets]
 
     mapping = {x.address: x for x in cte.output_columns}
 
     new_output: list[BuildConcept] = []
-    for x in query.output_columns:
+    for x in targets:
         if x.address in mapping:
             new_output.append(mapping[x.address])
         for oc in cte.output_columns:
             if x.address in oc.pseudonyms:
                 # create a wrapper BuildConcept to render the pseudonym under the original name
+                if any(x.address == y for y in mapping.keys()):
+                    continue
                 new_output.append(
                     BuildConcept(
                         name=x.name,
@@ -636,10 +647,7 @@ def sort_select_output_processed(
         [
             c.address
             for c in cte.output_columns
-            if (
-                c.address not in query.output_columns
-                or c.address in query.hidden_columns
-            )
+            if (c.address not in targets or c.address in hidden)
         ]
     )
     cte.output_columns = new_output
@@ -650,38 +658,4 @@ def sort_select_output(
     cte: CTE | UnionCTE, query: SelectStatement | MultiSelectStatement | ProcessedQuery
 ) -> CTE | UnionCTE:
 
-    if isinstance(query, ProcessedQuery):
-        return sort_select_output_processed(cte, query)
-
-    mapping = {x.address: x for x in cte.output_columns}
-
-    new_output: list[BuildConcept] = []
-    for x in query.output_components:
-        if x.address in mapping:
-            new_output.append(mapping[x.address])
-        else:
-            for oc in cte.output_columns:
-                if x.address in oc.pseudonyms:
-                    # create a wrapper BuildConcept to render the pseudonym under the original name
-                    new_output.append(
-                        BuildConcept(
-                            name=x.name,
-                            namespace=x.namespace,
-                            pseudonyms={oc.address},
-                            datatype=oc.datatype,
-                            purpose=oc.purpose,
-                            grain=oc.grain,
-                            build_is_aggregate=oc.build_is_aggregate,
-                        )
-                    )
-                    break
-    cte.output_columns = new_output
-    cte.hidden_concepts = set(
-        [
-            c.address
-            for c in query.output_components
-            if c.address in query.hidden_components
-        ]
-    )
-
-    return cte
+    return sort_select_output_processed(cte, query)

{pytrilogy-0.0.3.67 → pytrilogy-0.0.3.68}/trilogy/dialect/base.py

@@ -762,6 +762,7 @@ class BaseDialect:
             ] + [
                 f"{self.QUOTE_CHARACTER}{c.safe_address}{self.QUOTE_CHARACTER}"
                 for c in cte.join_derived_concepts
+                if c.address not in cte.hidden_concepts
             ]
         elif self.UNNEST_MODE in (UnnestMode.CROSS_JOIN_UNNEST, UnnestMode.PRESTO):
             select_columns = [
@@ -772,6 +773,7 @@ class BaseDialect:
             ] + [
                 f"{UNNEST_NAME} as {self.QUOTE_CHARACTER}{c.safe_address}{self.QUOTE_CHARACTER}"
                 for c in cte.join_derived_concepts
+                if c.address not in cte.hidden_concepts
             ]
         else:
             # otherwse, assume we are unnesting directly in the select