pytrilogy 0.0.2.27__tar.gz → 0.0.2.28__tar.gz

{pytrilogy-0.0.2.27/pytrilogy.egg-info → pytrilogy-0.0.2.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.27
+Version: 0.0.2.28
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28/pytrilogy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.27
+Version: 0.0.2.28
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/pytrilogy.egg-info/SOURCES.txt

@@ -13,6 +13,7 @@ tests/test_declarations.py
 tests/test_derived_concepts.py
 tests/test_discovery_nodes.py
 tests/test_environment.py
+tests/test_executor.py
 tests/test_functions.py
 tests/test_imports.py
 tests/test_metadata.py

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/tests/test_environment.py

@@ -20,7 +20,7 @@ def test_environment_from_path():
 
     env = Environment.from_file(Path(__file__).parent / "test_env.preql")
 
-    assert "id" in env.concepts
+    assert "local.id" in env.concepts
 
 
 def test_environment_merge():

pytrilogy-0.0.2.28/tests/test_executor.py

@@ -0,0 +1,8 @@
+from trilogy import Dialects
+from pathlib import Path
+
+
+def test_file_parsing():
+    target = Path(__file__).parent / "test_env.preql"
+    parsed = Dialects.DUCK_DB.default_executor().parse_file(target)
+    assert len(list(parsed)) == 1

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/tests/test_parsing.py

@@ -178,7 +178,7 @@ select
     )
 
     for name in ["name_alphabetical", "name_alphabetical_2"]:
-        assert name in env.concepts
+        assert f"local.{name}" in env.concepts
         assert env.concepts[name].purpose == Purpose.PROPERTY
         assert env.concepts[name].keys == (env.concepts["id"],)
 
@@ -197,7 +197,6 @@ select
     )
 
     for name in ["join_id"]:
-        assert name in env.concepts
         assert env.concepts[name].purpose == Purpose.PROPERTY
         assert env.concepts[name].keys == (
             env.concepts["id"],
@@ -225,7 +224,6 @@ select
     )
     # assert output_purpose == Purpose.METRIC
     for name in ["test_name_count"]:
-        assert name in env.concepts
         assert env.concepts[name].purpose == Purpose.METRIC
 
 

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/tests/test_undefined_concept.py

@@ -32,6 +32,6 @@ def test_undefined_concept_dict():
     try:
         env["orid"]
     except UndefinedConceptException as e:
-        assert e.suggestions == ["order_id"]
+        assert e.suggestions == ["local.order_id"]
         assert "suggestions" in e.message.lower()
         assert "order_id" in e.message.lower()

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.executor import Executor
 from trilogy.parser import parse
 from trilogy.constants import CONFIG
 
-__version__ = "0.0.2.27"
+__version__ = "0.0.2.28"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/trilogy/core/models.py

@@ -606,6 +606,8 @@ class Concept(Mergeable, Namespaced, SelectContext, BaseModel):
         return self.grain.components_copy if self.grain else []
 
     def with_namespace(self, namespace: str) -> "Concept":
+        if namespace == self.namespace:
+            return self
         return self.__class__(
             name=self.name,
             datatype=self.datatype,
@@ -3253,7 +3255,6 @@ class EnvironmentConceptDict(dict):
                 )
                 self.undefined[key] = undefined
                 return undefined
-
             matches = self._find_similar_concepts(key)
             message = f"Undefined concept: {key}."
             if matches:
@@ -3263,8 +3264,15 @@ class EnvironmentConceptDict(dict):
                 raise UndefinedConceptException(f"line: {line_no}: " + message, matches)
             raise UndefinedConceptException(message, matches)
 
-    def _find_similar_concepts(self, concept_name):
-        matches = difflib.get_close_matches(concept_name, self.keys())
+    def _find_similar_concepts(self, concept_name: str):
+        def strip_local(input: str):
+            if input.startswith(f"{DEFAULT_NAMESPACE}."):
+                return input[len(DEFAULT_NAMESPACE) + 1 :]
+            return input
+
+        matches = difflib.get_close_matches(
+            strip_local(concept_name), [strip_local(x) for x in self.keys()]
+        )
         return matches
 
     def items(self) -> ItemsView[str, Concept]:  # type: ignore
@@ -3325,7 +3333,6 @@ class Environment(BaseModel):
 
     materialized_concepts: List[Concept] = Field(default_factory=list)
     alias_origin_lookup: Dict[str, Concept] = Field(default_factory=dict)
-    canonical_map: Dict[str, str] = Field(default_factory=dict)
     _parse_count: int = 0
 
     @classmethod
@@ -3444,14 +3451,38 @@ class Environment(BaseModel):
                 exists = True
             imp_stm = ImportStatement(alias=alias, path=Path(source.working_path))
 
+        same_namespace = alias == self.namespace
+
         if not exists:
             self.imports[alias].append(imp_stm)
 
-        for _, concept in source.concepts.items():
-            self.add_concept(concept.with_namespace(alias), _ignore_cache=True)
+        for k, concept in source.concepts.items():
+            if same_namespace:
+                new = self.add_concept(concept, _ignore_cache=True)
+            else:
+                new = self.add_concept(
+                    concept.with_namespace(alias), _ignore_cache=True
+                )
+
+                k = address_with_namespace(k, alias)
+            # set this explicitly, to handle aliasing
+            self.concepts[k] = new
 
         for _, datasource in source.datasources.items():
-            self.add_datasource(datasource.with_namespace(alias), _ignore_cache=True)
+            if same_namespace:
+                self.add_datasource(datasource, _ignore_cache=True)
+            else:
+                self.add_datasource(
+                    datasource.with_namespace(alias), _ignore_cache=True
+                )
+        for key, val in source.alias_origin_lookup.items():
+            if same_namespace:
+                self.alias_origin_lookup[key] = val
+            else:
+                self.alias_origin_lookup[address_with_namespace(key, alias)] = (
+                    val.with_namespace(alias)
+                )
+
         self.gen_concept_list_caches()
         return self
 
@@ -3542,8 +3573,6 @@ class Environment(BaseModel):
             existing = self.validate_concept(concept, meta=meta)
             if existing:
                 concept = existing
-        if concept.namespace == DEFAULT_NAMESPACE:
-            self.concepts[concept.name] = concept
         self.concepts[concept.address] = concept
         from trilogy.core.environment_helpers import generate_related_concepts
 
@@ -3631,7 +3660,6 @@ class Environment(BaseModel):
                 v.pseudonyms.add(source.address)
             if v.address == source.address:
                 replacements[k] = target
-                self.canonical_map[k] = target.address
                 v.pseudonyms.add(target.address)
             # we need to update keys and grains of all concepts
             else:

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/trilogy/core/processing/utility.py

@@ -66,9 +66,6 @@ def resolve_join_order_v2(
 ) -> list[JoinOrderOutput]:
     datasources = [x for x in g.nodes if x.startswith("ds~")]
     concepts = [x for x in g.nodes if x.startswith("c~")]
-    # from trilogy.hooks.graph_hook import GraphHook
-
-    # GraphHook().query_graph_built(g)
 
     output: list[JoinOrderOutput] = []
     pivot_map = {
@@ -78,7 +75,7 @@ def resolve_join_order_v2(
     pivots = list(
         sorted(
             [x for x in pivot_map if len(pivot_map[x]) > 1],
-            key=lambda x: len(pivot_map[x]),
+            key=lambda x: (len(pivot_map[x]), len(x), x),
         )
     )
     solo = [x for x in pivot_map if len(pivot_map[x]) == 1]
@@ -95,7 +92,7 @@ def resolve_join_order_v2(
             root = pivots.pop()
 
         # sort so less partials is last and eligible lefts are
-        def score_key(x: str) -> int:
+        def score_key(x: str) -> tuple[int, int, str]:
             base = 1
             # if it's left, higher weight
             if x in eligible_left:
@@ -103,7 +100,7 @@ def resolve_join_order_v2(
             # if it has the concept as a partial, lower weight
             if root in partials.get(x, []):
                 base -= 1
-            return base
+            return (base, len(x), x)
 
         # get remainig un-joined datasets
         to_join = sorted(

{pytrilogy-0.0.2.27 → pytrilogy-0.0.2.28}/trilogy/executor.py

@@ -276,6 +276,20 @@ class Executor(object):
             output.append(compiled_sql)
         return output
 
+    def parse_file(self, file: str | Path, persist: bool = False) -> Generator[
+        ProcessedQuery
+        | ProcessedQueryPersist
+        | ProcessedShowStatement
+        | ProcessedRawSQLStatement
+        | ProcessedCopyStatement,
+        None,
+        None,
+    ]:
+        file = Path(file)
+        with open(file, "r") as f:
+            command = f.read()
+            return self.parse_text_generator(command, persist=persist)
+
     def parse_text(
         self, command: str, persist: bool = False
     ) -> List[
@@ -319,9 +333,11 @@ class Executor(object):
             x = self.generator.generate_queries(
                 self.environment, [t], hooks=self.hooks
             )[0]
+
+            yield x
+
             if persist and isinstance(x, ProcessedQueryPersist):
                 self.environment.add_datasource(x.datasource)
-            yield x
 
     def execute_raw_sql(
         self, command: str, variables: dict | None = None