pytrilogy 0.0.2.20__py3-none-any.whl → 0.0.2.22__py3-none-any.whl

{pytrilogy-0.0.2.20.dist-info → pytrilogy-0.0.2.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.20
+Version: 0.0.2.22
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 
@@ -145,7 +145,7 @@ Run the following from the directory the file is in.
 trilogy run hello.trilogy duckdb
 ```
 
-![UI Preview](./hello_world.png)
+![UI Preview](hello-world.png)
 
 ## Backends
 
@@ -158,9 +158,9 @@ The current Trilogy implementation supports these backends:
 
 ## Basic Example - Python
 
-Trilogy can be run directly in python.
+Trilogy can be run directly in python through the core SDK. Trilogy code can be defined and parsed inline or parsed out of files.
 
-A bigquery example, similar to bigquery [the quickstart](https://cloud.google.com/bigquery/docs/quickstarts/query-public-dataset-console)
+A bigquery example, similar to bigquery [the quickstart](https://cloud.google.com/bigquery/docs/quickstarts/query-public-dataset-console).
 
 ```python
 
@@ -224,7 +224,7 @@ and second the dialect to run.
 To pass arguments to a backend, append additional --<option> flags after specifying the dialect.
 
 Example:
-`trilogy run key in int; datasource test_source ( i:in) grain(in) address test; select in;" duckdb --path <path/to/duckdb>`
+`trilogy run "key x int; datasource test_source ( i:x) grain(in) address test; select x;" duckdb --path <path/to/database>`
 
 ### Bigquery Args
 N/A, only supports default auth. In python you can pass in a custom client.
@@ -267,7 +267,7 @@ Clone repository and install requirements.txt and requirements-test.txt.
 Please open an issue first to discuss what you would like to change, and then create a PR against that issue.
 
 ## Similar in space
-Trilogy combines two aspects; a semantic layer and a query language. We've covered examples of both below:
+Trilogy combines two aspects; a semantic layer and a query language. Examples of both are linked below:
 
 Python "semantic layers" are tools for defining data access to a warehouse in a more abstract way.
 
@@ -284,20 +284,26 @@ but all are worth checking out. Please open PRs/comment for anything missed!
 
 #### IMPORT
 
-`import <path> as <alias>;`
+`import [path] as [alias];`
 
 #### CONCEPT
 
-Types: `string | int | float | bool | date | datetime | time | numeric(scale, precision) | timestamp | interval`;
+Types: `string | int | float | bool | date | datetime | time | numeric(scale, precision) | timestamp | interval | list<[type]> | map<[type], [type]> | struct<name:[type], name:[type]>`;
 
 Key:
-`key <name> <type>;`
+`key [name] [type];`
 
 Property:
-`property <key>.<name> <type>;`
+`property [key>].[name] [type];`
+`property x.y int;`
+or 
+`property <[key](,[key])?>.<name> [type];`
+`property <x,y>.z int;`
+
 
 Transformation:
-`auto <name> <- <expression>;`
+`auto [name] <- [expression];`
+`auto x <- y + 1;`
 
 #### DATASOURCE
 ```sql

{pytrilogy-0.0.2.20.dist-info → pytrilogy-0.0.2.22.dist-info}/RECORD

@@ -1,31 +1,31 @@
-trilogy/__init__.py,sha256=jkM9h2qEkIh-R8xZca7g_Qzl5cC8w48aOmkcJUjjTAs,291
+trilogy/__init__.py,sha256=C9onmFcqcrpb9znQMhvQ84guVv4plpSoR0x6qC1SDs4,291
 trilogy/compiler.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/constants.py,sha256=pZkOneh_65f9Ua6NICu1bHAFAbmQxmiXRXS7tsmCWbQ,1235
+trilogy/constants.py,sha256=rHCe0Pe3LuB-VwCr2765QhzkUrTqZKEYPJ7rS0ykxYw,1273
 trilogy/engine.py,sha256=R5ubIxYyrxRExz07aZCUfrTsoXCHQ8DKFTDsobXdWdA,1102
-trilogy/executor.py,sha256=An6YLpHQOt96E7ozRQhwZels2hMsDbh0WV767kKCGU0,11294
+trilogy/executor.py,sha256=Sv623APcNOKScYTmiiSvDcSy_ZZiKa04Wtav6dO-TFs,11760
 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=LL8NLvxb3HRnAjvofyLRXqQJijLcYiXAQYQzGarVD-g,128
-trilogy/core/enums.py,sha256=A9VC0lbP5eo9sndm2TzA-nNJRRmvbjE918ZiEXtcQ_c,6043
-trilogy/core/env_processor.py,sha256=l7TAB0LalxjTYJdTlcmFIkLXuyxa9lrenWLeZfa9qw0,2276
+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/ergonomics.py,sha256=w3gwXdgrxNHCuaRdyKg73t6F36tj-wIjQf47WZkHmJk,1465
+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/graph_models.py,sha256=oJUMSpmYhqXlavckHLpR07GJxuQ8dZ1VbB1fB0KaS8c,2036
 trilogy/core/internal.py,sha256=jNGFHKENnbMiMCtAgsnLZYVSENDK4b5ALecXFZpTDzQ,1075
-trilogy/core/models.py,sha256=O1_HxOQ0muMbjWVcOH1mmEFG3IM7taaPgfgCnZv21W8,150676
+trilogy/core/models.py,sha256=IzB_IYcNmEWLYdqgG6fbplM3tNQOOxhW9oBkLP4XYs4,153920
 trilogy/core/optimization.py,sha256=od_60A9F8J8Nj24MHgrxl4vwRwmBFH13TMdoMQvgVKs,7717
-trilogy/core/query_processor.py,sha256=kXuBsIaRHu1s7zB_rAnT_gRe4-VgRSrPE1TnVJXFLtc,16447
+trilogy/core/query_processor.py,sha256=jTYYC0LjrC0ZSFNXSa26QUGsaImwdvWx2yHFFgWQZRU,16607
 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=DO9gybVLku8GEkO3uNPaCeqhalnufsjYYbvDs-gkwNc,35295
+trilogy/core/processing/concept_strategies_v3.py,sha256=J4efhZCSGSo_CXVRObn7p3Lxr5Ry_G01265amsr2iIU,35294
 trilogy/core/processing/graph_utils.py,sha256=aq-kqk4Iado2HywDxWEejWc-7PGO6Oa-ZQLAM6XWPHw,1199
 trilogy/core/processing/utility.py,sha256=v06sqXpnuYct_MMZXxEaiP0WwkeblWpO81QG1Ns3yGc,19420
 trilogy/core/processing/node_generators/__init__.py,sha256=-mzYkRsaRNa_dfTckYkKVFSR8h8a3ihEiPJDU_tAmDo,672
@@ -35,10 +35,10 @@ 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=4aoSkynWYcKAxeN4fU5jnCdxausa5rNgFokoVhPXI80,13511
-trilogy/core/processing/node_generators/rowset_node.py,sha256=gU_ybfYXO9tZqHjUSABIioVpb8AWtITpegj3IGSf2GI,4587
+trilogy/core/processing/node_generators/node_merge_node.py,sha256=ArwE7QoLgSoc2WUR_z9kyWJROxn9qq3KhMcdMZdH3k0,13977
+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=vUg3gXHGvagdbniIAE7DdqJcQ0V1VAfHtTrw3edYPso,1734
+trilogy/core/processing/node_generators/select_node.py,sha256=nwXHQF6C-aQUIelx9dyxN2pK3muL-4-6RIqnqQqNwtw,1808
 trilogy/core/processing/node_generators/unnest_node.py,sha256=cZ26CN338CBnd6asML1OBUtNcDzmNlFpY0Vnade4yrc,2256
 trilogy/core/processing/node_generators/window_node.py,sha256=jy3FF8uN0VA7yyrBeR40B9CAqR_5qBP4PiS6Gr-f-7w,2590
 trilogy/core/processing/nodes/__init__.py,sha256=qS5EJDRwwIrCEfS7ibCA2ESE0RPzsAIii1UWd_wNsHA,4760
@@ -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=QDeKbc7vgqfbR649-87cwsOz8G3VY63V19zH6I-WITo,33103
+trilogy/dialect/base.py,sha256=9hT4adhR4NG98AnrSYnJ9wGN0xJvth53fd-xLuyw3nI,33151
 trilogy/dialect/bigquery.py,sha256=15KJ-cOpBlk9O7FPviPgmg8xIydJeKx7WfmL3SSsPE8,2953
 trilogy/dialect/common.py,sha256=Hr0mxcNxjSvhpBM5Wvb_Q7aklAuYj5aBDrW433py0Zs,4403
 trilogy/dialect/config.py,sha256=tLVEMctaTDhUgARKXUNfHUcIolGaALkQ0RavUvXAY4w,2994
@@ -66,18 +66,18 @@ trilogy/hooks/graph_hook.py,sha256=onHvMQPwj_KOS3HOTpRFiy7QLLKAiycq2MzJ_Q0Oh5Y,2
 trilogy/hooks/query_debugger.py,sha256=Pe-Kw1JGngeLqQOMQb0E3-24jXEavqnPCQ-KOfTfjP8,4357
 trilogy/metadata/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/parsing/common.py,sha256=-4LM71ocidA8DI2RngqFEOmhzBrIt8VdBTO4x2BpD8E,9502
+trilogy/parsing/common.py,sha256=kbqWy30nnVc7ID-sdSDwxYomnxd3guyuIJF3yvlpQwg,9960
 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=_orHmZTdExJYkuNRmAaazdXpZcvtPMLKIBI9vBAgq6w,64871
-trilogy/parsing/render.py,sha256=8yxerPAi4AhlhPBlAfbYbOM3F9rz6HzpWVEWPtK2VEg,12321
-trilogy/parsing/trilogy.lark,sha256=0JAvQBACFNL-X61I0tB_0QPZgsguZgerfHBv903oKh0,11623
+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/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/scripts/trilogy.py,sha256=PHxvv6f2ODv0esyyhWxlARgra8dVhqQhYl0lTrSyVNo,3729
-pytrilogy-0.0.2.20.dist-info/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
-pytrilogy-0.0.2.20.dist-info/METADATA,sha256=pmZ2uTW1EBclZPel8B698DU3sdTmutM5vnu25tNTHfM,8132
-pytrilogy-0.0.2.20.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-pytrilogy-0.0.2.20.dist-info/entry_points.txt,sha256=0petKryjvvtEfTlbZC1AuMFumH_WQ9v8A19LvoS6G6c,54
-pytrilogy-0.0.2.20.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
-pytrilogy-0.0.2.20.dist-info/RECORD,,
+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,,

trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.executor import Executor
 from trilogy.parser import parse
 from trilogy.constants import CONFIG
 
-__version__ = "0.0.2.20"
+__version__ = "0.0.2.22"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

trilogy/constants.py

@@ -44,6 +44,7 @@ class Comments:
 class Config:
     strict_mode: bool = True
     human_identifiers: bool = True
+    randomize_cte_names: bool = False
     validate_missing: bool = True
     comments: Comments = field(default_factory=Comments)
     optimizations: Optimizations = field(default_factory=Optimizations)

trilogy/core/constants.py

@@ -1,3 +1,4 @@
 CONSTANT_DATASET: str = "preql_internal_constant_dataset"
 ALL_ROWS_CONCEPT = "all_rows"
 INTERNAL_NAMESPACE = "__preql_internal"
+PERSISTED_CONCEPT_PREFIX = "__pre_persist"

trilogy/core/enums.py

@@ -12,6 +12,8 @@ class UnnestMode(Enum):
 
 class ConceptSource(Enum):
     MANUAL = "manual"
+    CTE = "cte"
+    PERSIST_STATEMENT = "persist_statement"
     AUTO_DERIVED = "auto_derived"
 
 
@@ -205,6 +207,8 @@ class FunctionClass(Enum):
         FunctionType.CURRENT_DATETIME,
     ]
 
+    ONE_TO_MANY = [FunctionType.UNNEST]
+
 
 class Boolean(Enum):
     TRUE = "true"

trilogy/core/env_processor.py

@@ -10,9 +10,11 @@ def add_concept(concept: Concept, g: ReferenceGraph):
     g.add_node(concept)
     # if we have sources, recursively add them
     node_name = concept_to_node(concept)
-    if concept.sources:
-        for source in concept.sources:
+    if concept.concept_arguments:
+        for source in concept.concept_arguments:
             generic = source.with_default_grain()
+            add_concept(generic, g)
+
             g.add_edge(generic, node_name)
     for _, pseudonym in concept.pseudonyms.items():
         pseudonym = pseudonym.with_default_grain()

trilogy/core/ergonomics.py

@@ -1,3 +1,5 @@
+from trilogy.constants import CONFIG
+
 # source: https://github.com/aaronbassett/Pass-phrase
 CTE_NAMES = """quizzical
 highfalutin
@@ -103,8 +105,6 @@ mandrill
 marlin
 monitor
 ocelot
-osprey
-owl
 petrel
 python
 ray
@@ -132,7 +132,6 @@ cuckoo
 darter
 dove
 duck
-eagle
 falcon
 finch
 flamingo
@@ -184,4 +183,12 @@ warbler""".split(
     "\n"
 )
 
-CTE_NAMES = list(set(CTE_NAMES))
+
+def generate_cte_names():
+    if CONFIG.randomize_cte_names:
+        from random import shuffle
+
+        new = [*CTE_NAMES]
+        shuffle(new)
+        return new
+    return CTE_NAMES

trilogy/core/models.py

@@ -44,6 +44,7 @@ from trilogy.core.constants import (
     ALL_ROWS_CONCEPT,
     INTERNAL_NAMESPACE,
     CONSTANT_DATASET,
+    PERSISTED_CONCEPT_PREFIX,
 )
 from trilogy.core.enums import (
     InfiniteFunctionArgs,
@@ -912,10 +913,10 @@ class Grain(Mergeable, BaseModel):
         )
 
     @cached_property
-    def set(self):
+    def set(self) -> set[str]:
         base = []
         for x in self.components_copy:
-            if x.derivation == PurposeLineage.ROWSET:
+            if isinstance(x.lineage, RowsetItem):
                 base.append(x.lineage.content.address)
             else:
                 base.append(x.address)
@@ -3131,6 +3132,12 @@ class EnvironmentConceptDict(dict):
     def values(self) -> ValuesView[Concept]:  # type: ignore
         return super().values()
 
+    def get(self, key: str, default: Concept | None = None) -> Concept | None:  # type: ignore
+        try:
+            return self.__getitem__(key)
+        except UndefinedConceptException:
+            return default
+
     def __getitem__(
         self, key, line_no: int | None = None
     ) -> Concept | UndefinedConcept:
@@ -3257,24 +3264,62 @@ class Environment(BaseModel):
         for datasource in self.datasources.values():
             for concept in datasource.output_concepts:
                 concrete_addresses.add(concept.address)
-        self.materialized_concepts = [
-            c for c in self.concepts.values() if c.address in concrete_addresses
-        ] + [
-            c
-            for c in self.alias_origin_lookup.values()
-            if c.address in concrete_addresses
-        ]
+        self.materialized_concepts = unique(
+            [c for c in self.concepts.values() if c.address in concrete_addresses]
+            + [
+                c
+                for c in self.alias_origin_lookup.values()
+                if c.address in concrete_addresses
+            ],
+            "address",
+        )
 
-    def validate_concept(self, lookup: str, meta: Meta | None = None):
+    def validate_concept(self, new_concept: Concept, meta: Meta | None = None):
+        lookup = new_concept.address
         existing: Concept = self.concepts.get(lookup)  # type: ignore
         if not existing:
             return
-        elif existing and self.environment_config.allow_duplicate_declaration:
+
+        def handle_persist():
+            deriv_lookup = (
+                f"{existing.namespace}.{PERSISTED_CONCEPT_PREFIX}_{existing.name}"
+            )
+
+            alt_source = self.alias_origin_lookup.get(deriv_lookup)
+            if not alt_source:
+                return None
+            # if the new concept binding has no lineage
+            # nothing to cause us to think a persist binding
+            # needs to be invalidated
+            if not new_concept.lineage:
+                return existing
+            if str(alt_source.lineage) == str(new_concept.lineage):
+                logger.info(
+                    f"Persisted concept {existing.address} matched redeclaration, keeping current persistence binding."
+                )
+                return existing
+            logger.warning(
+                f"Persisted concept {existing.address} lineage {str(alt_source.lineage)} did not match redeclaration {str(new_concept.lineage)}, overwriting and invalidating persist binding."
+            )
+            for k, datasource in self.datasources.items():
+                if existing.address in datasource.output_concepts:
+                    datasource.columns = [
+                        x
+                        for x in datasource.columns
+                        if x.concept.address != existing.address
+                    ]
+            return None
+
+        if existing and self.environment_config.allow_duplicate_declaration:
+            if existing.metadata.concept_source == ConceptSource.PERSIST_STATEMENT:
+                return handle_persist()
             return
         elif existing.metadata:
+            if existing.metadata.concept_source == ConceptSource.PERSIST_STATEMENT:
+                return handle_persist()
             # if the existing concept is auto derived, we can overwrite it
             if existing.metadata.concept_source == ConceptSource.AUTO_DERIVED:
-                return
+                return None
         elif meta and existing.metadata:
             raise ValueError(
                 f"Assignment to concept '{lookup}' on line {meta.line} is a duplicate"
@@ -3390,11 +3435,12 @@ class Environment(BaseModel):
         _ignore_cache: bool = False,
     ):
         if not force:
-            self.validate_concept(concept.address, meta=meta)
+            existing = self.validate_concept(concept, meta=meta)
+            if existing:
+                concept = existing
         if concept.namespace == DEFAULT_NAMESPACE:
             self.concepts[concept.name] = concept
-        else:
-            self.concepts[concept.address] = concept
+        self.concepts[concept.address] = concept
         from trilogy.core.environment_helpers import generate_related_concepts
 
         generate_related_concepts(concept, self, meta=meta, add_derived=add_derived)
@@ -3408,21 +3454,42 @@ class Environment(BaseModel):
         meta: Meta | None = None,
         _ignore_cache: bool = False,
     ):
-
         self.datasources[datasource.env_label] = datasource
-        for column in datasource.columns:
-            current_concept = column.concept
+        for current_concept in datasource.output_concepts:
             current_derivation = current_concept.derivation
+            # TODO: refine this section;
+            # too hacky for maintainability
             if current_derivation not in (PurposeLineage.ROOT, PurposeLineage.CONSTANT):
-                new_concept = current_concept.model_copy(deep=True)
-                new_concept.set_name("_pre_persist_" + current_concept.name)
-                # remove the associated lineage
-                current_concept.lineage = None
-                self.add_concept(new_concept, meta=meta, force=True, _ignore_cache=True)
-                self.add_concept(
-                    current_concept, meta=meta, force=True, _ignore_cache=True
-                )
-                self.merge_concept(new_concept, current_concept, [])
+                persisted = f"{PERSISTED_CONCEPT_PREFIX}_" + current_concept.name
+                # override the current concept source to reflect that it's now coming from a datasource
+                if (
+                    current_concept.metadata.concept_source
+                    != ConceptSource.PERSIST_STATEMENT
+                ):
+                    new_concept = current_concept.model_copy(deep=True)
+                    new_concept.set_name(persisted)
+                    self.add_concept(
+                        new_concept, meta=meta, force=True, _ignore_cache=True
+                    )
+                    current_concept.metadata.concept_source = (
+                        ConceptSource.PERSIST_STATEMENT
+                    )
+                    # remove the associated lineage
+                    # to make this a root for discovery purposes
+                    # as it now "exists" in a table
+                    current_concept.lineage = None
+                    current_concept = current_concept.with_default_grain()
+                    self.add_concept(
+                        current_concept, meta=meta, force=True, _ignore_cache=True
+                    )
+                    self.merge_concept(new_concept, current_concept, [])
+                else:
+                    self.add_concept(current_concept, meta=meta, _ignore_cache=True)
+
+            # else:
+            #     self.add_concept(
+            #         current_concept, meta=meta, _ignore_cache=True
+            #     )
         if not _ignore_cache:
             self.gen_concept_list_caches()
         return datasource
@@ -4230,6 +4297,9 @@ class RowsetDerivationStatement(Namespaced, BaseModel):
     def __repr__(self):
         return f"RowsetDerivation<{str(self.select)}>"
 
+    def __str__(self):
+        return self.__repr__()
+
     @property
     def derived_concepts(self) -> List[Concept]:
         output: list[Concept] = []
@@ -4248,7 +4318,8 @@ class RowsetDerivationStatement(Namespaced, BaseModel):
                     content=orig_concept, where=self.select.where_clause, rowset=self
                 ),
                 grain=orig_concept.grain,
-                metadata=orig_concept.metadata,
+                # TODO: add proper metadata
+                metadata=Metadata(concept_source=ConceptSource.CTE),
                 namespace=(
                     f"{self.name}.{orig_concept.namespace}"
                     if orig_concept.namespace != self.namespace
@@ -4275,6 +4346,7 @@ class RowsetDerivationStatement(Namespaced, BaseModel):
                     components=[orig[c.address] for c in x.grain.components_copy]
                 )
             else:
+
                 x.grain = default_grain
         return output
 
@@ -4300,6 +4372,9 @@ class RowsetItem(Mergeable, Namespaced, BaseModel):
             f"<Rowset<{self.rowset.name}>: {str(self.content)} where {str(self.where)}>"
         )
 
+    def __str__(self):
+        return self.__repr__()
+
     def with_merge(self, source: Concept, target: Concept, modifiers: List[Modifier]):
         return RowsetItem(
             content=self.content.with_merge(source, target, modifiers),

trilogy/core/processing/concept_strategies_v3.py

@@ -432,7 +432,6 @@ def generate_node(
             conditions=conditions,
         )
         if not check:
-
             logger.info(
                 f"{depth_to_prefix(depth)}{LOGGER_PREFIX} Could not resolve root concepts, checking for expanded concepts"
             )

trilogy/core/processing/node_generators/node_merge_node.py

@@ -87,12 +87,10 @@ def determine_induced_minimal_nodes(
     for node in G.nodes:
         if concepts.get(node):
             lookup: Concept = concepts[node]
-            if lookup.derivation not in (PurposeLineage.BASIC, PurposeLineage.ROOT):
-                nodes_to_remove.append(node)
-            elif lookup.derivation == PurposeLineage.BASIC and G.out_degree(node) == 0:
+            if lookup.derivation in (PurposeLineage.CONSTANT,):
                 nodes_to_remove.append(node)
             # purge a node if we're already looking for all it's parents
-            elif filter_downstream and lookup.derivation == PurposeLineage.BASIC:
+            if filter_downstream and lookup.derivation not in (PurposeLineage.ROOT,):
                 nodes_to_remove.append(node)
 
     H.remove_nodes_from(nodes_to_remove)
@@ -105,11 +103,12 @@ def determine_induced_minimal_nodes(
         zero_out = list(
             x for x in H.nodes if G.out_degree(x) == 0 and x not in nodelist
         )
+
     try:
         paths = nx.multi_source_dijkstra_path(H, nodelist)
     except nx.exception.NodeNotFound:
+        logger.debug(f"Unable to find paths for {nodelist}")
         return None
-
     H.remove_nodes_from(list(x for x in H.nodes if x not in paths))
     sG: nx.Graph = ax.steinertree.steiner_tree(H, nodelist).copy()
     final: nx.DiGraph = nx.subgraph(G, sG.nodes).copy()
@@ -126,12 +125,24 @@ def determine_induced_minimal_nodes(
     # all concept nodes must have a parent
 
     if not all(
-        [final.in_degree(node) > 0 for node in final.nodes if node.startswith("c~")]
+        [
+            final.in_degree(node) > 0
+            for node in final.nodes
+            if node.startswith("c~") and node in nodelist
+        ]
     ):
+        missing = [
+            node
+            for node in final.nodes
+            if node.startswith("c~") and final.in_degree(node) == 0
+        ]
+        logger.debug(f"Skipping graph for {nodelist} as no in_degree {missing}")
         return None
 
     if not all([node in final.nodes for node in nodelist]):
+        logger.debug(f"Skipping graph for {nodelist} as missing nodes")
         return None
+    logger.debug(f"Found final graph {final.nodes}")
     return final
 
 
@@ -256,7 +267,9 @@ def resolve_weak_components(
 
     subgraphs: list[list[Concept]] = []
     # components = nx.strongly_connected_components(g)
+    node_list = [x for x in g.nodes if x.startswith("c~")]
     components = extract_ds_components(g, node_list)
+    logger.debug(f"Extracted components {components} from {node_list}")
     for component in components:
         # we need to take unique again as different addresses may map to the same concept
         sub_component = unique(

trilogy/core/processing/node_generators/rowset_node.py

@@ -96,7 +96,7 @@ def gen_rowset_node(
         # node.set_preexisting_conditions(conditions.conditional if conditions else None)
         return node
 
-    possible_joins = concept_to_relevant_joins(additional_relevant)
+    possible_joins = concept_to_relevant_joins(node.output_concepts)
     if not possible_joins:
         logger.info(
             f"{padding(depth)}{LOGGER_PREFIX} no possible joins for rowset node to get {[x.address for x in local_optional]}; have {[x.address for x in node.output_concepts]}"
@@ -104,7 +104,7 @@ def gen_rowset_node(
         return node
     enrich_node: MergeNode = source_concepts(  # this fetches the parent + join keys
         # to then connect to the rest of the query
-        mandatory_list=additional_relevant + local_optional,
+        mandatory_list=possible_joins + local_optional,
         environment=environment,
         g=g,
         depth=depth + 1,

trilogy/core/processing/node_generators/select_node.py

@@ -39,9 +39,10 @@ def gen_select_node(
         ]
     )
     if materialized_lcl != all_lcl:
+        missing = all_lcl.difference(materialized_lcl)
         logger.info(
             f"{padding(depth)}{LOGGER_PREFIX} Skipping select node generation for {concept.address}"
-            f" as it + optional includes non-materialized concepts (looking for all {all_lcl}) "
+            f" as it + optional includes non-materialized concepts (looking for all {all_lcl}, missing {missing}) "
         )
         if fail_if_not_found:
             raise NoDatasourceException(f"No datasource exists for {concept}")

trilogy/core/query_processor.py

@@ -11,6 +11,7 @@ from trilogy.core.models import (
     Concept,
     Environment,
     PersistStatement,
+    ConceptDeclarationStatement,
     SelectStatement,
     MultiSelectStatement,
     CTE,
@@ -31,7 +32,7 @@ from trilogy.utility import unique
 
 from trilogy.hooks.base_hook import BaseHook
 from trilogy.constants import logger
-from trilogy.core.ergonomics import CTE_NAMES
+from trilogy.core.ergonomics import generate_cte_names
 from trilogy.core.optimization import optimize_ctes
 from math import ceil
 from collections import defaultdict
@@ -168,15 +169,16 @@ def datasource_to_query_datasource(datasource: Datasource) -> QueryDatasource:
 
 
 def generate_cte_name(full_name: str, name_map: dict[str, str]) -> str:
+    cte_names = generate_cte_names()
     if CONFIG.human_identifiers:
         if full_name in name_map:
             return name_map[full_name]
         suffix = ""
         idx = len(name_map)
-        if idx >= len(CTE_NAMES):
-            int = ceil(idx / len(CTE_NAMES))
+        if idx >= len(cte_names):
+            int = ceil(idx / len(cte_names))
             suffix = f"_{int}"
-        valid = [x for x in CTE_NAMES if x + suffix not in name_map.values()]
+        valid = [x for x in cte_names if x + suffix not in name_map.values()]
         lookup = valid[0]
         new_name = f"{lookup}{suffix}"
         name_map[full_name] = new_name
@@ -393,6 +395,8 @@ def process_auto(
         return process_persist(environment, statement, hooks)
     elif isinstance(statement, SelectStatement):
         return process_query(environment, statement, hooks)
+    elif isinstance(statement, ConceptDeclarationStatement):
+        return None
     raise ValueError(f"Do not know how to process {type(statement)}")
 
 

trilogy/dialect/base.py

@@ -48,6 +48,7 @@ from trilogy.core.models import (
     MapType,
     StructType,
     MergeStatementV2,
+    Datasource,
 )
 from trilogy.core.query_processor import process_query, process_persist
 from trilogy.dialect.common import render_join, render_unnest
@@ -724,6 +725,7 @@ class BaseDialect:
                     MergeStatementV2,
                     ImportStatement,
                     RowsetDerivationStatement,
+                    Datasource,
                 ),
             ):
                 continue

trilogy/executor.py

@@ -23,7 +23,7 @@ from trilogy.dialect.base import BaseDialect
 from trilogy.dialect.enums import Dialects
 from trilogy.parser import parse_text
 from trilogy.hooks.base_hook import BaseHook
-
+from pathlib import Path
 from dataclasses import dataclass
 
 
@@ -152,6 +152,13 @@ class Executor(object):
     def _(self, query: RawSQLStatement) -> CursorResult:
         return self.execute_raw_sql(query.text)
 
+    @execute_query.register
+    def _(self, query: ShowStatement) -> CursorResult:
+        sql = self.generator.generate_queries(
+            self.environment, [query], hooks=self.hooks
+        )
+        return self.execute_query(sql[0])
+
     @execute_query.register
     def _(self, query: ProcessedShowStatement) -> CursorResult:
         return generate_result_set(
@@ -341,3 +348,9 @@ class Executor(object):
             if isinstance(statement, ProcessedQueryPersist):
                 self.environment.add_datasource(statement.datasource)
         return output
+
+    def execute_file(self, file: str | Path) -> List[CursorResult]:
+        file = Path(file)
+        with open(file, "r") as f:
+            command = f.read()
+        return self.execute_text(command)

trilogy/parsing/common.py

@@ -141,9 +141,12 @@ def function_to_concept(parent: Function, name: str, namespace: str) -> Concept:
             for x in parent.concept_arguments
             if not x.derivation == PurposeLineage.CONSTANT
         ]
-    grain = Grain()
+    grain: Grain | None = Grain()
     for x in pkeys:
         grain += x.grain
+    if parent.operator in FunctionClass.ONE_TO_MANY.value:
+        # if the function will create more rows, we don't know what grain this is at
+        grain = None
     modifiers = get_upstream_modifiers(pkeys)
     key_grain = []
     for x in pkeys:
@@ -156,13 +159,24 @@ def function_to_concept(parent: Function, name: str, namespace: str) -> Concept:
         purpose = Purpose.CONSTANT
     else:
         purpose = parent.output_purpose
+    if grain is not None:
+        return Concept(
+            name=name,
+            datatype=parent.output_datatype,
+            purpose=purpose,
+            lineage=parent,
+            namespace=namespace,
+            keys=keys,
+            modifiers=modifiers,
+            grain=grain,
+        )
+
     return Concept(
         name=name,
         datatype=parent.output_datatype,
         purpose=purpose,
         lineage=parent,
         namespace=namespace,
-        grain=grain,
         keys=keys,
         modifiers=modifiers,
     )

trilogy/parsing/parse_engine.py

@@ -461,40 +461,7 @@ class ParseToObjects(Transformer):
         while isinstance(source_value, Parenthetical):
             source_value = source_value.content
 
-        if (
-            isinstance(source_value, Function)
-            and source_value.operator == FunctionType.STRUCT
-        ):
-            concept = arbitrary_to_concept(
-                source_value,
-                name=name,
-                namespace=namespace,
-                purpose=purpose,
-                metadata=metadata,
-            )
-
-            if concept.metadata:
-                concept.metadata.line_number = meta.line
-            self.environment.add_concept(concept, meta=meta)
-            return ConceptDerivation(concept=concept)
-        elif (
-            isinstance(source_value, Function)
-            and source_value.operator == FunctionType.ALIAS
-        ):
-            concept = arbitrary_to_concept(
-                source_value,
-                name=name,
-                namespace=namespace,
-                purpose=purpose,
-                metadata=metadata,
-            )
-
-            if concept.metadata:
-                concept.metadata.line_number = meta.line
-            self.environment.add_concept(concept, meta=meta)
-            return ConceptDerivation(concept=concept)
-
-        elif isinstance(
+        if isinstance(
             source_value, (FilterItem, WindowItem, AggregateWrapper, Function)
         ):
             concept = arbitrary_to_concept(

trilogy/parsing/render.py

@@ -186,6 +186,8 @@ class Renderer:
 
     @to_string.register
     def _(self, arg: "Address"):
+        if arg.is_query:
+            return f"query '''{arg.location}'''"
         return f"address {arg.location}"
 
     @to_string.register

trilogy/parsing/trilogy.lark

@@ -200,29 +200,42 @@
     _constant_functions: fcurrent_date | fcurrent_datetime
     
     //string
-    like: "like"i "(" expr "," _string_lit ")"
-    ilike: "ilike"i "(" expr "," _string_lit ")"
-    alt_like: expr "like"i expr
-    upper: "upper"i "(" expr ")"
-    lower: "lower"i "(" expr ")"    
-    fsplit: "split"i "(" expr "," _string_lit ")"
-    fstrpos: "strpos"i "(" expr "," expr ")"
+    _LIKE.1: "like("i
+    like:  _LIKE expr "," _string_lit ")"
+    _ILIKE.1: "ilike("i
+    ilike:   _ILIKE expr "," _string_lit ")"
+    alt_like: expr  "like"i expr
+    _UPPER.1: "upper("i
+    upper: _UPPER expr ")"
+   _LOWER.1: "lower("i
+    lower: _LOWER expr ")"  
+    _SPLIT.1: "split("i  
+    fsplit: _SPLIT expr "," _string_lit ")"
+   _STRPOS.1: "strpos("i
+    fstrpos: _STRPOS expr "," expr ")"
     _SUBSTRING.1: "substring("i
     fsubstring: _SUBSTRING expr "," expr "," expr ")"
     
     _string_functions: like | ilike | upper | lower | fsplit | fstrpos | fsubstring 
     
     // special aggregate
-    fgroup: "group"i "(" expr ")" aggregate_over?
+    _GROUP.1: "group("i
+    fgroup: _GROUP expr ")" aggregate_over?
     //aggregates
     _COUNT.1: "count("i
     count:   _COUNT  expr ")"
+    
     count_distinct: "count_distinct"i "(" expr ")"
     
-    sum: "sum"i "(" expr ")"
-    avg: "avg"i "(" expr ")"
-    max: "max"i "(" expr ")"
-    min: "min"i "(" expr ")"
+    // avoid conflicts with the window
+    _SUM.1: "sum("i
+    sum: _SUM expr ")"
+    _AVG.1: "avg("i
+    avg: _AVG expr ")"
+    _MAX.1: "max("i
+    max: _MAX expr ")"
+    _MIN.1: "min("i
+    min: _MIN expr ")"
     
     //aggregates can force a grain
     aggregate_all: "*"
@@ -255,10 +268,14 @@
     fyear: _YEAR expr ")"
     
     DATE_PART: "DAY"i | "WEEK"i | "MONTH"i | "QUARTER"i | "YEAR"i | "MINUTE"i | "HOUR"i | "SECOND"i
-    fdate_trunc: "date_trunc"i "(" expr "," DATE_PART ")"
-    fdate_part: "date_part"i "(" expr "," DATE_PART ")"
-    fdate_add: "date_add"i "(" expr "," DATE_PART "," int_lit ")"
-    fdate_diff: "date_diff"i "(" expr "," expr "," DATE_PART ")"
+    _DATE_TRUNC.1: "date_trunc("i
+    fdate_trunc: _DATE_TRUNC expr "," DATE_PART ")"
+    _DATE_PART.1: "date_part("i
+    fdate_part: _DATE_PART expr "," DATE_PART ")"
+    _DATE_ADD.1: "date_add("i
+    fdate_add: _DATE_ADD expr "," DATE_PART "," int_lit ")"
+   _DATE_DIFF.1: "date_diff("i
+    fdate_diff: _DATE_DIFF expr "," expr "," DATE_PART ")"
     
     _date_functions: fdate | fdate_add | fdate_diff | fdatetime | ftimestamp | fsecond | fminute | fhour | fday | fday_of_week | fweek | fmonth | fquarter | fyear | fdate_part | fdate_trunc
     
@@ -288,8 +305,8 @@
 
     map_lit: "{" (literal ":" literal ",")* literal ":" literal ","? "}"
 
-   
-    struct_lit: "struct" "(" (IDENTIFIER "=" literal ",")* IDENTIFIER "=" literal ","? ")"
+    _STRUCT.1: "struct("i
+    struct_lit: _STRUCT (IDENTIFIER "=" literal ",")* IDENTIFIER "=" literal ","? ")"
     
     !bool_lit: "True"i | "False"i