pytrilogy 0.0.2.21__tar.gz → 0.0.2.22__tar.gz

{pytrilogy-0.0.2.21/pytrilogy.egg-info → pytrilogy-0.0.2.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.21
+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-0.0.2.21 → pytrilogy-0.0.2.22}/README.md

@@ -116,7 +116,7 @@ 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
 
@@ -129,9 +129,9 @@ 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
 
@@ -195,7 +195,7 @@ 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.
@@ -238,7 +238,7 @@ 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.
 
@@ -255,20 +255,26 @@ 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-0.0.2.21 → pytrilogy-0.0.2.22/pytrilogy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.21
+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-0.0.2.21 → pytrilogy-0.0.2.22}/pytrilogy.egg-info/SOURCES.txt

@@ -22,6 +22,7 @@ tests/test_parsing.py
 tests/test_partial_handling.py
 tests/test_query_processing.py
 tests/test_select.py
+tests/test_show.py
 tests/test_statements.py
 tests/test_undefined_concept.py
 tests/test_where_clause.py

pytrilogy-0.0.2.22/tests/test_show.py

@@ -0,0 +1,58 @@
+from trilogy.core.models import ShowStatement
+from trilogy.core.query_processor import process_query
+from trilogy import Dialects
+from trilogy.parser import parse
+
+
+def test_show_bigquery():
+    declarations = """
+    key user_id int metadata(description="the description");
+    property user_id.display_name string metadata(description="The display name ");
+    property user_id.about_me string metadata(description="User provided description");
+    key post_id int;
+
+
+    datasource posts (
+        user_id: user_id,
+        id: post_id
+        )
+        grain (post_id)
+        address bigquery-public-data.stackoverflow.post_history
+    ;
+
+
+    datasource users (
+        id: user_id,
+        display_name: display_name,
+        about_me: about_me,
+        )
+        grain (user_id)
+        address bigquery-public-data.stackoverflow.users
+    ;
+
+
+        """
+    env, parsed = parse(declarations)
+
+    q1 = """
+    metric post_count<- count(post_id);
+    metric distinct_post_count <- count_distinct(post_id);
+    
+    metric user_count <- count(user_id);
+    
+    show select
+        post_count,
+        distinct_post_count,
+        user_count
+    ;"""
+    env, parsed = parse(q1, environment=env)
+    select: ShowStatement = parsed[-1]
+
+    query = (
+        Dialects.DUCK_DB.default_executor(environment=env)
+        .execute_query(select)
+        .fetchall()
+    )
+    assert "FULL JOIN wakeful on 1=1" in query[0]["__preql_internal_query_text"], query[
+        0
+    ]["__preql_internal_query_text"]

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.executor import Executor
 from trilogy.parser import parse
 from trilogy.constants import CONFIG
 
-__version__ = "0.0.2.21"
+__version__ = "0.0.2.22"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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)

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/trilogy/core/enums.py

@@ -12,6 +12,7 @@ class UnnestMode(Enum):
 
 class ConceptSource(Enum):
     MANUAL = "manual"
+    CTE = "cte"
     PERSIST_STATEMENT = "persist_statement"
     AUTO_DERIVED = "auto_derived"
 
@@ -206,6 +207,8 @@ class FunctionClass(Enum):
         FunctionType.CURRENT_DATETIME,
     ]
 
+    ONE_TO_MANY = [FunctionType.UNNEST]
+
 
 class Boolean(Enum):
     TRUE = "true"

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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()

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/trilogy/core/models.py

@@ -3478,10 +3478,18 @@ class Environment(BaseModel):
                     # 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
@@ -4289,6 +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] = []
@@ -4307,7 +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
@@ -4334,6 +4346,7 @@ class RowsetDerivationStatement(Namespaced, BaseModel):
                     components=[orig[c.address] for c in x.grain.components_copy]
                 )
             else:
+
                 x.grain = default_grain
         return output
 
@@ -4359,6 +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),

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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"
             )

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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(

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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,

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/trilogy/core/query_processor.py

@@ -32,7 +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
@@ -169,15 +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

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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)

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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,
     )

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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(

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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

{pytrilogy-0.0.2.21 → pytrilogy-0.0.2.22}/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