pytrilogy 0.0.3.79__py3-none-any.whl → 0.0.3.81__py3-none-any.whl

{pytrilogy-0.0.3.79.dist-info → pytrilogy-0.0.3.81.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrilogy
-Version: 0.0.3.79
+Version: 0.0.3.81
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.3.79.dist-info → pytrilogy-0.0.3.81.dist-info}/RECORD

@@ -1,5 +1,5 @@
-pytrilogy-0.0.3.79.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
-trilogy/__init__.py,sha256=YY8Yc29Dawl2U9Xu5dC8ZXP8Q0yEh7iv4k_Neu-Nc3c,303
+pytrilogy-0.0.3.81.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
+trilogy/__init__.py,sha256=TMYRdrnDsNt6dIWHpcXgKPBKzjBkbMC5oJTgTrClxz0,303
 trilogy/compiler.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/constants.py,sha256=eKb_EJvSqjN9tGbdVEViwdtwwh8fZ3-jpOEDqL71y70,1691
 trilogy/engine.py,sha256=OK2RuqCIUId6yZ5hfF8J1nxGP0AJqHRZiafcowmW0xc,1728
@@ -11,24 +11,24 @@ trilogy/utility.py,sha256=euQccZLKoYBz0LNg5tzLlvv2YHvXh9HArnYp1V3uXsM,763
 trilogy/authoring/__init__.py,sha256=e74k-Jep4DLYPQU_2m0aVsYlw5HKTOucAKtdTbd6f2g,2595
 trilogy/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/core/constants.py,sha256=nizWYDCJQ1bigQMtkNIEMNTcN0NoEAXiIHLzpelxQ24,201
-trilogy/core/enums.py,sha256=tDUXVWxvWgnO1u7LLS0iIReeHYbyFLN2ZbpTdUyKdjE,8060
+trilogy/core/enums.py,sha256=kuwTeEur5TZ07DX8nO3fSiRQ32bLZ5jRK-vIjHbBUnc,8118
 trilogy/core/env_processor.py,sha256=pFsxnluKIusGKx1z7tTnfsd_xZcPy9pZDungkjkyvI0,3170
 trilogy/core/environment_helpers.py,sha256=VvPIiFemqaLLpIpLIqprfu63K7muZ1YzNg7UZIUph8w,8267
 trilogy/core/ergonomics.py,sha256=e-7gE29vPLFdg0_A1smQ7eOrUwKl5VYdxRSTddHweRA,1631
 trilogy/core/exceptions.py,sha256=jYEduuMehcMkmCpf-OC_taELPZm7qNfeSNzIWkDYScs,707
-trilogy/core/functions.py,sha256=wQ5yCvMKXSCkaSo7yiwlGY0wvqE4Sm2MI9e5NEr2ORw,30933
+trilogy/core/functions.py,sha256=9Q-c7UGxOR0SVwzcHt9mHX_aVroW9jEWwJr7BtHigw8,31766
 trilogy/core/graph_models.py,sha256=BYhJzHKSgnZHVLJs1CfsgrxTPHqKqPNeA64RlozGY0A,3498
 trilogy/core/internal.py,sha256=wFx4e1I0mtx159YFShSXeUBSQ82NINtAbOI-92RX4i8,2151
 trilogy/core/optimization.py,sha256=ojpn-p79lr03SSVQbbw74iPCyoYpDYBmj1dbZ3oXCjI,8860
 trilogy/core/query_processor.py,sha256=5aFgv-2LVM1Uku9cR_tFuTRDwyLnxc95bCMAHeFy2AY,20332
 trilogy/core/utility.py,sha256=3VC13uSQWcZNghgt7Ot0ZTeEmNqs__cx122abVq9qhM,410
 trilogy/core/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/core/models/author.py,sha256=9gQ2UBJ2qZ4ngFOXei4VbYQAp8UTrcAr_5GvWW2O2l8,78192
+trilogy/core/models/author.py,sha256=Xt_TRVl4xHF6fe-KTKPSt4Z8Srmplnv2KQe2grZXX3w,78411
 trilogy/core/models/build.py,sha256=0TRcL__hvajLcpFwYeLjCV35cow5oVPbJHXA3oO09XA,65931
 trilogy/core/models/build_environment.py,sha256=s_C9xAHuD3yZ26T15pWVBvoqvlp2LdZ8yjsv2_HdXLk,5363
 trilogy/core/models/core.py,sha256=q-8ExAaSB3PoSDX2XOqfZ01HBBvT1pZFs7jGg1vZizc,11096
 trilogy/core/models/datasource.py,sha256=wogTevZ-9CyUW2a8gjzqMCieircxi-J5lkI7EOAZnck,9596
-trilogy/core/models/environment.py,sha256=TBbPfsXHpJK49QKuqHwhgZD4PwHiSAYjXmTTTomRE7o,27861
+trilogy/core/models/environment.py,sha256=0IHSCFf5e5b4LPQN3vmjumtfM1iD1tN4WMoUr0UqxZI,27855
 trilogy/core/models/execute.py,sha256=Erufst3yroU3PgNJMWF5lICm14AkH02laYeesSB01UU,41705
 trilogy/core/optimizations/__init__.py,sha256=YH2-mGXZnVDnBcWVi8vTbrdw7Qs5TivG4h38rH3js_I,290
 trilogy/core/optimizations/base_optimization.py,sha256=gzDOKImoFn36k7XBD3ysEYDnbnb6vdVIztUfFQZsGnM,513
@@ -43,13 +43,13 @@ trilogy/core/processing/discovery_validation.py,sha256=fGWJmKpgEd1f4RkK-fYOBUT1c
 trilogy/core/processing/graph_utils.py,sha256=8QUVrkE9j-9C1AyrCb1nQEh8daCe0u1HuXl-Te85lag,1205
 trilogy/core/processing/utility.py,sha256=xsuVMRFi2nY2So0yohhweI2D92wZVsTpHezS0giM4ck,22583
 trilogy/core/processing/node_generators/__init__.py,sha256=w8TQQgNhyAra6JQHdg1_Ags4BGyxjXYruu6UeC5yOkI,873
-trilogy/core/processing/node_generators/basic_node.py,sha256=luN8LftafZepoFgDRv4gmvEGFlOI2j0icJ5fz4UT7uo,5165
+trilogy/core/processing/node_generators/basic_node.py,sha256=TLZCv4WS196a-0g5xgKuJGthnGP8Ugm46iz85_3NIY4,5626
 trilogy/core/processing/node_generators/common.py,sha256=PdysdroW9DUADP7f5Wv_GKPUyCTROZV1g3L45fawxi8,9443
 trilogy/core/processing/node_generators/filter_node.py,sha256=oRRq2-T3ufgn4D23uQsc58f20eFk-djs4QI3WKA75K8,10908
 trilogy/core/processing/node_generators/group_node.py,sha256=1QJhRxsTklJ5xq8wHlAURZaN9gL9FPpeCa1OJ7IwXnY,6769
 trilogy/core/processing/node_generators/group_to_node.py,sha256=jKcNCDOY6fNblrdZwaRU0sbUSr9H0moQbAxrGgX6iGA,3832
 trilogy/core/processing/node_generators/multiselect_node.py,sha256=GWV5yLmKTe1yyPhN60RG1Rnrn4ktfn9lYYXi_FVU4UI,7061
-trilogy/core/processing/node_generators/node_merge_node.py,sha256=KtTuvL9-xaTV_ZUO1DUyz2Rd595QfD9SvOv5filCDy0,17428
+trilogy/core/processing/node_generators/node_merge_node.py,sha256=bYhXGJqJDgT4JWlN4u761V3bkP96o6J25LFs6YBOiKQ,18304
 trilogy/core/processing/node_generators/recursive_node.py,sha256=l5zdh0dURKwmAy8kK4OpMtZfyUEQRk6N-PwSWIyBpSM,2468
 trilogy/core/processing/node_generators/rowset_node.py,sha256=5L5u6xz1In8EaHQdcYgR2si-tz9WB9YLXURo4AkUT9A,6630
 trilogy/core/processing/node_generators/select_merge_node.py,sha256=Cv2GwNiYSmwewjuK8T3JB3pbgrLZFPsB75DCP153BMA,22818
@@ -76,12 +76,12 @@ trilogy/core/statements/build.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 trilogy/core/statements/common.py,sha256=KxEmz2ySySyZ6CTPzn0fJl5NX2KOk1RPyuUSwWhnK1g,759
 trilogy/core/statements/execute.py,sha256=pfr1CZ_Cx1qQ-7LDyRI0JUfvtxBr_GGv-VeqiAjr43g,1406
 trilogy/dialect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-trilogy/dialect/base.py,sha256=aLJ7-Lq7TTe7I_FjMzhkC5LfrqyjN55AFD8T0lqsiRs,47202
+trilogy/dialect/base.py,sha256=0nVDvsnDS8iMTIlCUsBs_ymoZMW6uh04U4MMZxOuHUw,47428
 trilogy/dialect/bigquery.py,sha256=8xhEu0z_lKANjbvzvBbC7CeKrJf1iP8YyrHqNale-ug,4351
 trilogy/dialect/common.py,sha256=tSthIZOXXRPQ4KeMKnDDsH7KlTmf2EVqigVtLyoc4zc,6071
 trilogy/dialect/config.py,sha256=olnyeVU5W5T6b9-dMeNAnvxuPlyc2uefb7FRME094Ec,3834
 trilogy/dialect/dataframe.py,sha256=RUbNgReEa9g3pL6H7fP9lPTrAij5pkqedpZ99D8_5AE,1522
-trilogy/dialect/duckdb.py,sha256=0qWQkyijz1_MnsVFyY_Iqqx0ba6E8o50s8pvLLpZH6g,5138
+trilogy/dialect/duckdb.py,sha256=uqnZEd1IH4tO8FSbbUXe3Jl9EjoyrDde406k0VDuMXw,5544
 trilogy/dialect/enums.py,sha256=FRNYQ5-w-B6-X0yXKNU5g9GowsMlERFogTC5u2nxL_s,4740
 trilogy/dialect/postgres.py,sha256=el2PKwfyvWGk5EZtLudqAH5ewLitY1sFHJiocBSyxyM,3393
 trilogy/dialect/presto.py,sha256=yzSF8SZ6o1dizj1UueAa7S3lR0qNYJdSXbF78EHyhY0,3668
@@ -97,9 +97,9 @@ trilogy/parsing/common.py,sha256=yV1AckK0h8u1OFeGQBTMu-wuW5m63c5CcZuPicsTH_w,306
 trilogy/parsing/config.py,sha256=Z-DaefdKhPDmSXLgg5V4pebhSB0h590vI0_VtHnlukI,111
 trilogy/parsing/exceptions.py,sha256=Xwwsv2C9kSNv2q-HrrKC1f60JNHShXcCMzstTSEbiCw,154
 trilogy/parsing/helpers.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-trilogy/parsing/parse_engine.py,sha256=xtwWwe7EfYcmt9_lwJ0JH0AhKVcPHty97VJCpyM5beA,78068
+trilogy/parsing/parse_engine.py,sha256=ll3uBwpJ2iAxT-KbbXy7OuCqUvKfLPzB1gHr8gApv_s,78591
 trilogy/parsing/render.py,sha256=HSNntD82GiiwHT-TWPLXAaIMWLYVV5B5zQEsgwrHIBE,19605
-trilogy/parsing/trilogy.lark,sha256=wiGXJdKfPTG7E_XdkN1rf9g9Yy1-UMVAXyTxtrBPm9w,15037
+trilogy/parsing/trilogy.lark,sha256=Uhy6A00-GsC-L8fRCN0JZC6fL87ujOOd9_4LbQWApY4,15248
 trilogy/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/scripts/trilogy.py,sha256=1L0XrH4mVHRt1C9T1HnaDv2_kYEfbWTb5_-cBBke79w,3774
 trilogy/std/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -110,8 +110,8 @@ trilogy/std/money.preql,sha256=XWwvAV3WxBsHX9zfptoYRnBigcfYwrYtBHXTME0xJuQ,2082
 trilogy/std/net.preql,sha256=7l7MqIjs6TDCpO6dBAoNJU81Ex255jZRK36kBgE1GDs,158
 trilogy/std/ranking.preql,sha256=LDoZrYyz4g3xsII9XwXfmstZD-_92i1Eox1UqkBIfi8,83
 trilogy/std/report.preql,sha256=LbV-XlHdfw0jgnQ8pV7acG95xrd1-p65fVpiIc-S7W4,202
-pytrilogy-0.0.3.79.dist-info/METADATA,sha256=-WUI1LfhYvSwypFjkJOGe4KiAgTReZ4w-dcEB7L5J3E,9589
-pytrilogy-0.0.3.79.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pytrilogy-0.0.3.79.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
-pytrilogy-0.0.3.79.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
-pytrilogy-0.0.3.79.dist-info/RECORD,,
+pytrilogy-0.0.3.81.dist-info/METADATA,sha256=0A4NkUsyAunmuRlrFbsAPi8sksv9Yf0l4jAFh6Q_NeU,9589
+pytrilogy-0.0.3.81.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pytrilogy-0.0.3.81.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
+pytrilogy-0.0.3.81.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
+pytrilogy-0.0.3.81.dist-info/RECORD,,

trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.dialect.enums import Dialects
 from trilogy.executor import Executor
 from trilogy.parser import parse
 
-__version__ = "0.0.3.79"
+__version__ = "0.0.3.81"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

trilogy/core/enums.py

@@ -171,6 +171,7 @@ class FunctionType(Enum):
     RANDOM = "random"
     FLOOR = "floor"
     CEIL = "ceil"
+    LOG = "log"
 
     # Aggregates
     ## group is not a real aggregate - it just means group by this + some other set of fields
@@ -193,6 +194,8 @@ class FunctionType(Enum):
     SUBSTRING = "substring"
     STRPOS = "strpos"
     CONTAINS = "contains"
+    TRIM = "trim"
+    REPLACE = "replace"
 
     # STRING REGEX
     REGEXP_CONTAINS = "regexp_contains"

trilogy/core/functions.py

@@ -358,6 +358,16 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         output_type=DataType.INTEGER,
         arg_count=2,
     ),
+    FunctionType.REPLACE: FunctionConfig(
+        valid_inputs=[
+            {DataType.STRING},
+            {DataType.STRING},
+            {DataType.STRING},
+        ],
+        output_purpose=Purpose.PROPERTY,
+        output_type=DataType.STRING,
+        arg_count=3,
+    ),
     FunctionType.CONTAINS: FunctionConfig(
         valid_inputs=[
             {DataType.STRING},
@@ -367,6 +377,15 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         output_type=DataType.BOOL,
         arg_count=2,
     ),
+    FunctionType.TRIM: FunctionConfig(
+        valid_inputs=[
+            {DataType.STRING},
+            {DataType.STRING},
+        ],
+        output_purpose=Purpose.PROPERTY,
+        output_type=DataType.BOOL,
+        arg_count=2,
+    ),
     FunctionType.SUBSTRING: FunctionConfig(
         valid_inputs=[{DataType.STRING}, {DataType.INTEGER}, {DataType.INTEGER}],
         output_purpose=Purpose.PROPERTY,
@@ -688,6 +707,15 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         output_type=DataType.INTEGER,
         arg_count=1,
     ),
+    FunctionType.LOG: FunctionConfig(
+        valid_inputs=[
+            {DataType.INTEGER, DataType.FLOAT, DataType.NUMBER, DataType.NUMERIC},
+            {DataType.INTEGER},
+        ],
+        output_purpose=Purpose.PROPERTY,
+        output_type=DataType.FLOAT,
+        arg_count=2,
+    ),
     FunctionType.RANDOM: FunctionConfig(
         valid_inputs=[],
         output_purpose=Purpose.PROPERTY,
@@ -775,6 +803,7 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
             DataType.FLOAT,
             DataType.NUMBER,
             DataType.NUMERIC,
+            DataType.BOOL,
         },
         output_purpose=Purpose.METRIC,
         arg_count=1,

trilogy/core/models/author.py

@@ -1605,6 +1605,10 @@ def get_concept_arguments(expr) -> List["ConceptRef"]:
     return output
 
 
+def args_to_pretty(input: set[DataType]) -> str:
+    return ", ".join(sorted([f"'{x.value}'" for x in input if x != DataType.UNKNOWN]))
+
+
 class Function(DataTyped, ConceptArgs, Mergeable, Namespaced, BaseModel):
     operator: FunctionType
     arg_count: int = Field(default=1)
@@ -1669,9 +1673,10 @@ class Function(DataTyped, ConceptArgs, Mergeable, Namespaced, BaseModel):
                 and get_basic_type(arg.datatype.data_type) not in valid_inputs[idx]
             ):
                 if arg.datatype != DataType.UNKNOWN:
+
                     raise TypeError(
-                        f"Invalid input datatype {arg.datatype.data_type} passed into position {idx}"
-                        f" for {operator_name} from concept {arg.name}, valid is {valid_inputs[idx]}"
+                        f"Invalid argument type '{arg.datatype.data_type.value}' passed into {operator_name} function in position {idx+1}"
+                        f" from concept: {arg.name}. Valid: {args_to_pretty(valid_inputs[idx])}."
                     )
             if (
                 isinstance(arg, Function)
@@ -1679,8 +1684,8 @@ class Function(DataTyped, ConceptArgs, Mergeable, Namespaced, BaseModel):
             ):
                 if arg.output_datatype != DataType.UNKNOWN:
                     raise TypeError(
-                        f"Invalid input datatype {arg.output_datatype} passed into"
-                        f" {operator_name} from function {arg.operator.name}, need {valid_inputs[idx]}"
+                        f"Invalid argument type {arg.output_datatype}' passed into"
+                        f" {operator_name} function from function {arg.operator.name} in position {idx+1}. Valid: {args_to_pretty(valid_inputs[idx])}"
                     )
             # check constants
             comparisons: List[Tuple[Type, DataType]] = [

trilogy/core/models/environment.py

@@ -227,7 +227,7 @@ class Environment(BaseModel):
     alias_origin_lookup: Dict[str, Concept] = Field(default_factory=dict)
     # TODO: support freezing environments to avoid mutation
     frozen: bool = False
-    env_file_path: Path | None = None
+    env_file_path: Path | str | None = None
 
     def freeze(self):
         self.frozen = True
@@ -281,8 +281,7 @@ class Environment(BaseModel):
         )
         self.add_concept(concept)
 
-    def __init__(self, **data):
-        super().__init__(**data)
+    def model_post_init(self, context: Any) -> None:
         self._add_path_concepts()
 
     @classmethod

trilogy/core/processing/node_generators/basic_node.py

@@ -97,6 +97,9 @@ def gen_basic_node(
         and not any(x.address in y.pseudonyms for y in equivalent_optional)
         and x.address not in ignored_optional
     ]
+    logger.info(
+        f"{depth_prefix}{LOGGER_PREFIX} basic node for {concept} has non-equivalent optional {[x.address for x in non_equivalent_optional]}"
+    )
     all_parents: list[BuildConcept] = unique(
         parent_concepts + non_equivalent_optional, "address"
     )
@@ -122,10 +125,11 @@ def gen_basic_node(
     parent_node.add_output_concept(concept)
     for x in equivalent_optional:
         parent_node.add_output_concept(x)
-    targets = [concept] + local_optional
+
     logger.info(
         f"{depth_prefix}{LOGGER_PREFIX} Returning basic select for {concept}: output {[x.address for x in parent_node.output_concepts]}"
     )
+    targets = [concept] + local_optional + equivalent_optional
     should_hide = [
         x
         for x in parent_node.output_concepts
@@ -135,8 +139,14 @@ def gen_basic_node(
         )
     ]
     parent_node.hide_output_concepts(should_hide)
+    should_not_hide = [
+        x
+        for x in parent_node.output_concepts
+        if x.address in targets or any(x.address in y.pseudonyms for y in targets)
+    ]
+    parent_node.unhide_output_concepts(should_not_hide)
 
     logger.info(
-        f"{depth_prefix}{LOGGER_PREFIX} Returning basic select for {concept}: output {[x.address for x in parent_node.output_concepts]}"
+        f"{depth_prefix}{LOGGER_PREFIX} Returning basic select for {concept}: output {[x.address for x in parent_node.output_concepts]} hidden {[x for x in parent_node.hidden_concepts]}"
     )
     return parent_node

trilogy/core/processing/node_generators/node_merge_node.py

@@ -94,31 +94,45 @@ def determine_induced_minimal_nodes(
             # inclusion of aggregates can create ambiguous node relation chains
             # there may be a better way to handle this
             # can be revisited if we need to connect a derived synonym based on an aggregate
-            if lookup.derivation in (Derivation.CONSTANT, Derivation.AGGREGATE):
+            if lookup.derivation in (
+                Derivation.CONSTANT,
+                Derivation.AGGREGATE,
+                Derivation.FILTER,
+            ):
                 nodes_to_remove.append(node)
             # purge a node if we're already looking for all it's parents
             if filter_downstream and lookup.derivation not in (Derivation.ROOT,):
                 nodes_to_remove.append(node)
-
-    H.remove_nodes_from(nodes_to_remove)
-
-    H.remove_nodes_from(list(nx.isolates(H)))
+    if nodes_to_remove:
+        logger.debug(f"Removing nodes {nodes_to_remove} from graph")
+        H.remove_nodes_from(nodes_to_remove)
+    isolates = list(nx.isolates(H))
+    if isolates:
+        logger.debug(f"Removing isolates {isolates} from graph")
+        H.remove_nodes_from(isolates)
 
     zero_out = list(x for x in H.nodes if G.out_degree(x) == 0 and x not in nodelist)
     while zero_out:
+        logger.debug(f"Removing zero out nodes {zero_out} from graph")
         H.remove_nodes_from(zero_out)
         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)
         # logger.debug(f"Paths found for {nodelist}")
     except nx.exception.NodeNotFound:
         # logger.debug(f"Unable to find paths for {nodelist}- {str(e)}")
         return None
-    H.remove_nodes_from(list(x for x in H.nodes if x not in paths))
+    path_removals = list(x for x in H.nodes if x not in paths)
+    if path_removals:
+        logger.debug(f"Removing paths {path_removals} from graph")
+        H.remove_nodes_from(path_removals)
+    logger.debug(f"Graph after path removal {H.nodes}")
     sG: nx.Graph = ax.steinertree.steiner_tree(H, nodelist).copy()
+    if not sG.nodes:
+        logger.debug(f"No Steiner tree found for nodes {nodelist}")
+        return None
     # logger.debug(f"Steiner tree found for nodes {nodelist} {sG.nodes}")
     final: nx.DiGraph = nx.subgraph(G, sG.nodes).copy()
 
@@ -293,7 +307,8 @@ def resolve_weak_components(
             if not nx.is_weakly_connected(g):
                 break_flag = True
                 continue
-
+            # from trilogy.hooks.graph_hook import GraphHook
+            # GraphHook().query_graph_built(g, highlight_nodes=[concept_to_node(c.with_default_grain()) for c in all_concepts if "__preql_internal" not in c.address])
             all_graph_concepts = [
                 extract_concept(extract_address(node), environment)
                 for node in g.nodes

trilogy/dialect/base.py

@@ -205,6 +205,9 @@ FUNCTION_MAP = {
     FunctionType.MOD: lambda x: f"({x[0]} % {x[1]})",
     FunctionType.SQRT: lambda x: f"sqrt({x[0]})",
     FunctionType.RANDOM: lambda x: "random()",
+    FunctionType.LOG: lambda x: (
+        f"log({x[0]})" if x[1] == 10 else f"log({x[0]}, {x[1]})"
+    ),
     # aggregate types
     FunctionType.COUNT_DISTINCT: lambda x: f"count(distinct {x[0]})",
     FunctionType.COUNT: lambda x: f"count({x[0]})",
@@ -224,6 +227,8 @@ FUNCTION_MAP = {
     FunctionType.REGEXP_CONTAINS: lambda x: f"REGEXP_CONTAINS({x[0]},{x[1]})",
     FunctionType.REGEXP_EXTRACT: lambda x: f"REGEXP_EXTRACT({x[0]},{x[1]})",
     FunctionType.REGEXP_REPLACE: lambda x: f"REGEXP_REPLACE({x[0]},{x[1]}, {x[2]})",
+    FunctionType.TRIM: lambda x: f"TRIM({x[0]})",
+    FunctionType.REPLACE: lambda x: f"REPLACE({x[0]},{x[1]},{x[2]})",
     # FunctionType.NOT_LIKE: lambda x: f" CASE WHEN {x[0]} like {x[1]} THEN 0 ELSE 1 END",
     # date types
     FunctionType.DATE_TRUNCATE: lambda x: f"date_trunc({x[0]},{x[1]})",

trilogy/dialect/duckdb.py

@@ -33,11 +33,25 @@ def render_sort(args):
         return f"list_sort({args[0]}, '{order[0]}', '{order[1]}')"
 
 
+def render_log(args):
+    if len(args) == 1:
+        return f"log({args[0]})"
+    elif len(args) == 2:
+        if int(args[1]) == 10:
+            return f"log({args[0]})"
+        else:
+            # change of base formula
+            return f"log({args[0]})/log({args[1]})"
+    else:
+        raise ValueError("log function requires 1 or 2 arguments")
+
+
 FUNCTION_MAP = {
     FunctionType.COUNT: lambda args: f"count({args[0]})",
     FunctionType.SUM: lambda args: f"sum({args[0]})",
     FunctionType.AVG: lambda args: f"avg({args[0]})",
     FunctionType.LENGTH: lambda args: f"length({args[0]})",
+    FunctionType.LOG: lambda args: render_log(args),
     FunctionType.LIKE: lambda args: (
         f" CASE WHEN {args[0]} like {args[1]} THEN True ELSE False END"
     ),

trilogy/parsing/parse_engine.py

@@ -1793,10 +1793,18 @@ class ParseToObjects(Transformer):
     def fstrpos(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.STRPOS, meta)
 
+    @v_args(meta=True)
+    def freplace(self, meta, args):
+        return self.function_factory.create_function(args, FunctionType.REPLACE, meta)
+
     @v_args(meta=True)
     def fcontains(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.CONTAINS, meta)
 
+    @v_args(meta=True)
+    def ftrim(self, meta, args):
+        return self.function_factory.create_function(args, FunctionType.TRIM, meta)
+
     @v_args(meta=True)
     def fsubstring(self, meta, args):
         return self.function_factory.create_function(args, FunctionType.SUBSTRING, meta)
@@ -1971,6 +1979,12 @@ class ParseToObjects(Transformer):
             args.append(0)
         return self.function_factory.create_function(args, FunctionType.ROUND, meta)
 
+    @v_args(meta=True)
+    def flog(self, meta, args) -> Function:
+        if len(args) == 1:
+            args.append(10)
+        return self.function_factory.create_function(args, FunctionType.LOG, meta)
+
     @v_args(meta=True)
     def ffloor(self, meta, args) -> Function:
         return self.function_factory.create_function(args, FunctionType.FLOOR, meta)
@@ -2074,9 +2088,9 @@ def unpack_visit_error(e: VisitError, text: str | None = None):
                 extract = text[e.obj.meta.start_pos - 5 : e.obj.meta.end_pos + 5]
                 raise InvalidSyntaxException(
                     str(e.orig_exc)
-                    + " in "
+                    + " Raised when parsing rule: "
                     + str(e.rule)
-                    + f" Line: {e.obj.meta.line} ({extract})"
+                    + f' Line: {e.obj.meta.line} "...{extract}..."'
                 )
             InvalidSyntaxException(
                 str(e.orig_exc) + " in " + str(e.rule) + f" Line: {e.obj.meta.line}"

trilogy/parsing/trilogy.lark

@@ -222,6 +222,8 @@
     fmul: ("multiply"i "(" expr "," expr ")" ) 
     fdiv: ( "divide"i "(" expr "," expr ")") 
     fmod: ( "mod"i "(" expr "," (int_lit | concept_lit ) ")")  
+    _LOG.1: "log"i "("
+    flog: _LOG expr ("," expr)? ")"
     _ROUND.1: "round"i "("
     fround: _ROUND expr ("," expr)? ")"
     _FLOOR.1: "floor"i "("
@@ -234,7 +236,7 @@
     _RANDOM.1: "random("i
     frandom: _RANDOM expr ")"
         
-    _math_functions: fmul | fdiv | fadd | fsub | fround | ffloor | fceil | fmod | fabs | fsqrt | frandom
+    _math_functions: fmul | fdiv | fadd | fsub | fround | ffloor | fceil | fmod | flog | fabs | fsqrt | frandom
     
     //generic
     _fcast_primary: "cast"i "(" expr "as"i data_type ")"
@@ -278,6 +280,10 @@
     fstrpos: _STRPOS expr "," expr ")"
     _CONTAINS.1: "contains("i
     fcontains: _CONTAINS expr "," expr ")"
+    _TRIM.1: "trim("i
+    ftrim: _TRIM expr ")"
+    _REPLACE.1: "replace("i
+    freplace: _REPLACE expr "," expr "," expr ")"
     _SUBSTRING.1: "substring("i
     fsubstring: _SUBSTRING expr "," expr "," expr ")"
     _REGEXP_EXTRACT.1: "regexp_extract("
@@ -287,7 +293,7 @@
     _REGEXP_REPLACE.1: "regexp_replace("
     fregexp_replace: _REGEXP_REPLACE expr "," expr "," expr   ")"
 
-    _string_functions: like | ilike | upper | flower | fsplit | fstrpos | fsubstring | fcontains | fregexp_extract | fregexp_contains | fregexp_replace
+    _string_functions: like | ilike | upper | flower | fsplit | fstrpos | fsubstring | fcontains | ftrim | freplace | fregexp_extract | fregexp_contains | fregexp_replace
 
     //array_functions
     _ARRAY_SUM.1: "array_sum("i