sqlframe 3.22.0__py3-none-any.whl → 3.23.0__py3-none-any.whl

sqlframe/_version.py

@@ -1,8 +1,13 @@
-# file generated by setuptools_scm
+# file generated by setuptools-scm
 # don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
 TYPE_CHECKING = False
 if TYPE_CHECKING:
-    from typing import Tuple, Union
+    from typing import Tuple
+    from typing import Union
+
     VERSION_TUPLE = Tuple[Union[int, str], ...]
 else:
     VERSION_TUPLE = object
@@ -12,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.22.0'
-__version_tuple__ = version_tuple = (3, 22, 0)
+__version__ = version = '3.23.0'
+__version_tuple__ = version_tuple = (3, 23, 0)

sqlframe/base/catalog.py

@@ -70,13 +70,16 @@ class _BaseCatalog(t.Generic[SESSION, DF]):
         }
 
     def add_table(
-        self, table: exp.Table | str, column_mapping: t.Optional[ColumnMapping] = None
+        self,
+        table: exp.Table | str,
+        column_mapping: t.Optional[ColumnMapping] = None,
+        **kwargs: t.Any,
     ) -> None:
         # TODO: Making this an update or add
         table = self.ensure_table(table)
         if self._schema.find(table):
             return
-        if not column_mapping:
+        if column_mapping is None:
             try:
                 column_mapping = {
                     normalize_string(
@@ -100,7 +103,7 @@ class _BaseCatalog(t.Generic[SESSION, DF]):
             if column.this.quoted:
                 self._quoted_columns[table].append(column.this.name)
 
-        self._schema.add_table(table, column_mapping, dialect=self.session.input_dialect)
+        self._schema.add_table(table, column_mapping, dialect=self.session.input_dialect, **kwargs)
 
     def getDatabase(self, dbName: str) -> Database:
         """Get the database with the specified name.

sqlframe/base/functions.py

@@ -856,15 +856,21 @@ def expr(str: str) -> Column:
 
 @meta(unsupported_engines=["postgres"])
 def struct(col: t.Union[ColumnOrName, t.Iterable[ColumnOrName]], *cols: ColumnOrName) -> Column:
-    from sqlframe.base.function_alternatives import struct_with_eq
-
     session = _get_session()
-
-    if session._is_snowflake:
-        return struct_with_eq(col, *cols)
-
-    columns = ensure_list(col) + list(cols)
-    return Column.invoke_expression_over_column(None, expression.Struct, expressions=columns)
+    col_func = get_func_from_session("col")
+
+    columns = [col_func(x) for x in ensure_list(col) + list(cols)]
+    expressions = []
+    for column in columns:
+        expressions.append(
+            expression.PropertyEQ(
+                this=expression.parse_identifier(
+                    column.alias_or_name, dialect=session.input_dialect
+                ),
+                expression=column.column_expression,
+            )
+        )
+    return Column(expression.Struct(expressions=expressions))
 
 
 @meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])

sqlframe/base/util.py

@@ -279,15 +279,6 @@ def verify_openai_installed():
         )
 
 
-def verify_numpy_installed():
-    try:
-        import numpy  # noqa
-    except ImportError:
-        raise ImportError(
-            """Numpy is required for this functionality. `pip install "sqlframe[pandas]"` (also include your engine if needed) to install pandas/numpy."""
-        )
-
-
 def quote_preserving_alias_or_name(col: t.Union[exp.Column, exp.Alias]) -> str:
     from sqlframe.base.session import _BaseSession
 

sqlframe/base/window.py

@@ -82,37 +82,26 @@ class WindowSpec:
     def _calc_start_end(
         self, start: int, end: int
     ) -> t.Dict[str, t.Optional[t.Union[str, exp.Expression]]]:
-        kwargs: t.Dict[str, t.Optional[t.Union[str, exp.Expression]]] = {
-            "start_side": None,
-            "end_side": None,
+        def get_value_and_side(x: int) -> t.Tuple[t.Union[str, exp.Expression], t.Optional[str]]:
+            if x == Window.currentRow:
+                return "CURRENT ROW", None
+            if x < 0:
+                side = "PRECEDING"
+                value = "UNBOUNDED" if x <= Window.unboundedPreceding else F.lit(abs(x)).expression
+                return value, side
+            else:
+                side = "FOLLOWING"
+                value = "UNBOUNDED" if x >= Window.unboundedFollowing else F.lit(x).expression
+                return value, side
+
+        start, start_side = get_value_and_side(start)  # type: ignore
+        end, end_side = get_value_and_side(end)  # type: ignore
+        return {
+            "start": start,  # type: ignore
+            "start_side": start_side,
+            "end": end,  # type: ignore
+            "end_side": end_side,
         }
-        if start == Window.currentRow:
-            kwargs["start"] = "CURRENT ROW"
-        else:
-            kwargs = {
-                **kwargs,
-                **{
-                    "start_side": "PRECEDING",
-                    "start": (
-                        "UNBOUNDED"
-                        if start <= Window.unboundedPreceding
-                        else F.lit(start).expression
-                    ),
-                },
-            }
-        if end == Window.currentRow:
-            kwargs["end"] = "CURRENT ROW"
-        else:
-            kwargs = {
-                **kwargs,
-                **{
-                    "end_side": "FOLLOWING",
-                    "end": (
-                        "UNBOUNDED" if end >= Window.unboundedFollowing else F.lit(end).expression
-                    ),
-                },
-            }
-        return kwargs
 
     def rowsBetween(self, start: int, end: int) -> WindowSpec:
         window_spec = self.copy()

sqlframe/duckdb/session.py

@@ -4,7 +4,7 @@ import typing as t
 from functools import cached_property
 
 from sqlframe.base.session import _BaseSession
-from sqlframe.base.util import soundex, verify_numpy_installed
+from sqlframe.base.util import soundex
 from sqlframe.duckdb.catalog import DuckDBCatalog
 from sqlframe.duckdb.dataframe import DuckDBDataFrame
 from sqlframe.duckdb.readwriter import (
@@ -46,8 +46,6 @@ class DuckDBSession(
         if not hasattr(self, "_conn"):
             conn = conn or duckdb.connect()
             try:
-                # Creating a function requires numpy to be installed so if they don't have it, we'll just skip it
-                verify_numpy_installed()
                 conn.create_function("SOUNDEX", lambda x: soundex(x), return_type=VARCHAR)
             except ImportError:
                 pass

{sqlframe-3.22.0.dist-info → sqlframe-3.23.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.22.0
+Version: 3.23.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -17,7 +17,7 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <26.7,>=24.0.0
+Requires-Dist: sqlglot <26.9,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -25,7 +25,7 @@ Requires-Dist: google-cloud-bigquery[pandas] <4,>=3 ; extra == 'bigquery'
 Provides-Extra: databricks
 Requires-Dist: databricks-sql-connector <5,>=3.6 ; extra == 'databricks'
 Provides-Extra: dev
-Requires-Dist: duckdb <1.2,>=0.9 ; extra == 'dev'
+Requires-Dist: duckdb <1.3,>=1.2 ; extra == 'dev'
 Requires-Dist: findspark <3,>=2 ; extra == 'dev'
 Requires-Dist: mypy <1.16,>=1.10.0 ; extra == 'dev'
 Requires-Dist: openai <2,>=1.30 ; extra == 'dev'
@@ -36,7 +36,7 @@ Requires-Dist: psycopg <4,>=3.1 ; extra == 'dev'
 Requires-Dist: pyarrow <20,>=10 ; extra == 'dev'
 Requires-Dist: pyspark <3.6,>=2 ; extra == 'dev'
 Requires-Dist: pytest-forked ; extra == 'dev'
-Requires-Dist: pytest-postgresql <7,>=6 ; extra == 'dev'
+Requires-Dist: pytest-postgresql <8,>=6 ; extra == 'dev'
 Requires-Dist: pytest-xdist <3.7,>=3.6 ; extra == 'dev'
 Requires-Dist: pytest <8.4,>=8.2.0 ; extra == 'dev'
 Requires-Dist: ruff <0.10,>=0.4.4 ; extra == 'dev'
@@ -48,7 +48,7 @@ Requires-Dist: mkdocs-material ==9.0.5 ; extra == 'docs'
 Requires-Dist: mkdocs ==1.4.2 ; extra == 'docs'
 Requires-Dist: pymdown-extensions ; extra == 'docs'
 Provides-Extra: duckdb
-Requires-Dist: duckdb <1.2,>=0.9 ; extra == 'duckdb'
+Requires-Dist: duckdb <1.3,>=1.2 ; extra == 'duckdb'
 Requires-Dist: pandas <3,>=2 ; extra == 'duckdb'
 Provides-Extra: openai
 Requires-Dist: openai <2,>=1.30 ; extra == 'openai'
@@ -59,7 +59,7 @@ Requires-Dist: psycopg2 <3,>=2.8 ; extra == 'postgres'
 Provides-Extra: redshift
 Requires-Dist: redshift-connector <2.2.0,>=2.1.1 ; extra == 'redshift'
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[secure-local-storage] <3.14,>=3.10.0 ; extra == 'snowflake'
+Requires-Dist: snowflake-connector-python[secure-local-storage] <3.15,>=3.10.0 ; extra == 'snowflake'
 Provides-Extra: spark
 Requires-Dist: pyspark <3.6,>=2 ; extra == 'spark'
 

{sqlframe-3.22.0.dist-info → sqlframe-3.23.0.dist-info}/RECORD

@@ -1,14 +1,14 @@
 sqlframe/__init__.py,sha256=wfqm98eLoLid9oV_FzzpG5loKC6LxOhj2lXpfN7SARo,3138
-sqlframe/_version.py,sha256=z_95mpOa--N235aXeiPpCYjkuWuYr-3uQDssTEpMtnc,413
+sqlframe/_version.py,sha256=LBEtYNWSnG3GH8sBUqzbBkvKuUnJ78uz2Pmt2SqvhMY,513
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=b2clI5HI1zEZKB_3Msx3FeAJQyft44ubUifJwQRVXyQ,1298
-sqlframe/base/catalog.py,sha256=SzFQalTWdhWzxUY-4ut1f9TfOECp_JmJEgNPfrRKCe0,38457
+sqlframe/base/catalog.py,sha256=D39Mn4AIkUyaVyLJiI5gcX0Bv_pChl89GAyYHrtOw5g,38513
 sqlframe/base/column.py,sha256=oHVwkSWABO3ZlAbgBShsxSSlgbI06BOup5XJrRhgqJI,18097
 sqlframe/base/dataframe.py,sha256=9wcN5I5bSiGKs6m-mSCwlDUSRfrZ_ymfRUtJa8hggd4,83990
 sqlframe/base/decorators.py,sha256=ms-CvDOIW3T8IVB9VqDmLwAiaEsqXLYRXEqVQaxktiM,1890
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=KFkEm0aIHzajvQmiPZnzTLh-Ud9wjeg4lJ4Rk0vk-YU,53674
-sqlframe/base/functions.py,sha256=0lLefa959J1z7Ea6QBnQrru06lKCLurEX1xFYxGJbTc,223082
+sqlframe/base/functions.py,sha256=gWUxngV4cgbPvKqK7_N-2rYGycRyoKJnZqPfFyqIgbE,223305
 sqlframe/base/group.py,sha256=fsyG5990_Pd7gFPjTFrH9IEoAquL_wEkVpIlBAIkZJU,4091
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=xSPw74e59wYvNd6U1AlwziNCTG6Aftrbl4SybN9u9VE,3450
@@ -18,8 +18,8 @@ sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
 sqlframe/base/types.py,sha256=iBNk9bpFtb2NBIogYS8i7OlQZMRvpR6XxqzBebsjQDU,12280
 sqlframe/base/udf.py,sha256=O6hMhBUy9NVv-mhJRtfFhXTIa_-Z8Y_FkmmuOHu0l90,1117
-sqlframe/base/util.py,sha256=RmeAqsZEb1zlUEvlRXJnOcDEWJC7OOYEw229s3LzpFA,15805
-sqlframe/base/window.py,sha256=8hOv-ignPPIsZA9FzvYzcLE9J_glalVaYjIAUdRUX3o,4943
+sqlframe/base/util.py,sha256=QktpGRlkYsapQRs_uhuc3T736qRry2PNE7kcPxjYefo,15519
+sqlframe/base/window.py,sha256=vmQEUa3FnaDmdce2f3xzskOJe7XsZ7JhMyOIR4RdJuY,4806
 sqlframe/base/mixins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/mixins/catalog_mixins.py,sha256=9tn0mK8oPoqIIjNItystD5tdBMdK9YpkxTG7G9KQl8k,18619
 sqlframe/base/mixins/dataframe_mixins.py,sha256=9U556vWjhmAwnbqkQ4mDkKHxQRs-FkncwEEY9RWmm6U,1408
@@ -59,7 +59,7 @@ sqlframe/duckdb/functions.py,sha256=ix2efGGD4HLaY1rtCtEd3IrsicGEVGiBAeKOo5OD8rA,
 sqlframe/duckdb/functions.pyi,sha256=P0ky6k-J7LdCDrQ0OjfRC3ARIYNHPmAmmaB_jBEO5L0,12383
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
 sqlframe/duckdb/readwriter.py,sha256=-_Ama7evadIa3PYvynKDK6RcTMTDBHpHJzfANTine7g,4983
-sqlframe/duckdb/session.py,sha256=Uf7im6eBbBYRvIhVGV0VCTCF76FQ00A5FbKPCdNllzw,2898
+sqlframe/duckdb/session.py,sha256=H1qjMYmhpwUHmf6jOPA6IhPIEIeX8rlvOl3MTIEijG0,2719
 sqlframe/duckdb/table.py,sha256=AmEKoH2TZo98loS5NbNaTuqv0eg76SY_OckVBMmQ6Co,410
 sqlframe/duckdb/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/duckdb/udf.py,sha256=Du9LnOtT1lJvB90D4HSR2tB7MXy179jZngDR-EjVjQk,656
@@ -129,8 +129,8 @@ sqlframe/standalone/udf.py,sha256=azmgtUjHNIPs0WMVNId05SHwiYn41MKVBhKXsQJ5dmY,27
 sqlframe/standalone/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/testing/__init__.py,sha256=VVCosQhitU74A3NnE52O4mNtGZONapuEXcc20QmSlnQ,132
 sqlframe/testing/utils.py,sha256=PFsGZpwNUE_4-g_f43_vstTqsK0AQ2lBneb5Eb6NkFo,13008
-sqlframe-3.22.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.22.0.dist-info/METADATA,sha256=uN5N8oTC6EkNmVWzBgxkT_Ri1eIgTN3XIaC7VH3_zL4,8970
-sqlframe-3.22.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.22.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.22.0.dist-info/RECORD,,
+sqlframe-3.23.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.23.0.dist-info/METADATA,sha256=li6TMha72t0_876a0_gTA6ckfhiYptkeNrTtZL4c4M0,8970
+sqlframe-3.23.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.23.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.23.0.dist-info/RECORD,,