sqlframe 3.2.0__py3-none-any.whl → 3.3.0__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.2.0'
-__version_tuple__ = version_tuple = (3, 2, 0)
+__version__ = version = '3.3.0'
+__version_tuple__ = version_tuple = (3, 3, 0)

sqlframe/base/dataframe.py

@@ -1627,7 +1627,11 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     def createOrReplaceTempView(self, name: str) -> None:
         name = normalize_string(name, from_dialect="input")
-        self.session.temp_views[name] = self.copy()._convert_leaf_to_cte()
+        df = self.copy()._convert_leaf_to_cte()
+        self.session.temp_views[name] = df
+        self.session.catalog.add_table(
+            name, [x.alias_or_name for x in self._get_outer_select_columns(df.expression)]
+        )
 
     def count(self) -> int:
         if not self.session._has_connection:

sqlframe/base/functions.py

@@ -2052,7 +2052,7 @@ def cardinality(col: ColumnOrName) -> Column:
 
 @meta()
 def char(col: ColumnOrName) -> Column:
-    return Column.invoke_expression_over_column(col, expression.Chr)
+    return Column(expression.Chr(expressions=Column.ensure_col(col).expression))
 
 
 @meta(unsupported_engines="*")
@@ -2703,7 +2703,7 @@ def inline(col: ColumnOrName) -> Column:
     |  3|  4|
     +---+---+
     """
-    return Column.invoke_anonymous_function(col, "inline")
+    return Column.invoke_expression_over_column(col, expression.Inline)
 
 
 @meta(unsupported_engines="*")

sqlframe/base/session.py

@@ -391,7 +391,11 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, CONN, UDF_REGISTRATION
         )
         if qualify:
             expression = qualify_func(
-                expression, dialect=dialect, quote_identifiers=False, identify=False
+                expression,
+                dialect=dialect,
+                quote_identifiers=False,
+                identify=False,
+                schema=self.catalog._schema,
             )
         if self.temp_views:
             replacement_mapping = {}

sqlframe/base/util.py

@@ -306,7 +306,6 @@ def quote_preserving_alias_or_name(col: t.Union[exp.Column, exp.Alias]) -> str:
 def sqlglot_to_spark(sqlglot_dtype: exp.DataType) -> types.DataType:
     from sqlframe.base import types
 
-    sqlglot_to_spark
     primitive_mapping = {
         exp.DataType.Type.VARCHAR: types.VarcharType,
         exp.DataType.Type.CHAR: types.CharType,
@@ -325,6 +324,7 @@ def sqlglot_to_spark(sqlglot_dtype: exp.DataType) -> types.DataType:
         exp.DataType.Type.TIMESTAMPLTZ: types.TimestampType,
         exp.DataType.Type.TIMESTAMPNTZ: types.TimestampType,
         exp.DataType.Type.DATE: types.DateType,
+        exp.DataType.Type.JSON: types.StringType,
     }
     if sqlglot_dtype.this in primitive_mapping:
         pyspark_class = primitive_mapping[sqlglot_dtype.this]

sqlframe/duckdb/readwriter.py

@@ -93,6 +93,8 @@ class DuckDBDataFrameReader(_BaseDataFrameReader["DuckDBSession", "DuckDBDataFra
         else:
             from_clause = f"'{path}'"
         df = self.session.sql(exp.select(*select_columns).from_(from_clause), qualify=False)
+        if select_columns == [exp.Star()]:
+            return self.load(path=path, format=format, schema=df.schema, **options)
         self.session._last_loaded_file = path  # type: ignore
         return df
 

sqlframe/duckdb/session.py

@@ -54,8 +54,14 @@ class DuckDBSession(
 
     @classmethod
     def _try_get_map(cls, value: t.Any) -> t.Optional[t.Dict[str, t.Any]]:
-        if value and isinstance(value, dict) and "key" in value and "value" in value:
-            return dict(zip(value["key"], value["value"]))
+        if value and isinstance(value, dict):
+            # DuckDB < 1.1.0 support
+            if "key" in value and "value" in value:
+                return dict(zip(value["key"], value["value"]))
+            # DuckDB >= 1.1.0 support
+            # If a key is not a string then it must not represent a column and therefore must be a map
+            if len([k for k in value if not isinstance(k, str)]) > 0:
+                return value
         return None
 
     def _execute(self, sql: str) -> None:

sqlframe/spark/catalog.py

@@ -569,7 +569,9 @@ class SparkCatalog(
         return [
             Table(
                 name=normalize_string(x.name, from_dialect="execution", to_dialect="output"),
-                catalog=normalize_string(x.catalog, from_dialect="execution", to_dialect="output"),
+                catalog=normalize_string(x.catalog, from_dialect="execution", to_dialect="output")
+                if x.catalog
+                else None,
                 namespace=[
                     normalize_string(y, from_dialect="execution", to_dialect="output")
                     for y in x.namespace

{sqlframe-3.2.0.dist-info → sqlframe-3.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.2.0
+Version: 3.3.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -18,16 +18,16 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable (<3.11.1)
-Requires-Dist: sqlglot (<25.19,>=24.0.0)
+Requires-Dist: sqlglot (<25.22,>=24.0.0)
 Requires-Dist: typing-extensions (<5,>=4.8)
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage (<3,>=2) ; extra == 'bigquery'
 Requires-Dist: google-cloud-bigquery[pandas] (<4,>=3) ; extra == 'bigquery'
 Provides-Extra: dev
-Requires-Dist: duckdb (<1.1,>=0.9) ; extra == 'dev'
+Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'dev'
 Requires-Dist: findspark (<3,>=2) ; extra == 'dev'
 Requires-Dist: mypy (<1.12,>=1.10.0) ; extra == 'dev'
-Requires-Dist: openai (<1.44,>=1.30) ; extra == 'dev'
+Requires-Dist: openai (<1.46,>=1.30) ; extra == 'dev'
 Requires-Dist: pandas-stubs (<3,>=2) ; extra == 'dev'
 Requires-Dist: pandas (<3,>=2) ; extra == 'dev'
 Requires-Dist: psycopg (<4,>=3.1) ; extra == 'dev'
@@ -47,10 +47,10 @@ 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 (<1.1,>=0.9) ; extra == 'duckdb'
+Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'duckdb'
 Requires-Dist: pandas (<3,>=2) ; extra == 'duckdb'
 Provides-Extra: openai
-Requires-Dist: openai (<1.44,>=1.30) ; extra == 'openai'
+Requires-Dist: openai (<1.46,>=1.30) ; extra == 'openai'
 Provides-Extra: pandas
 Requires-Dist: pandas (<3,>=2) ; extra == 'pandas'
 Provides-Extra: postgres

{sqlframe-3.2.0.dist-info → sqlframe-3.3.0.dist-info}/RECORD

@@ -1,23 +1,23 @@
 sqlframe/__init__.py,sha256=E3qCJ4PSEgKz6Hg3ves6LWt3JrQOV8c9HVLSIUOzKNc,3106
-sqlframe/_version.py,sha256=h7Mhoil_jhKLMf7jtmaacYtrq1Z2IqB7uz4QBaHSlmw,411
+sqlframe/_version.py,sha256=gpz3Z6rZZLQ9xMKGzMu1kjC8nYs9HNBbzDT8oHplFPY,411
 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/column.py,sha256=C2xj6OHMsJbEgjbI-m5HuIvqHYt2DbbUtCjssKpplNk,17748
-sqlframe/base/dataframe.py,sha256=wIYKaV9xzILPVmAcujvRmbH-6dbKPx6hVNHNWCEuayM,71479
+sqlframe/base/dataframe.py,sha256=uTM46auSPniww-ZMtI5s0hrrCG1nOICMEhdZZ8E4cu8,71636
 sqlframe/base/decorators.py,sha256=Jy4bf8MhZ-AJ6CWTj59bBJRqamtLbPC0USUMFrY6g0w,449
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=IxNBqplehkAEkpzA625Dif-9Xyi4Hrho81A9U262rV0,50714
-sqlframe/base/functions.py,sha256=2dDfPepAuQvLcxwaZbj9qJeEeiqOaYJDI3vPoZXoM1Q,189959
+sqlframe/base/functions.py,sha256=p1aVgQ3htTLR5-mDzDtEh7W3iTcbt_XOOljLpza-dF8,189984
 sqlframe/base/group.py,sha256=fsyG5990_Pd7gFPjTFrH9IEoAquL_wEkVpIlBAIkZJU,4091
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=-AhNuEzcV7ZExoP1oY3blaKip-joQyJeQVvfBTs_2g4,3456
 sqlframe/base/readerwriter.py,sha256=FkImnUR_qNASmXktk0JDsFeOzfh799hd09vI2uznNH8,25350
-sqlframe/base/session.py,sha256=DgkzSKFc3LdzXiqB9ofsh47Ygivq2-Or6J2XbDLzxVs,25162
+sqlframe/base/session.py,sha256=6vQ2bJa357J1bycx1vMxkIUdcA2YbMIYq956bpytztI,25256
 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=ktQfPBcYyXXLPWCOg9Gg_acjMc83xNykC8CFjuqGU5E,14879
+sqlframe/base/util.py,sha256=9f_PpaQTDOrdKVAZeGdK9s5KQ_fL2vM8A2uulo-E1Pg,14908
 sqlframe/base/window.py,sha256=8hOv-ignPPIsZA9FzvYzcLE9J_glalVaYjIAUdRUX3o,4943
 sqlframe/base/mixins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/mixins/catalog_mixins.py,sha256=9tn0mK8oPoqIIjNItystD5tdBMdK9YpkxTG7G9KQl8k,18619
@@ -42,8 +42,8 @@ sqlframe/duckdb/dataframe.py,sha256=HZg_uMAz4RsubZJT4-MslUQS_0-InF0_P5Yq5HyJ3wE,
 sqlframe/duckdb/functions.py,sha256=Ee8o6YFtRdEiq0jNLXxgu5lcbc7Tsg0-lK6oRyxdcjo,1920
 sqlframe/duckdb/functions.pyi,sha256=Qn6j4zwwuBsh6q9341dR3Z5kpeRsgvM4u6Bb6FekKrI,5827
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
-sqlframe/duckdb/readwriter.py,sha256=jcb3WJClTtdQEJPKmVfNZ2lOR1h_2jTB0OgdMFp4POw,4679
-sqlframe/duckdb/session.py,sha256=Pho9H74_0xNQPP_oBdFa4aflBAsrxvpXPMQGSKyq1-4,2322
+sqlframe/duckdb/readwriter.py,sha256=iY0Wsms35gymilETOhAQGQCHfH8LCj9_uY8aCdF77ds,4806
+sqlframe/duckdb/session.py,sha256=h0gr4hzGTLTSYN2OECAYjb8HHh2QvSshInxAIUjEEs8,2615
 sqlframe/duckdb/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/duckdb/udf.py,sha256=Du9LnOtT1lJvB90D4HSR2tB7MXy179jZngDR-EjVjQk,656
 sqlframe/duckdb/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
@@ -83,7 +83,7 @@ sqlframe/snowflake/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,3
 sqlframe/snowflake/udf.py,sha256=yzMmky-n5BXFbdldgfzLP8hCrVm0DgruSUCUUy1_3sk,268
 sqlframe/snowflake/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/spark/__init__.py,sha256=QV0eNmY5fL4ulLvAJVVVx2OYFfQXN2KYV3R5cij7HTg,858
-sqlframe/spark/catalog.py,sha256=3T4aivgQmAhPTmlVk53jk3VvFBJlp1pKvWKNmTHz1W8,39741
+sqlframe/spark/catalog.py,sha256=8ghHiKz9rBJ2ohm768XIftyi9Htbw-1cSkJUlXemwrI,39796
 sqlframe/spark/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/spark/dataframe.py,sha256=_TD-h7oz0-i80r90v17UoLDoIzcGNchU2SL13ujOOic,1779
 sqlframe/spark/functions.py,sha256=AQfqfvaojJzCuo9DyDklz0JYZPhn_3dzWvztsklBO0o,586
@@ -107,8 +107,8 @@ 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=9DDYVuocO7tygee3RaajuJNZ24sJwf_LY556kKg7kTw,13011
-sqlframe-3.2.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.2.0.dist-info/METADATA,sha256=Vy6QKjJpatavSw884IL6gUeeT0ZZDmHyEPQvJEdACpM,8639
-sqlframe-3.2.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-3.2.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.2.0.dist-info/RECORD,,
+sqlframe-3.3.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.3.0.dist-info/METADATA,sha256=-o2sCV3CNc0IaqRVHFf84JAqkX63l-l9sZne6A7xsyI,8639
+sqlframe-3.3.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+sqlframe-3.3.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.3.0.dist-info/RECORD,,