sqlframe 1.1.3__py3-none-any.whl → 1.2.0__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.1.3'
-__version_tuple__ = version_tuple = (1, 1, 3)
+__version__ = version = '1.2.0'
+__version_tuple__ = version_tuple = (1, 2, 0)

sqlframe/base/catalog.py

@@ -26,6 +26,9 @@ else:
 class _BaseCatalog(t.Generic[SESSION, DF]):
     """User-facing catalog API, accessible through `SparkSession.catalog`."""
 
+    TEMP_CATALOG_FILTER: t.Optional[exp.Expression] = None
+    TEMP_SCHEMA_FILTER: t.Optional[exp.Expression] = None
+
     def __init__(self, sparkSession: SESSION, schema: t.Optional[MappingSchema] = None) -> None:
         """Create a new Catalog that wraps the underlying JVM object."""
         self.session = sparkSession
@@ -569,7 +572,9 @@ class _BaseCatalog(t.Generic[SESSION, DF]):
         """
         raise NotImplementedError
 
-    def listColumns(self, tableName: str, dbName: t.Optional[str] = None) -> t.List[Column]:
+    def listColumns(
+        self, tableName: str, dbName: t.Optional[str] = None, include_temp: bool = False
+    ) -> t.List[Column]:
         """Returns a t.List of columns for the given table/view in the specified database.
 
         .. versionadded:: 2.0.0

sqlframe/base/mixins/catalog_mixins.py

@@ -315,7 +315,9 @@ class ListTablesFromInfoSchemaMixin(_BaseInfoSchemaMixin, t.Generic[SESSION, DF]
 
 class ListColumnsFromInfoSchemaMixin(_BaseInfoSchemaMixin, t.Generic[SESSION, DF]):
     @normalize(["tableName", "dbName"])
-    def listColumns(self, tableName: str, dbName: t.Optional[str] = None) -> t.List[Column]:
+    def listColumns(
+        self, tableName: str, dbName: t.Optional[str] = None, include_temp: bool = False
+    ) -> t.List[Column]:
         """Returns a t.List of columns for the given table/view in the specified database.
 
         .. versionadded:: 2.0.0
@@ -385,12 +387,6 @@ class ListColumnsFromInfoSchemaMixin(_BaseInfoSchemaMixin, t.Generic[SESSION, DF
                     "catalog",
                     exp.parse_identifier(self.currentCatalog(), dialect=self.session.input_dialect),
                 )
-        # if self.QUALIFY_INFO_SCHEMA_WITH_DATABASE:
-        #     if not table.db:
-        #         raise ValueError("dbName must be specified when listing columns from INFORMATION_SCHEMA")
-        #     source_table = f"{table.db}.INFORMATION_SCHEMA.COLUMNS"
-        # else:
-        #     source_table = "INFORMATION_SCHEMA.COLUMNS"
         source_table = self._get_info_schema_table("columns", database=table.db)
         select = (
             exp.select(
@@ -402,9 +398,15 @@ class ListColumnsFromInfoSchemaMixin(_BaseInfoSchemaMixin, t.Generic[SESSION, DF
             .where(exp.column("table_name").eq(table.name))
         )
         if table.db:
-            select = select.where(exp.column("table_schema").eq(table.db))
+            schema_filter: exp.Expression = exp.column("table_schema").eq(table.db)
+            if include_temp and self.TEMP_SCHEMA_FILTER:
+                schema_filter = exp.Or(this=schema_filter, expression=self.TEMP_SCHEMA_FILTER)
+            select = select.where(schema_filter)
         if table.catalog:
-            select = select.where(exp.column("table_catalog").eq(table.catalog))
+            catalog_filter: exp.Expression = exp.column("table_catalog").eq(table.catalog)
+            if include_temp and self.TEMP_CATALOG_FILTER:
+                catalog_filter = exp.Or(this=catalog_filter, expression=self.TEMP_CATALOG_FILTER)
+            select = select.where(catalog_filter)
         results = self.session._fetch_rows(select)
         return [
             Column(

sqlframe/base/mixins/dataframe_mixins.py

@@ -0,0 +1,63 @@
+import typing as t
+
+from sqlglot import exp
+
+from sqlframe.base.catalog import Column
+from sqlframe.base.dataframe import (
+    GROUP_DATA,
+    NA,
+    SESSION,
+    STAT,
+    WRITER,
+    _BaseDataFrame,
+)
+
+
+class PrintSchemaFromTempObjectsMixin(
+    _BaseDataFrame, t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]
+):
+    def _get_columns_from_temp_object(self) -> t.List[Column]:
+        table = exp.to_table(self.session._random_id)
+        self.session._execute(
+            exp.Create(
+                this=table,
+                kind="VIEW",
+                replace=True,
+                properties=exp.Properties(expressions=[exp.TemporaryProperty()]),
+                expression=self.expression,
+            )
+        )
+        return self.session.catalog.listColumns(
+            table.sql(dialect=self.session.input_dialect), include_temp=True
+        )
+
+    def printSchema(self, level: t.Optional[int] = None) -> None:
+        def print_schema(
+            column_name: str, column_type: exp.DataType, nullable: bool, current_level: int
+        ):
+            if level and current_level >= level:
+                return
+            if current_level > 0:
+                print(" |   " * current_level, end="")
+            print(
+                f" |-- {column_name}: {column_type.sql(self.session.output_dialect).lower()} (nullable = {str(nullable).lower()})"
+            )
+            if column_type.this == exp.DataType.Type.STRUCT:
+                for column_def in column_type.expressions:
+                    print_schema(column_def.name, column_def.args["kind"], True, current_level + 1)
+            if column_type.this == exp.DataType.Type.ARRAY:
+                for data_type in column_type.expressions:
+                    print_schema("element", data_type, True, current_level + 1)
+            if column_type.this == exp.DataType.Type.MAP:
+                print_schema("key", column_type.expressions[0], True, current_level + 1)
+                print_schema("value", column_type.expressions[1], True, current_level + 1)
+
+        columns = self._get_columns_from_temp_object()
+        print("root")
+        for column in columns:
+            print_schema(
+                column.name,
+                exp.DataType.build(column.dataType, dialect=self.session.output_dialect),
+                column.nullable,
+                0,
+            )

sqlframe/bigquery/catalog.py

@@ -46,7 +46,9 @@ class BigQueryCatalog(
         return to_schema(self.session.default_dataset).db
 
     @normalize(["tableName", "dbName"])
-    def listColumns(self, tableName: str, dbName: t.Optional[str] = None) -> t.List[Column]:
+    def listColumns(
+        self, tableName: str, dbName: t.Optional[str] = None, include_temp: bool = False
+    ) -> t.List[Column]:
         """Returns a t.List of columns for the given table/view in the specified database.
 
         .. versionadded:: 2.0.0

sqlframe/duckdb/catalog.py

@@ -36,6 +36,8 @@ class DuckDBCatalog(
     ListColumnsFromInfoSchemaMixin["DuckDBSession", "DuckDBDataFrame"],
     _BaseCatalog["DuckDBSession", "DuckDBDataFrame"],
 ):
+    TEMP_CATALOG_FILTER = exp.column("table_catalog").eq("temp")
+
     def listFunctions(
         self, dbName: t.Optional[str] = None, pattern: t.Optional[str] = None
     ) -> t.List[Function]:

sqlframe/duckdb/dataframe.py

@@ -9,6 +9,7 @@ from sqlframe.base.dataframe import (
     _BaseDataFrameNaFunctions,
     _BaseDataFrameStatFunctions,
 )
+from sqlframe.base.mixins.dataframe_mixins import PrintSchemaFromTempObjectsMixin
 from sqlframe.duckdb.group import DuckDBGroupedData
 
 if sys.version_info >= (3, 11):
@@ -34,13 +35,14 @@ class DuckDBDataFrameStatFunctions(_BaseDataFrameStatFunctions["DuckDBDataFrame"
 
 
 class DuckDBDataFrame(
+    PrintSchemaFromTempObjectsMixin,
     _BaseDataFrame[
         "DuckDBSession",
         "DuckDBDataFrameWriter",
         "DuckDBDataFrameNaFunctions",
         "DuckDBDataFrameStatFunctions",
         "DuckDBGroupedData",
-    ]
+    ],
 ):
     _na = DuckDBDataFrameNaFunctions
     _stat = DuckDBDataFrameStatFunctions

sqlframe/postgres/catalog.py

@@ -34,6 +34,7 @@ class PostgresCatalog(
     _BaseCatalog["PostgresSession", "PostgresDataFrame"],
 ):
     CURRENT_CATALOG_EXPRESSION: exp.Expression = exp.column("current_catalog")
+    TEMP_SCHEMA_FILTER = exp.column("table_schema").like("pg_temp_%")
 
     def listFunctions(
         self, dbName: t.Optional[str] = None, pattern: t.Optional[str] = None

sqlframe/postgres/dataframe.py

@@ -9,6 +9,7 @@ from sqlframe.base.dataframe import (
     _BaseDataFrameNaFunctions,
     _BaseDataFrameStatFunctions,
 )
+from sqlframe.base.mixins.dataframe_mixins import PrintSchemaFromTempObjectsMixin
 from sqlframe.postgres.group import PostgresGroupedData
 
 if sys.version_info >= (3, 11):
@@ -33,13 +34,14 @@ class PostgresDataFrameStatFunctions(_BaseDataFrameStatFunctions["PostgresDataFr
 
 
 class PostgresDataFrame(
+    PrintSchemaFromTempObjectsMixin,
     _BaseDataFrame[
         "PostgresSession",
         "PostgresDataFrameWriter",
         "PostgresDataFrameNaFunctions",
         "PostgresDataFrameStatFunctions",
         "PostgresGroupedData",
-    ]
+    ],
 ):
     _na = PostgresDataFrameNaFunctions
     _stat = PostgresDataFrameStatFunctions

sqlframe/spark/catalog.py

@@ -468,7 +468,9 @@ class SparkCatalog(
                 )
         return [Table(*x) for x in self._spark_catalog.listTables(dbName, pattern)]
 
-    def listColumns(self, tableName: str, dbName: t.Optional[str] = None) -> t.List[Column]:
+    def listColumns(
+        self, tableName: str, dbName: t.Optional[str] = None, include_temp: bool = False
+    ) -> t.List[Column]:
         """Returns a t.List of columns for the given table/view in the specified database.
 
         .. versionadded:: 2.0.0

{sqlframe-1.1.3.dist-info → sqlframe-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.1.3
+Version: 1.2.0
 Summary: Taking the Spark out of PySpark by converting to SQL
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-1.1.3.dist-info → sqlframe-1.2.0.dist-info}/RECORD

@@ -1,8 +1,8 @@
 sqlframe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sqlframe/_version.py,sha256=HwUMBHweBEaQ6rszqbo52qsXT3x6N8a86Dx1PmA5rxM,411
+sqlframe/_version.py,sha256=zMnMemknXglcJs59xkicNzeEJTVgYd1omSfLWj76yWw,411
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=DuTay8-o9W-pw3RPZCgLunKNJLS9PkaV11G_pxXp9NY,1256
-sqlframe/base/catalog.py,sha256=jbEuY1wje4oPRuFSMgKdX-yTohBL99S57QuHhUXCybI,37085
+sqlframe/base/catalog.py,sha256=ATDGirouUjal05P4ymL-wIi8rgjg_8w4PoACamiO64A,37245
 sqlframe/base/column.py,sha256=1xFwPhBlzdO6ZL9tTpPESL7B3XQ3rFMPIoBekFm0TqM,15109
 sqlframe/base/dataframe.py,sha256=cFaJupLZflakMfwcR_KsrxtinV8ZckRZGRjWzx1vBs8,59136
 sqlframe/base/decorators.py,sha256=fnqT1Hqa0J_gUurDcVY1Dcscj6SXFxFJ5PKAw-xe5sU,2097
@@ -19,10 +19,11 @@ sqlframe/base/types.py,sha256=aJT5YXr-M_LAfUM0uK4asfbrQFab_xmsp1CP2zkG8p0,11924
 sqlframe/base/util.py,sha256=SeUC2pcSBGnsS1W5PL1p-IGC6bJG8_2a7En2hxSTmpA,7597
 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=ZNzNn-cWB0RwT7L1KZCWYke2JlP-cZze0MDNOzSfHew,14093
+sqlframe/base/mixins/catalog_mixins.py,sha256=arO9psYkFULnRi2-3XnnWJBYf_nwbU52fa0nEaRU4aE,14225
+sqlframe/base/mixins/dataframe_mixins.py,sha256=U2tKIY5pCLnoPy1boAQ1YWLgK1E-ZT4x47oRWtGoYLQ,2360
 sqlframe/base/mixins/readwriter_mixins.py,sha256=N2nsXOG3A2j6O3N195U-_fYOZMkqfifGcfduxODUcxs,4656
 sqlframe/bigquery/__init__.py,sha256=i2NsMbiXOj2xphCtPuNk6cVw4iYeq5_B1I9dVI9aGAk,712
-sqlframe/bigquery/catalog.py,sha256=HdRXZfZczoyLHEQ0y30nfCFKBvTTOJ1s6t0mafN_bGk,9277
+sqlframe/bigquery/catalog.py,sha256=h3aQAQAJg6MMvFpP8Ku0S4pcx30n5qYrqHhWSomxb6A,9319
 sqlframe/bigquery/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/bigquery/dataframe.py,sha256=fPQ6043aSS_ds30WsvrYOgNZJPH0jq7BeNHGLQ2MEW4,1372
 sqlframe/bigquery/functions.py,sha256=RF8yG_4MS3at_60V0NNTE5ADERJZa7kZGYFWI4ST3jM,11149
@@ -32,9 +33,9 @@ sqlframe/bigquery/session.py,sha256=1-hE1Wr2b6SqfD4M_-OGMqjaSbhD6wSQd74v71xHZv8,
 sqlframe/bigquery/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/bigquery/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/duckdb/__init__.py,sha256=t85TA3ufZtL1weQNFmEs8itCSwbJFtw03-p0GT4XGf8,669
-sqlframe/duckdb/catalog.py,sha256=SR1JWPGKjNJ2Dq2au-4rZAadPYr8Zn4WsK5EYKRyFm4,3829
+sqlframe/duckdb/catalog.py,sha256=rt3XuP3m4DbhuibOFyvx_95F2zZa6uDwCI_TmcvKy1A,3895
 sqlframe/duckdb/column.py,sha256=wkEPcp3xVsH5nC3kpacXqNkRv9htPtBgt-0uFRxIRNs,56
-sqlframe/duckdb/dataframe.py,sha256=9T6GV4JScaApFSA4T7fixot78HMUgkjGxU7TgjolOOM,1410
+sqlframe/duckdb/dataframe.py,sha256=RPdXSOv_wCB0R5E5fzRMYOGFHilb4egqRk3UgiT6WEU,1530
 sqlframe/duckdb/functions.py,sha256=srvzbk_Wg-wQPFGYp624dRDyYJghi47M8E-Tu7pBdY0,1507
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
 sqlframe/duckdb/readwriter.py,sha256=6xiyE3JKzY9ieKqvbAOBlifiHE6NpYISHul3Idlmoa0,4542
@@ -42,9 +43,9 @@ sqlframe/duckdb/session.py,sha256=TCAVsSqBGGj1Otb2iIkSkWqjbzzg1MeDAafGN928-O8,18
 sqlframe/duckdb/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/duckdb/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/postgres/__init__.py,sha256=Sz_MtgV_oh_QhfZTC7iKM07ICUmNcJEDV0kEkSW9ZKU,712
-sqlframe/postgres/catalog.py,sha256=4f4Ytacfn0Q3xnT0MWUeEYPq4SwNPdS1EmRc2fBK9yc,3652
+sqlframe/postgres/catalog.py,sha256=L5heEav8PTtKJDofJTf-51_cCLpZud5lDvZC-RFZIaw,3722
 sqlframe/postgres/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
-sqlframe/postgres/dataframe.py,sha256=bv_y9D9w03x-sfLdippb8n4goFQGazg1j0gZEPHe98k,1372
+sqlframe/postgres/dataframe.py,sha256=feGvQo7GD-YGmWWGc5h94CMVZm0gcgUQsdlAktXS4Ac,1492
 sqlframe/postgres/functions.py,sha256=UNL7dE6LmzekvolwqWB-aFt8ITamxeSfuG50_NP_G8c,2133
 sqlframe/postgres/group.py,sha256=KUXeSFKWTSH9yCRJAhW85OvjZaG6Zr4In9LR_ie3yGU,391
 sqlframe/postgres/readwriter.py,sha256=L1e3yKXzFVNR_W5s1DHaWol7G8x7l4jcZ5sLGualyMk,870
@@ -72,7 +73,7 @@ sqlframe/snowflake/session.py,sha256=oJK_3t43TeUiAj7KBfn2lD5d6AVHWsI39xLu-j_h5QM
 sqlframe/snowflake/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/snowflake/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/spark/__init__.py,sha256=jamKYQtQaKjjXnQ01QGPHvatbrZSw9sWno_VOUGSz6I,712
-sqlframe/spark/catalog.py,sha256=nqiZf14m2-PPbZALLlSgvLnpLqSskNnAiZz_ccI-nPs,32484
+sqlframe/spark/catalog.py,sha256=YeWBCUlkkhf2jDcmaFo-JvG4DQ6Daqyy1zEnVBx5gMo,32526
 sqlframe/spark/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/spark/dataframe.py,sha256=V3z5Bx9snLgYh4bDwJfJb5mj1P7UsZF8DMlLwZXopBg,1309
 sqlframe/spark/functions.py,sha256=eSGMM2DXcj17nIPH5ZDLG95ZMuE7F8Qvn0IqGO_wQVw,586
@@ -91,8 +92,8 @@ sqlframe/standalone/readwriter.py,sha256=EZNyDJ4ID6sGNog3uP4-e9RvchX4biJJDNtc5hk
 sqlframe/standalone/session.py,sha256=wQmdu2sv6KMTAv0LRFk7TY7yzlh3xvmsyqilEtRecbY,1191
 sqlframe/standalone/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/standalone/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
-sqlframe-1.1.3.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-1.1.3.dist-info/METADATA,sha256=-RpQ4lc5QSV9FvW0fau0TeW9in4ahPR2urnOGukAUXk,6873
-sqlframe-1.1.3.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-1.1.3.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-1.1.3.dist-info/RECORD,,
+sqlframe-1.2.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-1.2.0.dist-info/METADATA,sha256=KguQN7Rfbq_cqfdxvu28gdyMfisTRZ6-DVOCAt31Q2Y,6873
+sqlframe-1.2.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+sqlframe-1.2.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-1.2.0.dist-info/RECORD,,