sqlframe 1.7.0__py3-none-any.whl → 1.8.0__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.7.0'
-__version_tuple__ = version_tuple = (1, 7, 0)
+__version__ = version = '1.8.0'
+__version_tuple__ = version_tuple = (1, 8, 0)

sqlframe/base/functions.py

@@ -151,9 +151,10 @@ def sumDistinct(col: ColumnOrName) -> Column:
 sum_distinct = sumDistinct
 
 
-@meta(unsupported_engines="*")
-def product(col: ColumnOrName) -> Column:
-    raise NotImplementedError("Product is not currently implemented")
+# Product does not have a SQL function available
+# @meta(unsupported_engines="*")
+# def product(col: ColumnOrName) -> Column:
+# raise NotImplementedError("Product is not currently implemented")
 
 
 @meta()
@@ -1430,6 +1431,8 @@ def to_json(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = None) ->
 
 @meta(unsupported_engines="*")
 def schema_of_json(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = None) -> Column:
+    if isinstance(col, str):
+        col = lit(col)
     if options is not None:
         options_col = create_map([lit(x) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "SCHEMA_OF_JSON", options_col)
@@ -1438,6 +1441,8 @@ def schema_of_json(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = No
 
 @meta(unsupported_engines="*")
 def schema_of_csv(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = None) -> Column:
+    if isinstance(col, str):
+        col = lit(col)
     if options is not None:
         options_col = create_map([lit(x) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "SCHEMA_OF_CSV", options_col)
@@ -1560,7 +1565,9 @@ def from_csv(
 ) -> Column:
     schema = schema if isinstance(schema, Column) else lit(schema)
     if options is not None:
-        option_cols = create_map([lit(x) for x in _flatten(options.items())])
+        option_cols = create_map(
+            [lit(str(x) if isinstance(x, bool) else x) for x in _flatten(options.items())]
+        )
         return Column.invoke_anonymous_function(col, "FROM_CSV", schema, option_cols)
     return Column.invoke_anonymous_function(col, "FROM_CSV", schema)
 
@@ -1667,6 +1674,79 @@ def nullif(col1: ColumnOrName, col2: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col1, expression.Nullif, expression=col2)
 
 
+@meta(unsupported_engines="*")
+def stack(*cols: ColumnOrName) -> Column:
+    columns = [Column.ensure_col(x) for x in cols]
+    return Column.invoke_anonymous_function(
+        columns[0], "STACK", *columns[1:] if len(columns) > 1 else []
+    )
+
+
+@meta(unsupported_engines="*")
+def make_interval(
+    years: t.Optional[ColumnOrName] = None,
+    months: t.Optional[ColumnOrName] = None,
+    weeks: t.Optional[ColumnOrName] = None,
+    days: t.Optional[ColumnOrName] = None,
+    hours: t.Optional[ColumnOrName] = None,
+    mins: t.Optional[ColumnOrName] = None,
+    secs: t.Optional[ColumnOrName] = None,
+) -> Column:
+    values = [years, months, weeks, days, hours, mins, secs]
+    for value in reversed(values.copy()):
+        if value is not None:
+            break
+        values = values[:-1]
+    else:
+        raise ValueError("At least one value must be provided")
+    columns = [Column.ensure_col(x) if x is not None else lit(None) for x in values]
+    return Column.invoke_anonymous_function(columns[0], "MAKE_INTERVAL", *columns[1:])
+
+
+@meta(unsupported_engines="*")
+def try_add(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_ADD", right)
+
+
+@meta(unsupported_engines="*")
+def try_avg(col: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(col, "TRY_AVG")
+
+
+@meta(unsupported_engines="*")
+def try_divide(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_DIVIDE", right)
+
+
+@meta(unsupported_engines="*")
+def try_multiply(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_MULTIPLY", right)
+
+
+@meta(unsupported_engines="*")
+def try_subtract(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_SUBTRACT", right)
+
+
+@meta(unsupported_engines="*")
+def try_sum(col: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(col, "TRY_SUM")
+
+
+@meta(unsupported_engines="*")
+def try_to_binary(col: ColumnOrName, format: t.Optional[ColumnOrName] = None) -> Column:
+    if format is not None:
+        return Column.invoke_anonymous_function(col, "TRY_TO_BINARY", format)
+    return Column.invoke_anonymous_function(col, "TRY_TO_BINARY")
+
+
+@meta(unsupported_engines="*")
+def try_to_number(col: ColumnOrName, format: t.Optional[ColumnOrName] = None) -> Column:
+    if format is not None:
+        return Column.invoke_anonymous_function(col, "TRY_TO_NUMBER", format)
+    return Column.invoke_anonymous_function(col, "TRY_TO_NUMBER")
+
+
 @meta()
 def _lambda_quoted(value: str) -> t.Optional[bool]:
     return False if value == "_" else None

sqlframe/base/session.py

@@ -569,6 +569,7 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, CONN]):
             self,
             key: t.Optional[str] = None,
             value: t.Optional[t.Any] = None,
+            conf: t.Optional[t.Any] = None,
             *,
             map: t.Optional[t.Dict[str, t.Any]] = None,
         ) -> Self:

sqlframe/spark/catalog.py

@@ -519,7 +519,10 @@ class SparkCatalog(
                 )
                 for col in df.columns
             ]
-        return [Column(*x) for x in self._spark_catalog.listColumns(tableName, dbName)]
+        return [
+            Column(**{name: x._asdict()[name] for name in Column._fields})
+            for x in self._spark_catalog.listColumns(tableName, dbName)
+        ]
 
     def listFunctions(
         self, dbName: t.Optional[str] = None, pattern: t.Optional[str] = None

sqlframe/spark/functions.py

@@ -8,9 +8,7 @@ globals().update(
     {
         name: func
         for name, func in inspect.getmembers(module, inspect.isfunction)
-        if hasattr(func, "unsupported_engines")
-        and "spark" not in func.unsupported_engines
-        and "*" not in func.unsupported_engines
+        if hasattr(func, "unsupported_engines") and "spark" not in func.unsupported_engines
     }
 )
 

sqlframe/spark/functions.pyi

@@ -132,6 +132,7 @@ from sqlframe.base.functions import (
     lpad as lpad,
     ltrim as ltrim,
     make_date as make_date,
+    make_interval as make_interval,
     map_concat as map_concat,
     map_entries as map_entries,
     map_filter as map_filter,
@@ -177,6 +178,8 @@ from sqlframe.base.functions import (
     row_number as row_number,
     rpad as rpad,
     rtrim as rtrim,
+    schema_of_csv as schema_of_csv,
+    schema_of_json as schema_of_json,
     sec as sec,
     second as second,
     sentences as sentences,
@@ -200,6 +203,7 @@ from sqlframe.base.functions import (
     soundex as soundex,
     split as split,
     sqrt as sqrt,
+    stack as stack,
     stddev as stddev,
     stddev_pop as stddev_pop,
     stddev_samp as stddev_samp,
@@ -225,6 +229,14 @@ from sqlframe.base.functions import (
     translate as translate,
     trim as trim,
     trunc as trunc,
+    try_add as try_add,
+    try_avg as try_avg,
+    try_divide as try_divide,
+    try_multiply as try_multiply,
+    try_subtract as try_subtract,
+    try_sum as try_sum,
+    try_to_binary as try_to_binary,
+    try_to_number as try_to_number,
     typeof as typeof,
     unbase64 as unbase64,
     unhex as unhex,

{sqlframe-1.7.0.dist-info → sqlframe-1.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.7.0
+Version: 1.8.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -19,6 +19,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable (<3.11.0)
 Requires-Dist: sqlglot (<25.1,>=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'
@@ -36,7 +37,6 @@ Requires-Dist: pytest-xdist (<3.7,>=3.6) ; extra == 'dev'
 Requires-Dist: pytest (<8.3,>=8.2.0) ; extra == 'dev'
 Requires-Dist: ruff (<0.5,>=0.4.4) ; extra == 'dev'
 Requires-Dist: types-psycopg2 (<3,>=2.9) ; extra == 'dev'
-Requires-Dist: typing-extensions (<5,>=4.11) ; extra == 'dev'
 Requires-Dist: pre-commit (>=3.5) ; (python_version == "3.8") and extra == 'dev'
 Requires-Dist: pre-commit (<3.8,>=3.7) ; (python_version >= "3.9") and extra == 'dev'
 Provides-Extra: docs

{sqlframe-1.7.0.dist-info → sqlframe-1.8.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sqlframe/_version.py,sha256=2fEqxujmrV2dsREie2BmOYFLu66FowyHtZT2AoLuIzU,411
+sqlframe/_version.py,sha256=PikY8ZcokXQcck_OODdQtYmXxEq-zKRR9b1ZMOFZlds,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=ATDGirouUjal05P4ymL-wIi8rgjg_8w4PoACamiO64A,37245
@@ -8,12 +8,12 @@ sqlframe/base/dataframe.py,sha256=uL4neDTMy1a9XJH46YLQryzdDci4iDxNXBtiJOzfHfs,67
 sqlframe/base/decorators.py,sha256=I5osMgx9BuCgbtp4jVM2DNwYJVLzCv-OtTedhQEik0g,1882
 sqlframe/base/exceptions.py,sha256=pCB9hXX4jxZWzNg3JN1i38cv3BmpUlee5NoLYx3YXIQ,208
 sqlframe/base/function_alternatives.py,sha256=NDXs2igY7PBsStzTSRZvJcCshBOJkPQl2GbhpVFU6To,42931
-sqlframe/base/functions.py,sha256=QgVMWnZFClxfbiOV4CpILtOtdo7-Ey5wWTehdGy0qkA,54393
+sqlframe/base/functions.py,sha256=AXYdxziKsU--huK5o0bl_4DhBns3XFlwPtweCNCIH0E,57191
 sqlframe/base/group.py,sha256=TES9CleVmH3x-0X-tqmuUKfCKSWjH5vg1aU3R6dDmFc,4059
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=-AhNuEzcV7ZExoP1oY3blaKip-joQyJeQVvfBTs_2g4,3456
 sqlframe/base/readerwriter.py,sha256=5NPQMiOrw6I54U243R_6-ynnWYsNksgqwRpPp4IFjIw,25288
-sqlframe/base/session.py,sha256=nq4fz8eGZwtZ5nThZ9VsvwIboyi3Hc8BPvcukWNffPg,21949
+sqlframe/base/session.py,sha256=oQsOwlwAhbqtD8epR44kGXP29S31fIxM29NxfwCbcl0,21993
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
 sqlframe/base/types.py,sha256=aJT5YXr-M_LAfUM0uK4asfbrQFab_xmsp1CP2zkG8p0,11924
 sqlframe/base/util.py,sha256=hgmTVzdTvHhfc9d5I96wjk9LGr-vhSZlaB-MejENzcA,9110
@@ -77,11 +77,11 @@ sqlframe/snowflake/session.py,sha256=bDOlnuIiQ9j_zfF7F5H1gTLmpHUjruIxr2CfXcS_7YU
 sqlframe/snowflake/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/snowflake/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/spark/__init__.py,sha256=WhYQAZMJN1EMNAVGUH7BEinxNdYtXOrrr-6HUniJOyI,649
-sqlframe/spark/catalog.py,sha256=YeWBCUlkkhf2jDcmaFo-JvG4DQ6Daqyy1zEnVBx5gMo,32526
+sqlframe/spark/catalog.py,sha256=rIX5DtPnINbcPZRUe4Z1bOpkJoNRlrO9qWkUeTQClNc,32612
 sqlframe/spark/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/spark/dataframe.py,sha256=V3z5Bx9snLgYh4bDwJfJb5mj1P7UsZF8DMlLwZXopBg,1309
-sqlframe/spark/functions.py,sha256=eSGMM2DXcj17nIPH5ZDLG95ZMuE7F8Qvn0IqGO_wQVw,586
-sqlframe/spark/functions.pyi,sha256=DPmFkFF97XrQ-0dOon3d3Oy62nReQdz2WgqxS7_DGKY,6385
+sqlframe/spark/functions.py,sha256=PkK4MBpVADhnDbrgFDii5zFaNrhi4y-OYX3Lcu-SW0k,530
+sqlframe/spark/functions.pyi,sha256=GHL_4c5JUeeR7IP9hnZtYDs3FWufoYzO_YjF_52vYVQ,6757
 sqlframe/spark/group.py,sha256=MrvV_v-YkBc6T1zz882WrEqtWjlooWIyHBCmTQg3fCA,379
 sqlframe/spark/readwriter.py,sha256=w68EImTcGJv64X7pc1tk5tDjDxb1nAnn-MiIaaN9Dc8,812
 sqlframe/spark/session.py,sha256=ztIS7VCFxjR3B7i4JXaXo0evTUhUjOsIAZb7Ssqt2cU,4254
@@ -97,8 +97,8 @@ 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-1.7.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-1.7.0.dist-info/METADATA,sha256=1lyDm_FbsX04vuugYv5aM8VWwnKuEK8yWIxwdhMzBL0,7514
-sqlframe-1.7.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-1.7.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-1.7.0.dist-info/RECORD,,
+sqlframe-1.8.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-1.8.0.dist-info/METADATA,sha256=lUJKFXpvE7TFVd4VNSlyUYDYnKj3Uy9XzHZNKyr9msE,7496
+sqlframe-1.8.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+sqlframe-1.8.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-1.8.0.dist-info/RECORD,,