sqlframe 3.24.1__py3-none-any.whl → 3.26.0__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.24.1'
-__version_tuple__ = version_tuple = (3, 24, 1)
+__version__ = version = '3.26.0'
+__version_tuple__ = version_tuple = (3, 26, 0)

sqlframe/base/function_alternatives.py

@@ -551,6 +551,17 @@ def sha1_force_sha1_and_to_hex(col: ColumnOrName) -> Column:
     )
 
 
+def sha2_sha265(col: ColumnOrName) -> Column:
+    col_func = get_func_from_session("col")
+
+    return Column(
+        expression.Anonymous(
+            this="SHA256",
+            expressions=[col_func(col).column_expression],
+        )
+    )
+
+
 def hash_from_farm_fingerprint(*cols: ColumnOrName) -> Column:
     if len(cols) > 1:
         raise ValueError("This dialect only supports a single column for calculating hash")

sqlframe/base/functions.py

@@ -1492,7 +1492,7 @@ def md5(col: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col, expression.MD5)
 
 
-@meta(unsupported_engines=["duckdb", "postgres"])
+@meta(unsupported_engines=["postgres"])
 def sha1(col: ColumnOrName) -> Column:
     from sqlframe.base.function_alternatives import sha1_force_sha1_and_to_hex
 
@@ -1504,8 +1504,18 @@ def sha1(col: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col, expression.SHA)
 
 
-@meta(unsupported_engines=["bigquery", "duckdb", "postgres"])
+@meta(unsupported_engines=["bigquery", "postgres"])
 def sha2(col: ColumnOrName, numBits: int) -> Column:
+    from sqlframe.base.function_alternatives import sha2_sha265
+
+    session = _get_session()
+
+    if session._is_duckdb:
+        if numBits in [256, 0]:
+            return sha2_sha265(col)
+        else:
+            raise ValueError("This dialect only supports SHA-265 (numBits=256 or numBits=0)")
+
     return Column.invoke_expression_over_column(col, expression.SHA2, length=lit(numBits))
 
 
@@ -2355,15 +2365,31 @@ def from_json(
         schema = schema.simpleString()
     schema = schema if isinstance(schema, Column) else lit(schema)
     if options is not None:
-        options_col = create_map([lit(x) for x in _flatten(options.items())])
+        options_col = create_map([lit(str(x)) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "FROM_JSON", schema, options_col)
     return Column.invoke_anonymous_function(col, "FROM_JSON", schema)
 
 
-@meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])
+@meta(unsupported_engines=["bigquery", "postgres", "snowflake"])
 def to_json(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = None) -> Column:
+    session = _get_session()
+    if session._is_duckdb:
+        # check if Spark options match DuckDB's default behavior
+        is_spark_equivalent = (
+            options
+            and list(options.keys()) == ["ignoreNullFields"]  # only one option specified
+            and str(options.get("ignoreNullFields", "true")).lower() == "false"
+        )
+        if not is_spark_equivalent:
+            logger.warning(
+                "Options for `to_json()` ignored, since not supported in this dialect."
+                + " Potential `null` values are included in the returned JSON string."
+                + " This is different from Spark's default behavior."
+            )
+        options = None
+
     if options is not None:
-        options_col = create_map([lit(x) for x in _flatten(options.items())])
+        options_col = create_map([lit(str(x)) for x in _flatten(options.items())])
         return Column.invoke_expression_over_column(col, expression.JSONFormat, options=options_col)
     return Column.invoke_expression_over_column(col, expression.JSONFormat)
 
@@ -2373,7 +2399,7 @@ def schema_of_json(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = No
     if isinstance(col, str):
         col = lit(col)
     if options is not None:
-        options_col = create_map([lit(x) for x in _flatten(options.items())])
+        options_col = create_map([lit(str(x)) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "SCHEMA_OF_JSON", options_col)
     return Column.invoke_anonymous_function(col, "SCHEMA_OF_JSON")
 
@@ -2383,7 +2409,7 @@ def schema_of_csv(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = Non
     if isinstance(col, str):
         col = lit(col)
     if options is not None:
-        options_col = create_map([lit(x) for x in _flatten(options.items())])
+        options_col = create_map([lit(str(x)) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "SCHEMA_OF_CSV", options_col)
     return Column.invoke_anonymous_function(col, "SCHEMA_OF_CSV")
 
@@ -2391,7 +2417,7 @@ def schema_of_csv(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = Non
 @meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])
 def to_csv(col: ColumnOrName, options: t.Optional[t.Dict[str, str]] = None) -> Column:
     if options is not None:
-        options_col = create_map([lit(x) for x in _flatten(options.items())])
+        options_col = create_map([lit(str(x)) for x in _flatten(options.items())])
         return Column.invoke_anonymous_function(col, "TO_CSV", options_col)
     return Column.invoke_anonymous_function(col, "TO_CSV")
 

sqlframe/duckdb/functions.pyi

@@ -166,6 +166,7 @@ from sqlframe.base.functions import rpad as rpad
 from sqlframe.base.functions import rtrim as rtrim
 from sqlframe.base.functions import second as second
 from sqlframe.base.functions import sequence as sequence
+from sqlframe.base.functions import sha1 as sha1
 from sqlframe.base.functions import shiftLeft as shiftLeft
 from sqlframe.base.functions import shiftleft as shiftleft
 from sqlframe.base.functions import shiftRight as shiftRight
@@ -194,6 +195,7 @@ from sqlframe.base.functions import sumDistinct as sumDistinct
 from sqlframe.base.functions import tan as tan
 from sqlframe.base.functions import timestamp_seconds as timestamp_seconds
 from sqlframe.base.functions import to_date as to_date
+from sqlframe.base.functions import to_json as to_json
 from sqlframe.base.functions import to_timestamp as to_timestamp
 from sqlframe.base.functions import to_unix_timestamp as to_unix_timestamp
 from sqlframe.base.functions import toDegrees as toDegrees

{sqlframe-3.24.1.dist-info → sqlframe-3.26.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.24.1
+Version: 3.26.0
 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 <26.10,>=24.0.0
+Requires-Dist: sqlglot <26.12,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -39,7 +39,7 @@ Requires-Dist: pytest-forked ; 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'
+Requires-Dist: ruff <0.12,>=0.4.4 ; extra == 'dev'
 Requires-Dist: types-psycopg2 <3,>=2.9 ; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: mkdocs-include-markdown-plugin ==6.0.6 ; extra == 'docs'

{sqlframe-3.24.1.dist-info → sqlframe-3.26.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=bOjc-tAPBepEtx0iEev4SZqKYnCU7LBd6gdTvVgKhf4,513
+sqlframe/_version.py,sha256=O47f8PhfWsbiZ4mjHJkrL81FZEFxis7lNo0FJknkGus,513
 sqlframe/py.typed,sha256=Nqnn8clbgv-5l0PgxcTOldg8mkMKrFn4TvPL-rYUUGg,1
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=b2clI5HI1zEZKB_3Msx3FeAJQyft44ubUifJwQRVXyQ,1298
@@ -8,8 +8,8 @@ sqlframe/base/column.py,sha256=AG9Z_6RNhVxLhLU29kRCgzMgDNSm-_GFg96xLqk1-bs,19838
 sqlframe/base/dataframe.py,sha256=OgEUlDI5Y4rWrVngW5LttCUMC40WR-Pyr5af6aqbMNU,84028
 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=gWUxngV4cgbPvKqK7_N-2rYGycRyoKJnZqPfFyqIgbE,223305
+sqlframe/base/function_alternatives.py,sha256=Bs1bwl25fN3Yy9rb4GnUWBGunQ1C_yelkb2yV9DSZIY,53918
+sqlframe/base/functions.py,sha256=mSwASQe1WGyMzcwYudioJCR-bvOoqasuqNDFQ2GCC6g,224299
 sqlframe/base/group.py,sha256=4R9sOZm4ZRlTfShq2j3_HQOiL_Tj1bYkouenYsgnlII,4115
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
@@ -57,7 +57,7 @@ sqlframe/duckdb/catalog.py,sha256=89FCSJglMbOxonk3IXmlkMcdXCfMdePpGfqlbkkB_d0,51
 sqlframe/duckdb/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/duckdb/dataframe.py,sha256=Z8_K69UQGZVeBfVGXVwIJP8OMuIvNBB3DPKTP3Lfu4w,1908
 sqlframe/duckdb/functions.py,sha256=ix2efGGD4HLaY1rtCtEd3IrsicGEVGiBAeKOo5OD8rA,424
-sqlframe/duckdb/functions.pyi,sha256=P0ky6k-J7LdCDrQ0OjfRC3ARIYNHPmAmmaB_jBEO5L0,12383
+sqlframe/duckdb/functions.pyi,sha256=dileIrfRspqWPBFUlXn3R8YLBQqhq0XnH6_6Rp8x1PA,12487
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
 sqlframe/duckdb/readwriter.py,sha256=-_Ama7evadIa3PYvynKDK6RcTMTDBHpHJzfANTine7g,4983
 sqlframe/duckdb/session.py,sha256=H1qjMYmhpwUHmf6jOPA6IhPIEIeX8rlvOl3MTIEijG0,2719
@@ -130,8 +130,8 @@ 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-3.24.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.24.1.dist-info/METADATA,sha256=e3fUxg1B0Y2UNWFxg4_igcqsGue6PlytRssEeROM6KQ,8971
-sqlframe-3.24.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.24.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.24.1.dist-info/RECORD,,
+sqlframe-3.26.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.26.0.dist-info/METADATA,sha256=v5x-leHKJrTGK_cyWjXlJRBwLr0VrX1av511o4tKI-E,8971
+sqlframe-3.26.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.26.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.26.0.dist-info/RECORD,,