sqlframe 3.40.2__py3-none-any.whl → 3.42.0__py3-none-any.whl

sqlframe/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '3.40.2'
-__version_tuple__ = version_tuple = (3, 40, 2)
+__version__ = version = '3.42.0'
+__version_tuple__ = version_tuple = (3, 42, 0)
 
-__commit_id__ = commit_id = 'gdb7bc99bd'
+__commit_id__ = commit_id = 'gadde0dd66'

sqlframe/base/functions.py

@@ -1974,8 +1974,30 @@ def regexp_replace(
     )
 
 
-@meta(unsupported_engines="duckdb")
+@meta()
 def initcap(col: ColumnOrName) -> Column:
+    session = _get_session()
+
+    if session._is_duckdb:
+        split_func = get_func_from_session("split")
+        transform_func = get_func_from_session("transform")
+        reduce_func = get_func_from_session("reduce")
+        upper_func = get_func_from_session("upper")
+        lower_func = get_func_from_session("lower")
+        length_func = get_func_from_session("length")
+        concat_func = get_func_from_session("concat")
+        concat_ws_func = get_func_from_session("concat_ws")
+        return reduce_func(
+            transform_func(
+                split_func(col, r"\s+"),
+                lambda w: concat_func(
+                    upper_func(w.substr(1, 1)), lower_func(w.substr(2, length_func(w) - 1))
+                ),
+            ),
+            None,
+            merge=lambda x, y: concat_ws_func(" ", x, y),
+        )
+
     return Column.invoke_expression_over_column(col, expression.Initcap)
 
 
@@ -2133,6 +2155,11 @@ def bit_xor(col: ColumnOrName) -> Column:
 
 @meta(unsupported_engines=["postgres", "snowflake"])
 def bit_count(col: ColumnOrName) -> Column:
+    session = _get_session()
+
+    if session._is_duckdb:
+        return Column.invoke_anonymous_function(col, "BIT_COUNT")
+
     return Column.invoke_expression_over_column(col, expression.BitwiseCountAgg)
 
 
@@ -2681,7 +2708,7 @@ def from_csv(
     return Column.invoke_anonymous_function(col, "FROM_CSV", schema)
 
 
-@meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])
+@meta(unsupported_engines=["bigquery", "postgres", "snowflake"])
 def aggregate(
     col: ColumnOrName,
     initialValue: ColumnOrName,
@@ -2689,21 +2716,20 @@ def aggregate(
     finish: t.Optional[t.Callable[[Column], Column]] = None,
 ) -> Column:
     merge_exp = _get_lambda_from_func(merge)
+    kwargs = dict(
+        initial=initialValue,
+        merge=merge_exp,
+    )
+    session = _get_session()
     if finish is not None:
         finish_exp = _get_lambda_from_func(finish)
-        return Column.invoke_expression_over_column(
-            col,
-            expression.Reduce,
-            initial=initialValue,
-            merge=Column(merge_exp),
-            finish=Column(finish_exp),
-        )
-    return Column.invoke_expression_over_column(
-        col, expression.Reduce, initial=initialValue, merge=Column(merge_exp)
-    )
+        kwargs["finish"] = Column(finish_exp)
+    if session._is_duckdb:
+        kwargs.pop("initial", None)
+    return Column.invoke_expression_over_column(col, expression.Reduce, **kwargs)
 
 
-@meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])
+@meta(unsupported_engines="postgres")
 def transform(
     col: ColumnOrName,
     f: t.Union[t.Callable[[Column], Column], t.Callable[[Column, Column], Column]],
@@ -5216,7 +5242,7 @@ def regexp_count(str: ColumnOrName, regexp: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(str, "regexp_count", regexp)
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery", "postgres"])
 def regexp_extract_all(
     str: ColumnOrName, regexp: ColumnOrName, idx: t.Optional[t.Union[int, Column]] = None
 ) -> Column:
@@ -5251,6 +5277,9 @@ def regexp_extract_all(
     >>> df.select(regexp_extract_all('str', col("regexp")).alias('d')).collect()
     [Row(d=['100', '300'])]
     """
+    if idx is None:
+        idx = 1
+
     return Column.invoke_expression_over_column(
         str, expression.RegexpExtractAll, expression=regexp, group=idx
     )

{sqlframe-3.40.2.dist-info → sqlframe-3.42.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.40.2
+Version: 3.42.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -18,7 +18,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: more-itertools
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <27.13,>=24.0.0
+Requires-Dist: sqlglot <27.15,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -28,7 +28,7 @@ Requires-Dist: databricks-sql-connector[pyarrow] <5,>=3.6 ; extra == 'databricks
 Provides-Extra: dev
 Requires-Dist: duckdb <1.4,>=1.2 ; extra == 'dev'
 Requires-Dist: findspark <3,>=2 ; extra == 'dev'
-Requires-Dist: mypy <1.18,>=1.10.0 ; extra == 'dev'
+Requires-Dist: mypy <1.19,>=1.10.0 ; extra == 'dev'
 Requires-Dist: openai <2,>=1.30 ; extra == 'dev'
 Requires-Dist: pandas-stubs <3,>=2 ; extra == 'dev'
 Requires-Dist: pandas <3,>=2 ; extra == 'dev'
@@ -41,7 +41,7 @@ Requires-Dist: pytest-postgresql <8,>=6 ; extra == 'dev'
 Requires-Dist: pytest-rerunfailures ; extra == 'dev'
 Requires-Dist: pytest-xdist <3.9,>=3.6 ; extra == 'dev'
 Requires-Dist: pytest <8.5,>=8.2.0 ; extra == 'dev'
-Requires-Dist: ruff <0.13,>=0.4.4 ; extra == 'dev'
+Requires-Dist: ruff <0.14,>=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-3.40.2.dist-info → sqlframe-3.42.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=3OGXpC5dnC00OMMG_59F7UDDhHQJ9rorOrt-3thT5Zg,714
+sqlframe/_version.py,sha256=SsOOM9QJfro_JWrCpQSS5Pq52ergp6bxQ1nOQPkMZJs,714
 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
@@ -9,7 +9,7 @@ sqlframe/base/dataframe.py,sha256=Kl3WycARIWBBIze0enmZDGkfOt65mZDQ2hx_6pxRsxI,87
 sqlframe/base/decorators.py,sha256=IhE5xNQDkwJHacCvulq5WpUKyKmXm7dL2A3o5WuKGP4,2131
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=aTu3nQhIAkZoxrI1IpjpaHEAMxBNms0AnhS0EMR-TwY,51727
-sqlframe/base/functions.py,sha256=fc3jLuPAIJ3Hl4Bezm9Kgzsk4e5uFfgMgfajUCBKQG0,227919
+sqlframe/base/functions.py,sha256=QaCeMMBLz69LE-73x4ksXN6NbZlsshYADg-F8yRXTPA,228816
 sqlframe/base/group.py,sha256=fBm8EUve7W7xz11nybTXr09ih-yZxL_vvEiZVE1eb_0,12025
 sqlframe/base/normalize.py,sha256=YPeopWr8ZRjevArYfrM-DZBkQp4t4UfAEwynoj4VvcU,11773
 sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
@@ -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-3.40.2.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.40.2.dist-info/METADATA,sha256=Ed2s5MTrVUt6Xzx75bG-Wlfh71zZwO7-Bnr9xlMpCSk,9070
-sqlframe-3.40.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.40.2.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.40.2.dist-info/RECORD,,
+sqlframe-3.42.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.42.0.dist-info/METADATA,sha256=g3qTG2C4TsHFM1Q_pkybk7u_Sp4OY5nshpsSsQPKzTM,9070
+sqlframe-3.42.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.42.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.42.0.dist-info/RECORD,,