sqlframe 3.41.0__tar.gz → 3.42.0__tar.gz

{sqlframe-3.41.0 → sqlframe-3.42.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.41.0
+Version: 3.42.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.41.0 → sqlframe-3.42.0}/docs/bigquery.md

@@ -526,6 +526,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
 * [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
+* [transform](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.transform.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.41.0 → sqlframe-3.42.0}/docs/duckdb.md

@@ -268,6 +268,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [abs](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.abs.html)
 * [acos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acos.html)
 * [add_months](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.add_months.html)
+* [aggregate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.aggregate.html)
 * [any_value](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.any_value.html)
     * Always ignores nulls
 * [approxCountDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.approxCountDistinct.html)
@@ -380,6 +381,7 @@ See something that you would like to see supported? [Open an issue](https://gith
     * Uses a different hash algorithm than Spark
 * [hex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.hex.html)
 * [hour](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.hour.html)
+* [initcap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.initcap.html)
 * [input_file_name](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.input_file_name.html)
 * [instr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.instr.html)
 * [isnan](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.isnan.html)
@@ -433,6 +435,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [radians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.radians.html)
 * [rand](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rand.html)
 * [rank](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rank.html)
+* [reduce](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.reduce.html)
 * [regexp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.regexp.html)
 * [regexp_extract](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.regexp_extract.html)
 * [regexp_extract_all](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.regexp_extract_all.html)
@@ -484,6 +487,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
 * [to_unix_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_unix_timestamp.html)
     * The values must match the format string (null will not be returned if they do not)
+* [transform](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.transform.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.41.0 → sqlframe-3.42.0}/docs/snowflake.md

@@ -522,6 +522,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [to_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_number.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
 * [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
+* [transform](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.transform.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.41.0 → sqlframe-3.42.0}/sqlframe/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '3.41.0'
-__version_tuple__ = version_tuple = (3, 41, 0)
+__version__ = version = '3.42.0'
+__version_tuple__ = version_tuple = (3, 42, 0)
 
-__commit_id__ = commit_id = 'g961d3fda2'
+__commit_id__ = commit_id = 'gadde0dd66'

{sqlframe-3.41.0 → sqlframe-3.42.0}/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)
 
 
@@ -2686,7 +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,
@@ -2694,21 +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]],

{sqlframe-3.41.0 → sqlframe-3.42.0}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.41.0
+Version: 3.42.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman