sqlframe 3.7.0__tar.gz → 3.8.1__tar.gz

{sqlframe-3.7.0 → sqlframe-3.8.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.7.0
+Version: 3.8.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.7.0 → sqlframe-3.8.1}/docs/bigquery.md

@@ -425,6 +425,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [max_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.max_by.html)
 * [md5](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.md5.html)
 * [mean](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.mean.html)
+* [median](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.median.html)
 * [min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min.html)
 * [min_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min_by.html)
 * [minute](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.minute.html)

{sqlframe-3.7.0 → sqlframe-3.8.1}/docs/duckdb.md

@@ -308,6 +308,8 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [concat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat.html)                               
     * Only works on strings (does not work on arrays)
 * [concat_ws](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat_ws.html)
+* [contains](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.contains.html)
+  * Only works on strings (does not support binary)
 * [convert_timezone](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.convert_timezone.html)
 * [corr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.corr.html)
 * [cos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cos.html)
@@ -395,6 +397,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [max_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.max_by.html)
 * [md5](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.md5.html)
 * [mean](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.mean.html)
+* [median](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.median.html)
 * [min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min.html)
 * [min_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min_by.html)
 * [minute](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.minute.html)

{sqlframe-3.7.0 → sqlframe-3.8.1}/docs/snowflake.md

@@ -344,6 +344,8 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [concat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat.html)
   * Can only concat strings not arrays
 * [concat_ws](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat_ws.html)
+* [contains](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.contains.html)
+  * * Only works on strings (does not support binary)
 * [convert_timezone](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.convert_timezone.html)
 * [corr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.corr.html)
 * [cos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cos.html)
@@ -428,6 +430,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [max_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.max_by.html)
 * [md5](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.md5.html)
 * [mean](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.mean.html)
+* [median](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.median.html)
 * [min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min.html)
 * [min_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min_by.html)
 * [minute](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.minute.html)
@@ -510,6 +513,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [ucase](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ucase.html)
 * [unbase64](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unbase64.html)
 * [unhex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unhex.html)
+* [unix_seconds](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unix_seconds.html)
 * [unix_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unix_timestamp.html)
 * [upper](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.upper.html)
 * [var_pop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.var_pop.html)

{sqlframe-3.7.0 → sqlframe-3.8.1}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.8",
     install_requires=[
         "prettytable<3.12.1",
-        "sqlglot>=24.0.0,<25.29",
+        "sqlglot>=24.0.0,<25.32",
         "typing_extensions>=4.8,<5",
     ],
     extras_require={
@@ -32,7 +32,7 @@ setup(
             "duckdb>=0.9,<1.2",
             "findspark>=2,<3",
             "mypy>=1.10.0,<1.14",
-            "openai>=1.30,<1.54",
+            "openai>=1.30,<1.55",
             "pandas>=2,<3",
             "pandas-stubs>=2,<3",
             "psycopg>=3.1,<4",
@@ -58,7 +58,7 @@ setup(
             "pandas>=2,<3",
         ],
         "openai": [
-            "openai>=1.30,<1.54",
+            "openai>=1.30,<1.55",
         ],
         "pandas": [
             "pandas>=2,<3",

{sqlframe-3.7.0 → sqlframe-3.8.1}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.7.0'
-__version_tuple__ = version_tuple = (3, 7, 0)
+__version__ = version = '3.8.1'
+__version_tuple__ = version_tuple = (3, 8, 1)

{sqlframe-3.7.0 → sqlframe-3.8.1}/sqlframe/base/function_alternatives.py

@@ -1593,7 +1593,7 @@ def try_to_timestamp_pgtemp(col: ColumnOrName, format: t.Optional[ColumnOrName]
 def typeof_pg_typeof(col: ColumnOrName) -> Column:
     return (
         Column.invoke_anonymous_function(col, "pg_typeof")
-        .cast(expression.DataType.build("regtype", dialect="postgres"))
+        .cast(expression.DataType(this=expression.DataType.Type.USERDEFINED, kind="regtype"))
         .cast("text")
     )
 

{sqlframe-3.7.0 → sqlframe-3.8.1}/sqlframe/base/functions.py

@@ -2069,9 +2069,11 @@ def character_length(str: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(str, "character_length")
 
 
-@meta()
+@meta(unsupported_engines=["bigquery", "postgres"])
 def contains(left: ColumnOrName, right: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(left, "contains", right)
+    return Column.invoke_expression_over_column(
+        left, expression.Contains, expression=Column.ensure_col(right).expression
+    )
 
 
 @meta(unsupported_engines=["bigquery", "postgres"])
@@ -3484,7 +3486,7 @@ def mask(
     )
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery"])
 def median(col: ColumnOrName) -> Column:
     """
     Returns the median of the values in a group.
@@ -3520,7 +3522,7 @@ def median(col: ColumnOrName) -> Column:
     |dotNET|         10000.0|
     +------+----------------+
     """
-    return Column.invoke_anonymous_function(col, "median")
+    return Column.invoke_expression_over_column(col, expression.Median)
 
 
 @meta(unsupported_engines="*")
@@ -4106,11 +4108,9 @@ def regexp_extract_all(
     >>> df.select(regexp_extract_all('str', col("regexp")).alias('d')).collect()
     [Row(d=['100', '300'])]
     """
-    if idx is None:
-        return Column.invoke_anonymous_function(str, "regexp_extract_all", regexp)
-    else:
-        idx = lit(idx) if isinstance(idx, int) else idx
-        return Column.invoke_anonymous_function(str, "regexp_extract_all", regexp, idx)
+    return Column.invoke_expression_over_column(
+        str, expression.RegexpExtractAll, expression=regexp, group=idx
+    )
 
 
 @meta(unsupported_engines="*")
@@ -5426,7 +5426,7 @@ def unix_millis(col: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(col, "unix_millis")
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery", "duckdb", "postgres"])
 def unix_seconds(col: ColumnOrName) -> Column:
     """Returns the number of seconds since 1970-01-01 00:00:00 UTC.
     Truncates higher levels of precision.
@@ -5441,7 +5441,7 @@ def unix_seconds(col: ColumnOrName) -> Column:
     [Row(n=1437584400)]
     >>> spark.conf.unset("spark.sql.session.timeZone")
     """
-    return Column.invoke_anonymous_function(col, "unix_seconds")
+    return Column.invoke_expression_over_column(col, expression.UnixSeconds)
 
 
 @meta(unsupported_engines="*")

{sqlframe-3.7.0 → sqlframe-3.8.1}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.7.0
+Version: 3.8.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.7.0 → sqlframe-3.8.1}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<3.12.1
-sqlglot<25.29,>=24.0.0
+sqlglot<25.32,>=24.0.0
 typing_extensions<5,>=4.8
 
 [bigquery]
@@ -10,7 +10,7 @@ google-cloud-bigquery[pandas]<4,>=3
 duckdb<1.2,>=0.9
 findspark<3,>=2
 mypy<1.14,>=1.10.0
-openai<1.54,>=1.30
+openai<1.55,>=1.30
 pandas-stubs<3,>=2
 pandas<3,>=2
 psycopg<4,>=3.1
@@ -40,7 +40,7 @@ duckdb<1.2,>=0.9
 pandas<3,>=2
 
 [openai]
-openai<1.54,>=1.30
+openai<1.55,>=1.30
 
 [pandas]
 pandas<3,>=2

{sqlframe-3.7.0 → sqlframe-3.8.1}/tests/unit/standalone/test_functions.py

@@ -13,9 +13,11 @@ from sqlframe.standalone import functions as SF
 @pytest.mark.parametrize("name,func", inspect.getmembers(SF, inspect.isfunction))
 def test_invoke_anonymous(name, func):
     # array_size - converts to `size` but `array_size` and `size` behave differently
+    # exists - the spark exists takes a lambda function and the exists in SQLGlot seems more basic
+    # make_interval - SQLGlot doesn't support week
     # to_char - convert to a cast that ignores the format provided
     # ltrim/rtrim - don't seem to convert correctly on some engines
-    ignore_funcs = {"array_size", "to_char", "ltrim", "rtrim"}
+    ignore_funcs = {"array_size", "exists", "make_interval", "to_char", "ltrim", "rtrim"}
     if "invoke_anonymous_function" in inspect.getsource(func) and name not in ignore_funcs:
         func = parse_one(f"{name}()", read="spark", error_level=ErrorLevel.IGNORE)
         assert isinstance(func, exp.Anonymous)
@@ -4224,7 +4226,7 @@ def test_regexp_count(expression, expected):
             SF.regexp_extract_all("cola", "colb", SF.col("colc")),
             "REGEXP_EXTRACT_ALL(cola, colb, colc)",
         ),
-        (SF.regexp_extract_all("cola", "colb", 1), "REGEXP_EXTRACT_ALL(cola, colb, 1)"),
+        (SF.regexp_extract_all("cola", "colb", 2), "REGEXP_EXTRACT_ALL(cola, colb, 2)"),
     ],
 )
 def test_regexp_extract_all(expression, expected):