sqlframe 3.43.5__tar.gz → 3.43.7__tar.gz

{sqlframe-3.43.5 → sqlframe-3.43.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.43.5
+Version: 3.43.7
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/bigquery.md

@@ -684,7 +684,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -712,7 +712,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result
@@ -767,7 +767,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result
@@ -823,7 +823,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/databricks.md

@@ -227,7 +227,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -255,7 +255,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result
@@ -310,7 +310,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result
@@ -366,7 +366,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/duckdb.md

@@ -250,7 +250,7 @@ See something that you would like to see supported? [Open an issue](https://gith
     * SQLFrame Specific: Get the SQL representation of the WindowSpec
 * [stat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.stat.html)
 * [toArrow](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.toArrow.html)
-  * SQLFrame Specific Argument: `batch_size` sets the number of rows to read per-batch and returns a `RecrodBatchReader`
+  * SQLFrame Specific Argument: `batch_size` sets the number of rows to read per-batch and returns a `RecordBatchReader`
 * [toDF](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.toDF.html)
 * [toPandas](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.toPandas.html)
 * [union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.union.html)
@@ -397,6 +397,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [left](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.left.html)
 * [length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.length.html)
 * [levenshtein](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.levenshtein.html)
+* [like](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.like.html)
 * [lit](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lit.html)
 * [ln](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ln.html)
 * [locate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.locate.html)
@@ -478,6 +479,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [sumDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sumDistinct.html)
 * [sum_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sum_distinct.html)
 * [tan](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.tan.html)
+* [tanh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.tanh.html)
 * [timestamp_add](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.timestamp_add.html)
 * [timestamp_seconds](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.timestamp_seconds.html)
 * [toDegrees](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toDegrees.html)
@@ -634,7 +636,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -662,7 +664,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/postgres.md

@@ -392,6 +392,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [left](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.left.html)
 * [length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.length.html)
 * [levenshtein](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.levenshtein.html)
+* [like](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.like.html)
 * [lit](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lit.html)
 * [ln](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ln.html)
 * [locate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.locate.html)
@@ -621,7 +622,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -649,7 +650,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result
@@ -704,7 +705,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result
@@ -760,7 +761,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/redshift.md

@@ -209,7 +209,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -237,7 +237,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/docs/snowflake.md

@@ -309,7 +309,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [array_except](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_except.html)
 * [array_intersect](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_intersect.html)
 * [array_join](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_join.html)
-  * Null values are repsented as nothing instead of NULL. Ex: "a," instead of "a,NULL"
+  * Null values are represented as nothing instead of NULL. Ex: "a," instead of "a,NULL"
 * [array_max](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_max.html)
 * [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
 * [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
@@ -335,7 +335,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [bool_and](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bool_and.html)
 * [bool_or](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bool_or.html)
 * [bround](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bround.html)
-  * [Input must be a fixed-point nnumber](https://docs.snowflake.com/en/sql-reference/data-types-numeric.html#label-data-types-for-fixed-point-numbers)
+  * [Input must be a fixed-point number](https://docs.snowflake.com/en/sql-reference/data-types-numeric.html#label-data-types-for-fixed-point-numbers)
 * [btrim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.btrim.html)
 * [call_function](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.call_function.html)
 * [cbrt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cbrt.html)
@@ -426,6 +426,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.length.html)
 * [levenshtein](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.levenshtein.html)
   * threshold is not supported
+* [like](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.like.html)
 * [lit](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lit.html)
 * [ln](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ln.html)
 * [locate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.locate.html)
@@ -677,7 +678,7 @@ update_expr = table_employee.update(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the update statement
+# Executes the update statement
 update_expr.execute()
 
 # Show the result
@@ -705,7 +706,7 @@ delete_expr = table_employee.delete(
     where=table_employee["id"] == 1,
 )
 
-# Excecutes the delete statement
+# Executes the delete statement
 delete_expr.execute()
 
 # Show the result
@@ -760,7 +761,7 @@ merge_expr = table_employee.merge(
     ],
 )
 
-# Excecutes the merge statement
+# Executes the merge statement
 merge_expr.execute()
 
 # Show the result

{sqlframe-3.43.5 → sqlframe-3.43.7}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.9",
     install_requires=[
         "prettytable<4",
-        "sqlglot>=24.0.0,<27.26",
+        "sqlglot>=24.0.0,<27.29",
         "typing_extensions",
         "more-itertools",
     ],

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/__init__.py

@@ -6,6 +6,10 @@ import typing as t
 from contextlib import contextmanager
 from unittest.mock import MagicMock
 
+from sqlglot.dialects import spark
+
+spark.Spark.Generator.readparquet_sql = lambda self, x: x.sql(dialect="duckdb")  # type: ignore
+
 if t.TYPE_CHECKING:
     from sqlframe.base.session import CONN
 

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '3.43.5'
-__version_tuple__ = version_tuple = (3, 43, 5)
+__version__ = version = '3.43.7'
+__version_tuple__ = version_tuple = (3, 43, 7)
 
-__commit_id__ = commit_id = 'ge9449259f'
+__commit_id__ = commit_id = 'g745c96966'

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/base/dataframe.py

@@ -361,15 +361,31 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     def _replace_cte_names_with_hashes(self, expression: exp.Select):
         replacement_mapping = {}
-        for cte in expression.ctes:
+        seen_hashes: t.Dict[str, exp.Identifier] = {}
+        cte_indices_to_remove = []
+
+        for i, cte in enumerate(expression.ctes):
             old_name_id = cte.args["alias"].this
-            new_hashed_id = exp.to_identifier(
-                self._create_hash_from_expression(cte.this), quoted=old_name_id.args["quoted"]
-            )
-            replacement_mapping[old_name_id] = new_hashed_id
+            cte_hash = self._create_hash_from_expression(cte.this)
+
+            if cte_hash in seen_hashes:
+                # Duplicate CTE found - map its old name to the existing hash
+                replacement_mapping[old_name_id] = seen_hashes[cte_hash]
+                cte_indices_to_remove.append(i)
+            else:
+                # New unique CTE - process normally
+                new_hashed_id = exp.to_identifier(cte_hash, quoted=old_name_id.args["quoted"])
+                seen_hashes[cte_hash] = new_hashed_id
+                replacement_mapping[old_name_id] = new_hashed_id
+
             expression = expression.transform(replace_id_value, replacement_mapping).assert_is(
                 exp.Select
             )
+
+        # Remove duplicate CTEs by index in reverse order to avoid index shifting
+        for idx in reversed(cte_indices_to_remove):
+            del expression.args["with"].expressions[idx]
+
         return expression
 
     def _create_cte_from_expression(

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/base/functions.py

@@ -385,9 +385,9 @@ def tan(col: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col, expression.Tan)
 
 
-@meta(unsupported_engines="duckdb")
+@meta()
 def tanh(col: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(col, "TANH")
+    return Column.invoke_expression_over_column(col, expression.Tanh)
 
 
 @meta()
@@ -414,7 +414,7 @@ def radians(col: ColumnOrName) -> Column:
     if session._is_bigquery:
         return radians_bgutil(col)
 
-    return Column.invoke_anonymous_function(col, "RADIANS")
+    return Column.invoke_expression_over_column(col, expression.Radians)
 
 
 toRadians = radians
@@ -1078,7 +1078,7 @@ def hour(col: ColumnOrName) -> Column:
     if session._is_bigquery or session._is_postgres:
         return hour_from_extract(col)
 
-    return Column.invoke_anonymous_function(col, "HOUR")
+    return Column.invoke_expression_over_column(col, expression.Hour)
 
 
 @meta()
@@ -1090,7 +1090,7 @@ def minute(col: ColumnOrName) -> Column:
     if session._is_bigquery or session._is_postgres:
         return minute_from_extract(col)
 
-    return Column.invoke_anonymous_function(col, "MINUTE")
+    return Column.invoke_expression_over_column(col, expression.Minute)
 
 
 @meta()
@@ -1102,7 +1102,7 @@ def second(col: ColumnOrName) -> Column:
     if session._is_bigquery or session._is_postgres:
         return second_from_extract(col)
 
-    return Column.invoke_anonymous_function(col, "SECOND")
+    return Column.invoke_expression_over_column(col, expression.Second)
 
 
 @meta()
@@ -1398,7 +1398,7 @@ def next_day(col: ColumnOrName, dayOfWeek: str) -> Column:
     if session._is_bigquery:
         return next_day_bgutil(col, dayOfWeek)
 
-    return Column.invoke_anonymous_function(col, "NEXT_DAY", lit(dayOfWeek))
+    return Column.invoke_expression_over_column(col, expression.NextDay, expression=lit(dayOfWeek))
 
 
 @meta()
@@ -2160,7 +2160,7 @@ def bit_count(col: ColumnOrName) -> Column:
     if session._is_duckdb:
         return Column.invoke_anonymous_function(col, "BIT_COUNT")
 
-    return Column.invoke_expression_over_column(col, expression.BitwiseCountAgg)
+    return Column.invoke_expression_over_column(col, expression.BitwiseCount)
 
 
 @meta(unsupported_engines="*")
@@ -4108,7 +4108,7 @@ def left(str: ColumnOrName, len: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(str, expression.Left, expression=len)
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines="bigquery")
 def like(
     str: ColumnOrName, pattern: ColumnOrName, escapeChar: t.Optional["Column"] = None
 ) -> Column:
@@ -4886,7 +4886,7 @@ def parse_url(
     )
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery", "snowflake"])
 def pi() -> Column:
     """Returns Pi.
 
@@ -4901,7 +4901,7 @@ def pi() -> Column:
     |3.141592653589793|
     +-----------------+
     """
-    return Column.invoke_anonymous_function(None, "pi")
+    return Column.invoke_expression_over_column(None, expression.Pi)
 
 
 @meta(unsupported_engines="*")
@@ -6805,7 +6805,7 @@ def weekday(col: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(col, "weekday")
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery", "duckdb", "postgres"])
 def width_bucket(
     v: ColumnOrName,
     min: ColumnOrName,
@@ -6854,7 +6854,9 @@ def width_bucket(
     +----------------------------+
     """
     numBucket = lit(numBucket) if isinstance(numBucket, int) else numBucket
-    return Column.invoke_anonymous_function(v, "width_bucket", min, max, numBucket)
+    return Column.invoke_expression_over_column(
+        v, expression.WidthBucket, min_value=min, max_value=max, num_buckets=numBucket
+    )
 
 
 @meta(unsupported_engines=["*", "spark"])

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/base/operations.py

@@ -78,7 +78,7 @@ def operation(
 
 # Here decorate a function (self: _BaseGroupedData[DF], *args, **kwargs) -> DF
 # Hence we work with t.Callable[Concatenate[_BaseGroupedData[DF], P], DF]
-# We simplify the parameters, as Pyright (used for VSCode autocomplete) doesn't unterstand this
+# We simplify the parameters, as Pyright (used for VSCode autocomplete) doesn't understand this
 def group_operation(
     op: Operation,
 ) -> t.Callable[[t.Callable[P, DF]], t.Callable[P, DF]]:

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/base/util.py

@@ -239,7 +239,7 @@ def soundex(s):
     result = [s[0]]
     count = 1
 
-    # find would-be replacment for first character
+    # find would-be replacement for first character
     for lset, sub in replacements:
         if s[0] in lset:
             last = sub

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe/databricks/readwriter.py

@@ -231,7 +231,7 @@ class DatabricksDataFrameWriter(
             elif mode == "ignore":
                 pass
             else:
-                raise RuntimeError(f"Unssuported mode: {mode}")
+                raise RuntimeError(f"Unsupported mode: {mode}")
 
     def insertInto(
         self,

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.43.5
+Version: 3.43.7
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.43.5 → sqlframe-3.43.7}/sqlframe.egg-info/requires.txt

@@ -1,6 +1,6 @@
 more-itertools
 prettytable<4
-sqlglot<27.26,>=24.0.0
+sqlglot<27.29,>=24.0.0
 typing_extensions
 
 [bigquery]

{sqlframe-3.43.5 → sqlframe-3.43.7}/tests/integration/engines/duck/test_duckdb_dataframe.py

@@ -4,6 +4,7 @@ import pytest
 
 from sqlframe.base import types
 from sqlframe.duckdb import DuckDBDataFrame, DuckDBSession
+from sqlframe.duckdb import functions as F
 
 pytest_plugins = ["tests.integration.fixtures"]
 
@@ -266,3 +267,23 @@ def test_explain(duckdb_employee: DuckDBDataFrame, capsys):
 └───────────────────────────┘
 """.strip()
     )
+
+
+def test_duplicate_cte(duckdb_session: DuckDBSession):
+    con = duckdb_session._conn
+
+    con.execute("CREATE VIEW foo AS SELECT 'a' as key, 1 as idx")
+    con.execute("CREATE VIEW bar AS SELECT 'b' as key, 2 as smth")
+
+    foo = duckdb_session.table("foo").filter(F.col("idx") == 1)
+    bar = duckdb_session.table("bar").filter(F.col("smth") == 2)
+
+    df = foo.join(bar, "key", "left")
+
+    df = df.unionByName(df)
+
+    results = duckdb_session._collect(expressions=df._get_expressions(optimize=True))
+    assert results == [
+        types.Row(key="a", idx=1, smth=None),
+        types.Row(key="a", idx=1, smth=None),
+    ]

{sqlframe-3.43.5 → sqlframe-3.43.7}/tests/integration/engines/test_int_functions.py

@@ -4424,7 +4424,7 @@ def test_parse_url(get_session_and_func, get_func):
 
 def test_pi(get_session_and_func, get_func):
     session, pi = get_session_and_func("pi")
-    assert session.range(1).select(pi()).first()[0] == math.pi
+    assert session.range(1).select(pi()).first()[0] in (math.pi, 3.141592654)
 
 
 def test_pmod(get_session_and_func, get_func):