sqlframe 3.4.0__py3-none-any.whl → 3.5.0__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.4.0'
-__version_tuple__ = version_tuple = (3, 4, 0)
+__version__ = version = '3.5.0'
+__version_tuple__ = version_tuple = (3, 5, 0)

sqlframe/base/column.py

@@ -338,6 +338,9 @@ class Column:
         new_expression = exp.Not(this=exp.Is(this=self.column_expression, expression=exp.Null()))
         return Column(new_expression)
 
+    def eqNullSafe(self, other: ColumnOrLiteral) -> Column:
+        return self.binary_op(exp.NullSafeEQ, other)
+
     def cast(
         self,
         dataType: t.Union[str, DataType, exp.DataType, exp.DataType.Type],
@@ -385,7 +388,7 @@ class Column:
 
     def isin(self, *cols: t.Union[ColumnOrLiteral, t.Iterable[ColumnOrLiteral]]):
         columns = flatten(cols) if isinstance(cols[0], (list, set, tuple)) else cols  # type: ignore
-        expressions = [self._lit(x).expression for x in columns]
+        expressions = [self._lit(x).expression for x in columns]  # type: ignore
         return Column.invoke_expression_over_column(self, exp.In, expressions=expressions)  # type: ignore
 
     def between(

sqlframe/base/dataframe.py

@@ -15,7 +15,7 @@ from dataclasses import dataclass
 
 import sqlglot
 from prettytable import PrettyTable
-from sqlglot import Dialect
+from sqlglot import Dialect, maybe_parse
 from sqlglot import expressions as exp
 from sqlglot import lineage as sqlglot_lineage
 from sqlglot.helper import ensure_list, flatten, object_to_dict, seq_get
@@ -460,16 +460,40 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         df.expression.ctes[-1].set("cache_storage_level", storage_level)
         return df
 
-    @classmethod
-    def _add_ctes_to_expression(cls, expression: exp.Select, ctes: t.List[exp.CTE]) -> exp.Select:
+    def _add_ctes_to_expression(self, expression: exp.Select, ctes: t.List[exp.CTE]) -> exp.Select:
         expression = expression.copy()
         with_expression = expression.args.get("with")
         if with_expression:
             existing_ctes = with_expression.expressions
-            existsing_cte_names = {x.alias_or_name for x in existing_ctes}
+            existing_cte_counts = {x.alias_or_name: 0 for x in existing_ctes}
+            replaced_cte_names = {}  # type: ignore
             for cte in ctes:
-                if cte.alias_or_name not in existsing_cte_names:
-                    existing_ctes.append(cte)
+                if replaced_cte_names:
+                    cte = cte.transform(replace_id_value, replaced_cte_names)  # type: ignore
+                if cte.alias_or_name in existing_cte_counts:
+                    existing_cte_counts[cte.alias_or_name] += 10
+                    cte.set(
+                        "this",
+                        cte.this.where(
+                            exp.EQ(
+                                this=exp.Literal.number(existing_cte_counts[cte.alias_or_name]),
+                                expression=exp.Literal.number(
+                                    existing_cte_counts[cte.alias_or_name]
+                                ),
+                            )
+                        ),
+                    )
+                    new_cte_alias = self._create_hash_from_expression(cte.this)
+                    replaced_cte_names[cte.args["alias"].this] = maybe_parse(
+                        new_cte_alias, dialect=self.session.input_dialect, into=exp.Identifier
+                    )
+                    cte.set(
+                        "alias",
+                        maybe_parse(
+                            new_cte_alias, dialect=self.session.input_dialect, into=exp.TableAlias
+                        ),
+                    )
+                existing_ctes.append(cte)
         else:
             existing_ctes = ctes
         expression.set("with", exp.With(expressions=existing_ctes))
@@ -843,11 +867,11 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             logger.warning("Got no value for on. This appears to change the join to a cross join.")
             how = "cross"
         other_df = other_df._convert_leaf_to_cte()
+        join_expression = self._add_ctes_to_expression(self.expression, other_df.expression.ctes)
         # We will determine actual "join on" expression later so we don't provide it at first
-        join_expression = self.expression.join(
-            other_df.latest_cte_name, join_type=how.replace("_", " ")
+        join_expression = join_expression.join(
+            join_expression.ctes[-1].alias, join_type=how.replace("_", " ")
         )
-        join_expression = self._add_ctes_to_expression(join_expression, other_df.expression.ctes)
         self_columns = self._get_outer_select_columns(join_expression)
         other_columns = self._get_outer_select_columns(other_df.expression)
         join_columns = self._ensure_and_normalize_cols(on)

sqlframe/base/function_alternatives.py

@@ -1320,8 +1320,8 @@ def flatten_using_array_flatten(col: ColumnOrName) -> Column:
 def map_concat_using_map_cat(*cols: t.Union[ColumnOrName, t.Iterable[ColumnOrName]]) -> Column:
     columns = list(flatten(cols)) if not isinstance(cols[0], (str, Column)) else cols  # type: ignore
     if len(columns) == 1:
-        return Column.invoke_anonymous_function(columns[0], "MAP_CAT")
-    return Column.invoke_anonymous_function(columns[0], "MAP_CAT", *columns[1:])
+        return Column.invoke_anonymous_function(columns[0], "MAP_CAT")  # type: ignore
+    return Column.invoke_anonymous_function(columns[0], "MAP_CAT", *columns[1:])  # type: ignore
 
 
 def sequence_from_generate_series(

sqlframe/base/functions.py

@@ -1652,8 +1652,8 @@ def arrays_zip(*cols: ColumnOrName) -> Column:
 def map_concat(*cols: t.Union[ColumnOrName, t.Iterable[ColumnOrName]]) -> Column:
     columns = list(flatten(cols)) if not isinstance(cols[0], (str, Column)) else cols  # type: ignore
     if len(columns) == 1:
-        return Column.invoke_anonymous_function(columns[0], "MAP_CONCAT")
-    return Column.invoke_anonymous_function(columns[0], "MAP_CONCAT", *columns[1:])
+        return Column.invoke_anonymous_function(columns[0], "MAP_CONCAT")  # type: ignore
+    return Column.invoke_anonymous_function(columns[0], "MAP_CONCAT", *columns[1:])  # type: ignore
 
 
 @meta(unsupported_engines="postgres")
@@ -4697,7 +4697,7 @@ def spark_partition_id() -> Column:
     return Column.invoke_anonymous_function(None, "spark_partition_id")
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines=["bigquery", "postgres"])
 def split_part(src: ColumnOrName, delimiter: ColumnOrName, partNum: ColumnOrName) -> Column:
     """
     Splits `str` by delimiter and return requested part of the split (1-based).
@@ -4723,7 +4723,9 @@ def split_part(src: ColumnOrName, delimiter: ColumnOrName, partNum: ColumnOrName
     >>> df.select(split_part(df.a, df.b, df.c).alias('r')).collect()
     [Row(r='13')]
     """
-    return Column.invoke_anonymous_function(src, "split_part", delimiter, partNum)
+    return Column.invoke_expression_over_column(
+        src, expression.SplitPart, delimiter=delimiter, part_index=partNum
+    )
 
 
 @meta()

sqlframe/duckdb/functions.pyi

@@ -177,6 +177,7 @@ from sqlframe.base.functions import (
     skewness as skewness,
     sort_array as sort_array,
     soundex as soundex,
+    split_part as split_part,
     sqrt as sqrt,
     startswith as startswith,
     stddev as stddev,

sqlframe/snowflake/functions.pyi

@@ -187,6 +187,7 @@ from sqlframe.base.functions import (
     sinh as sinh,
     size as size,
     soundex as soundex,
+    split_part as split_part,
     sqrt as sqrt,
     startswith as startswith,
     stddev as stddev,

{sqlframe-3.4.0.dist-info → sqlframe-3.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.4.0
+Version: 3.5.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -18,7 +18,7 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable (<3.11.1)
-Requires-Dist: sqlglot (<25.25,>=24.0.0)
+Requires-Dist: sqlglot (<25.26,>=24.0.0)
 Requires-Dist: typing-extensions (<5,>=4.8)
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage (<3,>=2) ; extra == 'bigquery'
@@ -26,8 +26,8 @@ Requires-Dist: google-cloud-bigquery[pandas] (<4,>=3) ; extra == 'bigquery'
 Provides-Extra: dev
 Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'dev'
 Requires-Dist: findspark (<3,>=2) ; extra == 'dev'
-Requires-Dist: mypy (<1.12,>=1.10.0) ; extra == 'dev'
-Requires-Dist: openai (<1.52,>=1.30) ; extra == 'dev'
+Requires-Dist: mypy (<1.13,>=1.10.0) ; extra == 'dev'
+Requires-Dist: openai (<1.53,>=1.30) ; extra == 'dev'
 Requires-Dist: pandas-stubs (<3,>=2) ; extra == 'dev'
 Requires-Dist: pandas (<3,>=2) ; extra == 'dev'
 Requires-Dist: psycopg (<4,>=3.1) ; extra == 'dev'
@@ -36,7 +36,7 @@ Requires-Dist: pyspark (<3.6,>=2) ; extra == 'dev'
 Requires-Dist: pytest-postgresql (<7,>=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 (<0.7,>=0.4.4) ; extra == 'dev'
+Requires-Dist: ruff (<0.8,>=0.4.4) ; extra == 'dev'
 Requires-Dist: types-psycopg2 (<3,>=2.9) ; extra == 'dev'
 Requires-Dist: pre-commit (>=3.5) ; (python_version == "3.8") and extra == 'dev'
 Requires-Dist: pre-commit (<4.1,>=3.7) ; (python_version >= "3.9") and extra == 'dev'
@@ -50,7 +50,7 @@ Provides-Extra: duckdb
 Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'duckdb'
 Requires-Dist: pandas (<3,>=2) ; extra == 'duckdb'
 Provides-Extra: openai
-Requires-Dist: openai (<1.52,>=1.30) ; extra == 'openai'
+Requires-Dist: openai (<1.53,>=1.30) ; extra == 'openai'
 Provides-Extra: pandas
 Requires-Dist: pandas (<3,>=2) ; extra == 'pandas'
 Provides-Extra: postgres

{sqlframe-3.4.0.dist-info → sqlframe-3.5.0.dist-info}/RECORD

@@ -1,14 +1,14 @@
 sqlframe/__init__.py,sha256=E3qCJ4PSEgKz6Hg3ves6LWt3JrQOV8c9HVLSIUOzKNc,3106
-sqlframe/_version.py,sha256=YWGqQYvejjlymmjzg4jncyBgDC760jlRmyon_Rd-2uQ,411
+sqlframe/_version.py,sha256=wy34mXzQ8fLJu7i4fZikKwCDGQODEviQb-OrdMe9F4Q,411
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=b2clI5HI1zEZKB_3Msx3FeAJQyft44ubUifJwQRVXyQ,1298
 sqlframe/base/catalog.py,sha256=SzFQalTWdhWzxUY-4ut1f9TfOECp_JmJEgNPfrRKCe0,38457
-sqlframe/base/column.py,sha256=C2xj6OHMsJbEgjbI-m5HuIvqHYt2DbbUtCjssKpplNk,17748
-sqlframe/base/dataframe.py,sha256=uTM46auSPniww-ZMtI5s0hrrCG1nOICMEhdZZ8E4cu8,71636
+sqlframe/base/column.py,sha256=06fhVZ2nCn2QLxnfjdK-oYKeTFJC_smgSxu7u2UYlVg,17878
+sqlframe/base/dataframe.py,sha256=coeUwntwYbT1g6YKVwk3ZfWMfJqAzd1ECYabBSsNsV0,72892
 sqlframe/base/decorators.py,sha256=Jy4bf8MhZ-AJ6CWTj59bBJRqamtLbPC0USUMFrY6g0w,449
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
-sqlframe/base/function_alternatives.py,sha256=IxNBqplehkAEkpzA625Dif-9Xyi4Hrho81A9U262rV0,50714
-sqlframe/base/functions.py,sha256=b6rjrBHHpTMzBU2N5ubdXMJACM40qw4WnbI_RqusWIU,189878
+sqlframe/base/function_alternatives.py,sha256=Cqt-OjyWewCXZJ8PV-2vc8yrDG2ennLPm6yWaxWVXRc,50746
+sqlframe/base/functions.py,sha256=JDVULt3WI1cwWYboU8ybenIXZPdKSNtnzg7A4xC1Lao,189978
 sqlframe/base/group.py,sha256=fsyG5990_Pd7gFPjTFrH9IEoAquL_wEkVpIlBAIkZJU,4091
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=-AhNuEzcV7ZExoP1oY3blaKip-joQyJeQVvfBTs_2g4,3456
@@ -40,7 +40,7 @@ sqlframe/duckdb/catalog.py,sha256=YYYVmetLUaJOdObKw4AJ7L0P-msshkta4xHlcZQ9zEA,47
 sqlframe/duckdb/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/duckdb/dataframe.py,sha256=HZg_uMAz4RsubZJT4-MslUQS_0-InF0_P5Yq5HyJ3wE,1708
 sqlframe/duckdb/functions.py,sha256=Ee8o6YFtRdEiq0jNLXxgu5lcbc7Tsg0-lK6oRyxdcjo,1920
-sqlframe/duckdb/functions.pyi,sha256=mKr9hI4snRyXEeWWTYfRNpBJmWd5T2EujdQ0oJxpEjY,5849
+sqlframe/duckdb/functions.pyi,sha256=bWfQl7Cm1eecI39LJAyyRcC4z7epDJ-h9JOozPsEc34,5879
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
 sqlframe/duckdb/readwriter.py,sha256=iY0Wsms35gymilETOhAQGQCHfH8LCj9_uY8aCdF77ds,4806
 sqlframe/duckdb/session.py,sha256=b5IrKbTkYUVNQGSG2EJPNV9MTdJw4onN-9aMrskjxck,2721
@@ -75,7 +75,7 @@ sqlframe/snowflake/catalog.py,sha256=Tp_B9oMTInnqLTiZNsT0UNc-a-aKXu3zFThlCwLeKCA
 sqlframe/snowflake/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
 sqlframe/snowflake/dataframe.py,sha256=ANDZ5Dpxz-WTlTtmKNcv-nJlzTeTsAOK0X0gR2euPqQ,2144
 sqlframe/snowflake/functions.py,sha256=iX67xU8Czy5k3HiNjNbN-x-via6yqGNaMPw1maV9HPs,2580
-sqlframe/snowflake/functions.pyi,sha256=DoRyF0zob8kV7qHkHonyyyPex-C_GIQvFDaSxf2lSa4,6207
+sqlframe/snowflake/functions.pyi,sha256=anVqp9rhkkD6uTTiQYGbScFed3dp_uRcyPwq1JnRmRI,6237
 sqlframe/snowflake/group.py,sha256=pPP1l2RRo_LgkXrji8a87n2PKo-63ZRPT-WUtvVcBME,395
 sqlframe/snowflake/readwriter.py,sha256=yhRc2HcMq6PwV3ghZWC-q-qaE7LE4aEjZEXCip4OOlQ,884
 sqlframe/snowflake/session.py,sha256=fnFYrJ9JxoOf4ZKTrQcSKjwr6wNp6A85cMqKczOi3vA,3320
@@ -107,8 +107,8 @@ 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=9DDYVuocO7tygee3RaajuJNZ24sJwf_LY556kKg7kTw,13011
-sqlframe-3.4.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.4.0.dist-info/METADATA,sha256=IDBAwEcCrJfWwGuAaa8kfV3Jxlte38uOYO87zcFWJfY,8639
-sqlframe-3.4.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-3.4.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.4.0.dist-info/RECORD,,
+sqlframe-3.5.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.5.0.dist-info/METADATA,sha256=vH1Trx574zbKeuhU0oPb0Q7dxgGvHqaONgNiO3tcbkk,8639
+sqlframe-3.5.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+sqlframe-3.5.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.5.0.dist-info/RECORD,,