sqlframe 3.43.5__py3-none-any.whl → 3.43.7__py3-none-any.whl

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/_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/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/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/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/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/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.dist-info → sqlframe-3.43.7.dist-info}/METADATA

@@ -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
@@ -18,7 +18,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: more-itertools
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <27.26,>=24.0.0
+Requires-Dist: sqlglot <27.29,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'

{sqlframe-3.43.5.dist-info → sqlframe-3.43.7.dist-info}/RECORD

@@ -1,25 +1,25 @@
-sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=IvY9cEQS0mR8Z_blqYVt_qrlrvrqKlUu84D9RGXXjQI,714
+sqlframe/__init__.py,sha256=Et338oqN6tgrUNzSHpaIyjTiXcXS9lze7qeLFYdRNVc,3536
+sqlframe/_version.py,sha256=rxxVqq9tM144VQj_9aHUEqtWXVIJXvf2oSYA3-oytsk,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
 sqlframe/base/catalog.py,sha256=-YulM2BMK8MoWbXi05AsJIPxd4AuiZDBCZuk4HoeMlE,38900
 sqlframe/base/column.py,sha256=f6rK6-hTiNx9WwJP7t6tqL3xEC2gwERPDlhWCS5iCBw,21417
-sqlframe/base/dataframe.py,sha256=3vlZij84GUKpS23DZSrTRm0mi5SRFjZv_BSn4rAJ0IE,89614
+sqlframe/base/dataframe.py,sha256=iKdiJ9OnMEbL0GAwydP9hQz0XsTKs1mpKi_6ajrCZ9I,90286
 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=6w-uUadya_Tih20uNW21M-UMQ2iM7VPgvZwIT-yn6Zg,229620
+sqlframe/base/functions.py,sha256=FtX9TAoST0Z_OrIlS9bOJ3V--lGmDE8o8rAEiNIL-5Q,229808
 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
+sqlframe/base/operations.py,sha256=v8BA80eDKBOOpfHB_Zxsdi2RrDkSl1-_gtA-GuwO8qY,4438
 sqlframe/base/readerwriter.py,sha256=b1CZgOZv-8h0sC3PWqPVAwAwlDMjpmRys6FGhugKspU,31391
 sqlframe/base/session.py,sha256=jMm18v5MYW7Z61pXda-yd-WNYYwnYU9i2jIaT8gKSvA,27687
 sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
 sqlframe/base/types.py,sha256=OktuJ5f7tEogOW0oupI0RBlHfzZMmKh7zGLke9cwllo,12305
 sqlframe/base/udf.py,sha256=O6hMhBUy9NVv-mhJRtfFhXTIa_-Z8Y_FkmmuOHu0l90,1117
-sqlframe/base/util.py,sha256=11rBF_GBFXGBCllSdlWWWo8EiZZATJn4me3u7OUNIFg,19782
+sqlframe/base/util.py,sha256=THc2Xpa3oo-cKohFFQ1KFTMn8WSrSD58sTjNMAtr7wM,19783
 sqlframe/base/window.py,sha256=7NaKDTlhun-95LEghukBCjFBwq0RHrPaajWQNCsLxok,4818
 sqlframe/base/mixins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/mixins/catalog_mixins.py,sha256=9fZGWToz9xMJSzUl1vsVtj6TH3TysP3fBCKJLnGUQzE,23353
@@ -46,7 +46,7 @@ sqlframe/databricks/dataframe.py,sha256=8kwT1kWU2TwGjR9zDrGdmkvabiBCivA_Mcg06r2X
 sqlframe/databricks/functions.py,sha256=La8rjAwO0hD4FBO0QxW5CtZtFAPvOrVc6lG4OtPGgbc,336
 sqlframe/databricks/functions.pyi,sha256=FzVBpzXCJzxIp73sIAo_R8Wx8uOJrix-W12HsgyeTcQ,23799
 sqlframe/databricks/group.py,sha256=dU3g0DVLRlfOSCamKchQFXRd1WTFbdxoXkpEX8tPD6Y,399
-sqlframe/databricks/readwriter.py,sha256=u2-0j_gXB4JikMxLBzUWhJZhJ5tYbGJpIGTqnWuDKqk,14521
+sqlframe/databricks/readwriter.py,sha256=RHwhfnYXC8LOCE_WSKufIB5CvHWeSiaKg5DUHjfGDTY,14521
 sqlframe/databricks/session.py,sha256=i2CgrLIHJb53Cx1qu_rE1-cmmm19S-Sw1MhTISX1zYU,4013
 sqlframe/databricks/table.py,sha256=Q0Vnrl5aUqnqFTQpTwfWMRyQ9AQnagtpnSnXmP6IKRs,678
 sqlframe/databricks/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
@@ -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-3.43.5.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.43.5.dist-info/METADATA,sha256=30lHlixHE3YTNzzWqPsYLh00DzthRRTU3KbM96TE8Cc,9070
-sqlframe-3.43.5.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.43.5.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.43.5.dist-info/RECORD,,
+sqlframe-3.43.7.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.43.7.dist-info/METADATA,sha256=pOTnxd_hgmoNGSbRzFF-4fWMETe2sq8VKRL3_HhMg0o,9070
+sqlframe-3.43.7.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.43.7.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.43.7.dist-info/RECORD,,