sqlframe 3.18.0__py3-none-any.whl → 3.19.0__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.18.0'
-__version_tuple__ = version_tuple = (3, 18, 0)
+__version__ = version = '3.19.0'
+__version_tuple__ = version_tuple = (3, 19, 0)

sqlframe/base/dataframe.py

@@ -1066,7 +1066,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                         left_col.sql(dialect=self.session.input_dialect),
                         right_col.sql(dialect=self.session.input_dialect),
                     ).alias(left_col.alias_or_name)
-                    if how == "full"
+                    if join_type == "full outer"
                     else left_col.alias_or_name
                     for left_col, right_col in join_column_pairs
                 ]

sqlframe/base/functions.py

@@ -8,6 +8,7 @@ import typing as t
 
 from sqlglot import Dialect
 from sqlglot import exp as expression
+from sqlglot.dialects.dialect import time_format
 from sqlglot.helper import ensure_list
 from sqlglot.helper import flatten as _flatten
 
@@ -2016,9 +2017,12 @@ def array_prepend(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
     return Column.invoke_anonymous_function(col, "ARRAY_PREPEND", value)
 
 
-@meta(unsupported_engines="*")
+@meta()
 def array_size(col: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(col, "ARRAY_SIZE")
+    session = _get_session()
+    if session._is_spark or session._is_databricks:
+        return Column.invoke_anonymous_function(col, "ARRAY_SIZE")
+    return Column.invoke_expression_over_column(col, expression.ArraySize)
 
 
 @meta(unsupported_engines="*")
@@ -6088,7 +6092,7 @@ def to_timestamp_ltz(
         return Column.invoke_anonymous_function(timestamp, "to_timestamp_ltz")
 
 
-@meta(unsupported_engines="*")
+@meta()
 def to_timestamp_ntz(
     timestamp: ColumnOrName,
     format: t.Optional[ColumnOrName] = None,
@@ -6118,6 +6122,32 @@ def to_timestamp_ntz(
     ... # doctest: +SKIP
     [Row(r=datetime.datetime(2016, 4, 8, 0, 0))]
     """
+    session = _get_session()
+
+    if session._is_duckdb:
+        to_timestamp_func = get_func_from_session("to_timestamp")
+        return to_timestamp_func(timestamp, format)
+
+    if session._is_bigquery:
+        if format is not None:
+            return Column.invoke_anonymous_function(
+                session.format_execution_time(format),  # type: ignore
+                "parse_datetime",
+                timestamp,
+            )
+        else:
+            return Column.ensure_col(timestamp).cast("datetime", dialect="bigquery")
+
+    if session._is_postgres:
+        if format is not None:
+            return Column.invoke_anonymous_function(
+                timestamp,
+                "to_timestamp",
+                session.format_execution_time(format),  # type: ignore
+            )
+        else:
+            return Column.ensure_col(timestamp).cast("timestamp", dialect="postgres")
+
     if format is not None:
         return Column.invoke_anonymous_function(timestamp, "to_timestamp_ntz", format)
     else:
@@ -6442,12 +6472,25 @@ def unix_micros(col: ColumnOrName) -> Column:
     """
     from sqlframe.base.function_alternatives import unix_micros_multiply_epoch
 
-    if (
-        _get_session()._is_bigquery
-        or _get_session()._is_duckdb
-        or _get_session()._is_postgres
-        or _get_session()._is_snowflake
-    ):
+    if _get_session()._is_duckdb:
+        return Column.invoke_anonymous_function(col, "epoch_us")
+
+    if _get_session()._is_bigquery:
+        return Column(
+            expression.Anonymous(
+                this="UNIX_MICROS",
+                expressions=[
+                    expression.Anonymous(
+                        this="TIMESTAMP",
+                        expressions=[
+                            Column.ensure_col(col).column_expression,
+                        ],
+                    )
+                ],
+            )
+        )
+
+    if _get_session()._is_postgres or _get_session()._is_snowflake:
         return unix_micros_multiply_epoch(col)
 
     return Column.invoke_anonymous_function(col, "unix_micros")

sqlframe/base/session.py

@@ -267,10 +267,6 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
         else:
             column_mapping = {}
 
-        column_mapping = {
-            normalize_identifiers(k, self.input_dialect).sql(dialect=self.input_dialect): v
-            for k, v in column_mapping.items()
-        }
         empty_df = not data
         rows = [[None] * len(column_mapping)] if empty_df else list(data)  # type: ignore
 
@@ -327,7 +323,6 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
             if isinstance(sample_row, Row):
                 sample_row = sample_row.asDict()
             if isinstance(sample_row, dict):
-                sample_row = normalize_dict(self, sample_row)
                 default_data_type = get_default_data_type(sample_row[name])
                 updated_mapping[name] = (
                     exp.DataType.build(default_data_type, dialect="spark")
@@ -387,7 +382,11 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
         sel_expression = exp.Select(**select_kwargs)
         if empty_df:
             sel_expression = sel_expression.where(exp.false())
-        return self._create_df(sel_expression)
+        df = self._create_df(sel_expression)
+        df._update_display_name_mapping(
+            df._ensure_and_normalize_cols(list(column_mapping.keys())), list(column_mapping.keys())
+        )
+        return df
 
     def sql(
         self,
@@ -526,7 +525,9 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
             col_id._meta = {"case_sensitive": True, **(col_id._meta or {})}
             case_sensitive_cols.append(col_id)
         columns = [
-            normalize_string(x, from_dialect="execution", to_dialect="output")
+            normalize_string(
+                x, from_dialect="execution", to_dialect="output", to_string_literal=True
+            )
             for x in case_sensitive_cols
         ]
         return [self._to_row(columns, row) for row in result]

sqlframe/spark/session.py

@@ -86,7 +86,7 @@ class SparkSession(
                 col_id = exp.parse_identifier(k, dialect=self.execution_dialect)
                 col_id._meta = {"case_sensitive": True, **(col_id._meta or {})}
                 col_name = normalize_string(
-                    col_id, from_dialect="execution", to_dialect="output", is_column=True
+                    col_id, from_dialect="execution", to_dialect="output", to_string_literal=True
                 )
                 rows_normalized[col_name] = v
             results.append(Row(**rows_normalized))

{sqlframe-3.18.0.dist-info → sqlframe-3.19.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.18.0
+Version: 3.19.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -17,7 +17,7 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <26.5,>=24.0.0
+Requires-Dist: sqlglot <26.7,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'

{sqlframe-3.18.0.dist-info → sqlframe-3.19.0.dist-info}/RECORD

@@ -1,19 +1,19 @@
 sqlframe/__init__.py,sha256=wfqm98eLoLid9oV_FzzpG5loKC6LxOhj2lXpfN7SARo,3138
-sqlframe/_version.py,sha256=sbqQ7wMrRCbK9h4-ahk9DoaetF-oPVAV49BG-2oJfiQ,413
+sqlframe/_version.py,sha256=bRGLbmtauY86O6qq58KRvSDdCcwrGM24X-Zm0Elw0sU,413
 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=oHVwkSWABO3ZlAbgBShsxSSlgbI06BOup5XJrRhgqJI,18097
-sqlframe/base/dataframe.py,sha256=5gF_zvafC60rZ1OdnB4klKALw35mmxllYTVgIIiZPY0,79340
+sqlframe/base/dataframe.py,sha256=mKXbIKYiKH5mh6qj0Dg7L_znmCL85q9kHlmHtCW4kJ4,79352
 sqlframe/base/decorators.py,sha256=ms-CvDOIW3T8IVB9VqDmLwAiaEsqXLYRXEqVQaxktiM,1890
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=NV31IaEhVYmfUSWetAEFISAvLzs2DxQ7bp-iMNgj0hQ,53786
-sqlframe/base/functions.py,sha256=1LHxazgC9tZ_GzyWNsjU945SRnAsQjUH2easMJLU3h4,221012
+sqlframe/base/functions.py,sha256=j_Sh4qIcR-2lesJT_2TzBlTIM46os35AcmMuwBm86DE,222512
 sqlframe/base/group.py,sha256=fsyG5990_Pd7gFPjTFrH9IEoAquL_wEkVpIlBAIkZJU,4091
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=xSPw74e59wYvNd6U1AlwziNCTG6Aftrbl4SybN9u9VE,3450
 sqlframe/base/readerwriter.py,sha256=w8926cqIrXF7NGHiINw5UHzP_3xpjsqbijTBTzycBRM,26605
-sqlframe/base/session.py,sha256=aSp83JXEW_zEMfe1JxPFcjqq2yUThwYboCnk0LqhUko,27290
+sqlframe/base/session.py,sha256=G5_bI_z1iJtAGm2SgEdjkKiyJmS0yOUopx9P5TEGdR4,27273
 sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
 sqlframe/base/types.py,sha256=iBNk9bpFtb2NBIogYS8i7OlQZMRvpR6XxqzBebsjQDU,12280
@@ -110,7 +110,7 @@ sqlframe/spark/functions.py,sha256=MYCgHsjRQWylT-rezWRBuLV6BivcaVarbaQtP4T0toQ,3
 sqlframe/spark/functions.pyi,sha256=GyOdUzv2Z7Qt99JAKEPKgV2t2Rn274OuqwAfcoAXlN0,24259
 sqlframe/spark/group.py,sha256=MrvV_v-YkBc6T1zz882WrEqtWjlooWIyHBCmTQg3fCA,379
 sqlframe/spark/readwriter.py,sha256=zXZcCPWpQMMN90wdIx8AD4Y5tWBcpRSL4-yKX2aZyik,874
-sqlframe/spark/session.py,sha256=fYu8aVSDRAJ7ZnA7zgba7acXjP8ROJshfX5UYmEq5mI,5667
+sqlframe/spark/session.py,sha256=irlsTky06pKRKAyPLwVzUtLGe4O8mALSgxIqLvqJNF8,5675
 sqlframe/spark/table.py,sha256=puWV8h_CqA64zwpzq0ydY9LoygMAvprkODyxyzZeF9M,186
 sqlframe/spark/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/spark/udf.py,sha256=owB8NDaGVkUQ0WGm7SZt2t9zfvLFCfi0W48QiPfgjck,1153
@@ -129,8 +129,8 @@ 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-3.18.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.18.0.dist-info/METADATA,sha256=5riMB4lxhi4MDtVWW-kgUK6_PQwdjLDaC5NXSYNNrQ8,8970
-sqlframe-3.18.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.18.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.18.0.dist-info/RECORD,,
+sqlframe-3.19.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.19.0.dist-info/METADATA,sha256=t_G87pTEVYezUc-A5TIumPN-sHNsgTjW8vNgZ4Jvjpw,8970
+sqlframe-3.19.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.19.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.19.0.dist-info/RECORD,,