sqlframe 3.28.1__py3-none-any.whl → 3.29.0__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.28.1'
-__version_tuple__ = version_tuple = (3, 28, 1)
+__version__ = version = '3.29.0'
+__version_tuple__ = version_tuple = (3, 29, 0)

sqlframe/base/dataframe.py

@@ -80,8 +80,6 @@ JOIN_HINTS = {
 }
 
 JOIN_TYPE_MAPPING = {
-    "inner": "inner",
-    "cross": "cross",
     "outer": "full_outer",
     "full": "full_outer",
     "fullouter": "full_outer",
@@ -91,10 +89,8 @@ JOIN_TYPE_MAPPING = {
     "rightouter": "right_outer",
     "semi": "left_semi",
     "leftsemi": "left_semi",
-    "left_semi": "left_semi",
     "anti": "left_anti",
     "leftanti": "left_anti",
-    "left_anti": "left_anti",
 }
 
 DF = t.TypeVar("DF", bound="BaseDataFrame")
@@ -1028,7 +1024,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     @operation(Operation.FROM)
     def join(
         self,
-        other_df: Self,
+        other: Self,
         on: t.Optional[t.Union[str, t.List[str], Column, t.List[Column]]] = None,
         how: str = "inner",
         **kwargs,
@@ -1044,7 +1040,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             logger.warning("Got cross join with an 'on' value. This will result in an inner join.")
             how = "inner"
 
-        other_df = other_df._convert_leaf_to_cte()
+        other_df = other._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_type = JOIN_TYPE_MAPPING.get(how, how).replace("_", " ")
@@ -1599,6 +1595,8 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     @operation(Operation.LIMIT)
     def limit(self, num: int) -> Self:
+        if limit_exp := self.expression.args.get("limit"):
+            num = min(num, int(limit_exp.expression.this))
         return self.copy(expression=self.expression.limit(num))
 
     def toDF(self, *cols: str) -> Self:
@@ -1854,11 +1852,11 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     def head(self, n: int) -> t.List[Row]: ...
 
     def head(self, n: t.Optional[int] = None) -> t.Union[t.Optional[Row], t.List[Row]]:
-        n = n or 1
-        df = self.limit(n)
-        if n == 1:
-            return df.collect()[0]
-        return df.collect()
+        df = self.limit(n or 1)
+        collected = df.collect()
+        if n is None:
+            return seq_get(collected, 0)
+        return collected
 
     def first(self) -> t.Optional[Row]:
         return self.head()
@@ -1939,6 +1937,11 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     def createGlobalTempView(self, name: str) -> None:
         raise NotImplementedError("Global temp views are not yet supported")
 
+    def isEmpty(self) -> bool:
+        from sqlframe.base import functions as F
+
+        return not bool(self.select(F.lit(True)).head())
+
     """
     Stat Functions
     """

{sqlframe-3.28.1.dist-info → sqlframe-3.29.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.28.1
+Version: 3.29.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -69,18 +69,19 @@ Requires-Dist: pyspark <3.6,>=2 ; extra == 'spark'
 
 SQLFrame implements the PySpark DataFrame API in order to enable running transformation pipelines directly on database engines - no Spark clusters or dependencies required.
 
-SQLFrame currently supports the following engines (many more in development):
+SQLFrame currently supports the following engines:
 
 * [BigQuery](https://sqlframe.readthedocs.io/en/stable/bigquery/)
+* [Databricks](https://sqlframe.readthedocs.io/en/stable/databricks)
 * [DuckDB](https://sqlframe.readthedocs.io/en/stable/duckdb)
 * [Postgres](https://sqlframe.readthedocs.io/en/stable/postgres)
 * [Snowflake](https://sqlframe.readthedocs.io/en/stable/snowflake)
 * [Spark](https://sqlframe.readthedocs.io/en/stable/spark)
 
-There are also two engines in development. These engines lack test coverage and robust documentation, but are available for early testing:
+There is also one engine in development. This engine lacks test coverage and robust documentation, but is available for testing:
 
 * [Redshift](https://sqlframe.readthedocs.io/en/stable/redshift)
-* [Databricks](https://sqlframe.readthedocs.io/en/stable/databricks)
+
 
 SQLFrame also has a "Standalone" session that be used to generate SQL without any connection to a database engine.
 
@@ -98,6 +99,8 @@ SQLFrame is great for:
 ```bash
 # BigQuery
 pip install "sqlframe[bigquery]"
+# Databricks
+pip install "sqlframe[databricks]"
 # DuckDB
 pip install "sqlframe[duckdb]"
 # Postgres
@@ -108,8 +111,6 @@ pip install "sqlframe[snowflake]"
 pip install "sqlframe[spark]"
 # Redshift (in development)
 pip install "sqlframe[redshift]"
-# Databricks (in development)
-pip install "sqlframe[databricks]"
 # Standalone
 pip install sqlframe
 ```

{sqlframe-3.28.1.dist-info → sqlframe-3.29.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=A-DozXRgJ1GLBl_eHEhQbTd1M98mV_YRq5bK5pd8Y5s,513
+sqlframe/_version.py,sha256=OsI8JHahRj2deRNv0lP32D0W4kMOH1vXOQfyhRqxRos,513
 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=ZuU_qmt4yjSoTYgecSGnOhitOdh3rJbGCUjnUBp5mlc,38564
 sqlframe/base/column.py,sha256=AG9Z_6RNhVxLhLU29kRCgzMgDNSm-_GFg96xLqk1-bs,19838
-sqlframe/base/dataframe.py,sha256=YaXf2rixLRz8CIqyH__XZNz6zhtW3cLwJcHMezUv_BU,84138
+sqlframe/base/dataframe.py,sha256=D2N2Kvh_tiF60fYODUikq0xRCJYY4WB2aHbEcq5NIUo,84310
 sqlframe/base/decorators.py,sha256=IhE5xNQDkwJHacCvulq5WpUKyKmXm7dL2A3o5WuKGP4,2131
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=Bs1bwl25fN3Yy9rb4GnUWBGunQ1C_yelkb2yV9DSZIY,53918
@@ -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-3.28.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.28.1.dist-info/METADATA,sha256=Uj6Y7-cFVwC36CpmSaZLn3Ual76hfPkqr2jjF7TqFLg,8971
-sqlframe-3.28.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.28.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.28.1.dist-info/RECORD,,
+sqlframe-3.29.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.29.0.dist-info/METADATA,sha256=0bSBzyT55lAQRUMQcz92sGhoaFOrc9h2EPIRyKPHRbo,8918
+sqlframe-3.29.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.29.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.29.0.dist-info/RECORD,,