sqlframe 3.14.2__py3-none-any.whl → 3.15.1__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.14.2'
-__version_tuple__ = version_tuple = (3, 14, 2)
+__version__ = version = '3.15.1'
+__version_tuple__ = version_tuple = (3, 15, 1)

sqlframe/base/function_alternatives.py

@@ -6,9 +6,7 @@ import re
 import typing as t
 
 from sqlglot import exp as expression
-from sqlglot.dialects.dialect import build_formatted_time
 from sqlglot.helper import ensure_list
-from sqlglot.helper import flatten as _flatten
 
 from sqlframe.base.column import Column
 from sqlframe.base.util import (
@@ -1410,6 +1408,14 @@ def regexp_replace_global_option(
     )
 
 
+def regexp_with_matches(str: ColumnOrName, regexp: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(str, "REGEXP_MATCHES", regexp)
+
+
+def regexp_with_contains(str: ColumnOrName, regexp: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(str, "REGEXP_CONTAINS", regexp)
+
+
 def degrees_bgutil(col: ColumnOrName) -> Column:
     return Column(
         expression.Anonymous(
@@ -1519,6 +1525,43 @@ def unix_timestamp_bgutil(
     )
 
 
+def unix_seconds_extract_epoch(col: ColumnOrName) -> Column:
+    return Column(
+        expression.Extract(
+            this=expression.Var(this="EPOCH"),
+            expression=Column.ensure_col(col).column_expression,
+        )
+    )
+
+
+def unix_millis_multiply_epoch(col: ColumnOrName) -> Column:
+    unix_seconds = get_func_from_session("unix_seconds")
+
+    return Column(
+        expression.Cast(
+            this=expression.Mul(
+                this=unix_seconds(col).column_expression,
+                expression=expression.Literal.number(1000),
+            ),
+            to=expression.DataType.build("bigint"),
+        )
+    )
+
+
+def unix_micros_multiply_epoch(col: ColumnOrName) -> Column:
+    unix_seconds = get_func_from_session("unix_seconds")
+
+    return Column(
+        expression.Cast(
+            this=expression.Mul(
+                this=unix_seconds(col).column_expression,
+                expression=expression.Literal.number(1000000),
+            ),
+            to=expression.DataType.build("bigint"),
+        )
+    )
+
+
 def format_number_bgutil(col: ColumnOrName, d: int) -> Column:
     round = get_func_from_session("round")
     lit = get_func_from_session("lit")

sqlframe/base/functions.py

@@ -51,6 +51,8 @@ def col(column_name: t.Union[ColumnOrName, t.Any]) -> Column:
 def lit(value: t.Optional[t.Any] = None) -> Column:
     if isinstance(value, str):
         return Column(expression.Literal.string(value))
+    if isinstance(value, float) and value in {float("inf"), float("-inf")}:
+        return Column(expression.Literal.string(str(value)))
     return Column(value)
 
 
@@ -961,12 +963,15 @@ def dayofweek(col: ColumnOrName) -> Column:
         return dayofweek_from_extract(col)
 
     if session._is_postgres:
-        return dayofweek_from_extract_with_isodow(col)
+        return dayofweek_from_extract_with_isodow(col) + 1
 
-    return Column.invoke_expression_over_column(
+    result = Column.invoke_expression_over_column(
         Column(expression.TsOrDsToDate(this=Column.ensure_col(col).column_expression)),
         expression.DayOfWeek,
     )
+    if session._is_duckdb or session._is_snowflake:
+        return result + 1
+    return result
 
 
 @meta()
@@ -2962,14 +2967,14 @@ def char(col: ColumnOrName) -> Column:
     return Column(expression.Chr(expressions=Column.ensure_col(col).column_expression))
 
 
-@meta(unsupported_engines="*")
+@meta()
 def char_length(str: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(str, "char_length")
+    return Column.invoke_expression_over_column(str, expression.Length)
 
 
-@meta(unsupported_engines="*")
+@meta()
 def character_length(str: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(str, "character_length")
+    return Column.invoke_expression_over_column(str, expression.Length)
 
 
 @meta(unsupported_engines=["bigquery", "postgres"])
@@ -4946,7 +4951,7 @@ def reflect(*cols: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(cols[0], "reflect")
 
 
-@meta(unsupported_engines="*")
+@meta(unsupported_engines="snowflake")
 def regexp(str: ColumnOrName, regexp: ColumnOrName) -> Column:
     r"""Returns true if `str` matches the Java regex `regexp`, or false otherwise.
 
@@ -4996,12 +5001,21 @@ def regexp(str: ColumnOrName, regexp: ColumnOrName) -> Column:
     |               true|
     +-------------------+
     """
-    from sqlframe.base.function_alternatives import regexp_extract_only_one_group
+    from sqlframe.base.function_alternatives import (
+        regexp_with_contains,
+        regexp_with_matches,
+    )
 
     session = _get_session()
 
+    if session._is_duckdb:
+        return regexp_with_matches(str, regexp)
+
+    if session._is_postgres:
+        return Column.invoke_expression_over_column(str, expression.RegexpILike, expression=regexp)
+
     if session._is_bigquery:
-        return regexp_extract_only_one_group(str, regexp)  # type: ignore
+        return regexp_with_contains(str, regexp)
 
     return Column.invoke_anonymous_function(str, "regexp", regexp)
 
@@ -5485,7 +5499,7 @@ def regr_syy(y: ColumnOrName, x: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(y, "regr_syy", x)
 
 
-@meta(unsupported_engines="*")
+@meta()
 def replace(
     src: ColumnOrName, search: ColumnOrName, replace: t.Optional[ColumnOrName] = None
 ) -> Column:
@@ -5513,6 +5527,11 @@ def replace(
     >>> df.select(replace(df.a, df.b).alias('r')).collect()
     [Row(r='ABC')]
     """
+    if replace is None and (
+        _get_session()._is_duckdb or _get_session()._is_postgres or _get_session()._is_bigquery
+    ):
+        replace = expression.Literal.string("")  # type: ignore
+
     if replace is not None:
         return Column.invoke_anonymous_function(src, "replace", search, replace)
     else:
@@ -6397,7 +6416,7 @@ def unix_date(col: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col, expression.UnixDate)
 
 
-@meta(unsupported_engines="*")
+@meta()
 def unix_micros(col: ColumnOrName) -> Column:
     """Returns the number of microseconds since 1970-01-01 00:00:00 UTC.
 
@@ -6411,10 +6430,20 @@ def unix_micros(col: ColumnOrName) -> Column:
     [Row(n=1437584400000000)]
     >>> spark.conf.unset("spark.sql.session.timeZone")
     """
+    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
+    ):
+        return unix_micros_multiply_epoch(col)
+
     return Column.invoke_anonymous_function(col, "unix_micros")
 
 
-@meta(unsupported_engines="*")
+@meta()
 def unix_millis(col: ColumnOrName) -> Column:
     """Returns the number of milliseconds since 1970-01-01 00:00:00 UTC.
     Truncates higher levels of precision.
@@ -6429,10 +6458,20 @@ def unix_millis(col: ColumnOrName) -> Column:
     [Row(n=1437584400000)]
     >>> spark.conf.unset("spark.sql.session.timeZone")
     """
+    from sqlframe.base.function_alternatives import unix_millis_multiply_epoch
+
+    if (
+        _get_session()._is_bigquery
+        or _get_session()._is_duckdb
+        or _get_session()._is_postgres
+        or _get_session()._is_snowflake
+    ):
+        return unix_millis_multiply_epoch(col)
+
     return Column.invoke_anonymous_function(col, "unix_millis")
 
 
-@meta(unsupported_engines=["bigquery", "duckdb", "postgres"])
+@meta()
 def unix_seconds(col: ColumnOrName) -> Column:
     """Returns the number of seconds since 1970-01-01 00:00:00 UTC.
     Truncates higher levels of precision.
@@ -6447,6 +6486,27 @@ def unix_seconds(col: ColumnOrName) -> Column:
     [Row(n=1437584400)]
     >>> spark.conf.unset("spark.sql.session.timeZone")
     """
+    from sqlframe.base.function_alternatives import unix_seconds_extract_epoch
+
+    if _get_session()._is_postgres:
+        return unix_seconds_extract_epoch(col)
+
+    if _get_session()._is_bigquery:
+        return Column(
+            expression.Anonymous(
+                this="UNIX_SECONDS",
+                expressions=[
+                    expression.Anonymous(
+                        this="TIMESTAMP",
+                        expressions=[
+                            Column.ensure_col(col).column_expression,
+                            expression.Literal.string("UTC"),
+                        ],
+                    )
+                ],
+            )
+        )
+
     return Column.invoke_expression_over_column(col, expression.UnixSeconds)
 
 

sqlframe/base/session.py

@@ -108,6 +108,11 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
         if not getattr(self, "schema", None) or schema:
             self._schema = schema
 
+    # https://github.com/eakmanrq/sqlframe/issues/262
+    @property
+    def execution_dialect_name(self) -> str:
+        return self.execution_dialect.__class__.__name__.lower()
+
     @property
     def read(self) -> READER:
         return self._reader(self)

{sqlframe-3.14.2.dist-info → sqlframe-3.15.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.14.2
+Version: 3.15.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.14.2.dist-info → sqlframe-3.15.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=wfqm98eLoLid9oV_FzzpG5loKC6LxOhj2lXpfN7SARo,3138
-sqlframe/_version.py,sha256=jOmVUgfrjHuKbVMclbnyeOg5hq5CSFD43rU-r3QVgI8,413
+sqlframe/_version.py,sha256=rNfI2qI8EULJid-fGjytQ8KiqfMi0Ktaq6sNSFSM_1s,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
@@ -7,13 +7,13 @@ sqlframe/base/column.py,sha256=wRghgieYAA51aw4WuFQWOvl0TFOToZbBhBuIamEzxx4,18011
 sqlframe/base/dataframe.py,sha256=E1zWlB_a2FNOxjTcQ68MtL_A4c8fnLiHY3MeZttK4Xk,76570
 sqlframe/base/decorators.py,sha256=P56cgs8DANxGRIwVs5uOMnDy-BlXZZYMbf4fdnkpWPI,1889
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
-sqlframe/base/function_alternatives.py,sha256=8kDCh1cOXtdCcBPYBQ8byXxRAZvphS9N8GDs4txBzGg,52544
-sqlframe/base/functions.py,sha256=8gBaQGUnfbwtJk9sg87HQul8d4Q9lCw3rPU9koYWxE0,218776
+sqlframe/base/function_alternatives.py,sha256=NV31IaEhVYmfUSWetAEFISAvLzs2DxQ7bp-iMNgj0hQ,53786
+sqlframe/base/functions.py,sha256=9mN54Nx6yqos1njfyW2-WRzfFUsA96P9z1ldJVtovSs,220543
 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=LwGYgKOymzlX5CKl_vZG-J2j5fkuGO3uPIRKpMqB6MI,26190
+sqlframe/base/session.py,sha256=s9M9_nbtOQQgLyEBZs-ijkMeHkYkILHfBc8JsU2SLmU,26369
 sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
 sqlframe/base/types.py,sha256=iBNk9bpFtb2NBIogYS8i7OlQZMRvpR6XxqzBebsjQDU,12280
@@ -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-3.14.2.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.14.2.dist-info/METADATA,sha256=jaarma0pQSOhwGo8XtkdteTdJadSB4CIiVrjLLQovu0,8970
-sqlframe-3.14.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.14.2.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.14.2.dist-info/RECORD,,
+sqlframe-3.15.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.15.1.dist-info/METADATA,sha256=-MxovSCoyQnT-6Ujd4BDA_yVpf9KWra2v1CQGN2TmG4,8970
+sqlframe-3.15.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.15.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.15.1.dist-info/RECORD,,