datazone-sdk 6.0.0.dev1__tar.gz → 6.0.1.dev2__tar.gz

{datazone_sdk-6.0.0.dev1 → datazone_sdk-6.0.1.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datazone-sdk
-Version: 6.0.0.dev1
+Version: 6.0.1.dev2
 Summary: Database and Delta storage client library for working with Delta Lake tables
 Author: Team Enigma
 Author-email: enigma@energinet.dk

{datazone_sdk-6.0.0.dev1 → datazone_sdk-6.0.1.dev2}/datazone/deltastorage/generated_columns.py

@@ -97,18 +97,23 @@ class DateBucket(GeneratedColumn):
         Returns:
             tuple[str, dt.date]: List of conditions on the generated column
         """
-        timestamp = copy.copy(value)
-        if self.as_tz is not None:
-            timestamp = timestamp.astimezone(ZoneInfo(self.as_tz))
-        date = timestamp.date()
+
+        def date_from_timestamp(timestamp: dt.datetime) -> dt.date:
+            timestamp = copy.copy(timestamp)
+            if self.as_tz is not None:
+                timestamp = timestamp.astimezone(ZoneInfo(self.as_tz))
+            return timestamp.date()
 
         match op:
             case "=":
-                return [("=", date)]
+                return [("=", date_from_timestamp(value))]
             case ("<" | "<="):
-                return [("<=", date)]
+                return [("<=", date_from_timestamp(value))]
             case (">" | ">="):
-                return [(">=", date)]
+                return [(">=", date_from_timestamp(value))]
+            case "in":
+                dates = [date_from_timestamp(timestamp) for timestamp in value]
+                return [("in", list(dict.fromkeys(dates)))]
             case _:
                 # for other operations, we cannot make any
                 # useful filters on the generated column

{datazone_sdk-6.0.0.dev1 → datazone_sdk-6.0.1.dev2}/datazone/deltastorage/table.py

@@ -1,3 +1,4 @@
+import datetime as dt
 from typing import Any, Optional
 
 import deltalake as dl
@@ -8,6 +9,21 @@ from .schema import Schema
 from .slicing import HyperSlice
 
 
+def _sql_literal(value: Any) -> str:
+    if isinstance(value, dt.datetime):
+        return f"'{value.isoformat()}'"
+    if isinstance(value, dt.date):
+        return f"'{value.isoformat()}'"
+    if isinstance(value, str):
+        escaped_value = value.replace("'", "''")
+        return f"'{escaped_value}'"
+    if isinstance(value, bool):
+        return "TRUE" if value else "FALSE"
+    if value is None:
+        return "NULL"
+    return str(value)
+
+
 def _dnf_to_sql(dnf: list[tuple]) -> str:
     """Convert DNF expression to SQL expression."""
     if len(dnf) == 0:
@@ -17,10 +33,13 @@ def _dnf_to_sql(dnf: list[tuple]) -> str:
     for col, op, val in dnf:
         if op == "in":
             assert isinstance(val, list)
-            lst = ", ".join([f"'{item}'" for item in val])
-            sql_parts.append(f"{col} IN ({lst})")
+            if len(val) == 0:
+                sql_parts.append("false")
+            else:
+                values = " OR ".join([f"{col} = {_sql_literal(item)}" for item in val])
+                sql_parts.append(f"({values})")
         elif op in [">=", "<=", ">", "<", "="]:
-            sql_parts.append(f"{col} {op} '{val}'")
+            sql_parts.append(f"{col} {op} {_sql_literal(val)}")
         else:
             raise ValueError(f"Unsupported operation: {op}")
 
@@ -159,7 +178,6 @@ class Table:
         schema = self.schema()
         data = self._to_writable_pyarrow_table(df=df, schema=schema)
 
-        hyper_slice = schema.add_generated_filters(hyper_slice)
         if len(hyper_slice) == 0:
             predicate = None
         else:

{datazone_sdk-6.0.0.dev1 → datazone_sdk-6.0.1.dev2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datazone-sdk"
-version = "6.0.0.dev1"
+version = "6.0.1.dev2"
 description = "Database and Delta storage client library for working with Delta Lake tables"
 authors = [{ name = "Team Enigma", email = "enigma@energinet.dk" }]
 requires-python = ">=3.10"