meerschaum 2.6.9rc1__tar.gz → 2.6.11__tar.gz

{meerschaum-2.6.9rc1/meerschaum.egg-info → meerschaum-2.6.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: meerschaum
-Version: 2.6.9rc1
+Version: 2.6.11
 Summary: Sync Time-Series Pipes with Meerschaum
 Home-page: https://meerschaum.io
 Author: Bennett Meares
@@ -25,6 +25,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Database
 Classifier: Natural Language :: English
 Requires-Python: >=3.8

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/config/_version.py

@@ -2,4 +2,4 @@
 Specify the Meerschaum release version.
 """
 
-__version__ = "2.6.9rc1"
+__version__ = "2.6.11"

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/connectors/sql/_pipes.py

@@ -1664,7 +1664,7 @@ def sync_pipe(
 
     if update_df is not None and len(update_df) > 0:
         transact_id = generate_password(3)
-        temp_prefix = '##' if self.flavor != 'oracle' else ''
+        temp_prefix = '##' if self.flavor != 'oracle' else '_'
         temp_target = temp_prefix + transact_id + '_' + pipe.target
         self._log_temporary_tables_creation(temp_target, create=(not pipe.temporary), debug=debug)
         temp_pipe = Pipe(

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/core/Pipe/_dtypes.py

@@ -56,7 +56,7 @@ def enforce_dtypes(
                 chunksize=chunksize,
                 debug=debug,
             )
-        else:
+        elif isinstance(df, (dict, list)):
             df = parse_df_datetimes(
                 df,
                 ignore_cols=[

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/core/Pipe/_sync.py

@@ -567,6 +567,7 @@ def filter_existing(
     safe_copy: bool = True,
     date_bound_only: bool = False,
     include_unchanged_columns: bool = False,
+    enforce_dtypes: bool = False,
     chunksize: Optional[int] = -1,
     debug: bool = False,
     **kw
@@ -591,6 +592,10 @@ def filter_existing(
         If `True`, include the backtrack columns which haven't changed in the update dataframe.
         This is useful if you can't update individual keys.
 
+    enforce_dtypes: bool, default False
+        If `True`, ensure the given and intermediate dataframes are enforced to the correct dtypes.
+        Setting `enforce_dtypes=True` may impact performance.
+
     chunksize: Optional[int], default -1
         The `chunksize` used when fetching existing data.
 
@@ -618,8 +623,9 @@ def filter_existing(
     from meerschaum.config import get_config
     pd = import_pandas()
     pandas = attempt_import('pandas')
-    df = self.enforce_dtypes(df, chunksize=chunksize, debug=debug)
-    is_dask = 'dask' in df.__module__
+    if enforce_dtypes or 'dataframe' not in str(type(df)).lower():
+        df = self.enforce_dtypes(df, chunksize=chunksize, debug=debug)
+    is_dask = hasattr('df', '__module__') and 'dask' in df.__module__
     if is_dask:
         dd = attempt_import('dask.dataframe')
         merge = dd.merge
@@ -759,7 +765,8 @@ def filter_existing(
             dprint(f"No backtrack data was found for {self}.")
         return df, get_empty_df(), df
 
-    backtrack_df = self.enforce_dtypes(backtrack_df, chunksize=chunksize, debug=debug)
+    if enforce_dtypes:
+        backtrack_df = self.enforce_dtypes(backtrack_df, chunksize=chunksize, debug=debug)
 
     if debug:
         dprint(f"Existing data for {self}:\n" + str(backtrack_df), **kw)
@@ -796,7 +803,8 @@ def filter_existing(
         ),
         on_cols_dtypes,
     )
-    delta_df = self.enforce_dtypes(delta_df, chunksize=chunksize, debug=debug)
+    if enforce_dtypes:
+        delta_df = self.enforce_dtypes(delta_df, chunksize=chunksize, debug=debug)
 
     ### Cast dicts or lists to strings so we can merge.
     serializer = functools.partial(json.dumps, sort_keys=True, separators=(',', ':'), default=str)
@@ -820,7 +828,6 @@ def filter_existing(
         indicator=True,
         suffixes=('', '_old'),
     ) if on_cols else delta_df
-    joined_df = self.enforce_dtypes(joined_df, chunksize=chunksize, debug=debug)
     for col in casted_cols:
         if col in joined_df.columns:
             joined_df[col] = joined_df[col].apply(deserializer)
@@ -837,7 +844,6 @@ def filter_existing(
         .dropna(how='all')[cols]
         .reset_index(drop=True)
     ) if on_cols else delta_df
-    unseen_df = self.enforce_dtypes(unseen_df, chunksize=chunksize, debug=debug)
 
     ### Rows that have already been inserted but values have changed.
     update_df = (
@@ -846,7 +852,6 @@ def filter_existing(
         .dropna(how='all')[cols]
         .reset_index(drop=True)
     ) if on_cols else get_empty_df()
-    update_df = self.enforce_dtypes(update_df, chunksize=chunksize, debug=debug)
 
     if include_unchanged_columns and on_cols:
         unchanged_backtrack_cols = [
@@ -854,6 +859,8 @@ def filter_existing(
             for col in backtrack_df.columns
             if col in on_cols or col not in update_df.columns
         ]
+        if enforce_dtypes:
+            update_df = self.enforce_dtypes(update_df, chunksize=chunksize, debug=debug)
         update_df = merge(
             backtrack_df[unchanged_backtrack_cols],
             update_df,

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/utils/dataframe.py

@@ -1283,18 +1283,8 @@ def query_df(
                 if debug:
                     dprint(f"`end` will be cast to '{end}'.")
 
-            begin_tz = begin.tzinfo if begin is not None else None
-            end_tz = end.tzinfo if end is not None else None
-
-            if begin_tz is not None or end_tz is not None or df_tz is not None:
-                begin = coerce_timezone(begin, strip_utc=False)
-                end = coerce_timezone(end, strip_utc=False)
-                if df_tz is not None:
-                    if debug:
-                        dprint(f"Casting column '{datetime_column}' to UTC...")
-                    df[datetime_column] = coerce_timezone(df[datetime_column], strip_utc=False)
-                if debug:
-                    dprint(f"Using datetime bounds:\n{begin=}\n{end=}")
+            begin = coerce_timezone(begin, strip_utc=(df_tz is None)) if begin is not None else None
+            end = coerce_timezone(end, strip_utc=(df_tz is None)) if begin is not None else None
 
     in_ex_params = get_in_ex_params(params)
 
@@ -1340,15 +1330,24 @@ def query_df(
     ]
     for col in bool_cols:
         df[col] = df[col].astype('boolean[pyarrow]')
-    df['__mrsm_mask'] = query_mask.astype('boolean[pyarrow]')
 
-    if inplace:
-        df.where(query_mask, other=NA, inplace=True)
-        df.dropna(how='all', inplace=True)
-        result_df = df
+    if not isinstance(query_mask, bool):
+        df['__mrsm_mask'] = (
+            query_mask.astype('boolean[pyarrow]')
+            if hasattr(query_mask, 'astype')
+            else query_mask
+        )
+
+        if inplace:
+            df.where(query_mask, other=NA, inplace=True)
+            df.dropna(how='all', inplace=True)
+            result_df = df
+        else:
+            result_df = df.where(query_mask, other=NA)
+            result_df.dropna(how='all', inplace=True)
+
     else:
-        result_df = df.where(query_mask, other=NA)
-        result_df.dropna(how='all', inplace=True)
+        result_df = df
 
     if '__mrsm_mask' in df.columns:
         del df['__mrsm_mask']

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/utils/dtypes/__init__.py

@@ -267,8 +267,18 @@ def coerce_timezone(
 
     if dt_is_series:
         is_dask = 'dask' in dt.__module__
-        pandas = mrsm.attempt_import('pandas')
+        pandas = mrsm.attempt_import('pandas', lazy=False)
         dd = mrsm.attempt_import('dask.dataframe') if is_dask else None
+
+        if (
+            pandas.api.types.is_datetime64_any_dtype(dt) and (
+                (dt.dt.tz is not None and not strip_utc)
+                or
+                (dt.dt.tz is None and strip_utc)
+            )
+        ):
+            return dt
+
         dt_series = (
             pandas.to_datetime(dt, utc=True, format='ISO8601')
             if dd is None

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/meerschaum/utils/formatting/__init__.py

@@ -501,11 +501,12 @@ def fill_ansi(string: str, style: str = '') -> str:
     """
     from meerschaum.utils.packages import import_rich, attempt_import
     from meerschaum.utils.misc import iterate_chunks
-    rich = import_rich()
-    Text = attempt_import('rich.text').Text
+    _ = import_rich()
+    rich_ansi, rich_text = attempt_import('rich.ansi', 'rich.text')
+    Text = rich_text.Text
     try:
         msg = Text.from_ansi(string)
-    except AttributeError as e:
+    except AttributeError:
         import traceback
         traceback.print_stack()
         msg = ''

{meerschaum-2.6.9rc1 → meerschaum-2.6.11/meerschaum.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: meerschaum
-Version: 2.6.9rc1
+Version: 2.6.11
 Summary: Sync Time-Series Pipes with Meerschaum
 Home-page: https://meerschaum.io
 Author: Bennett Meares
@@ -25,6 +25,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Database
 Classifier: Natural Language :: English
 Requires-Python: >=3.8

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/setup.py

@@ -75,6 +75,7 @@ setup_kw_args = {
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "Topic :: Database",
         "Natural Language :: English",
     ],

{meerschaum-2.6.9rc1 → meerschaum-2.6.11}/tests/test_jobs.py

@@ -23,7 +23,7 @@ def test_create_job():
     success, msg = job.start()
     assert success, msg
 
-    duration = 1.0
+    duration = 2.0
     time.sleep(duration)
 
     success, msg = job.stop()