PyPI - hydroserverpy - Versions diffs - 1.4.0b3__tar.gz → 1.4.0b4__tar.gz - Mend

@@ -68,14 +68,21 @@ class Transformer(ABC):
     def standardize_dataframe(
         self, df: pd.DataFrame, mappings: List[SourceTargetMapping]
     ):
+        logging.info(f"Successfully read payload into dataframe:\n {df}")
         # 1) Normalize timestamp column
         df.rename(columns={self.timestamp.key: "timestamp"}, inplace=True)
         if "timestamp" not in df.columns:
             msg = f"Timestamp column '{self.timestamp.key}' not found in data."
             logging.error(msg)
             raise ValueError(msg)
+        logging.info(f"Renamed timestamp column to 'timestamp'")
         df["timestamp"] = self.timestamp_parser.parse_series(df["timestamp"])
+        logging.info(f"Normalized timestamp column \n {df}")
         df = df.drop_duplicates(subset=["timestamp"], keep="last")
+        logging.info(f"Removed duplicates\n")
         def _resolve_source_col(s_id: Union[str, int]) -> str:
             if isinstance(s_id, int) and s_id not in df.columns:
@@ -120,6 +127,8 @@ class Transformer(ABC):
                 target_col = str(path.target_identifier)
                 transformed_df[target_col] = _apply_transformations(base, path)
+        logging.info(f"Mapped payload sources to targets")
         # 6) Keep only timestamp + target columns
         df = pd.concat([df[["timestamp"]], pd.DataFrame(transformed_df)], axis=1)

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydroserverpy
-Version: 1.4.0b3
+Version: 1.4.0b4
 Requires-Python: <4,>=3.9
 License-File: LICENSE
 Requires-Dist: requests>=2

@@ -1,6 +1,6 @@
 [metadata]
 name = hydroserverpy
-version = 1.4.0b3
+version = 1.4.0b4
 [options]
 package_dir =

@@ -17,11 +17,8 @@ class HTTPExtractor(Extractor):
         url = self.resolve_placeholder_variables(payload, loader)
         logging.info(f"Requesting data from → {url}")
-        try:
-            response = requests.get(url)
-        except Exception as e:
-            logging.error(f"Failed to fetch {url}: {e}")
-            raise
+        response = requests.get(url)
+        response.raise_for_status()
         data = BytesIO()
         for chunk in response.iter_content(chunk_size=8192):

@@ -1,6 +1,6 @@
 from datetime import datetime
 from typing import Literal, Optional
-from pydantic import BaseModel, Field, EmailStr
+from pydantic import BaseModel, Field
 class Schedule(BaseModel):

@@ -73,7 +73,10 @@ class TimestampParser:
         return localized.dt.tz_convert(timezone.utc)
     def parse_series(self, raw_series: pd.Series) -> pd.Series:
-        s = raw_series.str.strip()
+        if pd.api.types.is_datetime64_any_dtype(raw_series):
+            s = raw_series  # already datetimes
+        else:
+            s = raw_series.astype("string", copy=False).str.strip()
         parsed = self._convert_series_to_UTC(s)
         if parsed.isna().any():

hydroserverpy 1.4.0b3tar.gz → 1.4.0b4tar.gz

@@ -24,7 +24,21 @@ class JSONTransformer(Transformer):
         Returns:
             pd.DataFrame: pandas DataFrames in the format pd.Timestamp, datastream_id_1, datastream_id_2, ...
         """
+        if data_file is None:
+            raise TypeError(
+                "JSONTransformer received None; expected file-like, bytes, or str"
+            )
         json_data = json.load(data_file)
+        logging.info(f"Read in json data: \n{data_file}")
+        logging.info(
+            "JSONTransformer cfg:\n jmespath=%r\n ts.key=%r\n ts.format=%r\n ts.custom=%r",
+            self.cfg.jmespath,
+            self.timestamp.key,
+            self.timestamp.format,
+            self.timestamp.custom_format,
+        )
         data_points = self.extract_data_points(json_data)
         if not data_points:
             logging.warning("No data points found in the JSON data.")