eba-xbridge 1.5.0rc4__py3-none-any.whl → 1.5.0rc5__py3-none-any.whl

{eba_xbridge-1.5.0rc4.dist-info → eba_xbridge-1.5.0rc5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eba-xbridge
-Version: 1.5.0rc4
+Version: 1.5.0rc5
 Summary: XBRL-XML to XBRL-CSV converter for EBA Taxonomy (version 4.1)
 License: Apache 2.0
 License-File: LICENSE

{eba_xbridge-1.5.0rc4.dist-info → eba_xbridge-1.5.0rc5.dist-info}/RECORD

@@ -1,8 +1,8 @@
-xbridge/__init__.py,sha256=joASbfhYee_2irYZhRCZ6J4oTn6u1fjt6ilQbXwL4M4,68
+xbridge/__init__.py,sha256=S6yAyrnTJ19Trbh-OrGVDIwi5lh88C2pCxDncQyX1VY,68
 xbridge/__main__.py,sha256=trtFEv7TRJgrLL84leIapPvgC_iVTj05qLHRRS1Olts,2219
 xbridge/api.py,sha256=NCBz7VRJWE3gID6ndgL4Awoxw0w1yMIIf_OTLRuZyyQ,1559
-xbridge/converter.py,sha256=uu6djzgGZcmq0nibrkmg5lW-npcolB4XtQoNWu1p_3o,23498
-xbridge/instance.py,sha256=KQpXhsZIM9oTYJf2hyrzc9pqFY2-1JBF5y1xbnLbqk8,29991
+xbridge/converter.py,sha256=vWlIaqQ2eA8Y5b1jqnqTIcOxeubJEu1itggMrFxYnS8,24077
+xbridge/instance.py,sha256=GA5D2p3IobCp5W4-x1dibgOQFuy_W4R8LmZnQ4H900g,32292
 xbridge/modules/ae_ae_4.2.json,sha256=AdFvwZqX0KVP3jF1iHeQc5QSnSMvvT3GvoA2G1AgXis,460165
 xbridge/modules/ae_con_cir-680-2014_2017-04-04.json,sha256=4n0t9dKJNU8Nb5QHpssrDs8ZLwzI-Mw75ax-ar9pLu0,363273
 xbridge/modules/ae_con_cir-680-2014_2018-03-31.json,sha256=aVWeLLs20p39kQQUthUzqrxBGKTycqhgX9WLk1rVlNw,363538
@@ -383,8 +383,8 @@ xbridge/modules/sepa_ipr_pay_4.2.json,sha256=JLJvR02LOAJy6SWPRuhV1TT02oXQhsG83FB
 xbridge/modules.py,sha256=bTvBXtp3w4Gad2DpEQE7Hb-UfuUQLlRl8gywRstQtpU,22399
 xbridge/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 xbridge/taxonomy_loader.py,sha256=K0lnJVryvkKsaoK3fMis-L2JpmwLO6z3Ruq3yj9FxDY,9317
-eba_xbridge-1.5.0rc4.dist-info/METADATA,sha256=5BAX_xFnRrIxcQiJbNi3y68A_42F8dR-qpL6Z-bBT0U,10430
-eba_xbridge-1.5.0rc4.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-eba_xbridge-1.5.0rc4.dist-info/entry_points.txt,sha256=FATct4icSewM04cegjhybtm7xcQWhaSahL-DTtuFdZw,49
-eba_xbridge-1.5.0rc4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-eba_xbridge-1.5.0rc4.dist-info/RECORD,,
+eba_xbridge-1.5.0rc5.dist-info/METADATA,sha256=88P20ZbVDK8cMGG0-rs1W7OihOdBrmOxujMvoeB3RQM,10430
+eba_xbridge-1.5.0rc5.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+eba_xbridge-1.5.0rc5.dist-info/entry_points.txt,sha256=FATct4icSewM04cegjhybtm7xcQWhaSahL-DTtuFdZw,49
+eba_xbridge-1.5.0rc5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+eba_xbridge-1.5.0rc5.dist-info/RECORD,,

xbridge/__init__.py

@@ -2,4 +2,4 @@
 Init file for eba-xbridge library
 """
 
-__version__ = "1.5.0rc4"
+__version__ = "1.5.0rc5"

xbridge/converter.py

@@ -300,17 +300,27 @@ class Converter:
         if instance_df.empty or table.variable_df is None:
             return set()
 
+        variable_columns = set(table.variable_columns or [])
         open_keys = set(table.open_keys)
 
+        # self.instance.instance_df is guaranteed to not be None due to check at line 296
+        instance_columns = set(self.instance.instance_df.columns)
+
         datapoint_df = table.variable_df.copy()
 
-        # For validation we match minimally on metric (concept) and any open keys present
-        merge_cols: list[str] = []
-        if "metric" in datapoint_df.columns and "metric" in instance_df.columns:
-            merge_cols.append("metric")
-        merge_cols.extend(
-            [key for key in open_keys if key in datapoint_df.columns and key in instance_df.columns]
-        )
+        # Handle missing columns by filtering datapoint_df (same as _variable_generator)
+        # This prevents requiring dimensions that don't exist in the instance
+        missing_cols = list(variable_columns - instance_columns)
+        if "data_type" in missing_cols:
+            missing_cols.remove("data_type")
+        if missing_cols:
+            mask = datapoint_df[missing_cols].isnull().all(axis=1)
+            datapoint_df = datapoint_df.loc[mask]
+            datapoint_df = datapoint_df.drop(columns=missing_cols)
+
+        # Match on all variable columns (dimensions) to avoid Cartesian product
+        # explosion. Consistent with _variable_generator() to prevent OOM.
+        merge_cols = list(variable_columns & instance_columns)
 
         instance_df = instance_df.copy()
         instance_df["_idx"] = instance_df.index

xbridge/instance.py

@@ -40,6 +40,49 @@ def _derive_csv_prefix(namespace_uri: str) -> Optional[str]:
     return prefix
 
 
+def _derive_metric_prefix(namespace_uri: str) -> Optional[str]:
+    """
+    Derive the CSV prefix for metrics from a namespace URI.
+
+    For metrics, we preserve version suffixes in the prefix:
+    - http://www.eba.europa.eu/xbrl/crr/dict/met -> eba_met
+    - http://www.eba.europa.eu/xbrl/crr/dict/met/3.5 -> eba_met_3.5
+    - http://www.eba.europa.eu/xbrl/crr/dict/met/4.0 -> eba_met_4.0
+    """
+    if not namespace_uri:
+        return None
+
+    cached = _namespace_prefix_cache.get(f"metric:{namespace_uri}")
+    if cached is not None:
+        return cached
+
+    cleaned = namespace_uri.rstrip("#/")
+
+    # Split the URI into path segments
+    segments = cleaned.split("/")
+
+    # Find the 'met' (metrics) segment and check if there's a version after it
+    prefix = None
+    for i, segment in enumerate(segments):
+        if segment == "met":
+            # Check if there's a version suffix (e.g., "3.5", "4.0")
+            if i + 1 < len(segments):
+                version = segments[i + 1]
+                prefix = f"eba_met_{version}"
+            else:
+                prefix = "eba_met"
+            break
+
+    # If we didn't find 'met', fall back to the standard logic
+    if prefix is None:
+        prefix = _derive_csv_prefix(namespace_uri)
+
+    if prefix:
+        _namespace_prefix_cache[f"metric:{namespace_uri}"] = prefix
+
+    return prefix
+
+
 def _normalize_namespaced_value(
     value: Optional[str], nsmap: Dict[Optional[str], str]
 ) -> Optional[str]:
@@ -67,6 +110,34 @@ def _normalize_namespaced_value(
     return value
 
 
+def _normalize_metric_value(
+    value: Optional[str], nsmap: Dict[Optional[str], str]
+) -> Optional[str]:
+    """
+    Normalize a metric namespaced value to the CSV prefix convention.
+    For metrics, we preserve version suffixes (e.g., eba_met_3.5, eba_met_4.0).
+    Returns the original value if no namespace can be resolved.
+    """
+    if value is None:
+        return None
+
+    # Clark notation: {uri}local
+    if value.startswith("{") and "}" in value:
+        uri, local = value[1:].split("}", 1)
+        derived = _derive_metric_prefix(uri)
+        return f"{derived}:{local}" if derived else value
+
+    # Prefixed notation: prefix:local
+    if ":" in value:
+        potential_prefix, local = value.split(":", 1)
+        namespace_uri = nsmap.get(potential_prefix)
+        if namespace_uri:
+            derived = _derive_metric_prefix(namespace_uri)
+            return f"{derived}:{local}" if derived else value
+
+    return value
+
+
 class Instance:
     """
     Abstract class representing an XBRL instance file.
@@ -728,8 +799,8 @@ class Fact:
     def __dict__(self) -> Dict[str, Any]:  # type: ignore[override]
         metric_clean = ""
         if self.metric:
-            # Normalize metric to use consistent eba_* prefix like other dimensions
-            metric_clean = _normalize_namespaced_value(self.metric, self.fact_xml.nsmap) or ""
+            # Normalize metric using metric-specific logic that preserves version suffixes
+            metric_clean = _normalize_metric_value(self.metric, self.fact_xml.nsmap) or ""
             # If still in Clark notation, extract the local name
             if metric_clean.startswith("{") and "}" in metric_clean:
                 metric_clean = metric_clean.split("}", 1)[1]