tracepipe 0.3.3__py3-none-any.whl → 0.3.4__py3-none-any.whl

tracepipe/__init__.py

@@ -81,7 +81,7 @@ from .core import TracePipeConfig, TracePipeMode
 from .snapshot import DiffResult, Snapshot, diff, snapshot
 
 # === VERSION ===
-__version__ = "0.3.3"
+__version__ = "0.3.4"
 
 # === MINIMAL __all__ ===
 __all__ = [

tracepipe/storage/lineage_store.py

@@ -32,6 +32,22 @@ from ..core import (
 from ..utils.value_capture import capture_typed_value
 
 
+def _stable_repr(val) -> str:
+    """Create a stable string representation for deduplication.
+
+    Handles NaN, None, and other values that don't compare equal to themselves.
+    """
+    if val is None:
+        return "None"
+    # Handle NaN (which doesn't equal itself)
+    try:
+        if isinstance(val, float) and val != val:  # NaN check
+            return "NaN"
+    except (TypeError, ValueError):
+        pass
+    return repr(val)
+
+
 class InMemoryLineageStore:
     """
     Columnar storage for lineage data using Structure of Arrays (SoA).
@@ -556,12 +572,15 @@ class InMemoryLineageStore:
         Follows merge lineage recursively to build complete cell provenance.
         This is essential for tracking changes that happened before merge operations.
 
+        Deduplicates events by (col, old_val, new_val, operation) signature to prevent
+        cross-pipeline contamination when multiple DataFrames share row IDs.
+
         Args:
             row_id: Row ID to trace
             max_depth: Maximum merge depth to follow (prevents infinite loops)
 
         Returns:
-            List of events in chronological order, including parent row events.
+            List of UNIQUE events in chronological order, including parent row events.
         """
         visited: set[int] = set()
 
@@ -589,7 +608,23 @@ class InMemoryLineageStore:
         # Sort by step_id to ensure chronological order across lineage
         all_events.sort(key=lambda e: e["step_id"])
 
-        return all_events
+        # Deduplicate by (col, old_val, new_val, operation) signature
+        # This prevents cross-pipeline contamination when multiple DataFrames
+        # share the same row IDs (e.g., df.copy() followed by parallel transforms)
+        seen_signatures: set[tuple] = set()
+        unique_events = []
+        for event in all_events:
+            sig = (
+                event.get("col"),
+                _stable_repr(event.get("old_val")),
+                _stable_repr(event.get("new_val")),
+                event.get("operation"),
+            )
+            if sig not in seen_signatures:
+                seen_signatures.add(sig)
+                unique_events.append(event)
+
+        return unique_events
 
     def get_cell_history_with_lineage(
         self, row_id: int, column: str, max_depth: int = 10

{tracepipe-0.3.3.dist-info → tracepipe-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tracepipe
-Version: 0.3.3
+Version: 0.3.4
 Summary: Row-level data lineage tracking for pandas pipelines
 Project-URL: Homepage, https://github.com/tracepipe/tracepipe
 Project-URL: Documentation, https://tracepipe.github.io/tracepipe/

{tracepipe-0.3.3.dist-info → tracepipe-0.3.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-tracepipe/__init__.py,sha256=VhfrIqYHgzY7mDQwcsmH_Gw8_j7U_libclBKXTFMwE0,3342
+tracepipe/__init__.py,sha256=1vKVGGc_fePrf1FNjP1R7-RPjtVnAc3Ori9QQl-E_4U,3342
 tracepipe/api.py,sha256=WdcKvvzI3voDt6fxZWa8vjyZQU8lfRshx7T78oj7oFE,13351
 tracepipe/context.py,sha256=_povLpqa5wd_ESHt5hbSmWTSMTF3nUfeutEQo4RMK2E,3856
 tracepipe/contracts.py,sha256=m-rjPrgnCiAgKEkweOS7P95jrjDptt5UPdvUlqaV_rU,16226
@@ -17,13 +17,13 @@ tracepipe/instrumentation/pandas_inst.py,sha256=2YSoju9ml2PjLOYzsx8MHH1iqhjgnXHb
 tracepipe/instrumentation/series_capture.py,sha256=i7FiA2ndEzS6duIj5y-a7SDfIMl2cCY_jGC1tmG7TGU,11271
 tracepipe/storage/__init__.py,sha256=pGFMfbIgIi2kofVPwYDqe2HTYMYJoabiGjTq77pYi-g,348
 tracepipe/storage/base.py,sha256=7DV_-rp37DjBMr9B1w85hLVYhC8OQShk2PcEhT-n4tE,4894
-tracepipe/storage/lineage_store.py,sha256=swMMf59isoCQZHaezCmquA-0R5iGNH3eGWjc9d9LGmo,27392
+tracepipe/storage/lineage_store.py,sha256=KhGri2uC_O_43fUivFGEHY6KBDHd1I0O_PPd_KD3L4M,28683
 tracepipe/storage/row_identity.py,sha256=HBU0gTTJlFtFTcAdUCKuX-c9cHa0lo3CDIodDPDgOzA,17161
 tracepipe/utils/__init__.py,sha256=CI_GXViCjdMbu1j6HuzZhoQZEW0sIB6WAve6j5pfOC0,182
 tracepipe/utils/value_capture.py,sha256=wGgegQmJnVHxHbwHSH9di7JAOBChzD3ERJrabZNiayk,4092
 tracepipe/visualization/__init__.py,sha256=M3s44ZTUNEToyghjhQW0FgbmWHKPr4Xc-7iNF6DpI_E,132
 tracepipe/visualization/html_export.py,sha256=G0hfZTJctUCfpun17zXX1NIXhvJZbca6hKmP3rcIjbg,42282
-tracepipe-0.3.3.dist-info/METADATA,sha256=OnHkiCjZ0-fUERI4PoUh3VmIWMZ_sePk8-pFBwo_8cI,9152
-tracepipe-0.3.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-tracepipe-0.3.3.dist-info/licenses/LICENSE,sha256=HMOAFHBClL79POwWL-2_aDcx42DJAq7Ce-nwJPvMB9U,1075
-tracepipe-0.3.3.dist-info/RECORD,,
+tracepipe-0.3.4.dist-info/METADATA,sha256=DooQHiRi1HBiFK-QZPpE3PfLg43xE5Yg93kXWEdxhNY,9152
+tracepipe-0.3.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+tracepipe-0.3.4.dist-info/licenses/LICENSE,sha256=HMOAFHBClL79POwWL-2_aDcx42DJAq7Ce-nwJPvMB9U,1075
+tracepipe-0.3.4.dist-info/RECORD,,