show duplicates on non-unique query (#73)

* show duplicates on non-unique query * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update filefinder/_filefinder.py Remove comment Co-authored-by: Mathias Hauser <[email protected]> * Update filefinder/_filefinder.py Co-authored-by: Mathias Hauser <[email protected]> --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Mathias Hauser <[email protected]>
mpytools · Feb 7, 2024 · 6b89335 · 6b89335
1 parent 10cd2e6
commit 6b89335
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 1 deletion.
diff --git a/.gitignore b/.gitignore
@@ -5,6 +5,9 @@ __pycache__
 
 .pytest_cache/
 
+# development scripts
+devel/*
+
 # C extensions
 *.so
 

diff --git a/filefinder/_filefinder.py b/filefinder/_filefinder.py
@@ -115,8 +115,10 @@ def find(self, keys=None, *, _allow_empty=False, **keys_kwargs):
         len_all = len(fc.df)
         len_unique = len(fc.combine_by_key().unique())
 
-        msg = "This query leads to non-unique metadata. Please adjust your query."
         if len_all != len_unique:
+            duplicated = fc.df[fc.df.duplicated()]
+            msg = f"This query leads to non-unique metadata. Please adjust your query.\nFirst five duplicates:\n{duplicated.head()}"
+
             raise ValueError(msg)
 
         return fc
-Original file line number
+Diff line change
@@ Expand Up / @@ -5,6 +5,9 @@ __pycache__ @@
     .pytest_cache/
+    # development scripts
+    devel/*
     # C extensions
     *.so
@@ Expand Down @@