From bc62afe69b630ae42b206ccc9943ff012e8c6bd0 Mon Sep 17 00:00:00 2001
From: Farsidetfs <wilsoros@oregonstate.edu>
Date: Mon, 12 May 2025 22:35:10 +0000
Subject: [PATCH] BUG: Raise MergeError when suffixes result in duplicate
 column names (GH#61402)

---
 doc/source/whatsnew/v3.0.0.rst           |  1 +
 pandas/core/reshape/merge.py             | 12 +++++++-----
 pandas/tests/reshape/merge/test_merge.py |  9 +++++++++
 3 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
index 099e5bc48353a..6823ef65c2e37 100644
--- a/doc/source/whatsnew/v3.0.0.rst
+++ b/doc/source/whatsnew/v3.0.0.rst
@@ -847,6 +847,7 @@ Reshaping
 - Bug in :meth:`DataFrame.stack` with the new implementation where ``ValueError`` is raised when ``level=[]`` (:issue:`60740`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
 - Bug in :meth:`concat` where concatenating DataFrame and Series with ``ignore_index = True`` drops the series name (:issue:`60723`, :issue:`56257`)
+- Bug in :meth:`DataFrame.merge` where user-provided suffixes could result in duplicate column names if the resulting names matched existing columns. Now raises a :class:`MergeError` in such cases. (:issue:`61402`)
 
 Sparse
 ^^^^^^
diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
index 68d61da0cf7dd..b8ad932abc2b0 100644
--- a/pandas/core/reshape/merge.py
+++ b/pandas/core/reshape/merge.py
@@ -3058,17 +3058,19 @@ def renamer(x, suffix: str | None):
     llabels = left._transform_index(lrenamer)
     rlabels = right._transform_index(rrenamer)
 
-    dups = []
+    dups = set()
     if not llabels.is_unique:
         # Only warn when duplicates are caused because of suffixes, already duplicated
         # columns in origin should not warn
-        dups = llabels[(llabels.duplicated()) & (~left.duplicated())].tolist()
+        dups.update(llabels[(llabels.duplicated()) & (~left.duplicated())])
     if not rlabels.is_unique:
-        dups.extend(rlabels[(rlabels.duplicated()) & (~right.duplicated())].tolist())
+        dups.update(rlabels[(rlabels.duplicated()) & (~right.duplicated())])
+    # Suffix addition creates duplicate to pre-existing column name
+    dups.update(llabels.intersection(right.difference(to_rename)))
+    dups.update(rlabels.intersection(left.difference(to_rename)))
     if dups:
         raise MergeError(
-            f"Passing 'suffixes' which cause duplicate columns {set(dups)} is "
-            f"not allowed.",
+            f"Passing 'suffixes' which cause duplicate columns {dups} is not allowed.",
         )
 
     return llabels, rlabels
diff --git a/pandas/tests/reshape/merge/test_merge.py b/pandas/tests/reshape/merge/test_merge.py
index f0f67aebd85ec..f3418ad047afe 100644
--- a/pandas/tests/reshape/merge/test_merge.py
+++ b/pandas/tests/reshape/merge/test_merge.py
@@ -3060,3 +3060,12 @@ def test_merge_on_all_nan_column():
         {"x": [1, 2, 3], "y": [np.nan, np.nan, np.nan], "z": [4, 5, 6], "zz": [4, 5, 6]}
     )
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("suffixes", [("_dup", ""), ("", "_dup")])
+def test_merge_for_suffix_collisions(suffixes):
+    # GH#61402
+    df1 = DataFrame({"col1": [1], "col2": [2]})
+    df2 = DataFrame({"col1": [1], "col2": [2], "col2_dup": [3]})
+    with pytest.raises(MergeError, match="duplicate columns"):
+        merge(df1, df2, on="col1", suffixes=suffixes)