BUG: Presence of softlink in HDF5 file breaks HDFStore.keys() (GH20523)

Author: Andrew Bui

doc/source/whatsnew/v0.23.0.txt

@@ -1020,6 +1020,7 @@ I/O
 - Bug in :meth:`pandas.io.stata.StataReader.value_labels` raising an ``AttributeError`` when called on very old files. Now returns an empty dict (:issue:`19417`)
 - Bug in :func:`read_pickle` when unpickling objects with :class:`TimedeltaIndex` or :class:`Float64Index` created with pandas prior to version 0.20 (:issue:`19939`)
 - Bug in :meth:`pandas.io.json.json_normalize` where subrecords are not properly normalized if any subrecords values are NoneType (:issue:`20030`)
+- Bug in :func:`HDFStore.keys` when reading a file with a softlink causes exception (:issue:`20523`)
 
 Plotting
 ^^^^^^^^

pandas/io/pytables.py

@@ -1073,10 +1073,11 @@ def groups(self):
         self._check_if_open()
         return [
             g for g in self._handle.walk_nodes()
-            if (getattr(g._v_attrs, 'pandas_type', None) or
-                getattr(g, 'table', None) or
+            if (not isinstance(g, _table_mod.link.Link) and
+                (getattr(g._v_attrs, 'pandas_type', None) or
+                 getattr(g, 'table', None) or
                 (isinstance(g, _table_mod.table.Table) and
-                 g._v_name != u('table')))
+                 g._v_name != u('table'))))
         ]
 
     def get_node(self, key):

pandas/tests/io/test_pytables.py

@@ -373,6 +373,23 @@ def test_keys(self):
             assert set(store.keys()) == expected
             assert set(store) == expected
 
+    def test_keys_ignore_hdf_softlink(self):
+
+        # GH 20523
+        # Puts a softlink into HDF file and rereads
+
+        with ensure_clean_store(self.path) as store:
+
+            df = DataFrame(dict(A=lrange(5), B=lrange(5)))
+            store.put("df", df)
+
+            assert store.keys() == ["/df"]
+
+            store._handle.create_soft_link(store._handle.root, "symlink", "df")
+
+            # Should ignore the softlink
+            assert store.keys() == ["/df"]
+
     def test_iter_empty(self):
 
         with ensure_clean_store(self.path) as store: