util.get_unique_names: Add more flexible arguments

Author: janezd

Orange/data/tests/test_util.py

@@ -0,0 +1,49 @@
+import unittest
+
+from Orange.data import Domain, ContinuousVariable
+from Orange.data.util import get_unique_names
+
+
+class TestGetUniqueNames(unittest.TestCase):
+    def test_get_unique_names(self):
+        names = ["foo", "bar", "baz", "baz (3)"]
+        self.assertEqual(get_unique_names(names, ["qux"]), ["qux"])
+        self.assertEqual(get_unique_names(names, ["foo"]), ["foo (1)"])
+        self.assertEqual(get_unique_names(names, ["baz"]), ["baz (4)"])
+        self.assertEqual(get_unique_names(names, ["baz (3)"]), ["baz (3) (1)"])
+        self.assertEqual(
+            get_unique_names(names, ["qux", "quux"]), ["qux", "quux"])
+        self.assertEqual(
+            get_unique_names(names, ["bar", "baz"]), ["bar (4)", "baz (4)"])
+        self.assertEqual(
+            get_unique_names(names, ["qux", "baz"]), ["qux (4)", "baz (4)"])
+        self.assertEqual(
+            get_unique_names(names, ["qux", "bar"]), ["qux (1)", "bar (1)"])
+
+        self.assertEqual(get_unique_names(names, "qux"), "qux")
+        self.assertEqual(get_unique_names(names, "foo"), "foo (1)")
+        self.assertEqual(get_unique_names(names, "baz"), "baz (4)")
+
+    def test_get_unique_names_with_domain(self):
+        a, b, c, d = map(ContinuousVariable, ["foo", "bar", "baz", "baz (3)"])
+        domain = Domain([a, b], c, [d])
+        self.assertEqual(get_unique_names(domain, ["qux"]), ["qux"])
+        self.assertEqual(get_unique_names(domain, ["foo"]), ["foo (1)"])
+        self.assertEqual(get_unique_names(domain, ["baz"]), ["baz (4)"])
+        self.assertEqual(get_unique_names(domain, ["baz (3)"]), ["baz (3) (1)"])
+        self.assertEqual(
+            get_unique_names(domain, ["qux", "quux"]), ["qux", "quux"])
+        self.assertEqual(
+            get_unique_names(domain, ["bar", "baz"]), ["bar (4)", "baz (4)"])
+        self.assertEqual(
+            get_unique_names(domain, ["qux", "baz"]), ["qux (4)", "baz (4)"])
+        self.assertEqual(
+            get_unique_names(domain, ["qux", "bar"]), ["qux (1)", "bar (1)"])
+
+        self.assertEqual(get_unique_names(domain, "qux"), "qux")
+        self.assertEqual(get_unique_names(domain, "foo"), "foo (1)")
+        self.assertEqual(get_unique_names(domain, "baz"), "baz (4)")
+
+
+if __name__ == "__main__":
+    unittest.main()

Orange/data/util.py

@@ -2,6 +2,8 @@
 Data-manipulation utilities.
 """
 import re
+from itertools import chain
+
 import numpy as np
 import bottleneck as bn
 from scipy import sparse as sp
@@ -139,15 +141,32 @@ def get_indices(names, name):
 
 def get_unique_names(names, proposed):
     """
-    Returns unique names of variables. Variables which are duplicate get appended by
-    unique index which is the same in all proposed variable names in a list.
-    :param names: list of strings
-    :param proposed: list of strings
-    :return: list of strings
+    Returns unique names for variables
+
+    Proposed is a list of names (or a string with a single name). If any name
+    already appears in `names`, the function appends an index in parentheses,
+    which is one higher than the highest index at these variables.
+
+    If argument `names` is domain, the method observes all variables and metas.
+
+    Function returns a string if `proposed` is a string, and a list if it's a
+    list.
+
+    Args:
+        names (Domain or list of str): used names
+        proposed (str or list of str): proposed name
+
+    Return:
+        str or list of str
     """
-    if len([name for name in proposed if name in names]):
-        max_index = max([max(get_indices(names, name),
-                             default=1) for name in proposed], default=1)
+    from Orange.data import Domain  # prevent cyclic import
+    if isinstance(names, Domain):
+        names = [var.name for var in chain(names.variables, names.metas)]
+    if isinstance(proposed, str):
+        return get_unique_names(names, [proposed])[0]
+    if set(proposed) & set(names):
+        max_index = max(max(get_indices(names, name), default=0)
+                        for name in proposed)
         for i, name in enumerate(proposed):
             proposed[i] = "{} ({})".format(name, max_index + 1)
     return proposed