Merge branch 'master' of ssh://github.com/KarrLab/wc_utils

tests/util/test_list.py

@@ -8,10 +8,10 @@
 """
 
 import unittest
-from wc_utils.util.list import is_sorted, transpose, difference, det_dedupe, elements_to_str
+from wc_utils.util.list import is_sorted, transpose, difference, det_dedupe, det_find_dupes, elements_to_str
 
 
-class TestTranspose(unittest.TestCase):
+class TestListUtilities(unittest.TestCase):
 
     def test_is_sorted(self):
         self.assertTrue(is_sorted([1, 2, 3]))
@@ -43,6 +43,13 @@ def test_det_dedupe(self):
         with self.assertRaises(TypeError):
             det_dedupe([[]])
 
+    def test_det_find_dupes(self):
+        l = [0, 1, 2, 0, 1, 7, 1]
+        expected = [0, 1]
+        self.assertEqual(det_find_dupes(l), expected)
+        with self.assertRaises(TypeError):
+            det_find_dupes([[]])
+
     def test_elements_to_str(self):
         l = 'a b c'.split()
         self.assertEqual(elements_to_str(l), l)

wc_utils/util/list.py

@@ -87,6 +87,34 @@ def det_dedupe(l):
             s.add(e)
     return t
 
+
+def det_find_dupes(l):
+    """ Deterministically find dupes in an iterable
+
+    Returns the duplicates in `l`. That is, returns a new list that contains one instance of
+    each element that has multiple copies in `l` and orders these instances by their first occurrence in `l`.
+    Costs O(n), where n is the length of `l`.
+
+    Args:
+        l (:obj:`list`): a list with hashable elements
+
+    Returns:
+        :obj:`list`: a deterministically deduplicated copy of `l`
+
+    Raises:
+        `TypeError` if an element of `l` is an unhashable (mutable) type
+    """
+    counts_to_2 = {}
+    dupes = []
+    for e in l:
+        if e not in counts_to_2:
+            counts_to_2[e] = 1
+        elif counts_to_2[e] == 1:
+            counts_to_2[e] += 1
+            dupes.append(e)
+    return dupes
+
+
 def elements_to_str(l):
     """ Convert each element in an iterator to a string representation
 

wc_utils/workbook/io.py

@@ -473,10 +473,10 @@ def initialize_workbook(self):
         return Workbook()
 
     def get_sheet_names(self):
-        """ Get names of sheets contained within path
+        """ Get names of files contained within path glob
 
         Returns:
-            obj:`list` of `str`: list of sheet names
+            obj:`list` of `str`: list of file names
 
         Raises:
             :obj:`ValueError`: if glob does not find any matching files