ENH: allow duplicates in index when parsing file, close #1173

Author: wesm

pandas/io/parsers.py

@@ -653,12 +653,12 @@ def get_chunk(self, rows=None):
         else:
             index = Index(np.arange(len(content)))
 
-        if not index.is_unique:
-            dups = index.get_duplicates()
-            idx_str = 'Index' if not self._implicit_index else 'Implicit index'
-            err_msg = ('%s (columns %s) have duplicate values %s'
-                       % (idx_str, self.index_col, str(dups)))
-            raise Exception(err_msg)
+        # if not index.is_unique:
+        #     dups = index.get_duplicates()
+        #     idx_str = 'Index' if not self._implicit_index else 'Implicit index'
+        #     err_msg = ('%s (columns %s) have duplicate values %s'
+        #                % (idx_str, self.index_col, str(dups)))
+        #     raise Exception(err_msg)
 
         if len(self.columns) != len(zipped_content):
             raise Exception('wrong number of columns')

pandas/io/tests/test_parsers.py

@@ -325,8 +325,10 @@ def test_read_table_duplicate_index(self):
 bar,12,13,14,15
 """
 
-        self.assertRaises(Exception, read_csv, StringIO(data),
-                          index_col=0)
+        result = read_csv(StringIO(data), index_col=0)
+        expected = read_csv(StringIO(data)).set_index('index',
+                                                      verify_integrity=False)
+        assert_frame_equal(result, expected)
 
     def test_read_table_duplicate_index_implicit(self):
         data = """A,B,C,D
@@ -338,8 +340,8 @@ def test_read_table_duplicate_index_implicit(self):
 bar,12,13,14,15
 """
 
-        self.assertRaises(Exception, read_csv, StringIO(data),
-                          index_col=0)
+        # it works!
+        result = read_csv(StringIO(data))
 
     def test_parse_bools(self):
         data = """A,B