Merge branch 'ujson-unique-keys' of https://github.com/Komnomnomnom/pandas into Komnomnomnom-ujson-unique-keys

Author: jreback

pandas/io/json.py

@@ -78,6 +78,9 @@ class SeriesWriter(Writer):
     _default_orient = 'index'
 
     def _format_axes(self):
+        if not self.obj.index.is_unique and self.orient == 'index':
+            raise ValueError("Series index must be unique for orient="
+                             "'%s'" % self.orient)
         if self._needs_to_date(self.obj.index):
             self.copy_if_needed()
             self.obj.index = self._format_to_date(self.obj.index.to_series())
@@ -97,6 +100,15 @@ class FrameWriter(Writer):
 
     def _format_axes(self):
         """ try to axes if they are datelike """
+        if not self.obj.index.is_unique and self.orient in (
+                'index', 'columns'):
+            raise ValueError("DataFrame index must be unique for orient="
+                             "'%s'." % self.orient)
+        if not self.obj.columns.is_unique and self.orient in (
+                'index', 'columns', 'records'):
+            raise ValueError("DataFrame columns must be unique for orient="
+                             "'%s'." % self.orient)
+
         if self.orient == 'columns':
             axis = 'index'
         elif self.orient == 'index':
@@ -134,10 +146,14 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
         Series :
           default is 'index'
           allowed values are: {'split','records','index'}
+          The Series index must be unique for orient 'index'.
 
         DataFrame :
           default is 'columns'
           allowed values are: {'split','records','index','columns','values'}
+          The DataFrame index must be unique for orients 'index' and 'columns'.
+          The DataFrame columns must be unique for orients 'index', 'columns',
+          and 'records'.
 
         The format of the JSON string
           split : dict like {index -> [index], columns -> [columns], data -> [values]}

pandas/io/tests/test_json/test_pandas.py

@@ -54,6 +54,34 @@ def setUp(self):
         self.tsframe = _tsframe.copy()
         self.mixed_frame = _mixed_frame.copy()
 
+    def test_frame_non_unique_index(self):
+        df = DataFrame([['a', 'b'], ['c', 'd']], index=[1, 1],
+                       columns=['x', 'y'])
+
+        self.assertRaises(ValueError, df.to_json, orient='index')
+        self.assertRaises(ValueError, df.to_json, orient='columns')
+
+        assert_frame_equal(
+            df, read_json(df.to_json(orient='split'), orient='split'))
+        unser = read_json(df.to_json(orient='records'), orient='records')
+        self.assert_(df.columns.equals(unser.columns))
+        np.testing.assert_equal(df.values, unser.values)
+        unser = read_json(df.to_json(orient='values'), orient='values')
+        np.testing.assert_equal(df.values, unser.values)
+
+    def test_frame_non_unique_columns(self):
+        df = DataFrame([['a', 'b'], ['c', 'd']], index=[1, 2],
+                       columns=['x', 'x'])
+
+        self.assertRaises(ValueError, df.to_json, orient='index')
+        self.assertRaises(ValueError, df.to_json, orient='columns')
+        self.assertRaises(ValueError, df.to_json, orient='records')
+
+        assert_frame_equal(df, read_json(df.to_json(orient='split'),
+                                         orient='split', dtype=False))
+        unser = read_json(df.to_json(orient='values'), orient='values')
+        np.testing.assert_equal(df.values, unser.values)
+
     def test_frame_from_json_to_json(self):
 
         def _check_orient(df, orient, dtype=None, numpy=False, convert_axes=True, check_dtype=True, raise_ok=None):
@@ -236,6 +264,17 @@ def test_frame_to_json_except(self):
         df = DataFrame([1, 2, 3])
         self.assertRaises(ValueError, df.to_json, orient="garbage")
 
+    def test_series_non_unique_index(self):
+        s = Series(['a', 'b'], index=[1, 1])
+
+        self.assertRaises(ValueError, s.to_json, orient='index')
+
+        assert_series_equal(s, read_json(s.to_json(orient='split'),
+                            orient='split', typ='series'))
+        unser = read_json(s.to_json(orient='records'),
+                          orient='records', typ='series')
+        np.testing.assert_equal(s.values, unser.values)
+
     def test_series_from_json_to_json(self):
 
         def _check_orient(series, orient, dtype=None, numpy=False):