BUG: Apply min_itemsize to index even when not appending

closes pandas-dev#10381

Author: Pietro Battiston <[email protected]>

Closes pandas-dev#14812 from toobaz/to_hdf_min_itemsize and squashes the following commits:

c07f1e4 [Pietro Battiston] Whatsnew
38b8fcc [Pietro Battiston] Tests for previous commit
c838afa [Pietro Battiston] BUG: set min_itemsize even when there is no need to validate (pandas-dev#10381)

Author: toobaz

doc/source/whatsnew/v0.19.2.txt

@@ -60,6 +60,7 @@ Bug Fixes
 
 - Bug in ``HDFStore`` when writing a ``MultiIndex`` when using ``data_columns=True`` (:issue:`14435`)
 - Bug in ``HDFStore.append()`` when writing a ``Series`` and passing a ``min_itemsize`` argument containing a value for the ``index`` (:issue:`11412`)
+- Bug when writing to a ``HDFStore`` in ``table`` format with a ``min_itemsize`` value for the ``index`` and without asking to append (:issue:`10381`)
 - Bug in ``Series.groupby.nunique()`` raising an ``IndexError`` for an empty ``Series`` (:issue:`12553`)
 - Bug in ``DataFrame.nlargest`` and ``DataFrame.nsmallest`` when the index had duplicate values (:issue:`13412`)
 

pandas/io/pytables.py

@@ -3429,9 +3429,8 @@ def create_axes(self, axes, obj, validate=True, nan_rep=None,
         j = len(self.index_axes)
 
         # check for column conflicts
-        if validate:
-            for a in self.axes:
-                a.maybe_set_size(min_itemsize=min_itemsize)
+        for a in self.axes:
+            a.maybe_set_size(min_itemsize=min_itemsize)
 
         # reindex by our non_index_axes & compute data_columns
         for a in self.non_index_axes:

pandas/io/tests/test_pytables.py

@@ -1372,6 +1372,22 @@ def check_col(key, name, size):
                          min_itemsize={'index': 4})
             tm.assert_series_equal(store.select('ss2'), df['B'])
 
+            # min_itemsize in index without appending (GH 10381)
+            store.put('ss3', df, format='table',
+                      min_itemsize={'index': 6})
+            # just make sure there is a longer string:
+            df2 = df.copy().reset_index().assign(C='longer').set_index('C')
+            store.append('ss3', df2)
+            tm.assert_frame_equal(store.select('ss3'),
+                                  pd.concat([df, df2]))
+
+            # same as above, with a Series
+            store.put('ss4', df['B'], format='table',
+                      min_itemsize={'index': 6})
+            store.append('ss4', df2['B'])
+            tm.assert_series_equal(store.select('ss4'),
+                                   pd.concat([df['B'], df2['B']]))
+
             # with nans
             _maybe_remove(store, 'df')
             df = tm.makeTimeDataFrame()
@@ -1426,6 +1442,26 @@ def check_col(key, name, size):
             self.assertRaises(ValueError, store.append, 'df',
                               df, min_itemsize={'foo': 20, 'foobar': 20})
 
+    def test_to_hdf_with_min_itemsize(self):
+
+        with ensure_clean_path(self.path) as path:
+
+            # min_itemsize in index with to_hdf (GH 10381)
+            df = tm.makeMixedDataFrame().set_index('C')
+            df.to_hdf(path, 'ss3', format='table', min_itemsize={'index': 6})
+            # just make sure there is a longer string:
+            df2 = df.copy().reset_index().assign(C='longer').set_index('C')
+            df2.to_hdf(path, 'ss3', append=True, format='table')
+            tm.assert_frame_equal(pd.read_hdf(path, 'ss3'),
+                                  pd.concat([df, df2]))
+
+            # same as above, with a Series
+            df['B'].to_hdf(path, 'ss4', format='table',
+                           min_itemsize={'index': 6})
+            df2['B'].to_hdf(path, 'ss4', append=True, format='table')
+            tm.assert_series_equal(pd.read_hdf(path, 'ss4'),
+                                   pd.concat([df['B'], df2['B']]))
+
     def test_append_with_data_columns(self):
 
         with ensure_clean_store(self.path) as store: