TST/ENH: add locale testing utils

Author: cpcloud

ci/install.sh

@@ -57,6 +57,11 @@ time pip install $PIP_ARGS -r ci/requirements-${TRAVIS_PYTHON_VERSION}${JOB_TAG}
 time sudo apt-get install libatlas-base-dev gfortran
 
 
+# need to enable for locale testing
+time echo 'it_CH.UTF-8 UTF-8' | sudo tee -a /var/lib/locales/supported.d/it
+time sudo locale-gen
+
+
 # install gui for clipboard testing
 if [ -n "$GUI" ]; then
     echo "Using GUI clipboard: $GUI"

doc/source/release.rst

@@ -578,6 +578,9 @@ Bug Fixes
   - Fix a bug with ``NDFrame.replace()`` which made replacement appear as
     though it was (incorrectly) using regular expressions (:issue:`5143`).
   - Fix better error message for to_datetime (:issue:`4928`)
+  - Made sure different locales are tested on travis-ci (:issue:`4918`). Also
+    adds a couple of utilities for getting locales and setting locales with a
+    context manager.
 
 pandas 0.12.0
 -------------

pandas/io/tests/test_data.py

@@ -13,6 +13,7 @@
 from pandas.io.data import DataReader, SymbolWarning
 from pandas.util.testing import (assert_series_equal, assert_produces_warning,
                                  network, assert_frame_equal)
+import pandas.util.testing as tm
 from numpy.testing import assert_array_equal
 
 
@@ -44,9 +45,9 @@ def test_google(self):
         start = datetime(2010, 1, 1)
         end = datetime(2013, 1, 27)
 
-        self.assertEquals(
-            web.DataReader("F", 'google', start, end)['Close'][-1],
-            13.68)
+        with tm.set_locale('en_US.UTF-8'):
+            panel = web.DataReader("F", 'google', start, end)
+            self.assertEquals(panel.Close[-1], 13.68)
 
         self.assertRaises(Exception, web.DataReader, "NON EXISTENT TICKER",
                           'google', start, end)
@@ -58,13 +59,15 @@ def test_get_quote_fails(self):
 
     @network
     def test_get_goog_volume(self):
-        df = web.get_data_google('GOOG')
+        with tm.set_locale('en_US.UTF-8'):
+            df = web.get_data_google('GOOG').sort_index()
         self.assertEqual(df.Volume.ix['OCT-08-2010'], 2863473)
 
     @network
     def test_get_multi1(self):
         sl = ['AAPL', 'AMZN', 'GOOG']
-        pan = web.get_data_google(sl, '2012')
+        with tm.set_locale('en_US.UTF-8'):
+            pan = web.get_data_google(sl, '2012')
 
         def testit():
             ts = pan.Close.GOOG.index[pan.Close.AAPL > pan.Close.GOOG]
@@ -79,8 +82,9 @@ def testit():
     @network
     def test_get_multi2(self):
         with warnings.catch_warnings(record=True) as w:
-            pan = web.get_data_google(['GE', 'MSFT', 'INTC'], 'JAN-01-12',
-                                      'JAN-31-12')
+            with tm.set_locale('en_US.UTF-8'):
+                pan = web.get_data_google(['GE', 'MSFT', 'INTC'], 'JAN-01-12',
+                                        'JAN-31-12')
             result = pan.Close.ix['01-18-12']
             assert_n_failed_equals_n_null_columns(w, result)
 

pandas/tools/tests/test_util.py

@@ -1,11 +1,20 @@
 import os
-import nose
+import locale
+import codecs
 import unittest
 
+import nose
+
 import numpy as np
 from numpy.testing import assert_equal
 
 from pandas.tools.util import cartesian_product
+from pandas.util.testing import get_locales, set_locale
+
+
+CURRENT_LOCALE = locale.getlocale()
+LOCALE_OVERRIDE = os.environ.get('LOCALE_OVERRIDE', None)
+
 
 class TestCartesianProduct(unittest.TestCase):
 
@@ -16,6 +25,36 @@ def test_simple(self):
                     np.array([ 1, 22,  1, 22,  1, 22])]
         assert_equal(result, expected)
 
+
+class TestLocaleUtils(unittest.TestCase):
+    def test_get_locales(self):
+        assert len(get_locales(prefix='en')) > 0
+
+    def test_get_locales_prefix(self):
+        with set_locale('en_US.UTF-8'):
+            assert len(get_locales(prefix='en')) > 0
+
+    def test_set_locale(self):
+        old_locale = CURRENT_LOCALE
+
+        if LOCALE_OVERRIDE is not None:
+            lang, enc = LOCALE_OVERRIDE.split('.')
+        else:
+            lang, enc = 'it_CH', 'UTF-8'
+
+        enc = codecs.lookup(enc).name
+        new_locale = lang, enc
+
+        with set_locale(new_locale) as normalized_locale:
+            new_lang, new_enc = normalized_locale.split('.')
+            new_enc = codecs.lookup(enc).name
+            normalized_locale = new_lang, new_enc
+            self.assertEqual(normalized_locale, new_locale)
+
+        current_locale = locale.getlocale()
+        self.assertEqual(current_locale, old_locale)
+
+
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
                    exit=False)

pandas/tslib.pyx

@@ -2601,10 +2601,6 @@ cdef object _period_strftime(int64_t value, int freq, object fmt):
 
             result = result.replace(str_extra_fmts[i], repl)
 
-    # Py3?
-    #if not PyString_Check(result):
-        #result = str(result)
-
     if PY2:
        result = result.decode('utf-8', 'ignore')