ensure utf8 encoding all-around

mpcontribs/config.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals, print_function
 import os
 
 indent_symbol = '>'

mpcontribs/io/mpfile.py

@@ -1,8 +1,7 @@
 from __future__ import unicode_literals, print_function
 import os, json, six, codecs, locale
 from abc import ABCMeta
-from utils import make_pair, get_indentor, RecursiveDict, nest_dict, \
-        pandas_to_dict, force_encoded_string_output
+from utils import make_pair, get_indentor, RecursiveDict, nest_dict, pandas_to_dict
 from ..config import mp_level01_titles
 from recparse import RecursiveParser
 from pandas import DataFrame
@@ -128,7 +127,6 @@ def set_test_mode(self, mp_cat_id, idx=0):
         self.document[mp_cat_id].insert_before(
             first_sub_key, ('test_index', idx+733773))
 
-    @force_encoded_string_output
     def get_string(self, with_comments=False):
         """Returns a string to be written as a file"""
         lines = []

mpcontribs/io/recparse.py

@@ -83,7 +83,7 @@ def read_csv(self, title, body):
         return is_data_section, pd.read_csv(
             StringIO(body), comment=csv_comment_char,
             skipinitialspace=True, squeeze=True,
-            converters = converters,
+            converters=converters, encoding='utf8',
             **options
         ).dropna(how='all')
 

mpcontribs/io/utils.py

@@ -83,7 +83,7 @@ def _func(*args, **kwargs):
 def make_pair(key, value, sep=':'):
     """make a mp-specific key-value pair"""
     if not isinstance(value, string_types): value = str(value)
-    return '{} '.format(sep).join([key, value.decode('utf-8')])
+    return '{} '.format(sep).join([key, value])
 
 def get_indentor(n=0):
     """get level-n indentor"""