Unicode-compliant file reading and writing throughout the package.

.gitignore

@@ -3,6 +3,5 @@
 build/
 *.vdf
 *.2mdl
-.idea/workspace.xml
 .idea/*
 pysd.egg*

pysd/py_backend/vensim/table2py.py

@@ -41,9 +41,9 @@ def read_tabular(table_file, sheetname='Sheet1'):
         if extension in ['xls', 'xlsx']:
             table = pd.read_excel(table_file, sheetname=sheetname)
         elif extension == 'csv':
-            table = pd.read_csv(table_file)
+            table = pd.read_csv(table_file, encoding='UTF-8')
         elif extension == 'tab':
-            table = pd.read_csv(table_file, sep='\t')
+            table = pd.read_csv(table_file, sep='\t', encoding='UTF-8')
         else:
             raise ValueError('Unknown file or table type')
     else:

pysd/testing.py

@@ -202,9 +202,9 @@ def bounds_test(result, bounds=None, errors='return'):
         if bounds.split('.')[-1] in ['xls', 'xlsx']:
             bounds = _pd.read_excel(bounds, sheetname='Bounds', index_col='Real Name')
         elif bounds.split('.')[-1] == 'csv':
-            bounds = _pd.read_csv(bounds, index_col='Real Name')
+            bounds = _pd.read_csv(bounds, index_col='Real Name', encoding='UTF-8')
         elif bounds.split('.')[-1] == 'tab':
-            bounds = _pd.read_csv(bounds, sep='\t', index_col='Real Name')
+            bounds = _pd.read_csv(bounds, sep='\t', index_col='Real Name', encoding='UTF-8')
         else:
             raise ValueError('Unknown file type: bounds')
     else:
@@ -328,9 +328,9 @@ def sample_pspace(model, param_list=None, bounds=None, samples=100, seed=None):
         if bounds.split('.')[-1] in ['xls', 'xlsx']:
             bounds = _pd.read_excel(bounds, sheetname='Bounds', index_col='Real Name')
         elif bounds.split('.')[-1] == 'csv':
-            bounds = _pd.read_csv(bounds, index_col='Real Name')
+            bounds = _pd.read_csv(bounds, index_col='Real Name', encoding='UTF-8')
         elif bounds.split('.')[-1] == 'tab':
-            bounds = _pd.read_csv(bounds, sep='\t', index_col='Real Name')
+            bounds = _pd.read_csv(bounds, sep='\t', index_col='Real Name', encoding='UTF-8')
         else:
             raise ValueError('Unknown file type: bounds')
     else:

tests/integration_test_factory.py

@@ -47,7 +47,7 @@ class TestIntegrationExamples(unittest.TestCase):
 
         ''' % {'tests': ''.join(tests)})
 
-    with open('integration_test_pysd.py', 'w') as ofile:
+    with open('integration_test_pysd.py', 'w', encoding='UTF-8') as ofile:
         ofile.write(file_string)
 
     print('generated %i integration tests' % len(tests))

tests/test_utils.py

@@ -22,10 +22,10 @@ def runner(model_file):
 
     # load canonical output
     try:
-        canon = pd.read_csv(directory + '/output.csv', index_col='Time')
+        canon = pd.read_csv(directory + '/output.csv', index_col='Time', encoding='UTF-8')
     except IOError:
         try:
-            canon = pd.read_table(directory + '/output.tab', index_col='Time')
+            canon = pd.read_table(directory + '/output.tab', index_col='Time', encoding='UTF-8')
         except IOError:
             raise IOError('Canonical output file not found')