Added explicit utf8 encoding to file opens, reported in #11

pygoslin/domain/FunctionalGroup.py

@@ -254,7 +254,7 @@ def to_string(self, level):
 _known_functional_groups, s = {}, SumFormulaParser()
 fg_dir_name = path.dirname(pygoslin.__file__)
 fg_file_name = path.join(fg_dir_name, "data", "goslin", "functional-groups.csv")
-with open(fg_file_name, "rt") as fg_infile:
+with open(fg_file_name, mode = "rt", encoding= "utf-8") as fg_infile:
     fg_infile.readline()
     for line in fg_infile:
         line = line.strip()

pygoslin/domain/LipidClass.py

@@ -62,7 +62,7 @@ def get_class(name):
 
 all_lipids_dir_name = path.dirname(pygoslin.__file__)
 file_name = path.join(all_lipids_dir_name, "data", "goslin", "lipid-list.csv")
-with open(file_name, mode = "rt") as infile:
+with open(file_name, mode = "rt", encoding= "utf-8") as infile:
     line = infile.readline() # skip title row
     lipid_reader = csv.reader(infile, delimiter=',', quotechar='"')
     sum_formula_parser = SumFormulaParser()

pygoslin/parser/Parser.py

@@ -117,7 +117,7 @@ def __init__(self):
         dir_name = path.dirname(pygoslin.__file__)
         file_name = path.join(dir_name, "data", "goslin", "trivial-names.csv")
         
-        with open(file_name, "rt") as trivial_infile:
+        with open(file_name, "rt", encoding= "utf-8") as trivial_infile:
             trivial_infile.readline()
             for line in trivial_infile:
                 line = line.strip()

pygoslin/parser/ParserCommon.py

@@ -293,7 +293,7 @@ def top_nodes( rule_index):
     def extract_text_based_rules(grammar_filename, quote = DEFAULT_QUOTE):
         grammar, sb,current_position = "", [], 0
 
-        with open(grammar_filename, mode = "rt") as infile:
+        with open(grammar_filename, mode = "rt", encoding= "utf-8") as infile:
             grammar = infile.read() + "\n";
         grammar_length = len(grammar)
 
@@ -377,7 +377,7 @@ def extract_text_based_rules(grammar_filename, quote = DEFAULT_QUOTE):
 
 
     def dump_child(self, class_name, parser_event_handler_name):
-        with open("%s.py" % class_name, mode = "wt") as dumpfile:
+        with open("%s.py" % class_name, mode = "wt", encoding= "utf-8") as dumpfile:
             dumpfile.write("from pygoslin.parser.Parser import Parser\n")
             dumpfile.write("from pygoslin.parser.%s import %s\n\n" % (parser_event_handler_name, parser_event_handler_name))
             dumpfile.write("class %s(Parser):\n" % class_name)

pygoslin/tests/FattyAcidsTest.py

@@ -40,7 +40,7 @@ class LipidMapsTest(unittest.TestCase):
     def test_parser(self):
         lipid_data = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "fatty-acids-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             lipidreader = csv.reader(infile, delimiter=',', quotechar='"')
             for row in lipidreader:
                 lipid_data.append(row)

pygoslin/tests/GoslinTest.py

@@ -99,7 +99,7 @@ def test_sphingolipids(self):
     def test_parser(self):
         lipidnames = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "goslin-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             for line in infile:
                 line = line.strip().strip(" ")
                 if len(line) > 0: lipidnames.append(line)

pygoslin/tests/HmdbTest.py

@@ -96,7 +96,7 @@ def test_sphingolipids(self):
     def test_parser(self):
         lipidnames = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "hmdb-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             for line in infile:
                 line = line.strip().strip(" ")
                 if len(line) > 0: lipidnames.append(line)

pygoslin/tests/LipidMapsTest.py

@@ -92,7 +92,7 @@ def test_sphingolipids(self):
     def test_parser(self):
         lipidnames = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "lipid-maps-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             lipidreader = csv.reader(infile, delimiter=',', quotechar='"')
             for row in lipidreader:
                 lipidnames.append(row)

pygoslin/tests/MassesTest.py

@@ -44,7 +44,7 @@ class TestFormulas(unittest.TestCase):
     def test_masses(self):
         global parser
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", 'lipid-masses.csv')
-        with open(file_name, newline='') as csvfile:
+        with open(file_name, newline='', encoding= "utf-8") as csvfile:
             lipidreader = csv.reader(csvfile, delimiter=',', quotechar='\"')
             for i, row in enumerate(lipidreader):
                 if i == 0: continue

pygoslin/tests/ParserTest.py

@@ -539,7 +539,7 @@ def test_parser_read(self):
         global lipid_parser
         lipidnames = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "lipidnames.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             for line in infile:
                 line = line.strip().strip(" ")
                 if len(line) < 2: continue

pygoslin/tests/ShorthandTest.py

@@ -172,7 +172,7 @@ def test_sphingolipids(self):
     def test_nomenclature(self):
         data = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "shorthand-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             lipidreader = csv.reader(infile, delimiter=',', quotechar='"')
             for row in lipidreader:
                 row[-1] = row[-1].strip(" ")

pygoslin/tests/SwissLipidsTest.py

@@ -85,7 +85,7 @@ def test_sphingolipids(self):
     def teset_swiss_lipids_parser(self):
         lipidnames = []
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", "swiss-lipids-test.csv")
-        with open(file_name, mode = "rt") as infile:
+        with open(file_name, mode = "rt", encoding= "utf-8") as infile:
             for line in infile:
                 line = line.strip().strip(" ")
                 if len(line) > 0: lipidnames.append(line)

pygoslin/tests/TestFormulas.py

@@ -46,7 +46,7 @@ class TestFormulas(unittest.TestCase):
     def test_formulas_swiss_lipids(self):
         global swiss_lipids_parser
         file_names = os.path.join("pygoslin", "data", "goslin", "testfiles", 'formulas-swiss-lipids.csv')
-        with open(file_names, newline='') as csvfile:
+        with open(file_names, newline='', encoding= "utf-8") as csvfile:
             lipidreader = csv.reader(csvfile, delimiter=',', quotechar='\"')
 
             for row in lipidreader:
@@ -70,7 +70,7 @@ def test_formulas_swiss_lipids(self):
     def test_formulas_lipid_maps(self):
         global lipids_maps_parser
         file_name = os.path.join("pygoslin", "data", "goslin", "testfiles", 'formulas-lipid-maps.csv')
-        with open(file_name, newline='') as csvfile:
+        with open(file_name, newline='', encoding= "utf-8") as csvfile:
             lipidreader = csv.reader(csvfile, delimiter=',', quotechar='\"')
 
             for row in lipidreader: