add test

CHANGES.rst

@@ -1,6 +1,12 @@
 CHANGES
 =======
 
+2.1.x
+-----
+
+- update language models (uchardet)
+- add iso8859-2 test but disabled it
+
 2.1.4 (2018-09-27)
 ------------------
 

src/cchardet/__init__.py

@@ -17,6 +17,7 @@ def detect(msg):
         encoding = encoding.decode()
     return {"encoding": encoding, "confidence": confidence}
 
+
 class UniversalDetector(object):
     def __init__(self):
         self._detector = _cchardet.UniversalDetector()

src/tests/bench.py

@@ -16,7 +16,8 @@ def main():
             start_chardet = time.time()
             chardet.detect(msg)
             result_chardet += (time.time() - start_chardet)
-        print('chardet v%s:' % (chardet.__version__), 1 / (result_chardet / do_times), 'call(s)/s')
+        print('chardet v%s:' % (chardet.__version__), 1 /
+              (result_chardet / do_times), 'call(s)/s')
 
         # Test cchardet
         result_cchardet = 0
@@ -24,7 +25,9 @@ def main():
             start_cchardet = time.time()
             cchardet.detect(msg)
             result_cchardet += (time.time() - start_cchardet)
-        print('cchardet v%s:' % (cchardet.__version__), 1 / (result_cchardet / do_times), 'call(s)/s')
+        print('cchardet v%s:' % (cchardet.__version__),
+              1 / (result_cchardet / do_times), 'call(s)/s')
+
 
 if __name__ == '__main__':
     main()

src/tests/samples/iso8859-2.csv

@@ -0,0 +1,3 @@
+id,name
+1,english
+2,©

src/tests/test.py

@@ -14,6 +14,7 @@ SKIP_LIST = [
     'tests/testdata/he/iso-8859-8.txt'
 ]
 
+
 # Python can't decode encoding
 SKIP_LIST_02 = [
     'tests/testdata/vi/viscii.txt',
@@ -21,6 +22,7 @@ SKIP_LIST_02 = [
 ]
 SKIP_LIST_02.extend(SKIP_LIST)
 
+
 class TestCChardet():
     def test_ascii(self):
         detected_encoding = cchardet.detect(b'abcdefghijklmnopqrstuvwxyz')
@@ -73,7 +75,7 @@ class TestCChardet():
                 detected_encoding['encoding'].lower()
             )
         )
-    
+
     def test_github_issue_20(self):
         """
         https://github.com/PyYoshi/cChardet/issues/20
@@ -100,7 +102,8 @@ class TestCChardet():
                 try:
                     msg.decode(detected_encoding["encoding"])
                 except LookupError as e:
-                    print("LookupError: { file=%s, encoding=%s }" % (testfile, detected_encoding["encoding"]))
+                    print("LookupError: { file=%s, encoding=%s }" % (
+                        testfile, detected_encoding["encoding"]))
                     raise e
 
     def test_utf8_with_bom(self):
@@ -126,3 +129,17 @@ class TestCChardet():
                 detected_encoding['encoding']
             )
         )
+
+    # def test_iso8859_2_csv(self):
+    #     testfile = 'tests/samples/iso8859-2.csv'
+    #     with open(testfile, 'rb') as f:
+    #         msg = f.read()
+    #         detected_encoding = cchardet.detect(msg)
+    #         eq_(
+    #             "iso8859-2",
+    #             detected_encoding['encoding'].lower(),
+    #             'Expected %s, but got %s' % (
+    #                 "iso8859-2",
+    #                 detected_encoding['encoding'].lower()
+    #             )
+    #         )