1 files changed, 107 insertions, 0 deletions

diff --git a/test/test_tools/test_himo.py b/test/test_tools/test_himo.py
new file mode 100644
index 0000000..cb58ca5
--- /dev/null
+++ b/test/test_tools/test_himo.py
@@ -0,0 +1,107 @@
+import sys
+import os
+import unittest
+path = os.path.realpath(os.path.join(os.path.dirname(__file__), '..', '..'))
+sys.path.append(path)
+from dodai.tools.himo import String2Himo
+from dodai.tools.himo import Himo
+from dodai.tools.himo import HimoAsciiError
+from decimal import Decimal as D
+
+class TestString2Himo(unittest.TestCase):
+
+    def setUp(self):
+        self.string_to_himo_one = String2Himo()
+        self.string_to_himo_two = String2Himo('unicode_escape')
+
+    def test_regular_string_one(self):
+        obj = self.string_to_himo_one(str('abcd'))
+        self.assertTrue(isinstance(obj, Himo))
+
+    def test_regular_string_two(self):
+        test = str('abcd')
+        obj = self.string_to_himo_one(test)
+        self.assertTrue(obj == test)
+
+    def test_regular_string_three(self):
+        obj = self.string_to_himo_two(str('abcd'))
+        self.assertTrue(isinstance(obj, Himo))
+
+    def test_regular_string_four(self):
+        test = str('abcd')
+        obj = self.string_to_himo_two(test)
+        self.assertTrue(obj == test)
+
+    def test_regular_string_five(self):
+        test = 1
+        obj = self.string_to_himo_two(test)
+        self.assertEqual(int(obj), test)
+
+    def test_decode_html(self):
+        test = u'\u4e5d\xf2\xe5\xe9'
+        obj = self.string_to_himo_one(u'九òåé')
+        self.assertEqual(test, obj)
+
+    def test_decode_chardet(self):
+        # Korean Text in the EUC-KR character set
+        kor = '\xb4\xe7\xbd\xc5\xc0\xcc \xc3\xa3\xb4\xc2 \xb8\xf0\xb5\xe7 '\
+               '\xbd\xba\xc5\xb8\xc0\xcf, \xbf\xc1\xbc\xc7'
+        test = '\ub2f9\uc2e0\uc774 \ucc3e\ub294 \ubaa8\ub4e0 '\
+               '\uc2a4\ud0c0\uc77c, \uc625\uc158'.decode('unicode_escape')
+        obj = self.string_to_himo_one(kor)
+        self.assertEqual(obj, test)
+
+    def test_html_decode_one(self):
+        # Korean Text
+        kor = '당신이 찾는 모든 '\
+              '스타일, 옥션& foo'
+        test = u'\ub2f9\uc2e0\uc774 \ucc3e\ub294 \ubaa8\ub4e0 '\
+               u'\uc2a4\ud0c0\uc77c, \uc625\uc158& foo'
+        obj = self.string_to_himo_one(kor)
+        self.assertEqual(obj, test)
+
+    def test_html_decode_two(self):
+        kor = '&ampppe;'
+        obj = self.string_to_himo_one(kor)
+        self.assertEqual(obj, kor)
+
+
+class TestHimo(unittest.TestCase):
+
+    def setUp(self):
+        # "Elephants are our brothers" in Japanese.  This line comes from
+        # an episode of a old Japanese TV show called "Koko Ga Hen Da Yo,
+        # Nihonjin" http://en.wikipedia.org/wiki/Koko_ga_hen_da_yo,_nihonjin
+        # This line came from an African native who spoke Japanese fluently
+        self.jp = u'\u8c61\u306f\u79c1\u305f\u3061\u306e\u5144\u5f1f'\
+                  u'\u3067\u3059'
+        self.jp_html = u'象は私たちの'\
+                       u'兄弟です'
+
+    def test_html(self):
+        obj = Himo(self.jp)
+        test = obj.html()
+        self.assertEqual(test, self.jp_html)
+
+    def test_decimal(self):
+        obj = Himo('23.55')
+        obj = obj.decimal()
+        self.assertTrue(isinstance(obj, D))
+        self.assertEqual(obj, D('23.55'))
+
+    def test_ascii_one(self):
+        # "Elephants live in Africa" in spanish
+        obj = Himo(u'Los elefantes viven en \xc1frica')
+        test = u'Los elefantes viven en Africa'
+        self.assertEqual(obj.ascii(), test)
+
+    def test_ascii_two(self):
+        # "Elephants are our brothers" in French
+        obj = Himo(u'Les \xe9l\xe9phants sont nos fr\xe8res \xa9')
+        test = u'Les elephants sont nos freres (C)'
+        self.assertEqual(obj.ascii(), test)
+
+    def test_ascii_three(self):
+
+        obj = Himo(self.jp)
+        self.failUnlessRaises(HimoAsciiError, obj.ascii)