Added fastchardet tests; ready for bug 632276

This commit is contained in:
mattbasta 2011-02-08 04:05:44 -05:00
Родитель 87bdda36f6
Коммит 456a7100f1
1 изменённых файлов: 39 добавлений и 0 удалений

39
tests/test_fastchardet.py Normal file
Просмотреть файл

@ -0,0 +1,39 @@
import fastchardet
def test_ascii():
"Determines that fastchardet detects ASCII properly"
assert fastchardet.detect("This is plain ASCII")["encoding"] == "ascii"
def test_utf8():
"Determines that fastchardet properly detects UTF-8"
assert fastchardet.detect("""\xEF\xBB\xBF
Haldo, UTF-8
""")["encoding"] == "utf_8"
def test_utfn():
"Determines that fastchardet properly detects UTF-N"
assert fastchardet.detect("""\xFF\xFE\x00\x00
Haldo, UTF-Not 8
""")["encoding"] == "utf_n"
def test_unicode():
"For when we're silly sallies and pass unicode in"
assert fastchardet.detect(unicode("foo"))["encoding"] == "unicode"
def test_esoteric():
"Makes sure that fastchardet can detect other encodings"
a = lambda code: fastchardet.detect(code)["encoding"]
# High Bytes
print a("High Byte:\x91")
assert a("High Byte:\x91") == "windows-1252"
# UTF-8 without BOM
print a("\xc2\xbc + \xc2\xbd = \xcd\xbe")
assert a("\xc2\xbc + \xc2\xbd = \xcd\xbe") == "utf_8"