def test_utf8_string_builder():
s = rutf8.Utf8StringBuilder()
s.append("foo")
s.append_char("x")
assert s.getlength() == 4
assert s.build() == "foox"
s.append(u"\u1234".encode("utf8"))
assert s.getlength() == 5
assert s.build().decode("utf8") == u"foox\u1234"
s.append("foo")
s.append_char("x")
assert s.getlength() == 9
assert s.build().decode("utf8") == u"foox\u1234foox"
s = rutf8.Utf8StringBuilder()
s.append_code(0x1234)
assert s.build().decode("utf8") == u"\u1234"
assert s.getlength() == 1
s.append_code(0xD800)
assert s.getlength() == 2
s = rutf8.Utf8StringBuilder()
s.append_utf8("abc", 3)
assert s.getlength() == 3
assert s.build().decode("utf8") == u"abc"
s.append_utf8(u"\u1234".encode("utf8"), 1)
assert s.build().decode("utf8") == u"abc\u1234"
assert s.getlength() == 4
s.append_code(0xD800)
assert s.getlength() == 5
def _builder(self):
if self.is_unicode:
return rutf8.Utf8StringBuilder()
else:
return rstring.StringBuilder()
def descr_upper(s):
builder = rutf8.Utf8StringBuilder(len(s))
for ch in rutf8.Utf8StringIterator(s):
ch = unicodedb.toupper(ch)
builder.append_code(ch)
return builder.build()
def test_utf8_string_builder_bad_code():
s = rutf8.Utf8StringBuilder()
with pytest.raises(rutf8.OutOfRange):
s.append_code(0x110000)
assert s.build() == ''
assert s.getlength() == 0
