def make_ctx(self, w_string, pos=0, endpos=sys.maxint):
"""Make a StrMatchContext, BufMatchContext or a Utf8MatchContext for
searching in the given w_string object."""
space = self.space
if pos < 0:
pos = 0
if endpos < pos:
endpos = pos
if space.isinstance_w(w_string, space.w_unicode):
w_unicode_obj = space.convert_arg_to_w_unicode(w_string)
utf8str = w_unicode_obj._utf8
length = w_unicode_obj._len()
if pos <= 0:
bytepos = 0
elif pos >= length:
bytepos = len(utf8str)
else:
index_storage = w_unicode_obj._get_index_storage()
bytepos = rutf8.codepoint_position_at_index(
utf8str, index_storage, pos)
if endpos >= length:
endbytepos = len(utf8str)
else:
index_storage = w_unicode_obj._get_index_storage()
endbytepos = rutf8.codepoint_position_at_index(
utf8str, index_storage, endpos)
ctx = rsre_utf8.Utf8MatchContext(utf8str, bytepos, endbytepos,
self.flags)
# xxx we store the w_string on the ctx too, for
# W_SRE_Match.bytepos_to_charindex()
ctx.w_unicode_obj = w_unicode_obj
return ctx
elif space.isinstance_w(w_string, space.w_bytes):
str = space.bytes_w(w_string)
if pos > len(str):
pos = len(str)
if endpos > len(str):
endpos = len(str)
return self._make_str_match_context(str, pos, endpos)
else:
buf = space.readbuf_w(w_string)
size = buf.getlength()
assert size >= 0
if pos > size:
pos = size
if endpos > size:
endpos = size
return rsre_core.BufMatchContext(buf, pos, endpos, self.flags)
def test_codepoint_position_at_index_inverse(u):
print u
b = u.encode('utf8')
storage = rutf8.create_utf8_index_storage(b, len(u))
for i in range(len(u) + 1):
bytepos = rutf8.codepoint_position_at_index(b, storage, i)
assert rutf8.codepoint_index_at_byte_position(
b, storage, bytepos, len(u)) == i
def test_codepoint_position_at_index(u):
index = rutf8.create_utf8_index_storage(u.encode('utf8'), len(u))
for i in range(len(u) + 1):
assert (rutf8.codepoint_position_at_index(u.encode('utf8'), index, i) ==
len(u[:i].encode('utf8')))