def test_is_word():
assert rsre_char.is_word(ord('A'))
assert rsre_char.is_word(ord('_'))
assert not rsre_char.is_word(UPPER_PI)
assert not rsre_char.is_word(LOWER_PI)
assert not rsre_char.is_word(ord(','))
#
assert rsre_char.is_uni_word(ord('A'))
assert rsre_char.is_uni_word(ord('_'))
assert rsre_char.is_uni_word(UPPER_PI)
assert rsre_char.is_uni_word(LOWER_PI)
assert not rsre_char.is_uni_word(ord(','))
def test_is_word():
assert rsre_char.is_word(ord('A'))
assert rsre_char.is_word(ord('_'))
assert not rsre_char.is_word(UPPER_PI)
assert not rsre_char.is_word(LOWER_PI)
assert not rsre_char.is_word(ord(','))
#
assert rsre_char.is_uni_word(ord('A'))
assert rsre_char.is_uni_word(ord('_'))
assert rsre_char.is_uni_word(UPPER_PI)
assert rsre_char.is_uni_word(LOWER_PI)
assert not rsre_char.is_uni_word(ord(','))
def _parse_escape(source, info, in_set):
saved_ignore = source.ignore_space
source.ignore_space = False
ch = source.get()
source.ignore_space = saved_ignore
if not ch:
return Character(0)
if ch == u"g" and not in_set:
here = source.pos
try:
return _parse_group_ref(source, info)
except RegexpError:
source.pos = here
return make_character(info, ord(ch[0]), in_set)
elif ch == u"G" and not in_set:
return AtPosition(AT_BEGINNING)
elif ch in u"pP":
return _parse_property(source, info, ch == u"p", in_set)
elif is_word(ord(ch[0])):
if not in_set:
if ch in POSITION_ESCAPES:
return POSITION_ESCAPES[ch]
if ch in CHARSET_ESCAPES:
return CHARSET_ESCAPES[ch]
elif ch in CHARACTER_ESCAPES:
return Character(ord(CHARACTER_ESCAPES[ch]))
return make_character(info, ord(ch[0]), in_set)
if is_digit(ord(ch[0])):
return _parse_numeric_escape(source, info, ch, in_set)
else:
return make_character(info, ord(ch[0]), in_set)
def _parse_escape(source, info, in_set):
saved_ignore = source.ignore_space
source.ignore_space = False
ch = source.get()
source.ignore_space = saved_ignore
if not ch:
raise RegexpError("bad escape")
if ch == u"g" and not in_set:
here = source.pos
try:
return _parse_group_ref(source, info)
except RegexpError:
source.pos = here
return make_character(info, ord(ch[0]), in_set)
elif ch == u"G" and not in_set:
return AtPosition(AT_BEGINNING)
elif ch in u"pP":
return _parse_property(source, info, ch == u"p", in_set)
elif is_word(ord(ch[0])):
if not in_set:
if ch in POSITION_ESCAPES:
return POSITION_ESCAPES[ch]
if ch in CHARSET_ESCAPES:
return CHARSET_ESCAPES[ch]
elif ch in CHARACTER_ESCAPES:
return Character(ord(CHARACTER_ESCAPES[ch]))
return make_character(info, ord(ch[0]), in_set)
if is_digit(ord(ch[0])):
return _parse_numeric_escape(source, info, ch, in_set)
else:
return make_character(info, ord(ch[0]), in_set)
