Files
@ 9ddf4beb947b
Branch filter:
Location: Regular-Expresso/regexp.py
9ddf4beb947b
4.5 KiB
text/x-python
added tests
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | from abc import abstractmethod
class Token:
is_skippable = False
@abstractmethod
def list_first(self):
pass
@abstractmethod
def list_last(self):
pass
@abstractmethod
def list_neighbours(self):
pass
class Symbol(Token):
def __init__(self, position, value):
self.position = position
self.value = value
def list_first(self):
yield self.position
def list_last(self):
yield self.position
def list_neighbours(self):
yield from []
def __str__(self):
return self.value
class Plus(Token):
def __init__(self, content: Token):
self.content = content
def list_first(self):
yield from self.content.list_first()
def list_last(self):
yield from self.content.list_last()
def list_neighbours(self):
yield from self.content.list_neighbours()
for x in self.list_last():
for y in self.list_first():
yield (x, y)
def __str__(self):
return str(self.content) + "+"
class Asterisk(Plus):
is_skippable = True
def __str__(self):
return str(self.content) + "*"
class Chain(Token):
def __init__(self, content: list):
self.content = content
def list_first(self):
for token in self.content:
yield from token.list_first()
if not token.is_skippable:
break
def list_last(self):
for token in reversed(self.content):
yield from token.list_last()
if not token.is_skippable:
break
def list_neighbours(self):
previous = []
for token in self.content:
for t in previous:
for x in t.list_last():
for y in token.list_first():
yield (x, y)
yield from token.list_neighbours()
if token.is_skippable:
previous.append(token)
else:
previous = [token]
@property
def is_skippable(self):
return all(x.is_skippable for x in self.content)
def __str__(self):
return "(" + "".join(str(x) for x in self.content) + ")"
def find_closing_parenthesis(pattern, k):
counter = 0
for (i, c) in enumerate(pattern[k:]):
if c == "(":
counter += 1
elif c == ")":
counter -= 1
if counter == 0:
return k+i
return None
def parse(pattern, offset=0):
res = []
i = 0
while i < len(pattern):
c = pattern[i]
if c == "(":
j = find_closing_parenthesis(pattern, i)
inner_content = parse(pattern[i+1:j], offset+i+1)
res.append(inner_content)
i = j+1
elif c == "*":
token = res.pop()
res.append(Asterisk(token))
i += 1
elif c == "+":
token = res.pop()
res.append(Plus(token))
i += 1
else:
res.append(Symbol(i+offset, c))
i += 1
return Chain(res)
class Regexp:
def __init__(self, pattern):
(self.rules, self.end_states) = self._parse(pattern)
def _parse(self, s):
r = parse(s)
rules = dict()
for i in r.list_first():
c = s[i]
key = (-1, c)
if key not in rules:
rules[key] = set()
rules[key].add(i)
for (i, j) in r.list_neighbours():
c = s[j]
key = (i, c)
if key not in rules:
rules[key] = set()
rules[key].add(j)
end_states = set(r.list_last())
if r.is_skippable:
end_states.add(-1)
return rules, end_states
def match(self, s):
current = {-1}
for c in s:
new_state = set()
for st in current:
key = (st, c)
if key in self.rules:
new_state.update(self.rules[key])
current = new_state
return any(st in self.end_states for st in current)
def determinize(self):
rules = dict()
end_states = {(-1,)} if -1 in self.end_states else set()
stack = [(-1,)]
processed_states = set()
while stack:
multistate = stack.pop()
new_rules = dict()
for ((st, c), target) in filter(lambda item: item[0][0] in multistate, self.rules.items()):
if c not in new_rules:
new_rules[c] = set()
new_rules[c].update(target)
for (c, target_set) in new_rules.items():
new_target = tuple(sorted(target_set))
rules[(multistate, c)] = new_target
if any(st in self.end_states for st in new_target):
end_states.add(new_target)
if new_target not in processed_states:
stack.append(new_target)
processed_states.add(new_target)
return (rules, end_states)
class RegexpDFA:
def __init__(self, pattern):
r = Regexp(pattern)
(self.rules, self.end_states) = r.determinize()
def match(self, s):
st = (-1,)
for c in s:
key = (st, c)
if key in self.rules:
st = self.rules[key]
else:
return False
return st in self.end_states
if __name__ == "__main__":
tests = ["", "a", "ab", "aabb", "abab", "abcd", "abcbcdbcd"]
for pattern in ["a*b*", "a+b+", "(ab)*", "(ab)+", "a((bc)*d)*"]:
print("#", pattern)
r = RegexpDFA(pattern)
for t in tests:
print(t, r.match(t))
print()
|