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
|
# Writing a small proof-of-concept...
# - lexer
# - parser
# - compiler
# ...for regex.
#
# BNF
# expression -> ( char_class | CHAR ) quantifier? ( "|" expression )*
# char_class -> "[" CHAR+ "]"
# quantifier -> "?" | "*" | "+" | "{" INT? "," INT? "}"
#
# Of the numerous things I do not support, here are a few items of which I'm
# aware:
# - alternatives: (a|b)
# - capture groups: (ab)cd
from parser import Parser
import string
################################################################################
# Top-Level API
################################################################################
def tokenize(xs):
"""
Transform `xs` into a list of tokens.
Also: expand shorthand symbols using the following table:
- ? -> {0,1}
- * -> {0,}
- + -> {1,}
"""
result = []
i = 0
shorthand = {
"?": ["{", 0, ",", 1, "}"],
"*": ["{", 0, ",", "}"],
"+": ["{", 1, ",", "}"],
}
while i < len(xs):
if xs[i] in shorthand:
for c in shorthand[xs[i]]:
result.append(c)
i += 1
elif xs[i] == "{":
result.append(xs[i])
i += 1
curr = ""
while xs[i] in string.digits:
curr += xs[i]
i += 1
result.append(int(curr))
assert xs[i] == ","
result.append(",")
i += 1
curr = ""
while xs[i] in string.digits:
curr += xs[i]
i += 1
result.append(int(curr))
else:
result.append(xs[i])
i += 1
return result
def parse(expr):
"""
Tokenize `expr` and convert it into a parse-tree.
"""
tokens = tokenize(expr)
return parse_tokens(tokens)
def compile(xs):
"""
Transform `xs`, a parse-tree representing a regex, into a function that
accepts a string, and returns the substring that the regex matches.
"""
def fn(input):
match = ""
i = 0
for x in xs:
matches, q = x[1], x[2]
lo, hi = q[1], q[2]
for j in range(lo):
if i < len(input) and input[i] in matches:
match += input[i]
i += 1
else:
print("Failed to match {} with {}".format(input[i], matches))
return None
if hi == float('inf'):
while i < len(input) and input[i] in matches:
match += input[i]
i += 1
else:
for j in range(hi - lo):
if i < len(input) and input[i] in matches:
match += input[i]
i += 1
return match
return fn
################################################################################
# Helper Functions
################################################################################
def parse_tokens(tokens):
result = []
parser = Parser(tokens)
while not parser.exhausted():
result.append(parse_expression(parser))
return result
def parse_expression(parser):
if parser.curr() == "[":
return parse_character_class(parser)
else:
return parse_character(parser)
def parse_character_class(parser):
parser.expect("[")
beg = parser.consume()
parser.expect("-")
end = parser.consume()
parser.expect("]")
if parser.curr() == "{":
q = parse_quantifier(parser)
return char_class(xs=expand_range(beg, end), q=q)
def parse_quantifier(parser):
parser.expect("{")
if parser.match([","]):
end = parser.consume()
parser.expect("}")
return quantifier(beg=0, end=end)
else:
beg = parser.consume()
parser.expect(",")
if parser.match(["}"]):
return quantifier(beg=beg)
else:
end = parser.consume()
parser.expect("}")
return quantifier(beg=beg, end=end)
def parse_character(parser):
c = parser.consume()
q = None
if parser.curr() == "{":
q = parse_quantifier(parser)
return char_class(xs={c}, q=q)
def char_class(xs=set(), q=None):
if not q:
q = quantifier(beg=1, end=1)
return ["CHARACTER_CLASS", xs, q]
def expand_range(beg, end):
# TODO: Implement this
return {string.printable[i]
for i in range(string.printable.index(beg),
string.printable.index(end) + 1)}
def quantifier(beg=0, end=float('inf')):
return ['QUANTIFIER', beg, end]
################################################################################
# Tests
################################################################################
xs = [
("[a-c]*[0-9]{2,3}", ["dog"]),
("ca+t?", ["cat", "caaaat", "ca", "dog"]),
]
for re, inputs in xs:
print("Regex: {}".format(re))
print("Tokens: {}".format(tokenize(re)))
print("Parsed: {}".format(parse(re)))
print("\nTESTS")
for input in inputs:
print("Attempting to match \"{}\"...".format(input))
parser = compile(parse(re))
print("Result: \"{}\"\n".format(parser(input)))
|
