regex_parser/REparser.py at master · cpdeivis/regex_parser · GitHub

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
from sly import Parser
from RElex import RegexLexer
from Automata import eNFA


class RegexParser(Parser):
    # Obtem lista de tokens do lexer
    tokens = RegexLexer.tokens

    def __init__(self, isVerbose=False):
        self.Automaton = eNFA()
        self.Verbose = isVerbose

    # Regras gramaticais e ações
    # Os argumentos dos decoradores são o lado direito das regras da gramatica
    @_("union", "simple_re")
    def re(self, p):
        if self.Verbose:
            print(p._slice)
        if "union" in p._namemap:
            self.Automaton.Start = p.union[0]
            return p.union
        else:
            self.Automaton.Start = p.simple_re[0]
            return p.simple_re

    @_("re ALT simple_re")
    def union(self, p):
        if self.Verbose:
            print(p._slice)
        start = self.Automaton.createState(False)
        end = self.Automaton.createState(True)
        f_start, f_end = p.re
        s_start, s_end = p.simple_re

        self.Automaton.addEpsilonTransition(start, f_start)
        self.Automaton.addEpsilonTransition(start, s_start)

        self.Automaton.End.remove(f_end)
        self.Automaton.End.remove(s_end)
        self.Automaton.addEpsilonTransition(f_end, end)
        self.Automaton.addEpsilonTransition(s_end, end)

        return (start, end)

    @_("concatenation", "basic_re")
    def simple_re(self, p):
        if self.Verbose:
            print(p._slice)
        if "concatenation" in p._namemap:
            return p.concatenation
        else:
            return p.basic_re

    @_("simple_re basic_re")
    def concatenation(self, p):
        if self.Verbose:
            print(p._slice)
        f_start, f_end = p.simple_re
        s_start, s_end = p.basic_re

        self.Automaton.End.remove(f_end)
        self.Automaton.addEpsilonTransition(f_end, s_start)

        return (f_start, s_end)

    @_("star", "plus", "question", "elementary_re")
    def basic_re(self, p):
        if self.Verbose:
            print(p._slice)
        if "star" in p._namemap:
            return p.star
        elif "plus" in p._namemap:
            return p.plus
        elif "question" in p._namemap:
            return p.question
        else:
            return p.elementary_re

    @_("elementary_re F_STAR")
    def star(self, p):
        if self.Verbose:
            print(p._slice)
        start = self.Automaton.createState(False)
        end = self.Automaton.createState(True)
        p_start, p_end = p.elementary_re

        self.Automaton.End.remove(p_end)
        self.Automaton.addEpsilonTransition(start, end)
        self.Automaton.addEpsilonTransition(start, p_start)
        self.Automaton.addEpsilonTransition(p_end, end)
        self.Automaton.addEpsilonTransition(p_end, p_start)

        return (start, end)

    @_("elementary_re F_PLUS")
    def plus(self, p):
        if self.Verbose:
            print(p._slice)
        end = self.Automaton.createState(True)
        start, p_end = p.elementary_re

        self.Automaton.End.remove(p_end)
        self.Automaton.addEpsilonTransition(p_end, end)
        self.Automaton.addEpsilonTransition(end, start)

        return (start, end)

    @_("elementary_re QMARK")
    def question(self, p):
        if self.Verbose:
            print(p._slice)
        start = self.Automaton.createState(False)
        end = self.Automaton.createState(True)
        p_start, p_end = p.elementary_re

        self.Automaton.End.remove(p_end)
        self.Automaton.addEpsilonTransition(start, end)
        self.Automaton.addEpsilonTransition(start, p_start)
        self.Automaton.addEpsilonTransition(p_end, end)

        return (start, end)

    # @_("group", "ESCAPE", "DOT", "CHAR", "set")
    @_("group", "ESCAPE", "CHAR", "set")
    def elementary_re(self, p):
        if self.Verbose:
            print(p._slice)
        symbol = (
            p.ESCAPE
            if "ESCAPE" in p._namemap
            else (p.CHAR if "CHAR" in p._namemap else None)
        )
        if symbol:
            start = self.Automaton.createState(False)
            end = self.Automaton.createState(True)
            self.Automaton.addSymbolTransition(symbol, start, end)

            return (start, end)

        return p.group if "group" in p._namemap else p.set

    @_("LPAREN re RPAREN")
    def group(self, p):
        if self.Verbose:
            print(p._slice)
        return p.re

    @_("LBRACK set_items RBRACK")
    def set(self, p):
        if self.Verbose:
            print(p.set_items)
        start = self.Automaton.createState(False)
        end = self.Automaton.createState(True)
        for item in p.set_items:
            self.Automaton.addSymbolTransition(item, start, end)

        return (start, end)

    @_("set_items set_item")
    def set_items(self, p):
        if self.Verbose:
            print(p._slice)
        p.set_items.append(p.set_item)
        return p.set_items

    @_("set_item")
    def set_items(self, p):
        return [p.set_item]

    # @_("ESCAPE", "DOT", "CHAR")
    @_("ESCAPE", "CHAR")
    def set_item(self, p):
        if self.Verbose:
            print(p._slice)
        symbol = p.CHAR if "CHAR" in p._namemap else p.ESCAPE

        return symbol

    def error(self, token):
        if token:
            lineno = getattr(token, "lineno", 0)
            if lineno:
                print(f"Erro de sintaxe na linha {lineno}, token={token.type}!")
            else:
                print(f"Erro de sintaxe, token={token.type}!")
        else:
            print("Erro ao parsear a entrada. EOF\n")

        raise KeyError()