aboutsummaryrefslogtreecommitdiff
path: root/lexer.py
blob: 0c555c5a613dab5d12b4b9c12b8466f7e62bf994 (plain)
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
from enum import Enum
from symbol import LexToken, TablaLex, tokens

def inicio_lexer(data):
    tabla = TablaLex()
    
    selector = ''
    recol_string = ''
    recol_caracter = ''
    recol_comentario = ''
    recol_operador = ''
    recol_ident = ''
    
    for c in data + "\n":
        # print (c + ' (' + selector + ')')
        
        if selector == '':
            # Entradas a tokens
            if c == '"':
                selector = 'STRING_LIT'
                continue
            elif c == '\'':
                selector = 'CHAR_LIT'
                continue
            elif c.isalpha() or c == '_':
                selector = 'ID/RESERVADA'
            elif c == '/':
                recol_comentario = '/'
            elif (c == '=' or c == '+' or c == '-' or c == '&' or c == '|') and recol_operador == '':
                recol_operador = c
                continue
            elif c == '!' or c == '<' or c == '>':
                recol_operador = c
                continue
            elif (c == '{' or c == '}' or c == '(' or c == ')' or
                  c == ',' or c == '.' or c == ';' or (c == '*' and recol_comentario == '')):
                tabla.insertar(LexToken(c, None, None, 1))
                continue

            # Apertura de comentario
            if recol_comentario == '/' and c == '*':
                selector = 'COMMENT'
                recol_comentario = ''
                continue

            # Apertura de operador compuesto
            if len(recol_operador) > 0:
                rc = recol_operador + c
                if (rc == '>=' or rc == '<=' or rc == '==' or rc == '!=' or
                    rc == '&&' or rc == '||' or rc == '++' or rc == '--'):
                    # Operador compuesto
                    tabla.insertar(LexToken(rc, None, None, 1))
                    recol_operador = ''
                    continue
                else:
                    # Operador simple
                    tabla.insertar(LexToken(recol_operador, None, None, 1))
                    recol_operador = ''
        
        # Cadenas de texto
        if selector == 'STRING_LIT':
            if c == '"':
                tabla.insertar(LexToken('STRING_LIT', None, recol_string, 1))
                selector = ''
                recol_string = ''
            else:
                recol_string += c

        # Caracteres
        if selector == 'CHAR_LIT':
            if len(recol_caracter) > 1:
                print ('Error: más de un caracter en una literal de caracter')
                break
            if c == '\'':
                if len(recol_caracter) == 0:
                    print ('Error: literal de caracter vacía')
                    break
                tabla.insertar(LexToken('CHAR_LIT', None, recol_caracter, 1))
                selector = ''
                recol_caracter = ''
            else:
                recol_caracter += c

        # Comentarios
        if selector == 'COMMENT':
            if c == '*':
                recol_comentario = c
            elif recol_comentario == '*':
                if c == '/':
                    selector = ''
                    recol_comentario = ''
                else:
                    recol_comentario = ''

        # Identificador o palabra reservada
        if selector == 'ID/RESERVADA':
            if c.isalnum() or c == '_':
                recol_ident += c
            else:
                if recol_ident == 'booleano':
                    tabla.insertar(LexToken('BOOLEAN', None, None, 1))
                elif recol_ident == 'detener':
                    tabla.insertar(LexToken('BREAK', None, None, 1))
                elif recol_ident == 'byte':
                    tabla.insertar(LexToken('BYTE', None, None, 1))
                elif recol_ident == 'caracter':
                    tabla.insertar(LexToken('CHAR', None, None, 1))
                elif recol_ident == 'doble':
                    tabla.insertar(LexToken('DOUBLE', None, None, 1))
                elif recol_ident == 'sino':
                    tabla.insertar(LexToken('ELSE', None, None, 1))
                elif recol_ident == 'porcada':
                    tabla.insertar(LexToken('FOR', None, None, 1))
                elif recol_ident == 'si':
                    tabla.insertar(LexToken('IF', None, None, 1))
                elif recol_ident == 'entero':
                    tabla.insertar(LexToken('INT', None, None, 1))
                elif recol_ident == 'imprimir':
                    tabla.insertar(LexToken('PRINT', None, None, 1))
                elif recol_ident == 'leer':
                    tabla.insertar(LexToken('READ', None, None, 1))
                elif recol_ident == 'retorna':
                    tabla.insertar(LexToken('RETURN', None, None, 1))
                elif recol_ident == 'vacio':
                    tabla.insertar(LexToken('VOID', None, None, 1))
                elif recol_ident == 'mientras':
                    tabla.insertar(LexToken('WHILE', None, None, 1))
                elif recol_ident == 'verdadero':
                    tabla.insertar(LexToken('BOOLEAN_LIT', None, True, 1))
                elif recol_ident == 'falso':
                    tabla.insertar(LexToken('BOOLEAN_LIT', None, False, 1))
                else:
                    tabla.insertar(LexToken('IDENT', recol_ident, None, 1))
                recol_ident = ''
                selector = ''
                

    # Imprimir tabla de símbolos
    print (str(tabla))