Parser-tiny-language/functions.py at master · groot8/Parser-tiny-language · 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
#!/usr/bin/python
import re


def isLetter(string):
    match = re.match('[a-zA-Z]',string)
    if (match) or (string=='_'):
        return 1
    else:
        return 0

def isNumber(string):
    match = re.match('[0-9]',string)
    if (match):
        return 1
    else:

        return 0


def isIdentfier(string):
    match = re.match('[_a-zA-Z][_a-zA-Z0-9]?',string)
    if (match):
        return 1
    else:
        return 0


def reservedWords(string):

     if string == "if":
         return 1
     elif string == "then":
         return 1
     elif string == "else":
         return 1
     elif string == "read":
         return 1
     elif string == "end":
         return 1
     elif string == "repeat":
         return 1
     elif string == "write":
         return 1
     elif string == "until":
         return 1
     else:
         return 0


def isSpecial(string):
     match = re.match('[< > * () _ + := \- ; / ]', string)

     if string == ' ':
         return 0

     if (match):
        return 1
     else:

        return 0


def classifier(tokens):

    tokens_list = []

    for token in tokens:
        if (reservedWords(token)):
            temp = token

        elif (isSpecial(token)):
            temp = token

        elif((isIdentfier(token))):
            temp = token

        elif ((isNumber(token))):
            temp = token

        else:
            temp = token
        tokens_list.append(temp)

    return tokens_list

'''

    type_value_list = {'ReservedWords' : [], 'SpecialSymbols' : [],'Identfier' : [],'Number' : [], 'Other' : []}

    for token in tokens:

        if(reservedWords(token)):
            type_value_list['ReservedWords'].append(token)

        elif (isSpecial(token)):
            type_value_list['SpecialSymbols'].append(token)

        elif (isIdentfier(token)):
            type_value_list['Identfier'].append(token)

        elif (isNumber(token)):
            type_value_list['Number'].append(token)


        else:
            type_value_list['SpecialSymbols'].append(token)


    return type_value_list
'''


# isSpecial('safd')
# identfier("777")
# isChar('?')
# isNumber('7')
# reservedWords("until")


# words = ["if" , "then" , "else" , "read" , "end" , "repeat", "write", "until"]
# print(words)
# print(len(words))