henu-Compilers-Principles-Lab/res.py at master · mxrush129/henu-Compilers-Principles-Lab · 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
import examples
import err
import utils.utils as tools
import utils.errorHelper as error

# 存放资源

# 关键字表
keyWords = [
    'begin',
    'end',
    'if',
    'then',
    'while',
    'do',
    'const',
    'var',
    'call',
    'procedure',
    'odd'
]

# 算符与界符表
operators = [
    '+',
    '-',
    '*',
    '/',
    '=',
    '#',
    '<',
    '>',
    ':=',
    '(',
    ')',
    ',',
    '.',
    ';'
]

# 标识符表
identifiers = []

# 读入代码
code = ""

# 字符流，由code转化，方便处理
buffer = ""

# 词法分析器解析出来的单词二元组（种别，属性值）
words = []


class Word:
    def __init__(self, category='none', attribute='none'):
        self.category = category
        self.attribute = attribute

    def set(self, s: str):
        success = False

        # 关键字匹配
        for keyword in sorted(keyWords, key=lambda t: len(t), reverse=True):
            pos = s.find(keyword)
            if pos != -1:
                success = True
                self.category = keyword

                return success, len(keyword)

        # 算符匹配
        for operator in sorted(operators, key=lambda t: len(t), reverse=True):
            pos = s.find(operator)
            if pos == 0:
                success = True
                self.category = operator

                return success, len(operator)

        # 常数匹配
        if s[0].isdigit():
            pointer = 0
            while pointer < len(s) and s[pointer].isdigit():
                pointer += 1

            success = True
            self.category = 'number'
            self.attribute = int(s[:pointer])
            return success, pointer

        # 标识符匹配
        if s[0].isalpha():
            pointer = 0
            while pointer < len(s) and s[pointer].isalnum():
                pointer += 1

            if pointer > 10:
                error.showError(err.LENGTH, s[:pointer])
                return success, -1

            success = True
            self.category = 'ident'
            self.attribute = tools.findPosition(identifiers, s[:pointer])
            return success, pointer

        error.showError(err.WORD, s)

        return success, -1


if __name__ == '__main__':
    word = Word()

    # success, l = word.set(examples.exaDict['常数'].s)
    # success, l = word.set(examples.exaDict['长度>10'].s)
    success, l = word.set(examples.exaDict['非法字符'].s)
    print(success, l)
    print(word.category, word.attribute)