脚本之家，脚本语言编程技术及教程分享平台！
分类导航

Python|VBS|Ruby|Lua|perl|VBA|Golang|PowerShell|Erlang|autoit|Dos|bat|

服务器之家 - 脚本之家 - Python - python实现词法分析器

python实现词法分析器

2021-05-25 00:34追_梦_者 Python

这篇文章主要为大家详细介绍了python实现词法分析器的相关资料，具有一定的参考价值，感兴趣的小伙伴们可以参考一下

简单python词法分析器实现，供大家参考，具体内容如下

词法分析器状态转换图：

python实现词法分析器

词法分析器总流程图：

python实现词法分析器

预处理程序：

python实现词法分析器

词法分析器：

python实现词法分析器

词法分析器程序详细设计

python实现词法分析器

详细代码实现:

?
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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
#!/usr/bin/env python3.4
# coding=utf-8
import sys
import string
 
 
keywards = {}
 
# 关键字部分
keywards['false'] = 101
keywards['class'] = 102
keywards['finally'] = 103
keywards['is'] = 104
keywards['return'] = 105
keywards['none'] = 106
keywards['continue'] = 107
keywards['for'] = 108
keywards['lambda'] = 109
keywards['try'] = 110
keywards['true'] = 111
keywards['def'] = 112
keywards['from'] = 113
keywards['nonlocal'] = 114
keywards['while'] = 115
keywards['and'] = 116
keywards['del'] = 117
keywards['global'] = 118
keywards['not'] = 119
keywards['with'] = 120
keywards['as'] = 121
keywards['elif'] = 122
keywards['if'] = 123
keywards['or'] = 124
keywards['yield'] = 125
keywards['assert'] = 126
keywards['else'] = 127
keywards['import'] = 128
keywards['pass'] = 129
keywards['break'] = 130
keywards['except'] = 131
keywards['in'] = 132
keywards['raise'] = 133
 
# 符号
keywards['+'] = 201
keywards['-'] = 202
keywards['*'] = 203
keywards['/'] = 204
keywards['='] = 205
keywards[':'] = 206
keywards['<'] = 207
keywards['>'] = 208
keywards['%'] = 209
keywards['&'] = 210
keywards['!'] = 211
keywards['('] = 212
keywards[')'] = 213
keywards['['] = 214
keywards[']'] = 215
keywards['{'] = 216
keywards['}'] = 217
keywards['#'] = 218
keywards['|'] = 219
keywards[','] = 220
# 变量
# keywards['var'] = 301
 
# 常量
# keywards['const'] = 401
 
# error
# keywards['const'] = 501
 
signlist = {}
 
 
# 预处理函数，将文件中的空格，换行等无关字符处理掉
def pretreatment(file_name):
 try:
  fp_read = open(file_name, 'r')
  fp_write = open('file.tmp', 'w')
  sign = 0
  while true:
   read = fp_read.readline()
   if not read:
    break
   length = len(read)
   i = -1
   while i < length - 1:
    i += 1
    if sign == 0:
     if read[i] == ' ':
      continue
    if read[i] == '#':
     break
    elif read[i] == ' ':
     if sign == 1:
      continue
     else:
      sign = 1
      fp_write.write(' ')
    elif read[i] == '\t':
     if sign == 1:
      continue
     else:
      sign = 1
      fp_write.write(' ')
    elif read[i] == '\n':
     if sign == 1:
      continue
     else:
      fp_write.write(' ')
      sign = 1
    elif read[i] == '"':
     fp_write.write(read[i])
     i += 1
     while i < length and read[i] != '"':
      fp_write.write(read[i])
      i += 1
     if i >= length:
      break
     fp_write.write(read[i])
    elif read[i] == "'":
     fp_write.write(read[i])
     i += 1
     while i < length and read[i] != "'":
      fp_write.write(read[i])
      i += 1
     if i >= length:
      break
     fp_write.write(read[i])
    else:
     sign = 3
     fp_write.write(read[i])
 except exception:
  print(file_name, ': this filename not found!')
 
 
def save(string):
 if string in keywards.keys():
  if string not in signlist.keys():
   signlist[string] = keywards[string]
 else:
  try:
   float(string)
   save_const(string)
  except valueerror:
   save_var(string)
 
 
def save_var(string):
 if string not in signlist.keys():
  if len(string.strip()) < 1:
   pass
  else:
   if is_signal(string) == 1:
    signlist[string] = 301
   else:
    signlist[string] = 501
 
 
def save_const(string):
 if string not in signlist.keys():
  signlist[string] = 401
 
 
def save_error(string):
 if string not in signlist.keys():
  signlist[string] = 501
 
 
def is_signal(s):
 if s[0] == '_' or s[0] in string.ascii_letters:
  for i in s:
   if i in string.ascii_letters or i == '_' or i in string.digits:
    pass
   else:
    return 0
  return 1
 else:
  return 0
 
 
def recognition(filename):
 try:
  fp_read = open(filename, 'r')
  string = ""
  sign = 0
  while true:
   read = fp_read.read(1)
   if not read:
    break
 
   if read == ' ':
    if len(string.strip()) < 1:
     sign = 0
     pass
    else:
     if sign == 1 or sign == 2:
      string += read
     else:
      save(string)
      string = ""
      sign = 0
   elif read == '(':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save('(')
   elif read == ')':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save(')')
   elif read == '[':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save('[')
   elif read == ']':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save(']')
   elif read == '{':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save('{')
   elif read == '}':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save('}')
   elif read == '<':
    save(string)
    string = ""
    save('<')
   elif read == '>':
    save(string)
    string = ""
    save('>')
   elif read == ',':
    save(string)
    string = ""
    save(',')
   elif read == "'":
    string += read
    if sign == 1:
     sign = 0
     save_const(string)
     string = ""
    else:
     if sign != 2:
      sign = 1
   elif read == '"':
    string += read
    if sign == 2:
     sign = 0
     save_const(string)
     string = ""
    else:
     if sign != 1:
      sign = 2
   elif read == ':':
    if sign == 1 or sign == 2:
     string += read
    else:
     save(string)
     string = ""
     save(':')
   elif read == '+':
    save(string)
    string = ""
    save('+')
   elif read == '=':
    save(string)
    string = ""
    save('=')
   else:
    string += read
 
 except exception as e:
  print(e)
 
 
def main():
 if len(sys.argv) < 2:
  print("please input filename")
 else:
  pretreatment(sys.argv[1])
 recognition('file.tmp')
 for i in signlist.keys():
  print("(", signlist[i], ",", i, ")")
 
 
if __name__ == '__main__':
 main()

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持服务器之家。

原文链接：https://blog.csdn.net/IT_DREAM_ER/article/details/53485583

  • Python
  • 词法分析器

    • 延伸 · 阅读

    精彩推荐
    最近更新
    编辑推荐
    阅读排行
    热门标签
    2048 　 6006 　 contextlib 　 SLOTS 　 MELIAE 　 FEEDPARSER 　 暂存 　 持久性管理 　 pickle模块 　 THREADING 　 reduce 　 nignx 　 装饰器 　 函数式编程 　 兔子毒药 　 监控文件 　 流量监控 　 Web框架 　 办公工具 　 PIL库 　 高斯模糊 　 wxPython 　 import 　 自定义模块 　 Python开发 　 元类 　 metaclass 　 魔术方法 　 DNSPod 　 动态解析域名 　
    © 2019-2023 脚本之家 | 服务器之家(www.zzvips.com)旗下站点 版权所有关于我们联系我们版权申明网站地图