1. -> no of charecters words lines
2. FILE_PATH = "./text.txt"
3. defmain() ->None:
4.     c, l, w = 0, 0, 0
5. withopen(FILE_PATH, "r") as f:
6. for line in f.readlines():
7.             c += len(line)
8.             w += len(line.split())
9.             l += 1
10. print(f"Number of char: {c}, line: {l} and word: {w}")
11. if__name__ == "__main__":
12. exit(main() or0)
13.  
14. ->identify different tokens and token types from a file.
15. fromenumimportEnum
16.  
17. FILE_PATH = "./test.txt"
18. classTokType(Enum):
19. String = 1
20. Constant = 2
21. Special = 3
22.  
23. deftokens(data: list):
24. toks = []
25. cl = 0
26. forlineindata:
27. cl += 1
28. fortokinline.split():
29. try:
30. int(tok)
31. toks.append((cl, tok, TokType.Constant))
32. exceptValueError:
33. iftok.isalpha():
34. toks.append((cl, tok, TokType.String))
35. else:
36. toks.append((cl, tok, TokType.Special))
37. returntoks
38. defmain() ->None:
39. data = []
40. withopen(FILE_PATH, "r") asf:
41. data = f.readlines()
42. toks = tokens(data)
43. print(f"Total token(s): {len(toks)}")
44. print("Tokens:-")
45. fortokintoks:
46. print(f"line: {tok[0]}\"{tok[1]}\"\tis\t{tok[2]}")
47.  
48. if__name__ == "__main__":
49. exit(main() or0)
50.  
51. ->to implement lexical analyzer without using lex tool.
52.  
53. fromenumimportEnum
54.  
55. FILE_PATH = "./hello.c"
56.  
57. K_WORDS = ["int", "float", "char", "return", "double", "break", "continue", "if", "else", "for", "while", "do", "include"]
58.  
59. classTkType(Enum):
60. Ident = 0
61. Literal = 1
62. Symbol = 2
63. Const = 3
64. Keyword = 4
65.  
66. deftoks(data: str):
67. a = data
68. tks = []
69. buf = []
70. n = len(data)
71. i = 0
72. l, c = 1, 1
73. whilei<n:
74. ifa[i] == ''ora[i] == '\t':
75. c += 1
76. i += 1
77. continue
78. ifa[i] == '\n':
79. l += 1
80. c = 1
81. i += 1
82. continue
83. buf.clear()
84. ifa[i].isalpha():
85. whilei<nanda[i].isalpha():
86. buf.append(a[i])
87. i += 1
88. c += 1
89. i -= 1
90. if"".join(buf) inK_WORDS:
91. tks.append(((l, c - len(buf)), "".join(buf), TkType.Keyword))
92. else:
93. tks.append(((l, c - len(buf)), "".join(buf), TkType.Ident))
94. elifa[i].isdigit():
95. whilei<nanda[i].isdigit():
96. buf.append(a[i])
97. i += 1
98. c += 1
99. i -= 1
100. tks.append(((l, c - len(buf)), "".join(buf), TkType.Const))
101. elifa[i] == '"':
102. i += 1
103. whilei<nanda[i] != '"':
104. buf.append(a[i])
105. i += 1
106. c += 1
107. tks.append(((l, c - len(buf)), '"' + "".join(buf) + '"', TkType.Literal))
108. else:
109. tks.append(((l, c), a[i], TkType.Symbol))
110. i += 1
111. c += 1
112. returntks
113. defmain() ->None:
114. data = ""
115. withopen(FILE_PATH, "r") asf:
116. data = f.read()
117. tks = toks(data)
118. print(f"TokenType\tline:col:Token")
119. fortkintks:
120. print(f"{tk[2]}\t{tk[0][0]}:{tk[0][1]}:{tk[1]}")
121.  
122. if__name__ == "__main__":
123. exit(main() or0)
124.  
125.  
126.  
127.