Sunbelt Computer Software

PL/B Language Development and Support

codeflash/code_to_optimize/text_processor.py at main · codeflash-ai/codeflash · GitHub

190 lines (187 loc) · 3.8 KB

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

class TextProcessor:

def __init__(self):

self.version = "0.1"

def find_unique_words(self, text):

stop_words = {

"a",

"about",

"above",

"after",

"again",

"against",

"ain",

"all",

"am",

"an",

"and",

"any",

"are",

"aren",

"aren't",

"as",

"at",

"be",

"because",

"been",

"before",

"being",

"below",

"between",

"both",

"but",

"by",

"can",

"couldn",

"couldn't",

"did",

"didn",

"didn't",

"do",

"does",

"doesn",

"doesn't",

"doing",

"don",

"don't",

"down",

"during",

"each",

"few",

"for",

"from",

"further",

"had",

"hadn",

"hadn't",

"has",

"hasn",

"hasn't",

"have",

"haven",

"haven't",

"having",

"he",

"her",

"here",

"hers",

"herself",

"him",

"himself",

"his",

"how",

"i",

"if",

"in",

"into",

"is",

"isn",

"isn't",

"it",

"it's",

"its",

"itself",

"just",

"ll",

"let's",

"ma",

"me",

"mightn",

"mightn't",

"more",

"most",

"mustn",

"mustn't",

"my",

"myself",

"needn",

"needn't",

"no",

"nor",

"not",

"now",

"o",

"of",

"off",

"on",

"once",

"only",

"or",

"other",

"our",

"ours",

"ourselves",

"out",

"over",

"own",

"re",

"s",

"same",

"shan",

"shan't",

"she",

"she's",

"should",

"should've",

"shouldn",

"shouldn't",

"so",

"some",

"such",

"t",

"than",

"that",

"that'll",

"the",

"their",

"theirs",

"them",

"themselves",

"then",

"there",

"these",

"they",

"this",

"those",

"through",

"to",

"too",

"under",

"until",

"up",

"ve",

"very",

"was",

"wasn",

"wasn't",

"we",

"were",

"weren",

"weren't",

"what",

"when",

"where",

"which",

"while",

"who",

"whom",

"why",

"will",

"with",

"won",

"won't",

"wouldn",

"wouldn't",

"y",

"you",

"you'd",

"you'll",

"you're",

"you've",

"your",

"yours",

"yourself",

"yourselves",

}

words = text.lower().split()

unique_words = [word for word in words if word not in stop_words]

return unique_words