Towhidul commited on
Commit
95f9e8f
·
verified ·
1 Parent(s): ceb045a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +53 -48
app.py CHANGED
@@ -107,35 +107,6 @@ def find_matching_words(sentence1, sentence2):
107
 
108
 
109
 
110
- matching_bigrams_list = []
111
- combined_words_list = []
112
-
113
- for paraphrase in paraphrases:
114
- # Find matching words
115
- matching_words = find_matching_words(main_sentence, paraphrase)
116
- matching_bigrams_list.append(matching_words)
117
-
118
- def combine_matching_bigrams(matching_bigrams):
119
- combined_words = []
120
- combined_word = ""
121
-
122
- for i, bigram in enumerate(matching_bigrams):
123
- if i == 0:
124
- combined_word += ' '.join(bigram)
125
- elif bigram[0] == matching_bigrams[i-1][1]:
126
- combined_word += ' ' + bigram[1]
127
- else:
128
- combined_words.append(combined_word)
129
- combined_word = ' '.join(bigram)
130
-
131
- # Append the last combined word
132
- combined_words.append(combined_word)
133
-
134
- return combined_words
135
-
136
- # Combine matching bigrams into single words
137
- combined_words = combine_matching_bigrams(matching_words)
138
- combined_words_list.append(combined_words)
139
 
140
  def remove_overlapping(input_set):
141
  sorted_set = sorted(input_set, key=len, reverse=True)
@@ -162,21 +133,6 @@ def find_longest_match(string1, string2):
162
 
163
  return longest_match
164
 
165
- common_substrings = set()
166
- highlighted_text = []
167
-
168
- for i in combined_words_list[0]:
169
- for j in combined_words_list[1]:
170
- for k in combined_words_list[2]:
171
- for l in combined_words_list[3]:
172
- for m in combined_words_list[4]:
173
- matching_portion = find_longest_match(i, j)
174
- matching_portion = find_longest_match(matching_portion, k)
175
- matching_portion = find_longest_match(matching_portion, l)
176
- matching_portion = find_longest_match(matching_portion, m)
177
- if matching_portion:
178
- common_substrings.add(matching_portion)
179
-
180
 
181
 
182
 
@@ -203,17 +159,66 @@ else:
203
 
204
  main_sentence = check
205
 
 
206
  st.markdown("**Main Sentence**:")
207
  st.write(main_sentence)
208
 
209
  # Generate paraphrases
210
  paraphrases = paraphrase(main_sentence)
211
 
212
- # Extracting longest common sequences
213
- longest_common_sequences = find_longest_common_sequences(main_sentence, paraphrases)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
214
 
215
- color_palette = ["#FF0000", "#008000", "#0000FF", "#FF00FF", "#00FFFF"]
216
- highlighted_sentences = []
217
 
218
 
219
  highlighted_sentence = main_sentence
 
107
 
108
 
109
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
 
111
  def remove_overlapping(input_set):
112
  sorted_set = sorted(input_set, key=len, reverse=True)
 
133
 
134
  return longest_match
135
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
 
137
 
138
 
 
159
 
160
  main_sentence = check
161
 
162
+
163
  st.markdown("**Main Sentence**:")
164
  st.write(main_sentence)
165
 
166
  # Generate paraphrases
167
  paraphrases = paraphrase(main_sentence)
168
 
169
+ matching_bigrams_list = []
170
+ combined_words_list = []
171
+
172
+ for paraphrase in paraphrases:
173
+ # Find matching words
174
+ matching_words = find_matching_words(main_sentence, paraphrase)
175
+ matching_bigrams_list.append(matching_words)
176
+
177
+ def combine_matching_bigrams(matching_bigrams):
178
+ combined_words = []
179
+ combined_word = ""
180
+
181
+ for i, bigram in enumerate(matching_bigrams):
182
+ if i == 0:
183
+ combined_word += ' '.join(bigram)
184
+ elif bigram[0] == matching_bigrams[i-1][1]:
185
+ combined_word += ' ' + bigram[1]
186
+ else:
187
+ combined_words.append(combined_word)
188
+ combined_word = ' '.join(bigram)
189
+
190
+ # Append the last combined word
191
+ combined_words.append(combined_word)
192
+
193
+ return combined_words
194
+
195
+ # Combine matching bigrams into single words
196
+ combined_words = combine_matching_bigrams(matching_words)
197
+ combined_words_list.append(combined_words)
198
+
199
+ common_substrings = set()
200
+ highlighted_text = []
201
+
202
+ for i in combined_words_list[0]:
203
+ for j in combined_words_list[1]:
204
+ for k in combined_words_list[2]:
205
+ for l in combined_words_list[3]:
206
+ for m in combined_words_list[4]:
207
+ matching_portion = find_longest_match(i, j)
208
+ matching_portion = find_longest_match(matching_portion, k)
209
+ matching_portion = find_longest_match(matching_portion, l)
210
+ matching_portion = find_longest_match(matching_portion, m)
211
+ if matching_portion:
212
+ common_substrings.add(matching_portion)
213
+
214
+
215
+
216
+
217
+ # # Extracting longest common sequences
218
+ # longest_common_sequences = find_longest_common_sequences(main_sentence, paraphrases)
219
 
220
+ # color_palette = ["#FF0000", "#008000", "#0000FF", "#FF00FF", "#00FFFF"]
221
+ # highlighted_sentences = []
222
 
223
 
224
  highlighted_sentence = main_sentence