Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -155,7 +155,7 @@ def find_sentences_with_keywords(text, keywords):
|
|
| 155 |
# Split text into sentences using regular expression to match sentence-ending punctuation
|
| 156 |
sentences = re.split(r'(?<=[.!?])\s+', text)
|
| 157 |
|
| 158 |
-
matched_sentences =
|
| 159 |
|
| 160 |
# For each keyword, find sentences that contain the keyword as a whole word
|
| 161 |
for keyword in keywords:
|
|
@@ -163,9 +163,9 @@ def find_sentences_with_keywords(text, keywords):
|
|
| 163 |
|
| 164 |
for sentence in sentences:
|
| 165 |
if keyword_pattern.search(sentence):
|
| 166 |
-
matched_sentences.
|
| 167 |
|
| 168 |
-
return matched_sentences
|
| 169 |
|
| 170 |
|
| 171 |
# Main function to process both PDFs based on the Excel file names and the sheet name
|
|
|
|
| 155 |
# Split text into sentences using regular expression to match sentence-ending punctuation
|
| 156 |
sentences = re.split(r'(?<=[.!?])\s+', text)
|
| 157 |
|
| 158 |
+
matched_sentences = set() # Use a set to store unique sentences
|
| 159 |
|
| 160 |
# For each keyword, find sentences that contain the keyword as a whole word
|
| 161 |
for keyword in keywords:
|
|
|
|
| 163 |
|
| 164 |
for sentence in sentences:
|
| 165 |
if keyword_pattern.search(sentence):
|
| 166 |
+
matched_sentences.add(sentence) # Add to set to ensure uniqueness
|
| 167 |
|
| 168 |
+
return list(matched_sentences) # Convert set back to list for consistent output
|
| 169 |
|
| 170 |
|
| 171 |
# Main function to process both PDFs based on the Excel file names and the sheet name
|