File size: 3,047 Bytes
bdfde60 |
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 |
# import nbimporter
import nbimporter
from Text2List import text_to_list
def convert_to_list(text, text_list):
matched_words = []
unmatched_text = '' # To accumulate unmatched characters
# Sort text_list by length in descending order to prioritize longest matches first
text_list_sorted = sorted(text_list, key=len, reverse=True)
while text:
matched = False
for word in text_list_sorted:
if text.startswith(word):
# Add any accumulated unmatched text before appending the matched word
if unmatched_text:
matched_words.append(unmatched_text)
unmatched_text = '' # Reset unmatched text accumulator
matched_words.append(word)
text = text[len(word):] # Remove the matched part from text
matched = True
break
if not matched:
# Accumulate unmatched characters
unmatched_text += text[0]
text = text[1:]
# If there's any remaining unmatched text, add it to the result
if unmatched_text:
matched_words.append(unmatched_text)
# Join matched words and unmatched text with a space
result = ' '.join(matched_words)
return result
# text = "जीरोएकदोतीनचारपांचछहसातआठनौदसजीरोएकदोतीनचारपांच"
if __name__=="__main__":
converted=convert_to_list(text, text_to_list())
print(converted)
# In[ ]:
# # import nbimporter
# import nbimporter
# from Text2List import text_to_list
# def convert_to_list(text, text_list):
# matched_words = []
# unmatched_text = '' # To accumulate unmatched characters
# # Sort text_list by length in descending order to prioritize longest matches first
# text_list_sorted = sorted(text_list, key=len, reverse=True)
# while text:
# matched = False
# for word in text_list_sorted:
# if word in text:
# # Add any accumulated unmatched text before appending the matched word
# if unmatched_text:
# matched_words.append(unmatched_text)
# unmatched_text = '' # Reset unmatched text accumulator
# matched_words.append(word)
# text = text[len(word):] # Remove the matched part from text
# matched = True
# break
# if not matched:
# # Accumulate unmatched characters
# unmatched_text += text[0]
# text = text[1:]
# # If there's any remaining unmatched text, add it to the result
# if unmatched_text:
# matched_words.append(unmatched_text)
# # Join matched words and unmatched text with a space
# result = ' '.join(matched_words)
# return result
# text = "जीरोएकदोतीनचार"
# if __name__=="__main__":
# converted=convert_to_list(text, text_to_list())
# print(converted)
|