Programme Python : recherchez l'index de début et de fin de tous les mots d'une chaîne

#function for given word indices
def StartandEndIndex(givenStr):
   indexList = []
   startNum = 0
   lengthOfSentence=len(givenStr)
   #iterate though the given string
   for indexitem in range(0,lengthOfSentence):
      #check if there is a separate word
      if givenStr[indexitem] == " ":
         indexList.append((startNum, indexitem - 1))
         indexitem += 1
         startNum = indexitem
             
   if startNum != len(givenStr):
      indexList.append((startNum, len(givenStr) - 1))
   return indexList
 

givenStr = 'Keep your face always toward the sunshine and shadows will fall behind you'
#call the function StartandEndIndex(givenStr) 
#and get the list having starting and ending indices of all words
indexListt = StartandEndIndex(givenStr)

# make a list of words separately
listofwords= givenStr.split()
print("\nThe given String or Sentence is ")
print(givenStr)
print("\nThe list of words is ")
print(listofwords)

#make a dictionary using words and their indices
resDict = {listofwords[indx]: indexListt[indx] for indx in range(len(listofwords))}
print("\nWords and their indices : " + str(resDict))

The given String or Sentence is
Keep your face always toward the sunshine and shadows will fall behind you

The list of words is
['Keep', 'your', 'face', 'always', 'toward', 'the', 'sunshine', 'and', 'shadows', 'will', 'fall', 'behind', 'you']

Words and their indices : {'Keep': (0, 3), 'your': (5, 8), 'face': (10, 13), 'always': (15, 20), 'toward': (22, 27), 'the': (29, 31), 'sunshine': (33, 40), 'and': (42, 44), 'shadows': (46, 52), 'will': (54, 57), 'fall': (59, 62), 'behind': (64, 69), 'you': (71, 73)}

#Use pip install nltk to install this library

#import align tokens
from nltk.tokenize.util import align_tokens

#specify a string for testing
givenStr = 'Keep your face always toward the sunshine and shadows will fall behind you'

#make a list of words
listofwords= givenStr.split()

print("\nThe given String or Sentence is ")
print(givenStr)
print("\nThe list of words is ")
print(listofwords)

#this will include blank spaces with words while giving indices
indices_includingspace= align_tokens(listofwords, givenStr)
indices_withoutspace=[]

#reduce the last index number of the word indices
for item in indices_includingspace:
   #convert tuple to list
   lst = list(item)
   lst[1]=lst[1] - 1
   #convert list to tuple again
   tup = tuple(lst)
   indices_withoutspace.append(tup)
print(indices_withoutspace)

#make the dictionary of all words in a string with their indices
resDict = {listofwords[indx]: indices_withoutspace[indx] for indx in range(len(listofwords))}
print("\nWords and their indices : " + str(resDict))

The given String or Sentence is
Keep your face always toward the sunshine and shadows will fall behind you

The list of words is
['Keep', 'your', 'face', 'always', 'toward', 'the', 'sunshine', 'and', 'shadows', 'will', 'fall', 'behind', 'you']
[(0, 3), (5, 8), (10, 13), (15, 20), (22, 27), (29, 31), (33, 40), (42, 44), (46, 52), (54, 57), (59, 62), (64, 69), (71, 73)]

Words and their indices : {'Keep': (0, 3), 'your': (5, 8), 'face': (10, 13), 'always': (15, 20), 'toward': (22, 27), 'the': (29, 31), 'sunshine': (33, 40), 'and': (42, 44), 'shadows': (46, 52), 'will': (54, 57), 'fall': (59, 62), 'behind': (64, 69), 'you': (71, 73)}