def concordance(text, word):
cindex = ConcordanceIndex(text, key=lambda x: x.lower())
offsetList = cindex.offsets(word)
contexts = []
for i in offsetList[:10]:
pre = i - 10
post = i + 10
contextStr = " ".join(text[pre:post])
contexts.append(contextStr)
return contexts
def concordance(text, word):
cindex = ConcordanceIndex(text, key=lambda x:x.lower())
offsetList = cindex.offsets(word)
contexts = []
for i in offsetList[:10]:
pre = i-10
post = i+10
contextStr = ' '.join(text[pre:post])
contexts.append(contextStr)
return contexts
def phrasesContenant_bkp(corpus, mots):
"""
:DEPRECATED utiliser phrasesContenant() à la place
"""
print("début phrasesContenant()")
phrasesContenant = []
index = ConcordanceIndex(corpus)
#Pour chaque mot
for mot in mots:
positions = index.offsets(mot)
print("positions:", positions)
for position in positions:
phrasesContenant.append(corpus[position])
print("nb tokens:", len(phrasesContenant))
# print("tokens:",phrasesContenant)
print("fin phrasesContenant()")
return phrasesContenant
