def getContext(wordref, i, window, stopwords, toporef):
j = i
contextlist = [[wordref[j], "MainTopo", (i-j)]]
while j > 1:
j = j - 1
if i - window >= j:
break
if j in toporef:
if " " in wordref[j]:
contextlist.append([wordref[j].strip().replace(" ", "|"), "OtherTopo", (i-j)])
else:
contextlist.append([wordref[j], "OtherTopo", (i-j)])
elif wordref[j] not in stopwords:
try:
#u1 = unicode(wordref[j], 'utf-8')
if len(wordref[j]) == 1 and UnicodeBlocks.block(wordref[j]) == "General Punctuation":
pass
#print "~~~~Forbidden Character~~~~"
#print wordref[j]
#print "~~~~~~~~~~~~~~~~~~~~~"
#sys.exit()
else:
contextlist.append([wordref[j], "Word", (i-j)])
except:
#print "~~~~Broken String~~~~"
#print wordref[j]
pass
# print "~~~~~~~~~~~~~~~~~~~~~"
#print len(contextlist)
j = i
while j < len(wordref):
j = j + 1
if i + window < j:
break
if j in toporef:
if " " in wordref[j]:
contextlist.append([wordref[j].strip().replace(" ", "|"), "OtherTopo", (i-j)])
else:
contextlist.append([wordref[j], "OtherTopo", (i-j)])
elif wordref[j] not in stopwords:
try:
if len(wordref[j]) == 1 and UnicodeBlocks.block(wordref[j]) == "General Punctuation":
pass
#print "~~~~Forbidden Character~~~~"
#print wordref[j]
#print "~~~~~~~~~~~~~~~~~~~~~"
#sys.exit()
else:
contextlist.append([wordref[j], "Word", (i-j)])
except:
pass
#print "~~~~Broken String~~~~"
#print wordref[j]
# print "~~~~~~~~~~~~~~~~~~~~~"
return contextlist
def getContext(wordref, i, window, stopwords, toporef):
j = i
contextlist = [[wordref[j], "MainTopo", (i-j)]]
while j > 1:
j = j - 1
if i - window >= j:
break
if j in toporef:
if " " in wordref[j]:
contextlist.append([wordref[j].strip().replace(" ", "|"), "OtherTopo", (i-j)])
else:
contextlist.append([wordref[j], "OtherTopo", (i-j)])
elif wordref[j] not in stopwords:
try:
if len(wordref[j]) == 1 and UnicodeBlocks.block(wordref[j]) == "General Punctuation":
pass
else:
contextlist.append([wordref[j], "Word", (i-j)])
except:
pass
j = i
while j < len(wordref):
j = j + 1
if i + window < j:
break
if j in toporef:
if " " in wordref[j]:
contextlist.append([wordref[j].strip().replace(" ", "|"), "OtherTopo", (i-j)])
else:
contextlist.append([wordref[j], "OtherTopo", (i-j)])
elif wordref[j] not in stopwords:
try:
if len(wordref[j]) == 1 and UnicodeBlocks.block(wordref[j]) == "General Punctuation":
pass
else:
contextlist.append([wordref[j], "Word", (i-j)])
except:
pass
return contextlist