def getOtherTaggedText(info): taggedtext = TextMarker.getTaggedText(info) # print taggedtext # print '' btags2 = ['B_WHAT', 'B_WHO', 'B_WHEN', 'B_WHERE', 'B_WHY', 'B_HOW'] etags2 = ['E_WHAT', 'E_WHO', 'E_WHEN', 'E_WHERE', 'E_WHY', 'E_HOW'] for i, tag in enumerate(btags2): taggedtext = taggedtext.replace(TextMarker.btags[i], tag) for i, tag in enumerate(etags2): taggedtext = taggedtext.replace(TextMarker.etags[i], tag) text = "" state = 0 for token in Tokenizer.getTokens(taggedtext): if (reduce( (lambda x, y: x or y), list(map((lambda x: x in token), btags2)) )): state += len([item for item in list(map((lambda x: x in token), btags2)) if item]) if (state==0): # print "%s\t%s" % (state, TextMarker.othertags[0] + token + TextMarker.othertags[1]) text += TextMarker.othertags[0] + token + TextMarker.othertags[1] else: # print "%s\t%s" % (state, token) text += token + " " if (reduce( (lambda x, y: x or y), list(map((lambda x: x in token), etags2)) )): state -= len([item for item in list(map((lambda x: x in token), etags2)) if item]) for i, tag in enumerate(TextMarker.btags): text = text.replace(btags2[i], tag) for i, tag in enumerate(TextMarker.etags): text = text.replace(etags2[i], tag) return text
def __init__(self, _what, _who, _when, _where, _why, _how, _text):
self.what = Tokenizer.removeNonAscii(_what).replace(".\"",". \"")
self.who = Tokenizer.removeNonAscii(_who).replace(".\"",". \"")
self.when = Tokenizer.removeNonAscii(_when).replace(".\"",". \"")
self.where = Tokenizer.removeNonAscii(_where).replace(".\"",". \"")
self.why = Tokenizer.removeNonAscii(_why).replace(".\"",". \"")
self.how = Tokenizer.removeNonAscii(_how).replace(".\"",". \"")
self.text = Tokenizer.removeNonAscii(_text).replace(".\"",". \"")
self.sentences = Tokenizer.getSentences(self.text)
self.tokenized_sentences = [Tokenizer.getTokens(sentence) for sentence in self.sentences]
def getMarkedText(info): omtext = TextMarker.getOtherTaggedText(info) # print omtext result = "" searchObj = re.findall( r'\[b(.+?)\](.+?)\[e.+?\]', omtext) # print len(searchObj) for tup in searchObj: # print tup if (tup[0]=="other"): result += "[%s]%s[%s]" % (tup[0], tup[1], tup[0]) else: label = tup[0] tokens = Tokenizer.getTokens(tup[1]) for i, token in enumerate(tokens): prefix = "beg" if(i==0) else "in" result += "[%s_%s]%s[%s_%s]" % (prefix, label, token, prefix, label) return result
def getMarkedText(info):
omtext = TextMarker.getOtherTaggedText(info)
# print omtext
result = ""
searchObj = re.findall(r'\[b(.+?)\](.+?)\[e.+?\]', omtext)
# print len(searchObj)
for tup in searchObj:
# print tup
if (tup[0] == "other"):
result += "[%s]%s[%s]" % (tup[0], tup[1], tup[0])
else:
label = tup[0]
tokens = Tokenizer.getTokens(tup[1])
for i, token in enumerate(tokens):
prefix = "beg" if (i == 0) else "in"
result += "[%s_%s]%s[%s_%s]" % (prefix, label, token,
prefix, label)
return result
def main():
inputBuffer = ""
outputBuffer = ""
if (len(sys.argv) >= 2):
inputBuffer = readFile(sys.argv[1])
tokenizer = Tokenizer(inputBuffer)
tokenizer.tokenize()
tokens = tokenizer.getTokens()
parser = Parser(tokens)
parser.parse()
outputBuffer = parser.getOutput()
# print(outputBuffer)
if (len(sys.argv) == 3):
writeFile(sys.argv[2], outputBuffer)
else:
writeFile("output.html", outputBuffer)
def getOtherTaggedText(info):
taggedtext = TextMarker.getTaggedText(info)
# print taggedtext
# print ''
btags2 = ['B_WHAT', 'B_WHO', 'B_WHEN', 'B_WHERE', 'B_WHY', 'B_HOW']
etags2 = ['E_WHAT', 'E_WHO', 'E_WHEN', 'E_WHERE', 'E_WHY', 'E_HOW']
for i, tag in enumerate(btags2):
taggedtext = taggedtext.replace(TextMarker.btags[i], tag)
for i, tag in enumerate(etags2):
taggedtext = taggedtext.replace(TextMarker.etags[i], tag)
text = ""
state = 0
for token in Tokenizer.getTokens(taggedtext):
if (reduce((lambda x, y: x or y),
list(map((lambda x: x in token), btags2)))):
state += len([
item for item in list(map((lambda x: x in token), btags2))
if item
])
if (state == 0):
# print "%s\t%s" % (state, TextMarker.othertags[0] + token + TextMarker.othertags[1])
text += TextMarker.othertags[0] + token + TextMarker.othertags[
1]
else:
# print "%s\t%s" % (state, token)
text += token + " "
if (reduce((lambda x, y: x or y),
list(map((lambda x: x in token), etags2)))):
state -= len([
item for item in list(map((lambda x: x in token), etags2))
if item
])
for i, tag in enumerate(TextMarker.btags):
text = text.replace(btags2[i], tag)
for i, tag in enumerate(TextMarker.etags):
text = text.replace(etags2[i], tag)
return text
