def dothenlp():
if request.method == "POST":
try:
myData = request.json['myData']
recogniser = ternip.recogniser()
normaliser = ternip.normaliser()
doc = TernDocument(myData)
strdoc = str(doc)
ref_date = find_between(strdoc, "<DATE_TIME>",
"</DATE_TIME>").replace("-", "")
sents = recogniser.tag(doc.get_sents())
normaliser.annotate(sents, ref_date)
doc.reconcile(sents)
# Single Sentences
s = find_between(str(doc), "<TEXT>",
"</TEXT>").replace("\n", " <br>")
s = s.replace("_QUOTE_", """)
s = s.replace("_APOSTROPHE_", "'")
s = s.replace("_AND_", "&")
sent_tokens = nltk.sent_tokenize(s)
t = str(doc).split("<TEXT>")[0]
t = t.replace("_QUOTE_", """)
t = t.replace("_APOSTROPHE_", "'")
t = t.replace("_AND_", "&")
output = t + "\n\n<SENTENCES>\n\n" + str(
sent_tokens) + "\n\n</SENTENCES>"
return jsonify(result=output)
except:
return jsonify(result="something wrong")
def normalize_temporal_expressions(content, reference_date):
"""
Constructs a corpus from documents.
Params:
content (str): Tokenized string
reference_date (date): Reference date.
"""
recogniser = ternip.recogniser()
normaliser = ternip.normaliser()
content = f'<TimeML>\n{content}\n</TimeML>'
doc = TimeMlDocument(content,"TimeML")
sents = recogniser.tag(doc.get_sents())
normaliser.annotate(sents, reference_date.strftime('%Y%m%d'))
doc.reconcile(sents)
xml_str = str(doc)
unsupported_annotations = ["T24","T24","TMO", "TAF", "TEV", "TNI"]
for ua in unsupported_annotations:
xml_str = xml_str.replace(ua,"")
return xml_str
def dothenlp():
if request.method == "POST":
try:
myData = request.json['myData']
recogniser = ternip.recogniser()
normaliser = ternip.normaliser()
doc = TernDocument(myData)
strdoc = str(doc)
ref_date = find_between(strdoc, "<DATE_TIME>", "</DATE_TIME>").replace("-","")
sents = recogniser.tag(doc.get_sents())
normaliser.annotate(sents, ref_date)
doc.reconcile(sents)
# Single Sentences
s = find_between(str(doc), "<TEXT>", "</TEXT>").replace("\n"," <br>")
s = s.replace("_QUOTE_",""")
s = s.replace("_APOSTROPHE_","'")
s = s.replace("_AND_","&")
sent_tokens = nltk.sent_tokenize(s)
t = str(doc).split("<TEXT>")[0]
t = t.replace("_QUOTE_",""")
t = t.replace("_APOSTROPHE_","'")
t = t.replace("_AND_","&")
output = t + "\n\n<SENTENCES>\n\n" + str(sent_tokens) + "\n\n</SENTENCES>"
return jsonify(result=output)
except:
return jsonify(result="something wrong")
from score_entities import score_entities
console = logging.StreamHandler()
console.setFormatter(logging.Formatter('[%(asctime)s] %(name)-12s %(levelname)-8s %(message)s'))
logging.getLogger().addHandler(console)
logging.getLogger('ternip').setLevel(logging.INFO)
print
print "TERNIP TempEval-2 evaluator"
print
# Load TERNIP
recogniser = ternip.recogniser()
print "TERNIP loaded", recogniser.num_rules, "recognition rules"
normaliser = ternip.normaliser()
print "TERNIP loaded", normaliser.num_rules, "normalisation rules"
print
print "Loading data..."
# Load testing data
data_path = os.path.normpath('../sample_data/tempeval-training-2/english/data/')
with open(os.path.join(data_path, 'base-segmentation.tab')) as fd:
with open(os.path.join(data_path, 'dct.txt')) as dct_fd:
docs = TempEval2Document.load_multi(fd.read(), dct_fd.read())
temp = tempfile.mkdtemp()
ternip_extents = open(os.path.join(temp, 'ternip-extents.tab'), 'w')
ternip_attrs = open(os.path.join(temp, 'ternip-attrs.tab'), 'w')
