def run_measurement_finder(filename):
measurements = list()
try:
p = Popen(
['java', '-jar', FULL_JAR, '-f', filename, '-m', MODEL_FULL_DIR],
stdout=PIPE,
stderr=STDOUT)
json_str = ''
for line in p.stdout:
json_str += str(line, 'utf-8')
json_obj = json.loads(json_str)
results = json_obj['results']
for res in results:
meas_count = int(res["measurementCount"])
if meas_count > 0:
# print("found %d measurements" % meas_count)
meas_results = res['measurements']
for meas in meas_results:
meas_obj = Measurement.from_dict(meas)
meas_obj.__setattr__('sentence', res['sentence'])
measurements.append(meas_obj)
except Exception as e:
print(e)
return measurements
def run_value_extractor_full(term_list,
text,
minimum_value,
maximum_value,
is_case_sensitive_text=False,
denom_only=False):
# convert terms to lowercase unless doing a case-sensitive match
if not is_case_sensitive_text:
term_list = [term.lower() for term in term_list]
text = text.lower()
# do range check on numerator values for fractions
if isinstance(minimum_value, str):
if -1 != minimum_value.find('/'):
minimum_value = minimum_value.split('/')[0]
if isinstance(maximum_value, str):
if -1 != maximum_value.find('/'):
maximum_value = maximum_value.split('/')[0]
minval = float(minimum_value)
maxval = float(maximum_value)
sentence_list = segmentor.parse_sentences(text)
process_results = []
matchers = [re.compile(r"\b%s\b" % t, re.IGNORECASE) for t in term_list]
vals = product(sentence_list, matchers)
for v in vals:
sentence = v[0]
matcher = v[1]
match = matcher.search(sentence)
if match:
term = match.group(0)
value_results = extract_value(term,
sentence,
minval,
maxval,
denom_only=denom_only)
if len(value_results) > 0:
for x in value_results:
process_results.append(
Measurement(sentence=sentence,
text=x.matching_term,
start=x.start,
end=x.end,
condition=x.cond,
X=x.num1,
Y=x.num2))
return process_results
def run_measurement_finder_full(text, term_list, is_case_sensitive_text=False):
if not is_case_sensitive_text:
term_list = [term.lower() for term in term_list]
text = text.lower()
term_count = len(term_list)
terms = ",".join(term_list)
results = []
sentence_list = segmentor.parse_sentences(text)
for s in sentence_list:
json_str = run_subject_finder(terms, s)
json_obj = json.loads(json_str)
if 0 == json_obj['measurementCount']:
continue
if term_count > 0 and not json_obj['querySuccess']:
# ignore if query term(s) not found
continue
if json_obj and 'measurementList' in json_obj:
for x in json_obj['measurementList']:
try:
m = Measurement(sentence=s,
text=x['text'],
start=x['start'],
end=x['end'],
temporality=x['temporality'],
units=x['units'],
condition=x['condition'],
matching_terms=', '.join(
x['matchingTerm']),
subject=', '.join(x['subject']),
location=x['location'],
X=x['x'],
Y=x['y'],
Z=x['z'],
x_view=x['xView'],
y_view=x['yView'],
z_view=x['zView'],
value1=x['values'],
min_value=x['minValue'],
max_value=x['maxValue'])
results.append(m)
except Exception as ex:
log('measurement_finder_wrapper exception: {0}'.format(ex),
ERROR)
log(ERROR, ex)
return results
def run_value_extractor_full(term_list,
text,
minimum_value,
maximum_value,
enumlist=None,
is_case_sensitive_text=False,
denom_only=False,
values_before_terms=False):
if enumlist is None:
enumlist = list()
sentence_list = segmentor.parse_sentences(text)
process_results = []
for sentence in sentence_list:
json_string = run_value_extractor(
term_list,
sentence,
str_minval=minimum_value,
str_maxval=maximum_value,
str_enumlist=enumlist,
is_case_sensitive=is_case_sensitive_text,
is_denom_only=denom_only,
values_before_terms=values_before_terms)
if json_string is not None and len(json_string) > 0:
# parse the JSON result
json_data = json.loads(json_string)
# the individual value extractions are in the 'measurementList'
if 'measurementList' in json_data:
measurements = json_data['measurementList']
for m in measurements:
process_results.append(
Measurement(sentence=sentence,
text=m['text'],
start=m['start'],
end=m['end'],
condition=m['condition'],
X=m['x'],
Y=m['y'],
matching_terms=m['matchingTerm'],
min_value=m['minValue'],
max_value=m['maxValue']))
return process_results
def run_value_extractor_full(term_list,
text,
minimum_value,
maximum_value,
enumlist=None,
is_case_sensitive_text=False,
denom_only=False):
if enumlist is None:
enumlist = list()
sentence_list = segmentor.parse_sentences(text)
process_results = []
matchers = [re.compile(r"\b%s\b" % t, re.IGNORECASE) for t in term_list]
vals = product(sentence_list, matchers)
for v in vals:
sentence = v[0]
matcher = v[1]
match = matcher.search(sentence)
if match:
term = match.group(0)
value_str = run_value_extractor(
term,
sentence,
str_minval=minimum_value,
str_maxval=maximum_value,
str_enumlist=enumlist,
is_case_sensitive=is_case_sensitive_text,
is_denom_only=denom_only)
if len(value_str) > 0:
value_results = json.loads(value_str)
if 'measurementList' in value_results:
measurement_results = value_results['measurementList']
for x in measurement_results:
process_results.append(
Measurement(sentence=sentence,
text=x['matchingTerm'],
start=x['start'],
end=x['end'],
condition=x['condition'],
X=x['x'],
Y=x['y']))
return process_results
def run_measurement_finder_full(text, term_list, is_case_sensitive_text=False):
if not is_case_sensitive_text:
term_list = [term.lower() for term in term_list]
text = text.lower()
terms = ",".join(term_list)
results = []
sentence_list = segmentor.parse_sentences(text)
for s in sentence_list:
json_str = run_subject_finder(terms, s)
json_obj = json.loads(json_str)
if json_obj and 'measurementList' in json_obj:
for x in json_obj['measurementList']:
try:
results.append(
Measurement(sentence=s,
text=x['text'],
location=x['location'],
x_view=x['x_view'],
start=x['start'],
temporality=x['temporality'],
y_view=x['y_view'],
Z=x['z'],
subject=', '.join(x['subject']),
X=x['x'],
end=x['end'],
condition=x['condition'],
matching_terms=', '.join(
x['matchingTerm']),
value1=x['values'],
z_view=x['z_view'],
units=x['units'],
Y=x['y']))
except Exception as ex:
print(ex)
return results
def run_measurement_finder(filename):
measurements = list()
try:
p = Popen(['java', '-jar', FULL_JAR, '-f', filename, '-m', MODEL_FULL_DIR], stdout=PIPE, stderr=STDOUT)
json_str = ''
for line in p.stdout:
json_str += str(line, 'utf-8')
json_obj = json.loads(json_str)
results = json_obj['results']
for res in results:
meas_count = int(res["measurementCount"])
if meas_count > 0:
# print("found %d measurements" % meas_count)
meas_results = res['measurements']
for meas in meas_results:
meas_obj = Measurement.from_dict(meas)
meas_obj.__setattr__('sentence', res['sentence'])
measurements.append(meas_obj)
except Exception as e:
print(e)
return measurements