def bibclassify_exhaustive_call_text(text,
taxonomy,
rebuild_cache=False,
no_cache=False,
output_mode='text',
output_limit=20,
spires=False,
match_mode='full',
with_author_keywords=False,
extract_acronyms=False,
only_core_tags=False):
"""Call to bibclassify on a text."""
output_mode = output_mode.split(",")
if not isinstance(text, list):
text = [text]
return engine.get_keywords_from_text(
text_lines=text,
taxonomy_name=taxonomy,
rebuild_cache=rebuild_cache,
no_cache=no_cache,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
with_author_keywords=with_author_keywords,
extract_acronyms=extract_acronyms,
only_core_tags=only_core_tags,
api=True)
def run_microtest_suite(test_cases, results={}, plevel=1):
"""Runs all tests from the test_case
@var test_cases: microtest definitions
@keyword results: dict, where results are cummulated
@keyword plevel: int [0..1], performance level, results
below the plevel are considered unsuccessful
@return: nothing
"""
config = {}
if 'config' in test_cases:
config = test_cases['config']
del (test_cases['config'])
if 'taxonomy' not in config:
config['taxonomy'] = ['HEP']
for test_name in sorted(test_cases.keys()):
test = test_cases[test_name]
try:
log.debug('section: %s' % test_name)
phrase = test['phrase'][0]
(skw, ckw, akw, acr) = engine.get_keywords_from_text(test['phrase'], config['taxonomy'][0],
output_mode="raw")
details = analyze_results(test, (skw, ckw))
if details["plevel"] < plevel:
log.error("\n" + format_test_case(test))
log.error("results\n" + format_details(details))
else:
log.info("Success for section: %s" % (test_name))
log.info("\n" + format_test_case(test))
if plevel != 1:
log.info("results\n" + format_details(details))
results.setdefault(test_name, [])
results[test_name].append(details)
except Exception as msg:
log.error('Operational error executing section: %s' % test_name)
#log.error(msg)
log.error(traceback.format_exc())
def bibclassify_exhaustive_call_text(text, taxonomy, rebuild_cache=False,
no_cache=False, output_mode='text',
output_limit=20, spires=False,
match_mode='full',
with_author_keywords=False,
extract_acronyms=False,
only_core_tags=False):
"""Call to bibclassify on a text."""
output_mode = output_mode.split(",")
if not isinstance(text, list):
text = [text]
return engine.get_keywords_from_text(text_lines=text,
taxonomy_name=taxonomy,
rebuild_cache=rebuild_cache,
no_cache=no_cache,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
with_author_keywords=with_author_keywords,
extract_acronyms=extract_acronyms,
only_core_tags=only_core_tags,
api=True)