def test_cli_extract_from_url(self):
"""bibclassify -k ${taxonomy}.rdf {url/record/94}"""
path, url = self.get_test_file(94)
args = ("-k %s.rdf %s" % (self.taxonomy_name, url)).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"])
results, errors = self.unredirect()
res, msg = check_pdf2(results)
if not res:
self.fail(msg)
def test_cli_extract_from_directory(self):
"""bibclassify -k ${taxonomy}.rdf directory/"""
path, url = self.get_test_file(94)
path = os.path.dirname(path)
if not os.path.exists(path):
sys.stderr.write("No PDF folder for testing found, returning\n")
return
args = ("-k %s.rdf %s" % (self.taxonomy_name, path)).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"])
results, errors = self.unredirect()
res, msg = check_pdf2(results)
if not res:
self.fail(msg)
def test_cli_extract_from_url(self):
"""bibclassify -k ${taxonomy}.rdf {url/record/94}"""
path, url = self.get_test_file(94)
args = ("-k %s.rdf %s" % (self.taxonomy_name, url)).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"],
)
results, errors = self.unredirect()
res, msg = check_pdf2(results)
if not res:
self.fail(msg)
def test_cli_extract_from_directory(self):
"""bibclassify -k ${taxonomy}.rdf directory/"""
path, url = self.get_test_file(94)
path = os.path.dirname(path)
if not os.path.exists(path):
sys.stderr.write("No PDF folder for testing found, returning\n")
return
args = ("-k %s.rdf %s" % (self.taxonomy_name, path)).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"],
)
results, errors = self.unredirect()
res, msg = check_pdf2(results)
if not res:
self.fail(msg)
def test_full_and_partial_matching_mode(self):
"""bibclassify - difference of extraction on part or full contents of pdf"""
path, url = self.get_test_file(94)
if not os.path.exists(path):
sys.stderr.write("No PDF for testing found, returning\n")
return
results = []
for case in [
"-k %s.rdf %s" % (self.taxonomy_name, path),
"-k %s.rdf %s -m partial" % (self.taxonomy_name, path),
]:
args = (case).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"],
)
r, e = self.unredirect()
results.append(r)
res, msg = check_pdf1(results[1])
if not res:
self.fail(msg)
res, msg = check_pdf2(results[0])
if not res:
self.fail(msg)
def test_full_and_partial_matching_mode(self):
"""bibclassify - difference of extraction on part or full contents of pdf"""
path, url = self.get_test_file(94)
if not os.path.exists(path):
sys.stderr.write("No PDF for testing found, returning\n")
return
results = []
for case in [
"-k %s.rdf %s" % (self.taxonomy_name, path),
"-k %s.rdf %s -m partial" % (self.taxonomy_name, path)
]:
args = (case).split()
options = bibclassify_cli._read_options(args)
self.redirect()
bibclassify_engine.output_keywords_for_sources(
options["text_files"],
options["taxonomy"],
rebuild_cache=options["rebuild_cache"],
no_cache=options["no_cache"],
output_mode=options["output_mode"],
output_limit=options["output_limit"],
spires=options["spires"],
match_mode=options["match_mode"],
with_author_keywords=options["with_author_keywords"],
extract_acronyms=options["extract_acronyms"],
only_core_tags=options["only_core_tags"])
r, e = self.unredirect()
results.append(r)
res, msg = check_pdf1(results[1])
if not res:
self.fail(msg)
res, msg = check_pdf2(results[0])
if not res:
self.fail(msg)