def test_config_gen(self):
test_user = '******' #arbitrary user
default_headers = [
'UT', 'AU', 'DE', 'ID', 'TI', 'WC', 'CR', 'C1', 'PY', 'J9', 'VL',
'BP', 'DI', 'PT', 'DT', 'TC'
]
spanYears = [[100, 500],
[200, 600]] #arbitrary values to retrieve from dict
config.spanYears = spanYears
#Test with user for the website
CONFIG = config.gen(test_user, default_headers)
self.assertEqual([100, 500], CONFIG['spans']['span_name_0']['years'])
self.assertEqual([200, 600], CONFIG['spans']['span_name_1']['years'])
#Test locally for the scripts only (trigerred when the user is a blank space)
CONFIG = config.gen(' ', default_headers)
self.assertEqual([100, 500], CONFIG['spans']['span_name_0']['years'])
self.assertEqual([200, 600], CONFIG['spans']['span_name_1']['years'])
spanYears = []
for range in vars(args)['bound']:
boundPair = range.split(
"-") #string separated by '-' retains lowerbound-upperbound ordering
intBoundPair = list(map(int, boundPair))
spanYears.append(intBoundPair)
user = args.user
print(user)
# Run all scripts.
import config
config.spanYears = spanYears
CONFIG = config.gen(user, str(args.headers).split('-'))
print("\nMERGING CORPUS\n")
import merging_corpus
merging_corpus.CONFIG = CONFIG
merging_corpus.run()
print("\nPARSE AND GROUP\n")
import parse_and_group
parse_and_group.CONFIG = CONFIG
parse_and_group.run()
print("\nCORPUS PARSED OVERVIEW\n")
import corpus_parsed_overview
corpus_parsed_overview.CONFIG = CONFIG
corpus_parsed_overview.run()
def test_config_gen(self):
spanYears = [[100,500], [200,600]] #arbitrary values to retrieve from dict
config.spanYears = spanYears
CONFIG = config.gen()
self.assertEqual([100,500], CONFIG['spans']['span_name_0']['years'])
self.assertEqual([200,600], CONFIG['spans']['span_name_1']['years'])
nargs='+',
metavar='bound',
help='Year value',
default={"1900-1999", "2000-2018"})
args = parser.parse_args()
spanYears = []
for range in vars(args)['bound']:
boundPair = range.split(
"-") #string separated by '-' retains lowerbound-upperbound ordering
intBoundPair = list(map(int, boundPair))
spanYears.append(intBoundPair)
import config
config.spanYears = spanYears
CONFIG = config.gen()
print("\nMERGING CORPUS\n")
import merging_corpus
merging_corpus.CONFIG = CONFIG
merging_corpus.run()
print("\nPARSE AND GROUP\n")
import parse_and_group
parse_and_group.CONFIG = CONFIG
parse_and_group.run()
print("\nCORPUS PARSED OVERVIEW\n")
import corpus_parsed_overview
corpus_parsed_overview.CONFIG = CONFIG
corpus_parsed_overview.run()
class TestParsers(TestCase):
"""
These tests assess the ability of parsers.py to parse a test input and
separate the information into different categories.
These test wos_parser, which tests all the units in the parsers.py file.
"""
dir = os.path.dirname(os.path.dirname(__file__))
default_headers = ['UT', 'AU', 'DE', 'ID', 'TI', 'WC', 'CR', 'C1', 'PY', 'J9', 'VL', 'BP', 'DI', 'PT', 'DT', 'TC']
test_user = '******'
CONFIG = config.gen(test_user, default_headers)
parsers.CONFIG = CONFIG
parsers.initHeaders()
os.mkdir(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output"))
test_input_txt = open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/input_parser.txt"), "r")
parsers.wos_parser(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests"), os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output"), False)
test_input_txt.close()
"""
This test tests that after parsing articles, the output is correct with respects
to a known-correct base folder FOR ARTICLES.
"""
def test_parse_articles(self):
dir = os.path.dirname(os.path.dirname(__file__))
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/articles.dat"), "r") as myfile:
output = myfile.read().replace("\n", "")
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/desired_output/articles.dat"), "r") as myfile:
desired_output = myfile.read().replace("\n", "")
self.assertEqual(output, desired_output)
"""
This test tests that after parsing articles, the output is correct with respects
to a known-correct base folder FOR AUTHORS.
"""
def test_parse_authors(self):
dir = os.path.dirname(os.path.dirname(__file__))
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/authors.dat"), "r") as myfile:
output = myfile.read().replace("\n", "")
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/desired_output/authors.dat"), "r") as myfile:
desired_output = myfile.read().replace("\n", "")
self.assertEqual(output, desired_output)
"""
This test tests that after parsing articles, the output is correct with respects
to a known-correct base folder FOR COUNTRIES.
"""
def test_parse_countries(self):
dir = os.path.dirname(os.path.dirname(__file__))
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/countries.dat"), "r") as myfile:
output = myfile.read().replace("\n", "")
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/desired_output/countries.dat"), "r") as myfile:
desired_output = myfile.read().replace("\n", "")
self.assertEqual(output, desired_output)
"""
This test tests that after parsing articles, the output is correct with respects
to a known-correct base folder FOR ARTICLE KEYWORDS.
"""
def test_parse_article_keywords(self):
dir = os.path.dirname(os.path.dirname(__file__))
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/article_keywords.dat"), "r") as myfile:
output = myfile.read().replace("\n", "")
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/desired_output/article_keywords.dat"), "r") as myfile:
desired_output = myfile.read().replace("\n", "")
self.assertEqual(output, desired_output)
"""
This test tests that after parsing articles, the output is correct with respects
to a known-correct base folder FOR INSTITUTIONS.
"""
def test_parse_institutions(self):
dir = os.path.dirname(os.path.dirname(__file__))
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/institutions.dat"), "r") as myfile:
output = myfile.read().replace("\n", "")
with open(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/desired_output/institutions.dat"), "r") as myfile:
desired_output = myfile.read().replace("\n", "")
self.assertEqual(output, desired_output)
"""
This test tests meticulously the output .dat files to ensure they are not corrupted.
"""
def test_open_dat_files(self):
dir = os.path.dirname(os.path.dirname(__file__))
os.makedirs(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder"))
output_dir = os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder")
open_files = parsers.open_dat_files(output_dir)
for file_key in open_files:
open_files[file_key].close()
no_of_files_created = len(glob.glob("%s/*.dat" % output_dir))
if os.path.exists(os.path.dirname(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/article_keywords.dat"))):
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/article_keywords.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/articles.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/authors.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/countries.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/institutions.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/isi_keywords.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/references.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/subjects.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder/title_keywords.dat"))
if os.path.exists(os.path.dirname(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder"))):
os.rmdir(os.path.join(dir, "tests_bibliotools/testFiles/test_open_dat_files_folder"))
self.assertEqual(no_of_files_created, 9)
"""
This is a test teardown that closes and removes any open/useless files.
"""
def test_teardown(self):
dir = os.path.dirname(os.path.dirname(__file__))
if os.path.exists(os.path.dirname(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/article_keywords.dat"))):
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/article_keywords.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/articles.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/authors.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/countries.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/institutions.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/isi_keywords.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/references.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/subjects.dat"))
os.remove(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output/title_keywords.dat"))
if os.path.exists(os.path.dirname(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output"))):
os.rmdir(os.path.join(dir, "tests_bibliotools/testFiles/parser_tests/test_output"))
"""
This test tests that all_txt_files returns a correct number
when there is one .txt file in the given folder.
"""
def test_all_txt_files_for_at_least_one_file(self):
dir = os.path.dirname(os.path.dirname(__file__))
directory = os.path.join(dir, "tests_bibliotools/testFiles")
myfile = open(os.path.join(directory, "all_txt_file.txt"), "w")
result = False
if len(parsers.all_txt_files(directory)) >= 1:
result = True
myfile.close()
os.remove(os.path.join(directory, "all_txt_file.txt"))
self.assertEqual(True, result)