def test_dumps_multiple_unknown_tags_ris(tmp_path):
fp = tmp_path / "test_dump_unknown_tags.ris"
results = [{"title": "my-title", "abstract": "my-abstract", "does_not_exists": "test"}]
# check that we get a warning
with pytest.warns(UserWarning, match="label `does_not_exists` not exported"):
with open(fp, "w") as f:
rispy.dump(results, f)
# check that we get everything back except missing key
text = Path(fp).read_text()
entries = rispy.loads(text)
assert entries[0] == {
"type_of_reference": "JOUR",
"title": "my-title",
"abstract": "my-abstract",
}
# check file looks as expected
lines = text.splitlines()
assert lines[0] == "1."
assert lines[1] == "TY - JOUR"
assert lines[4] == "ER - "
assert len(lines) == 5
def test_file_implementation_write():
class CustomParser(rispy.RisParser):
DEFAULT_IGNORE = ["JF", "ID", "KW"]
class CustomWriter(rispy.RisWriter):
DEFAULT_IGNORE = ["JF", "ID", "KW"]
list_tags = ["SN", "T1", "A1", "UR"]
fn = DATA_DIR / "example_full.ris"
with open(fn, "r") as f:
entries = rispy.load(f, implementation=CustomParser, list_tags=list_tags)
fn_write = DATA_DIR / "example_full_write.ris"
with open(fn_write, "w") as f:
rispy.dump(entries, f, implementation=CustomWriter, list_tags=list_tags)
with open(fn_write, "r") as f:
reload = rispy.load(f, implementation=CustomParser, list_tags=list_tags)
assert reload == entries
def export(self):
# Open StringIO to grab in-memory file contents
file = io.StringIO()
entries = list()
for paper in self._papers:
entry = {
'primary_title':
paper.title,
'first_authors': [
", ".join([author.last_name, author.first_name])
for author in paper.authors.all()
],
'abstract':
paper.abstract,
'doi':
paper.doi,
'publication_year':
paper.published_at.year,
'publisher':
paper.host.name
}
if paper.pdf_url:
entry['url'] = paper.pdf_url
if paper.journal:
entry['journal_name'] = paper.journal.displayname
entry['type_of_reference'] = 'JOUR'
else:
entry['type_of_reference'] = 'GEN'
entries.append(entry)
rispy.dump(entries, file)
return file
def main():
# Get input arguments
parser = argparse.ArgumentParser(
description=
'Given a list of accession numbers in a file, extract records that match those ids'
)
parser.add_argument(
"-i",
"--input_file",
type=str,
help=
"The path to the file that contains the accession numbers to search for",
required=True)
parser.add_argument(
"-d",
"--data_file",
type=str,
help="The path to the data file. Should be in .ris format",
required=True)
parser.add_argument(
"-o",
"--output_file",
type=str,
help=
"The path to the output file for records taht match. Will be in .ris format",
required=True)
input_file = ''
data_file = ''
output_file = ''
try:
args = parser.parse_args()
input_file = args.input_file
data_file = args.data_file
output_file = args.output_file
except:
parser.print_help()
sys.exit(0)
# Get list of accession ids from input file
accession_no_list = []
try:
accession_no_list = [line.strip() for line in open(input_file)]
except:
print(f'Unable to open input file {input_file}')
sys.exit(0)
# Interate over data file and if ids is one specificed in the id file add to list
selected_records = []
try:
with open(data_file, 'r') as bibliography_file:
entries = rispy.load(bibliography_file)
for entry in entries:
if entry['accession_number'] in accession_no_list:
selected_records.append(entry)
except OSError as err:
print("OS error: {0}".format(err))
sys.exit(0)
except:
print("Unexpected error:", sys.exc_info()[0])
raise
# This is pretty inefficient. We are storing the selected records to a list
# and this list could get huge!
try:
with open(output_file, 'w') as output_file:
rispy.dump(selected_records, output_file)
except OSError as err:
print("OS error: {0}".format(err))
sys.exit(0)
except:
print("Unexpected error:", sys.exc_info()[0])
raise
import os
import rispy
entries = [{
'type_of_reference': 'JOUR',
'id': '42',
'primary_title': 'The title of the reference',
'first_authors': ['Marxus, Karlus', 'Lindgren, Astrid']
}, {
'type_of_reference': 'JOUR',
'id': '43',
'primary_title': 'Reference 43',
'abstract': 'Lorem ipsum'
}]
filepath = 'export.ris'
with open(filepath, 'w') as bibliography_file:
rispy.dump(entries, bibliography_file)
def write_entries_to_ris(entries, wpath, mode="w"):
if not isinstance(entries, list):
raise AssertionError("entries must be dictionary.")
with open(wpath, mode) as write:
rispy.dump(entries, write)