def run(self):
with self.output().open('w') as output:
for k1, k2 in itertools.combinations(list(self.input().keys()), 2):
s1 = load_set_from_target(self.input().get(k1))
s2 = load_set_from_target(self.input().get(k2))
for issn in sorted(s1.intersection(s2)):
output.write_tsv(k1, k2, issn)
def run(self):
amsl = load_set_from_target(self.input().get('amsl'))
crossref = load_set_from_target(self.input().get('crossref'))
with self.output().open('w') as output:
stats = {
'amsl': amsl,
'crossref': crossref,
'amsl_only': amsl - crossref,
'crossref_only': crossref - amsl,
'both': amsl & crossref,
}
output.write(json.dumps(stats, cls=SetEncoder))
def run(self):
amsl = load_set_from_target(self.input().get('amsl'))
crossref = load_set_from_target(self.input().get('crossref'))
with self.output().open('w') as output:
stats = {
'amsl': amsl,
'crossref': crossref,
'amsl_only': amsl - crossref,
'crossref_only': crossref - amsl,
'both': amsl & crossref,
}
output.write(json.dumps(stats, cls=SetEncoder))
def run(self):
seen = load_set_from_target(self.input().get('seen'))
written = set()
with self.input().get('mapping').open() as handle:
with self.output().open('w') as output:
for row in handle.iter_tsv(cols=('prefix', 'name', 'current')):
if row.prefix not in seen:
self.logger.debug("not seen: %s", row.prefix)
continue
cut = row[:2]
if tuple(cut) not in written:
output.write_tsv(*cut)
written.add(tuple(cut))
def run(self):
identifier_blacklist = load_set_from_target(self.input().get('blacklist'))
excludes = load_set_from_file(self.assets('028_doaj_filter.tsv'), func=lambda line: line.replace("-", ""))
with self.output().open('w') as output:
with self.input().get('dump').open() as handle:
for line in handle:
record, skip = json.loads(line), False
if record['id'] in identifier_blacklist:
continue
for issn in record["bibjson"]["journal"]["issns"]:
issn = issn.replace("-", "").strip()
if issn in excludes:
skip = True
break
if skip:
continue
output.write(line)