def get_args():
parser = utils.get_command_line_parser(
description='Set the password for an account.')
parser.add_argument('account',
action='store',
help='Account to set password for.')
return parser.parse_args()
def get_args():
parser = utils.get_command_line_parser(
description='Publications web server')
parser.add_argument('-p',
'--pidfile',
action='store',
dest='pidfile',
default=None,
metavar="FILE",
help="filename of file containing PID")
return parser.parse_args()
except KeyError as error:
errors.append(str(error))
else:
if label not in publ['labels']:
with PublicationSaver(doc=publ, db=db) as saver:
labels = publ['labels'].copy()
labels[label] = qualifier
saver['labels'] = labels
count += 1
print("Label '%s/%s' added to %i publications" % (label, qualifier, count))
for error in errors:
print(error)
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'Add a label to all publications in a list.')
parser.add_argument('--label', action='store', dest='label',
default=None, help='label to add')
parser.add_argument('--qualifier', action='store', dest='qualifier',
default=None, help='qualifier of label to add')
parser.add_argument('--file', action='store', dest='idfile',
metavar='IDFILE',
help='path to file containing publication identifiers')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
identifiers = []
with open(args.idfile) as infile:
for line in infile:
line = line.strip()
if line: identifiers.append(line)
count_files += 1
else:
doc = json.loads(itemdata)
atts = doc.pop('_attachments', dict())
db.save(doc)
count_items += 1
for attname, attinfo in list(atts.items()):
key = "{0}_att/{1}".format(doc['_id'], attname)
attachments[key] = dict(filename=attname,
content_type=attinfo['content_type'])
if count_items % 100 == 0:
logging.info("%s items loaded...", count_items)
infile.close()
designs.regenerate_indexes(db)
logging.info("undumped %s items and %s files from %s", count_items,
count_files, filepath)
if __name__ == '__main__':
parser = utils.get_command_line_parser('Load tar.gz dump file'
' into the database.')
parser.add_argument('dumpfile',
metavar='FILE',
type=str,
help='Dump file to load into the database.')
args = parser.parse_args()
utils.load_settings(filepath=args.settings, ignore_logging_filepath=True)
db = utils.get_db()
utils.initialize(db)
undump(db, args.dumpfile)
"Display all xrefs currently in database."
from publications import utils
def display_xrefs(db):
view = db.view('publication/created', include_docs=True)
dbs = set()
for item in view:
for xref in item.doc.get('xrefs', []):
print(xref)
dbs.add(xref['db'])
print(', '.join(dbs))
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'Check for duplicated based on title.')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
display_xrefs(db)
from publications import pubmed
from publications import utils
DELAY = 2.0
def fix_missing_pmids(db, jump=0):
view = db.view('publication/no_pmid', include_docs=True)
for pos, item in enumerate(view):
if pos < jump: continue
title = item.doc['title']
print("[%s]" % pos, title)
pmids = pubmed.search(title=title, delay=DELAY)
if len(pmids) == 1:
with PublicationSaver(doc=item.doc, db=db) as saver:
saver['pmid'] = pmids[0]
print('updated', pmids[0])
print()
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'Fix missing PMID in all publications by searching for title.')
parser.add_argument('-j', '--jump',
action='store', dest='jump', type=int, default=0,
help='jump over the first number of publications')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
fix_missing_pmids(db, jump=args.jump)
else:
if journal.get('issn-l') != issn_l:
if not dryrun:
with JournalSaver(doc=journal, db=db) as saver:
saver["issn-l"] = issn_l
updated.append(journal)
if dryrun:
print('NOTE: dry run! No changes made.')
print('count', count)
print('different', different)
print('updated', len(updated))
if __name__ == '__main__':
import sys
parser = utils.get_command_line_parser(
'Add ISSN-L to journals from file mapping ISSN to ISSN-L')
parser.add_argument('-f',
'--issnfile',
action='store',
dest='issnfile',
metavar='ISSNFILE',
help='path of ISSN to ISSN-L file')
parser.add_argument('-d',
'--dryrun',
action='store_true',
dest='dryrun',
default=False)
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
if not args.issnfile:
sys.exit('Error: no ISSN to ISSN-L file given')
for db in sorted(xref_count):
write((db, xref_count[db]))
write(())
write(('Xref curator', 'Total publs', 'Total xrefs'))
for email in sorted(curators):
publs = curators[email]
total_publs = len(publs)
new = set()
for xrefs in list(publs.values()):
new.update(xrefs)
total_xrefs = len(new)
write((email, total_publs, total_xrefs))
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'CSV file of statistics for xrefs editing.')
parser.add_argument('-c',
'--csvfile',
metavar='FILE',
action='store',
dest='csvfilename',
help='The name of the CSV file.')
parser.add_argument('-d',
'--since',
action='store',
dest='since',
help='The date since to sum up xrefs.')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
if args.csvfilename:
def get_args():
parser = utils.get_command_line_parser(
description='Create a new admin account.')
return parser.parse_args()
from publications import utils
def init_database(db):
"Initialize the database; load design documents."
print('wiping out database (slow method)...')
for doc in db:
del db[doc]
print('wiped out database')
utils.initialize(db)
if __name__ == '__main__':
import sys
parser = utils.get_command_line_parser(
description='Initialize the database, deleting all old data.')
parser.add_argument('-f',
'--force',
action='store_true',
dest='force',
default=False,
help='force deletion; skip question')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
if not args.force:
response = input('about to delete everything; really sure? [n] > ')
if not utils.to_bool(response):
sys.exit('aborted')
init_database(utils.get_db())
try:
if row[0]:
fetch_pmid(db, row[0], row[2], row[3])
elif row[1]:
pmids = pubmed.search(doi=row[1], delay=DELAY)
if len(pmids) == 1:
fetch_pmid(db, pmids[0], row[2], row[3])
else:
fetch_doi(db, row[1], row[2], row[3])
except KeyError as error:
errorfile.write(str(error))
errorfile.write('\n')
if __name__ == '__main__':
import sys
parser = utils.get_command_line_parser(
'Fetch publications in bulk from CSV file.')
parser.add_argument('-f',
'--csvfile',
action='store',
dest='csvfile',
metavar='CSVFILE',
help='path of CSV file')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
if not args.csvfile:
sys.exit('Error: no CSV file given')
db = utils.get_db()
fetch_bulk(db, args.csvfile)
def remove_label(db, label):
if not label:
raise ValueError('no label given')
view = db.view('label/value', key=label)
if len(view) == 0:
raise ValueError("label %s does not exist" % label)
view = db.view('publication/modified', include_docs=True)
for item in view:
if label in item.doc['labels']:
with PublicationSaver(doc=item.doc, db=db) as saver:
labels = item.doc['labels'].copy()
labels.pop(label)
saver['labels'] = labels
print(item.doc['_id'], item.doc['labels'])
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'Remove a label from all publications.')
parser.add_argument('--label',
action='store',
dest='label',
default=None,
help='label to remove')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
remove_label(db, args.label)
attfile = db.get_attachment(doc, attname)
if attfile is None: continue
data = attfile.read()
attfile.close()
info.size = len(data)
outfile.addfile(info, io.BytesIO(data))
count_files += 1
outfile.close()
logging.info("dumped %s items and %s files to %s",
count_items, count_files, filepath)
if __name__ == '__main__':
import os
import time
parser = utils.get_command_line_parser('Dump all data into a tar.gz file.')
parser.add_argument('-d', '--dumpfile', metavar='FILE',
action='store', dest='dumpfile',
help='The full path of the dump file.')
parser.add_argument('-D', '--dumpdir', metavar='DIR',
action='store', dest='dumpdir',
help='The directory to write the dump file'
' (with standard name) in.')
args = parser.parse_args()
utils.load_settings(filepath=args.settings, ignore_logging_filepath=True)
db = utils.get_db()
if args.dumpfile:
filepath = args.dumpfile
else:
filepath = "dump_{0}.tar.gz".format(time.strftime("%Y-%m-%d"))
if args.dumpdir:
qualifier = max(qualifier,
item.doc['labels'][existing_label])
if found:
for key, value in qualifier_lookup.items():
if value == qualifier:
qualifier = key
break
with PublicationSaver(doc=item.doc, db=db) as saver:
labels = item.doc['labels'].copy()
labels[new_label] = qualifier # May be None
saver['labels'] = labels
print(item.doc['_id'], item.doc['labels'], qualifier)
if __name__ == '__main__':
parser = utils.get_command_line_parser(
'Add a label to all publications having other label(s).')
parser.add_argument('--new',
action='store',
dest='new',
default=None,
help='new label to add')
parser.add_argument('--existing',
action='append',
dest='existing',
default=None,
help='existing label')
args = parser.parse_args()
utils.load_settings(filepath=args.settings)
db = utils.get_db()
add_label(db, args.new, args.existing)
