"""
import json
import couchdb
from pubrefdb import configuration
def undump(db, infile):
data = json.load(infile)
for id, doc in data.iteritems():
try:
del doc['_rev']
except KeyError:
pass
try:
olddoc = db[id]
except couchdb.http.ResourceNotFound:
pass
else:
doc['_rev'] = olddoc['_rev']
db.save(doc)
print id, doc['entitytype']
if __name__ == '__main__':
infile = open('dump.json')
undump(configuration.get_db(), infile)
infile.close()
""" PubRefDb: Web application for a database of publications.
Dump all documents having a defined entitytype to a file.
"""
import json
from pubrefdb import configuration
def dump(db, outfile):
data = dict()
for id in db:
doc = db[id]
if doc.has_key('entitytype'):
data[doc['_id']] = dict(doc)
print id, doc['entitytype']
json.dump(data, outfile)
if __name__ == '__main__':
import os
dirpath = os.path.expanduser('~/dumps/pubrefdb')
filepath = os.path.join(dirpath, "dump_%s.json" % configuration.get_date())
outfile = open(filepath, 'wb')
dump(configuration.get_db(), outfile)
outfile.close()
"""
view = db.view('publication/incomplete', include_docs=True)
for item in view:
pmid = item.value
if not pmid: continue
if log:
print 'Checking PMID', pmid
article = pubmed.Article(pmid)
if article.pmid:
patch_publication(db, item.doc, article, log=log)
time.sleep(delay)
def patch_publication(db, doc, article, log):
with PublicationSaver(db, doc=doc):
doc['type'] = article.type
doc['published'] = article.published
for key in ['volume', 'issue', 'pages']:
if not doc['journal'].get(key):
doc['journal'][key] = article.journal.get(key)
if log:
print 'Updated', article.pmid, article.title
return doc
if __name__ == '__main__':
import os
import sys
db = configuration.get_db()
patch(db, log=os.isatty(sys.stdin.fileno()))
if name.lower() not in names:
pis[i] = None
pis = [pi for pi in pis if pi is not None]
return [(pi.get('normalized_name', pi['name']),
[a.strip() for a in pi['affiliation'].split(',')])
for pi in pis]
def add_publication(db, pmid):
"""Add the publication to the database if not already in it.
Skip if the PMID has been excluded.
Set the tag 'SciLifeLab' if marked such in the affiliation.
"""
if len(db.view('publication/xref')[['pubmed', pmid]]) > 0: return
if len(db.view('publication/excluded')[['pubmed', pmid]]) > 0: return
article = pubmed.Article(pmid)
if not article.pmid: return
affiliation = article.affiliation or ''
affiliation = affiliation.lower()
for key in ['science for life laboratory', 'scilifelab']:
if key in affiliation:
article.tags.append('SciLifeLab')
break
with PublicationSaver(db, doc=article.get_data()) as doc:
pass
return doc
if __name__ == '__main__':
import sys
fetch(configuration.get_db(), pinames=sys.argv[1:])
