def get_publication(xd):
matching_publications = set()
all_headers = xd.get_header("Copyright").lower()
# source filename/metadata must be the priority
abbr = utils.parse_pubid(xd.filename)
all_pubs = metadb.xd_publications()
for publ in all_pubs.values():
if publ.PublicationAbbr == abbr.lower():
matching_publications.add((1, publ))
if publ.PublicationName and publ.PublicationName.lower() in all_headers:
matching_publications.add((2, publ))
if publ.PublisherName and publ.PublisherName.lower() in all_headers:
matching_publications.add((3, publ))
if not matching_publications:
return None
elif len(matching_publications) == 1:
return matching_publications.pop()[1]
# otherwise, filter out 'self' publications
matching_pubs = set([(pri, p) for pri, p in matching_publications if 'self' not in p.PublisherAbbr])
if not matching_pubs:
matching_pubs = matching_publications # right back where we started
elif len(matching_pubs) == 1:
return matching_pubs.pop()[1]
return sorted(matching_pubs)[0][1]
def main():
args = utils.get_args()
all_receipts = metadb.xd_receipts_header
receipts = metadb.xd_receipts_rows()
rids = set() # set of ReceiptId
for r in receipts:
oldpubid = ""
oldpubid = utils.parse_pubid(r.xdid or '')
newpubid = catalog.find_pubid("|".join((str(x) for x in r)))
d = r._asdict()
if newpubid and newpubid != oldpubid:
seqnum = utils.parse_seqnum(r.xdid or r.SourceFilename)
if seqnum:
newxdid = newpubid + seqnum
utils.info("changing xdid from '%s' to '%s'" %
(r.xdid, newxdid))
d["xdid"] = newxdid
else:
utils.info("no date or number in xdid, not reshelving")
all_receipts += metadb.xd_receipts_row(**d)
open(metadb.RECEIPTS_TSV, 'w').write(all_receipts)
def main():
args = utils.get_args()
all_receipts = metadb.xd_receipts_header
receipts = metadb.xd_receipts_rows()
rids = set() # set of ReceiptId
for r in receipts:
oldpubid = ""
oldpubid = utils.parse_pubid(r.xdid or '')
newpubid = catalog.find_pubid("|".join((str(x) for x in r)))
d = r._asdict()
if newpubid and newpubid != oldpubid:
seqnum = utils.parse_seqnum(r.xdid or r.SourceFilename)
if seqnum:
newxdid = newpubid + seqnum
utils.info("changing xdid from '%s' to '%s'" % (r.xdid, newxdid))
d["xdid"] = newxdid
else:
utils.info("no date or number in xdid, not reshelving")
all_receipts += metadb.xd_receipts_row(**d)
open(metadb.RECEIPTS_TSV, 'w').write(all_receipts)
def get_publication(xd):
matching_publications = set()
all_headers = xd.get_header("Copyright").lower()
# source filename/metadata must be the priority
abbr = utils.parse_pubid(xd.filename)
all_pubs = metadb.xd_publications()
for publ in all_pubs.values():
if publ.PublicationAbbr == abbr.lower():
matching_publications.add((1, publ))
if publ.PublicationName and publ.PublicationName.lower(
) in all_headers:
matching_publications.add((2, publ))
if publ.PublisherName and publ.PublisherName.lower() in all_headers:
matching_publications.add((3, publ))
if not matching_publications:
return None
elif len(matching_publications) == 1:
return matching_publications.pop()[1]
# otherwise, filter out 'self' publications
matching_pubs = set([(pri, p) for pri, p in matching_publications
if 'self' not in p.PublisherAbbr])
if not matching_pubs:
matching_pubs = matching_publications # right back where we started
elif len(matching_pubs) == 1:
return matching_pubs.pop()[1]
return sorted(matching_pubs)[0][1]