def convert_personid():
from invenio.dbquery import run_sql # oh come on, the whole function will be removed soon
from itertools import repeat
chunk = 1000
old_personid = run_sql("SELECT `personid`, `tag`, `data`, `flag`, `lcul` FROM `aidPERSONID`")
def flush_papers(args):
run_sql("INSERT INTO `aidPERSONIDPAPERS` "
"(`personid`, "
" `bibref_table`, "
" `bibref_value`, "
" `bibrec`, "
" `name`, "
" `flag`, "
" `lcul`) "
"VALUES " + " , ".join(repeat("(%s, %s, %s, %s, %s, %s, %s)", len(args) / 7))
, tuple(args))
def flush_data(args):
run_sql("INSERT INTO `aidPERSONIDDATA` "
"(`personid`, "
" `tag`, "
" `data`, "
" `opt1`, "
" `opt2`) "
"VALUES " + " , ".join(repeat("(%s, %s, %s, %s, %s)", len(args) / 5))
, tuple(args))
paper_args = []
data_args = []
for row in old_personid:
if row[1] == 'paper':
bibref, rec = row[2].split(',')
tab, ref = bibref.split(':')
try:
name = get_name_by_bibref((int(tab), int(ref), int(rec)))
except:
continue
name = split_name_parts(name)
name = create_normalized_name(name)
paper_args += [row[0], tab, ref, rec, name, row[3], row[4]]
if len(paper_args) > chunk:
flush_papers(paper_args)
paper_args = []
elif row[1] == 'gathered_name':
continue
else:
data_args += list(row)
if len(data_args) > chunk:
flush_data(data_args)
data_args = []
if paper_args:
flush_papers(paper_args)
if data_args:
flush_data(data_args)
def rabbit(bibrecs,
check_invalid_papers=False,
personids_to_update_extids=None,
verbose=False):
'''
@param bibrecs: an iterable full of bibrecs
@type bibrecs: an iterable of ints
@return: none
'''
logfile = open('/tmp/RABBITLOG-%s' % str(now()).replace(" ", "_"), 'w')
logfile.write("RABBIT %s running on %s \n" % (str(now()), str(bibrecs)))
def logwrite(msg, is_error):
verb = 9
if is_error or verbose:
verb = 1
write_message(msg, verbose=verb)
if bconfig.RABBIT_USE_CACHED_PID:
PID_NAMES_CACHE = get_name_to_authors_mapping()
def find_pids_by_exact_names_cache(name):
try:
return zip(PID_NAMES_CACHE[name])
except KeyError:
return []
def add_signature_using_names_cache(sig, name, pid):
try:
PID_NAMES_CACHE[name].add(pid)
except KeyError:
PID_NAMES_CACHE[name] = set([pid])
_add_signature(sig, name, pid)
def new_person_from_signature_using_names_cache(sig, name):
pid = get_free_author_id()
add_signature_using_names_cache(sig, name, pid)
return pid
add_signature = add_signature_using_names_cache
new_person_from_signature = new_person_from_signature_using_names_cache
find_pids_by_exact_name = find_pids_by_exact_names_cache
else:
add_signature = _add_signature
new_person_from_signature = _new_person_from_signature
find_pids_by_exact_name = _find_pids_by_exact_name
compare_names = cached_sym(lambda x: x)(comp_names)
# fast assign threshold
threshold = 0.80
if not bibrecs or check_invalid_papers:
all_bibrecs = get_all_valid_papers()
if not bibrecs:
bibrecs = all_bibrecs
if check_invalid_papers:
filter_bibrecs_outside(all_bibrecs)
if (bconfig.RABBIT_USE_CACHED_GET_GROUPED_RECORDS and len(bibrecs) >
bconfig.RABBIT_USE_CACHED_GET_GROUPED_RECORDS_THRESHOLD):
populate_partial_marc_caches()
SWAPPED_GET_GROUPED_RECORDS = True
else:
SWAPPED_GET_GROUPED_RECORDS = False
updated_pids = set()
deleted = frozenset(p[0] for p in get_deleted_papers())
for idx, rec in enumerate(bibrecs):
logwrite("\nConsidering %s" % str(rec), False)
if idx % 200 == 0:
task_sleep_now_if_required(True)
update_status(
float(idx) / len(bibrecs),
"%d/%d current: %d" % (idx, len(bibrecs), rec))
task_update_progress("%d/%d current: %d" %
(idx, len(bibrecs), rec))
if rec in deleted:
logwrite(
" - Record was deleted, removing from pid and continuing with next record",
True)
remove_papers([rec])
continue
markrefs = frozenset(
chain(
izip(cycle([100]),
imap(itemgetter(0), get_author_refs_of_paper(rec))),
izip(cycle([700]),
imap(itemgetter(0), get_coauthor_refs_of_paper(rec)))))
personid_rows = [
map(int, row[:3]) + [row[4]]
for row in get_signatures_of_paper(rec)
]
personidrefs_names = dict(
((row[1], row[2]), row[3]) for row in personid_rows)
personidrefs = frozenset(personidrefs_names.keys())
new_signatures = list(markrefs - personidrefs)
old_signatures = list(personidrefs - markrefs)
new_signatures_names = dict(
(new,
create_normalized_name(split_name_parts(get_name_by_bibref(new))))
for new in new_signatures)
# matrix |new_signatures| X |old_signatures|
matrix = [[
compare_names(new_signatures_names[new], personidrefs_names[old])
for old in old_signatures
] for new in new_signatures]
logwrite(" - Old signatures: %s" % str(old_signatures),
bool(old_signatures))
logwrite(" - New signatures: %s" % str(new_signatures),
bool(new_signatures))
logwrite(" - Matrix: %s" % str(matrix), bool(matrix))
# [(new_signatures, old_signatures)]
best_match = [(new_signatures[new], old_signatures[old])
for new, old, score in maximized_mapping(matrix)
if score > threshold]
logwrite(" - Best match: %s " % str(best_match), bool(best_match))
for new, old in best_match:
logwrite(
" - - Moving signature: %s on %s to %s as %s" %
(old, rec, new, new_signatures_names[new]), True)
modify_signature(old, rec, new, new_signatures_names[new])
remove_signatures(tuple(list(old) + [rec]) for old in old_signatures)
not_matched = frozenset(new_signatures) - frozenset(
map(itemgetter(0), best_match))
pids_having_rec = set(
[int(row[0]) for row in get_signatures_of_paper(rec)])
logwrite(" - Not matched: %s" % str(not_matched), bool(not_matched))
if not_matched:
used_pids = set(r[0] for r in personid_rows)
for sig in not_matched:
name = new_signatures_names[sig]
matched_pids = list()
if USE_EXT_IDS:
if USE_INSPIREID:
inspire_id = get_inspire_id_of_signature(sig + (rec, ))
if inspire_id:
matched_pids = list(
get_author_by_external_id(inspire_id[0]))
if matched_pids and int(
matched_pids[0][0]) in pids_having_rec:
matched_pids = list()
if matched_pids:
add_signature(list(sig) + [rec], name, matched_pids[0][0])
updated_pids.add(matched_pids[0][0])
pids_having_rec.add(matched_pids[0][0])
continue
matched_pids = find_pids_by_exact_name(name)
matched_pids = [
p for p in matched_pids if int(p[0]) not in used_pids
]
if not matched_pids or int(matched_pids[0][0]) in pids_having_rec:
new_pid = new_person_from_signature(list(sig) + [rec], name)
used_pids.add(new_pid)
updated_pids.add(new_pid)
else:
add_signature(list(sig) + [rec], name, matched_pids[0][0])
used_pids.add(matched_pids[0][0])
updated_pids.add(matched_pids[0][0])
pids_having_rec.add(matched_pids[0][0])
logwrite('Finished with %s' % str(rec), False)
update_status_final()
if personids_to_update_extids:
updated_pids |= personids_to_update_extids
if updated_pids: # an empty set will update all canonical_names
update_canonical_names_of_authors(updated_pids)
update_external_ids_of_authors(
updated_pids,
limit_to_claimed_papers=bconfig.
LIMIT_EXTERNAL_IDS_COLLECTION_TO_CLAIMED_PAPERS)
if SWAPPED_GET_GROUPED_RECORDS:
destroy_partial_marc_caches()
remove_empty_authors()
def convert_personid():
from invenio.dbquery import run_sql # oh come on, the whole function will be removed soon
from itertools import repeat
chunk = 1000
old_personid = run_sql(
"SELECT `personid`, `tag`, `data`, `flag`, `lcul` FROM `aidPERSONID`")
def flush_papers(args):
run_sql(
"INSERT INTO `aidPERSONIDPAPERS` "
"(`personid`, "
" `bibref_table`, "
" `bibref_value`, "
" `bibrec`, "
" `name`, "
" `flag`, "
" `lcul`) "
"VALUES " +
" , ".join(repeat("(%s, %s, %s, %s, %s, %s, %s)",
len(args) / 7)), tuple(args))
def flush_data(args):
run_sql(
"INSERT INTO `aidPERSONIDDATA` "
"(`personid`, "
" `tag`, "
" `data`, "
" `opt1`, "
" `opt2`) "
"VALUES " +
" , ".join(repeat("(%s, %s, %s, %s, %s)",
len(args) / 5)), tuple(args))
paper_args = []
data_args = []
for row in old_personid:
if row[1] == 'paper':
bibref, rec = row[2].split(',')
tab, ref = bibref.split(':')
try:
name = get_name_by_bibref((int(tab), int(ref), int(rec)))
except:
continue
name = split_name_parts(name)
name = create_normalized_name(name)
paper_args += [row[0], tab, ref, rec, name, row[3], row[4]]
if len(paper_args) > chunk:
flush_papers(paper_args)
paper_args = []
elif row[1] == 'gathered_name':
continue
else:
data_args += list(row)
if len(data_args) > chunk:
flush_data(data_args)
data_args = []
if paper_args:
flush_papers(paper_args)
if data_args:
flush_data(data_args)
def rabbit(bibrecs=None,
check_invalid_papers=False,
personids_to_update_extids=None,
verbose=False):
logger = Logger("Rabbit")
if verbose:
logger.verbose = True
if not bibrecs:
logger.log("Running on all records")
else:
logger.log("Running on %s " % (str(bibrecs)))
populate_mnames_pids_cache()
global M_NAME_PIDS_CACHE
memoized_compare_names = memoized(comp_names)
compare_names = lambda x, y: memoized_compare_names(*sorted((x, y)))
def find_pids_by_matchable_name_with_cache(matchable_name):
try:
matched_pids = [M_NAME_PIDS_CACHE[matchable_name]]
except KeyError:
matched_pids = get_authors_by_name(matchable_name,
use_matchable_name=True)
if matched_pids:
M_NAME_PIDS_CACHE[matchable_name] = matched_pids[0]
return matched_pids
if USE_EXT_IDS:
def get_matched_pids_by_external_ids(sig, rec, pids_having_rec):
'''
This function returns all the matched pids after iterating
through all available external IDs of the system.
'''
for get_external_id_of_signature in external_id_getters:
external_id = get_external_id_of_signature(sig + (rec, ))
if external_id:
matched_pids = list(
get_author_by_external_id(external_id[0]))
if matched_pids and int(
matched_pids[0][0]) in pids_having_rec:
matched_pids = list()
return matched_pids
threshold = 0.8
if not bibrecs or check_invalid_papers:
all_bibrecs = get_all_valid_bibrecs()
if not bibrecs:
bibrecs = all_bibrecs
if check_invalid_papers:
filter_bibrecs_outside(all_bibrecs)
updated_pids = set()
deleted = frozenset(p[0] for p in get_deleted_papers())
bibrecs = list(bibrecs)
for idx, rec in enumerate(bibrecs):
logger.log("Considering %s" % str(rec))
if idx % 100 == 0:
task_update_progress("%d/%d current: %d" %
(idx, len(bibrecs), rec))
if idx % 1000 == 0:
destroy_partial_marc_caches()
populate_partial_marc_caches(bibrecs[idx:idx + 1000])
logger.log(
float(idx) / len(bibrecs), "%d/%d" % (idx, len(bibrecs)))
if rec in deleted:
remove_papers([rec])
continue
author_refs = get_author_refs_of_paper(rec)
coauthor_refs = get_coauthor_refs_of_paper(rec)
markrefs = frozenset(
chain(izip(cycle([100]), imap(itemgetter(0), author_refs)),
izip(cycle([700]), imap(itemgetter(0), coauthor_refs))))
personid_rows = [
map(int, row[:3]) + [row[4]]
for row in get_signatures_of_paper(rec)
]
personidrefs_names = dict(
((row[1], row[2]), row[3]) for row in personid_rows)
personidrefs = frozenset(personidrefs_names.keys())
new_signatures = list(markrefs - personidrefs)
old_signatures = list(personidrefs - markrefs)
new_signatures_names = dict(
(new, get_name_by_bibref(new)) for new in new_signatures)
# matrix |new_signatures| X |old_signatures|
matrix = [[
compare_names(new_signatures_names[new], personidrefs_names[old])
for old in old_signatures
] for new in new_signatures]
logger.log(" - Deleted signatures: %s" % str(old_signatures))
logger.log(" - Added signatures: %s" % str(new_signatures))
logger.log(" - Matrix: %s" % str(matrix))
#[new_signatures, old_signatures]
best_match = [(new_signatures[new], old_signatures[old])
for new, old, score in maximized_mapping(matrix)
if score > threshold]
logger.log(" - Best match: %s " % str(best_match))
for new, old in best_match:
logger.log(" - - Moving signature: %s on %s to %s as %s" %
(old, rec, new, new_signatures_names[new]))
modify_signature(old, rec, new, new_signatures_names[new])
remove_signatures(tuple(list(old) + [rec]) for old in old_signatures)
not_matched = frozenset(new_signatures) - frozenset(
map(itemgetter(0), best_match))
remaining_personid_rows = ([
x for x in personid_rows if x[1:3] in old_signatures
])
pids_having_rec = set([int(row[0]) for row in remaining_personid_rows])
logger.log(" - Not matched: %s" % str(not_matched))
if not_matched:
used_pids = set(r[0] for r in personid_rows)
for sig in not_matched:
name = new_signatures_names[sig]
matchable_name = create_matchable_name(name)
matched_pids = list()
if USE_EXT_IDS:
matched_pids = get_matched_pids_by_external_ids(
sig, rec, pids_having_rec)
if matched_pids:
add_signature(list(sig) + [rec],
name,
matched_pids[0][0],
m_name=matchable_name)
M_NAME_PIDS_CACHE[matchable_name] = matched_pids[0][0]
updated_pids.add(matched_pids[0][0])
pids_having_rec.add(matched_pids[0][0])
continue
matched_pids = find_pids_by_matchable_name_with_cache(
matchable_name)
if not matched_pids:
for matching_function in M_NAME_FUNCTIONS[1:]:
matchable_name = matching_function(name)
matched_pids = find_pids_by_matchable_name_with_cache(
matchable_name)
if matched_pids:
break
matched_pids = [p for p in matched_pids if int(p) not in used_pids]
best_matched_pid = None
for matched_pid in matched_pids:
# Because of the wrongly labeled data in the db, all
# of the possible choices have to be checked. If one of the
# coauthors, who had his signature already considered, claimed
# in the past one of the signatures of currently considered
# author, the algorithm will think that two signatures belong
# to the same person, and, will create an unnecessary new
# profile.
if not int(matched_pid) in pids_having_rec:
best_matched_pid = matched_pid
break
if not best_matched_pid:
new_pid = new_person_from_signature(
list(sig) + [rec], name, matchable_name)
M_NAME_PIDS_CACHE[matchable_name] = new_pid
used_pids.add(new_pid)
updated_pids.add(new_pid)
else:
add_signature(list(sig) + [rec],
name,
best_matched_pid,
m_name=matchable_name)
M_NAME_PIDS_CACHE[matchable_name] = best_matched_pid
used_pids.add(best_matched_pid)
updated_pids.add(best_matched_pid)
pids_having_rec.add(best_matched_pid)
logger.log('Finished with %s' % str(rec))
logger.update_status_final()
destroy_partial_marc_caches()
if personids_to_update_extids:
updated_pids |= set(personids_to_update_extids)
if updated_pids: # an empty set will update all canonical_names
update_canonical_names_of_authors(updated_pids)
update_external_ids_of_authors(
updated_pids,
limit_to_claimed_papers=bconfig.
LIMIT_EXTERNAL_IDS_COLLECTION_TO_CLAIMED_PAPERS,
force_cache_tables=True)
destroy_partial_marc_caches()
destroy_mnames_pids_cache()
remove_empty_authors()
task_update_progress("Done!")
def rabbit(bibrecs, check_invalid_papers=False, personids_to_update_extids=None, verbose=False):
'''
@param bibrecs: an iterable full of bibrecs
@type bibrecs: an iterable of ints
@return: none
'''
logfile = open('/tmp/RABBITLOG-%s' % str(now()).replace(" ", "_"), 'w')
logfile.write("RABBIT %s running on %s \n" % (str(now()), str(bibrecs)))
def logwrite(msg, is_error):
verb = 9
if is_error or verbose:
verb = 1
write_message(msg, verbose=verb)
if bconfig.RABBIT_USE_CACHED_PID:
PID_NAMES_CACHE = get_name_to_authors_mapping()
def find_pids_by_exact_names_cache(name):
try:
return zip(PID_NAMES_CACHE[name])
except KeyError:
return []
def add_signature_using_names_cache(sig, name, pid):
try:
PID_NAMES_CACHE[name].add(pid)
except KeyError:
PID_NAMES_CACHE[name] = set([pid])
_add_signature(sig, name, pid)
def new_person_from_signature_using_names_cache(sig, name):
pid = get_free_author_id()
add_signature_using_names_cache(sig, name, pid)
return pid
add_signature = add_signature_using_names_cache
new_person_from_signature = new_person_from_signature_using_names_cache
find_pids_by_exact_name = find_pids_by_exact_names_cache
else:
add_signature = _add_signature
new_person_from_signature = _new_person_from_signature
find_pids_by_exact_name = _find_pids_by_exact_name
compare_names = cached_sym(lambda x: x)(comp_names)
# fast assign threshold
threshold = 0.80
if not bibrecs or check_invalid_papers:
all_bibrecs = get_all_valid_papers()
if not bibrecs:
bibrecs = all_bibrecs
if check_invalid_papers:
filter_bibrecs_outside(all_bibrecs)
if (bconfig.RABBIT_USE_CACHED_GET_GROUPED_RECORDS and
len(bibrecs) > bconfig.RABBIT_USE_CACHED_GET_GROUPED_RECORDS_THRESHOLD):
populate_partial_marc_caches()
SWAPPED_GET_GROUPED_RECORDS = True
else:
SWAPPED_GET_GROUPED_RECORDS = False
updated_pids = set()
deleted = frozenset(p[0] for p in get_deleted_papers())
for idx, rec in enumerate(bibrecs):
logwrite("\nConsidering %s" % str(rec), False)
if idx%200 == 0:
task_sleep_now_if_required(True)
update_status(float(idx) / len(bibrecs), "%d/%d current: %d" % (idx, len(bibrecs), rec))
task_update_progress("%d/%d current: %d" % (idx, len(bibrecs), rec))
if rec in deleted:
logwrite(" - Record was deleted, removing from pid and continuing with next record", True)
remove_papers([rec])
continue
markrefs = frozenset(chain(izip(cycle([100]), imap(itemgetter(0), get_author_refs_of_paper(rec))),
izip(cycle([700]), imap(itemgetter(0), get_coauthor_refs_of_paper(rec)))))
personid_rows = [map(int, row[:3]) + [row[4]] for row in get_signatures_of_paper(rec)]
personidrefs_names = dict(((row[1], row[2]), row[3]) for row in personid_rows)
personidrefs = frozenset(personidrefs_names.keys())
new_signatures = list(markrefs - personidrefs)
old_signatures = list(personidrefs - markrefs)
new_signatures_names = dict((new, create_normalized_name(split_name_parts(get_name_by_bibref(new))))
for new in new_signatures)
# matrix |new_signatures| X |old_signatures|
matrix = [[compare_names(new_signatures_names[new], personidrefs_names[old])
for old in old_signatures] for new in new_signatures]
logwrite(" - Old signatures: %s" % str(old_signatures), bool(old_signatures))
logwrite(" - New signatures: %s" % str(new_signatures), bool(new_signatures))
logwrite(" - Matrix: %s" % str(matrix), bool(matrix))
# [(new_signatures, old_signatures)]
best_match = [(new_signatures[new], old_signatures[old])
for new, old, score in maximized_mapping(matrix) if score > threshold]
logwrite(" - Best match: %s " % str(best_match), bool(best_match))
for new, old in best_match:
logwrite(" - - Moving signature: %s on %s to %s as %s" % (old, rec, new, new_signatures_names[new]), True)
modify_signature(old, rec, new, new_signatures_names[new])
remove_signatures(tuple(list(old) + [rec]) for old in old_signatures)
not_matched = frozenset(new_signatures) - frozenset(map(itemgetter(0), best_match))
pids_having_rec = set([int(row[0]) for row in get_signatures_of_paper(rec)])
logwrite(" - Not matched: %s" % str(not_matched), bool(not_matched))
if not_matched:
used_pids = set(r[0] for r in personid_rows)
for sig in not_matched:
name = new_signatures_names[sig]
matched_pids = list()
if USE_EXT_IDS:
if USE_INSPIREID:
inspire_id = get_inspire_id_of_signature(sig + (rec,))
if inspire_id:
matched_pids = list(get_author_by_external_id(inspire_id[0]))
if matched_pids and int(matched_pids[0][0]) in pids_having_rec:
matched_pids = list()
if matched_pids:
add_signature(list(sig) + [rec], name, matched_pids[0][0])
updated_pids.add(matched_pids[0][0])
pids_having_rec.add(matched_pids[0][0])
continue
matched_pids = find_pids_by_exact_name(name)
matched_pids = [p for p in matched_pids if int(p[0]) not in used_pids]
if not matched_pids or int(matched_pids[0][0]) in pids_having_rec:
new_pid = new_person_from_signature(list(sig) + [rec], name)
used_pids.add(new_pid)
updated_pids.add(new_pid)
else:
add_signature(list(sig) + [rec], name, matched_pids[0][0])
used_pids.add(matched_pids[0][0])
updated_pids.add(matched_pids[0][0])
pids_having_rec.add(matched_pids[0][0])
logwrite('Finished with %s' % str(rec), False)
update_status_final()
if personids_to_update_extids:
updated_pids |= personids_to_update_extids
if updated_pids: # an empty set will update all canonical_names
update_canonical_names_of_authors(updated_pids)
update_external_ids_of_authors(updated_pids, limit_to_claimed_papers=bconfig.LIMIT_EXTERNAL_IDS_COLLECTION_TO_CLAIMED_PAPERS)
if SWAPPED_GET_GROUPED_RECORDS:
destroy_partial_marc_caches()
remove_empty_authors()