def _run_personid_gc(paperslist, all_records=False): # insert_user_log('daemon', '-1', 'PGC', 'bibsched', 'status', # comment='bibauthorid_daemon, personid_gc (update_personid_from_papers) on ' # + str(paperslist)) if not paperslist and all_records: #update_authornames_tables_from_paper() insert_user_log('daemon', '-1', 'PGC', 'bibsched', 'status', comment='bibauthorid_daemon, personid_gc (update_personid_from_papers) on all papers') update_personID_table_from_paper() elif not paperslist: last_log = get_user_log(userinfo='daemon', action='PGC', only_most_recent=True) if len(last_log) >= 1: #select only the most recent papers recently_modified, min_date = get_papers_recently_modified(date=last_log[0][2]) insert_user_log('daemon', '-1', 'PGC', 'bibsched', 'status', comment='bibauthorid_daemon, update_personid_from_papers on ' + str([paperslist, all_records, recently_modified]), timestamp=min_date[0][0]) if not recently_modified: bibtask.write_message("update_personID_table_from_paper: " "All person entities up to date.", stream=sys.stdout, verbose=0) else: bibtask.write_message("update_personID_table_from_paper: Running on: " + str(recently_modified), stream=sys.stdout, verbose=0) personid_fast_assign_papers(recently_modified) else: insert_user_log('daemon', '-1', 'PGC', 'bibsched', 'status', comment='bibauthorid_daemon, personid_gc (update_personid_from_papers) on all papers') update_personID_table_from_paper() else: insert_user_log('daemon', '-1', 'PGC', 'bibsched', 'status', comment='bibauthorid_daemon, personid_gc (update_personid_from_papers) on ' + str(paperslist)) update_authornames_tables_from_paper(paperslist) update_personID_table_from_paper(paperslist)
def _run_update_personID_table_from_paper(record_ids=None, all_records=False): ''' Runs the update on the papers which have been modified since the last run This is removing no-longer existing papers from the personid table. @note: Update recommended monthly. @warning: quite resource intensive. ''' if not record_ids and not all_records: last_log = get_user_log(userinfo='daemon', action='UPITFP', only_most_recent=True) if len(last_log) >= 1: #select only the most recent papers recently_modified, min_date = get_papers_recently_modified(date=last_log[0][2]) insert_user_log('daemon', '-1', 'UPITFP', 'bibsched', 'status', comment='bibauthorid_daemon, update_personID_table_from_paper', timestamp=min_date[0][0]) if not recently_modified: bibtask.write_message("update_personID_table_from_paper: " "All person entities up to date.", stream=sys.stdout, verbose=0) else: bibtask.write_message("update_personID_table_from_paper: Running on: " + str(recently_modified), stream=sys.stdout, verbose=0) update_personID_table_from_paper(recently_modified) else: # Should not process all papers, hence authornames population writes # the appropriate log. In case the log is missing, process everything. recently_modified, min_date = get_papers_recently_modified() insert_user_log('daemon', '-1', 'UPITFP', 'bibsched', 'status', comment='bibauthorid_daemon, update_personID_table_from_paper', timestamp=min_date[0][0]) bibtask.write_message("update_personID_table_from_paper: Running on: " + str(recently_modified), stream=sys.stdout, verbose=0) update_personID_table_from_paper(recently_modified) else: update_personID_table_from_paper(record_ids)