示例#1
0
 def handle(self, *args, **options):
     load_essays(settings.ESSAYS_FEED, index=True)
示例#2
0
 def handle(self, *args, **options):
     load_essays(settings.ESSAYS_FEED, index=True)
示例#3
0
    def handle(self, *args, **options):
        start = datetime.now()

        _logger.info("Starting title sync process.")
        # only load titles if the BIB_STORAGE is there, not always the case
        # for folks in the opensource world
        bib_isdir = os.path.isdir(settings.BIB_STORAGE)
        bib_hasattr = hasattr(settings, "BIB_STORAGE")
        bib_settings = bool(bib_hasattr and bib_isdir)
        if bib_settings:
            bib_storage = settings.BIB_STORAGE
            worldcat_dir = bib_storage + '/worldcat_titles/'

            pull_titles = bool(options['pull_title_updates'] and hasattr(settings, "WORLDCAT_KEY"))
            if pull_titles:
                call_command('pull_titles',)

            _logger.info("Starting load of OCLC titles.")
            bulk_dir = worldcat_dir + 'bulk'
            if os.path.isdir(bulk_dir):
                call_command('load_titles', bulk_dir, skip_index=True)

            tnu = self.find_titles_not_updated()

            # Only update by individual lccn if there are records that need updating.
            if pull_titles and len(tnu):
                _logger.info("Pulling titles from OCLC by individual lccn & oclc num.")
                self.pull_lccn_updates(tnu)

            _logger.info("Loading titles from second title pull.")
            lccn_dir = worldcat_dir + 'lccn'
            if os.path.isdir(lccn_dir):
                call_command('load_titles', lccn_dir, skip_index=True)

            tnu = self.find_titles_not_updated(limited=False)
            _logger.info("Running pre-deletion checks for these titles.")

        # Make sure that our essays are up to date
        if not options['skip_essays']:
            load_essays(settings.ESSAYS_FEED)

        if bib_settings:
            if len(tnu):
                # Delete titles haven't been update & do not have essays or issues attached.
                for title in tnu:
                    essays = title.essays.all()
                    issues = title.issues.all()

                    error = "DELETION ERROR: Title %s has " % title
                    error_end = "It will not be deleted."

                    if not essays or not issues:
                        delete_txt = (title.name, title.lccn, title.oclc)
                        _logger.info('TITLE DELETED: %s, lccn: %s, oclc: %s' % delete_txt)
                        title.delete()
                    elif essays:
                        _logger.warning(error + 'essays.' + error_end)
                        continue
                    elif issues:
                        _logger.warning(error + 'issues.' + error_end)
                        continue

            # Load holdings for all remaining titles.
            holdings_dir = settings.BIB_STORAGE + '/holdings'
            call_command('load_holdings', holdings_dir)

        # overlay place info harvested from dbpedia onto the places table
        try:
            self.load_place_links()
        except Exception, e:
            _logger.exception(e)
示例#4
0
    def handle(self, *args, **options):
        start = datetime.now()

        LOGGER.info("Starting title sync process.")
        # only load titles if the BIB_STORAGE is there, not always the case
        # for folks in the opensource world
        bib_in_settings = validate_bib_dir()
        if bib_in_settings:
            worldcat_dir = bib_in_settings + '/worldcat_titles/'

            pull_titles = bool(options['pull_title_updates']
                               and hasattr(settings, "WORLDCAT_KEY"))
            if pull_titles:
                call_command('pull_titles')

            LOGGER.info("Starting load of OCLC titles.")
            bulk_dir = worldcat_dir + 'bulk'
            if os.path.isdir(bulk_dir):
                call_command('load_titles', bulk_dir, skip_index=True)

            tnu = self.find_titles_not_updated()

            # Only update by individual lccn if there are records that need updating.
            if pull_titles and len(tnu):
                LOGGER.info(
                    "Pulling titles from OCLC by individual lccn & oclc num.")
                self.pull_lccn_updates(tnu)

            LOGGER.info("Loading titles from second title pull.")
            lccn_dir = worldcat_dir + 'lccn'
            if os.path.isdir(lccn_dir):
                call_command('load_titles', lccn_dir, skip_index=True)

            tnu = self.find_titles_not_updated(limited=False)
            LOGGER.info("Running pre-deletion checks for these titles.")

        # Make sure that our essays are up to date
        if not options['skip_essays']:
            load_essays(settings.ESSAYS_FEED)

        if bib_in_settings:
            if len(tnu):
                # Delete titles haven't been update & do not have essays or issues attached.
                for title in tnu:
                    essays = title.essays.all()
                    issues = title.issues.all()

                    error = "DELETION ERROR: Title %s has " % title
                    error_end = "It will not be deleted."

                    if not essays or not issues:
                        delete_txt = (title.name, title.lccn, title.oclc)
                        LOGGER.info('TITLE DELETED: %s, lccn: %s, oclc: %s' %
                                    delete_txt)
                        title.delete()
                    elif essays:
                        LOGGER.warning(error + 'essays.' + error_end)
                        continue
                    elif issues:
                        LOGGER.warning(error + 'issues.' + error_end)
                        continue

            # Load holdings for all remaining titles.
            call_command('load_holdings')

        # overlay place info harvested from dbpedia onto the places table
        try:
            self.load_place_links()
        except Exception as e:
            LOGGER.exception(e)

        index.index_titles()

        # Time of full process run
        end = datetime.now()
        total_time = end - start
        LOGGER.info('start time: %s' % start)
        LOGGER.info('end time: %s' % end)
        LOGGER.info('total time: %s' % total_time)
        LOGGER.info("title_sync done.")