Python Resources.sec_ac方法代码示例

# 需要导入模块: from resources import Resources [as 别名]
# 或者: from resources.Resources import sec_ac [as 别名]
def main(resource_directory=None, cron=False, no_download=False):
    """ Overview:
        Collect resources
        Display info on missing ones
        Ask - Download missing ones
        Ask - Insert new GO editions
        Ask - Insert new GOA editions
        Ask - Update sec_ac
        Ask - preprocess
    """

    # Connect to database
    gotrack = gtdb.GOTrack(cursorclass=MySQLdb.cursors.SSCursor, **CREDS)
    LOG.info("Connected to host: %s, db: %s, user: %s", CREDS['host'], CREDS['db'], CREDS['user'])

    # Collect current state of resources
    if resource_directory is None:
        resource_directory = tempfile.mkdtemp()
        LOG.warn("No resource directory specified. Creating temporary folder at %s", resource_directory)

    check_ftp = not no_download and (cron or query_yes_no("Check FTP sites for new data?"))
    res = Resources(resource_directory, gotrack.fetch_current_state(), check_ftp)

    # Display current state of resource directory, database, and ftp site
    LOG.info(res)

    # if cron, force download of accession history file
    res.sec_ac = None if cron else res.sec_ac

    # Deal with missing data
    if res.ftp_checked and res.is_missing_data():
        missing_cnt = len(res.missing_go)
        if missing_cnt:
            LOG.warn("Missing %s GO Versions from FTP", missing_cnt)
            if cron or query_yes_no("Download missing GO Versions?"):
                res.download_missing_go_data()

        missing_cnt = sum([len(goa_sp) for goa_sp in res.missing_goa.values()])
        if missing_cnt:
            LOG.warn("Missing %s GOA Editions from FTP", missing_cnt)
            if cron or query_yes_no("Download missing GOA Editions?"):
                res.download_missing_goa_data()

        if not res.sec_ac:
            LOG.warn("Missing secondary accession file (sec_ac.txt)")
            if cron or query_yes_no("Download missing secondary accession file?"):
                res.download_accession_history(skip_if_exists=not cron)

        LOG.info("Re-checking state of resource directory")
        res.populate_existing_files()
        res.populate_missing_data()
        LOG.info(res)

        if res.is_missing_data() or not (cron or query_yes_no("Continue with updates?")):
            return

    # Insert new GO data
    new_go = res.get_new_go()
    if new_go:
        LOG.info("New GO Versions ready to update: %s", len(new_go))
        if cron or query_yes_no("Update GO tables? (Affected tables: '{go_edition}', '{go_term}', "
                                "'{go_adjacency}', '{go_alternate}')".format(**gotrack.tables)):
            for go_date in sorted(new_go.keys()):
                go_file = new_go[go_date]
                LOG.info("Begin: %s", go_date.strftime('%Y-%m-%d'))
                ont = Ontology.from_file_data(go_date, go_file)
                gotrack.update_go_tables(ont)

        newest_go_date = max(new_go)
        LOG.info("Newest ontology available for GO definitions: %s", newest_go_date.strftime('%Y-%m-%d'))
        if cron or query_yes_no("Update GO definitions with this ontology? (Affected tables: '{go_definition}'"
                                .format(**gotrack.tables)):
            ont = Ontology.from_file_data(newest_go_date, new_go[newest_go_date])
            gotrack.update_current_go_definitions(ont)

    else:
        LOG.info("There are no new GO Versions available to update")

    # Insert new GOA data
    new_goa = res.get_new_goa()
    new_goa_cnt = sum([len(goa_sp) for goa_sp in new_goa.values()])
    if new_goa_cnt:
        LOG.info("New GOA Editions ready to update: %s", new_goa_cnt)
        if cron or query_yes_no("Update GOA tables? (Affected tables: '{edition}', "
                                "'{accession}', '{annotation}', '{synonyms}')".format(**gotrack.tables)):
            goa_skipped = []
            for species, goa_eds in new_goa.iteritems():
                LOG.info("Begin Species: %s", species)
                sp_id = res.sp_map[species]

                for edition in sorted(goa_eds.keys()):
                    LOG.info("Edition: %s", edition)
                    gpa_file, gpi_file = goa_eds[edition]

                    meta = parsers.check_goa_gpa(gpa_file)

                    if meta is None:
                        LOG.warn('Skipping edition %s for species %s', edition, species)
                        goa_skipped.append((edition,species))
                        continue
#.........这里部分代码省略.........