comparison data_manager/kraken2_build_database.py @ 5:2f27f3b86827 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_build_kraken2_database/ commit 648fe4911ce49173697f314d70e63e0de95b7e66"

4:0eebe086fd58

from enum import Enum

try:
    # Python3
    from urllib.request import urlopen
except ImportError:
    from urllib2 import urlopen


DATA_TABLE_NAME = "kraken2_databases"


class KrakenDatabaseTypes(Enum):
    standard = 'standard'
    minikraken = 'minikraken'
    special = 'special'
    custom = 'custom'

    def __str__(self):

class Minikraken2Versions(Enum):
    v1 = 'v1'
    v2 = 'v2'

    def __str__(self):
        return self.value

        "minimizer-spaces", str(kraken2_args["minimizer_spaces"]),
        "load-factor", str(kraken2_args["load_factor"]),
    ])

    database_name = " ".join([
        "Standard",
        "(Created:",
        now + ",",
        "kmer-len=" + str(kraken2_args["kmer_len"]) + ",",
        "minimizer-len=" + str(kraken2_args["minimizer_len"]) + ",",
        "minimizer-spaces=" + str(kraken2_args["minimizer_spaces"]) + ")",

    }

    return data_table_entry


def kraken2_build_minikraken(minikraken2_version, target_directory, data_table_name=DATA_TABLE_NAME):

    now = datetime.datetime.utcnow().strftime("%Y-%m-%dT%H%M%SZ")

    database_value = "_".join([

    ])

    database_path = database_value

    # download the minikraken2 data
    src = urlopen(
        'ftp://ftp.ccb.jhu.edu/pub/data/kraken2_dbs/minikraken2_%s_8GB_201904_UPDATE.tgz'
        % minikraken2_version
    )
    with open('tmp_data.tar.gz', 'wb') as dst:
        shutil.copyfileobj(src, dst)
    # unpack the downloaded archive to the target directory
    with tarfile.open('tmp_data.tar.gz', 'r:gz') as fh:
        for member in fh.getmembers():

    parser.add_argument('--minimizer-spaces', dest='minimizer_spaces', default=6, help='minimizer spaces')
    parser.add_argument('--load-factor', dest='load_factor', type=float, default=0.7, help='load factor')
    parser.add_argument('--threads', dest='threads', default=1, help='threads')
    parser.add_argument('--database-type', dest='database_type', type=KrakenDatabaseTypes, choices=list(KrakenDatabaseTypes), required=True, help='type of kraken database to build')
    parser.add_argument('--minikraken2-version', dest='minikraken2_version', type=Minikraken2Versions, choices=list(Minikraken2Versions), help='MiniKraken2 version (only applies to --database-type minikraken)')
    parser.add_argument('--special-database-type', dest='special_database_type', type=SpecialDatabaseTypes, choices=list(SpecialDatabaseTypes), help='type of special database to build (only applies to --database-type special)')
    parser.add_argument('--custom-fasta', dest='custom_fasta', help='fasta file for custom database (only applies to --database-type custom)')
    parser.add_argument('--custom-database-name', dest='custom_database_name', help='Name for custom database (only applies to --database-type custom)')
    parser.add_argument('--skip-maps', dest='skip_maps', action='store_true', help='')
    parser.add_argument('--clean', dest='clean', action='store_true', help='Clean up extra files')

        else:
            raise

    data_manager_output = {}

    if str(args.database_type) == 'standard':
        kraken2_args = {
            "kmer_len": args.kmer_len,
            "minimizer_len": args.minimizer_len,
            "minimizer_spaces": args.minimizer_spaces,
            "load_factor": args.load_factor,

            "clean": args.clean,
        }
        data_manager_output = kraken2_build_standard(
            kraken2_args,
            target_directory,
        )
    elif str(args.database_type) == 'minikraken':
        data_manager_output = kraken2_build_minikraken(
            str(args.minikraken2_version),
            target_directory

5:2f27f3b86827

from enum import Enum

try:
    # Python3
    from urllib.request import urlopen
    from urllib.error import URLError
except ImportError:
    from urllib2 import urlopen
    from urllib2 import URLError


DATA_TABLE_NAME = "kraken2_databases"


class KrakenDatabaseTypes(Enum):
    standard_local_build = 'standard_local_build'
    standard_prebuilt = 'standard_prebuilt'
    minikraken = 'minikraken'
    special = 'special'
    custom = 'custom'

    def __str__(self):

class Minikraken2Versions(Enum):
    v1 = 'v1'
    v2 = 'v2'

    def __str__(self):
        return self.value


class StandardPrebuiltSizes(Enum):
    full = 'full'
    gb_16 = '16'
    gb_8 = '8'

    def __str__(self):
        return self.value

        "minimizer-spaces", str(kraken2_args["minimizer_spaces"]),
        "load-factor", str(kraken2_args["load_factor"]),
    ])

    database_name = " ".join([
        "Standard (Local Build)",
        "(Created:",
        now + ",",
        "kmer-len=" + str(kraken2_args["kmer_len"]) + ",",
        "minimizer-len=" + str(kraken2_args["minimizer_len"]) + ",",
        "minimizer-spaces=" + str(kraken2_args["minimizer_spaces"]) + ")",

    }

    return data_table_entry


def kraken2_build_standard_prebuilt(standard_prebuilt_size, prebuilt_date, target_directory, data_table_name=DATA_TABLE_NAME):

    now = datetime.datetime.utcnow().strftime("%Y-%m-%dT%H%M%SZ")

    database_value = "_".join([
        now,
        "standard_prebuilt",
        standard_prebuilt_size
    ])

    database_name = " ".join([
        "Standard (Prebuilt)",
        standard_prebuilt_size,
        "(Downloaded:",
        now + ")"
    ])

    database_path = database_value

    size_to_url_str = {
        'full': '',
        '16': '_16gb',
        '8': '_8gb',
    }
    # we may need to let the user choose the date when new DBs are posted.
    date_url_str = prebuilt_date.replace('-', '')
    standard_prebuilt_size_url = size_to_url_str[standard_prebuilt_size]
    # download the pre-built database
    try:
        download_url = 'https://genome-idx.s3.amazonaws.com/kraken/k2_standard%s_%s.tar.gz' % (standard_prebuilt_size_url, date_url_str)
        src = urlopen(download_url)
    except URLError as e:
        print('url: ' + download_url, file=sys.stderr)
        print(e, file=sys.stderr)
        exit(1)

    with open('tmp_data.tar.gz', 'wb') as dst:
        shutil.copyfileobj(src, dst)
    # unpack the downloaded archive to the target directory
    with tarfile.open('tmp_data.tar.gz', 'r:gz') as fh:
        for member in fh.getmembers():
            if member.isreg():
                member.name = os.path.basename(member.name)
                fh.extract(member, os.path.join(target_directory, database_path))

    data_table_entry = {
        'data_tables': {
            data_table_name: [
                {
                    "value": database_value,
                    "name": database_name,
                    "path": database_path,
                }
            ]
        }
    }

    return data_table_entry


def kraken2_build_minikraken(minikraken2_version, target_directory, data_table_name=DATA_TABLE_NAME):

    now = datetime.datetime.utcnow().strftime("%Y-%m-%dT%H%M%SZ")

    database_value = "_".join([

    ])

    database_path = database_value

    # download the minikraken2 data
    try:
        download_url = 'https://genome-idx.s3.amazonaws.com/kraken/minikraken2_%s_8GB_201904.tgz' % minikraken2_version
        src = urlopen(download_url)
    except URLError as e:
        print('url: ' + download_url, file=sys.stderr)
        print(e, file=sys.stderr)
        exit(1)

    with open('tmp_data.tar.gz', 'wb') as dst:
        shutil.copyfileobj(src, dst)
    # unpack the downloaded archive to the target directory
    with tarfile.open('tmp_data.tar.gz', 'r:gz') as fh:
        for member in fh.getmembers():

    parser.add_argument('--minimizer-spaces', dest='minimizer_spaces', default=6, help='minimizer spaces')
    parser.add_argument('--load-factor', dest='load_factor', type=float, default=0.7, help='load factor')
    parser.add_argument('--threads', dest='threads', default=1, help='threads')
    parser.add_argument('--database-type', dest='database_type', type=KrakenDatabaseTypes, choices=list(KrakenDatabaseTypes), required=True, help='type of kraken database to build')
    parser.add_argument('--minikraken2-version', dest='minikraken2_version', type=Minikraken2Versions, choices=list(Minikraken2Versions), help='MiniKraken2 version (only applies to --database-type minikraken)')
    parser.add_argument('--standard-prebuilt-size', dest='standard_prebuilt_size', type=StandardPrebuiltSizes, choices=list(StandardPrebuiltSizes), help='Size of standard prebuilt database to download (only applies to --database-type standard_prebuilt. Options are: "8", "16", "full".)')
    parser.add_argument('--prebuilt-date', dest='prebuilt_date', help='Database build date (YYYY-MM-DD). Only applies to --database-type standard_prebuilt.')
    parser.add_argument('--special-database-type', dest='special_database_type', type=SpecialDatabaseTypes, choices=list(SpecialDatabaseTypes), help='type of special database to build (only applies to --database-type special)')
    parser.add_argument('--custom-fasta', dest='custom_fasta', help='fasta file for custom database (only applies to --database-type custom)')
    parser.add_argument('--custom-database-name', dest='custom_database_name', help='Name for custom database (only applies to --database-type custom)')
    parser.add_argument('--skip-maps', dest='skip_maps', action='store_true', help='')
    parser.add_argument('--clean', dest='clean', action='store_true', help='Clean up extra files')

        else:
            raise

    data_manager_output = {}

    if str(args.database_type) == 'standard_local_build':
        kraken2_args = {
            "kmer_len": args.kmer_len,
            "minimizer_len": args.minimizer_len,
            "minimizer_spaces": args.minimizer_spaces,
            "load_factor": args.load_factor,

            "clean": args.clean,
        }
        data_manager_output = kraken2_build_standard(
            kraken2_args,
            target_directory,
        )
    elif str(args.database_type) == 'standard_prebuilt':
        data_manager_output = kraken2_build_standard_prebuilt(
            str(args.standard_prebuilt_size),
            str(args.prebuilt_date),
            target_directory
        )
    elif str(args.database_type) == 'minikraken':
        data_manager_output = kraken2_build_minikraken(
            str(args.minikraken2_version),
            target_directory