Mercurial > repos > devteam > data_manager_fetch_genome_dbkeys_all_fasta
changeset 4:60994ca04177 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_fetch_genome_dbkeys_all_fasta commit 8652f36a3a3838dca989426961561e81432acf4f
author | iuc |
---|---|
date | Tue, 04 Apr 2017 17:13:31 -0400 (2017-04-04) |
parents | 86fa71e9b427 |
children | a246b4f11133 |
files | data_manager/data_manager_fetch_genome_all_fasta_dbkeys.py data_manager/data_manager_fetch_genome_all_fasta_dbkeys.xml test-data/test.tar test-data/test.tar.gz test-data/test.zip |
diffstat | 5 files changed, 256 insertions(+), 210 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/data_manager_fetch_genome_all_fasta_dbkeys.py Fri Aug 26 12:46:47 2016 -0400 +++ b/data_manager/data_manager_fetch_genome_all_fasta_dbkeys.py Tue Apr 04 17:13:31 2017 -0400 @@ -1,35 +1,36 @@ #!/usr/bin/env python -#Dan Blankenberg +# Dan Blankenberg -import sys +import bz2 +import gzip +import optparse import os -import tempfile import shutil -import optparse -from ftplib import FTP +import sys import tarfile +import tempfile import zipfile -import gzip -import bz2 +from ftplib import FTP +from json import dumps, loads + try: # For Python 3.0 and later - from urllib.request import urlopen from io import BytesIO as StringIO from io import UnsupportedOperation + from urllib.request import urlopen except ImportError: - # Fall back to Python 2's urllib2 + # Fall back to Python 2 imports + from StringIO import StringIO from urllib2 import urlopen - from StringIO import StringIO + UnsupportedOperation = AttributeError -from json import loads, dumps + +CHUNK_SIZE = 2 ** 20 # 1mb -CHUNK_SIZE = 2**20 # 1mb - - -def cleanup_before_exit( tmp_dir ): - if tmp_dir and os.path.exists( tmp_dir ): - shutil.rmtree( tmp_dir ) +def cleanup_before_exit(tmp_dir): + if tmp_dir and os.path.exists(tmp_dir): + shutil.rmtree(tmp_dir) def stop_err(msg): @@ -37,20 +38,20 @@ sys.exit(1) -def get_dbkey_dbname_id_name( params, dbkey_description=None ): +def get_dbkey_dbname_id_name(params, dbkey_description=None): dbkey = params['param_dict']['dbkey_source']['dbkey'] - #TODO: ensure sequence_id is unique and does not already appear in location file + # TODO: ensure sequence_id is unique and does not already appear in location file sequence_id = params['param_dict']['sequence_id'] if not sequence_id: - sequence_id = dbkey #uuid.uuid4() generate and use an uuid instead? - + sequence_id = dbkey # uuid.uuid4() generate and use an uuid instead? + if params['param_dict']['dbkey_source']['dbkey_source_selector'] == 'new': dbkey_name = params['param_dict']['dbkey_source']['dbkey_name'] if not dbkey_name: dbkey_name = dbkey else: dbkey_name = None - + sequence_name = params['param_dict']['sequence_name'] if not sequence_name: sequence_name = dbkey_description @@ -59,146 +60,146 @@ return dbkey, dbkey_name, sequence_id, sequence_name -def _get_files_in_ftp_path( ftp, path ): +def _get_files_in_ftp_path(ftp, path): path_contents = [] - ftp.retrlines( 'MLSD %s' % ( path ), path_contents.append ) - return [ line.split( ';' )[ -1 ].lstrip() for line in path_contents ] + ftp.retrlines('MLSD %s' % (path), path_contents.append) + return [line.split(';')[-1].lstrip() for line in path_contents] -def _get_stream_readers_for_tar( fh, tmp_dir ): - fasta_tar = tarfile.open( fileobj=fh, mode='r:*' ) +def _get_stream_readers_for_tar(fh, tmp_dir): + fasta_tar = tarfile.open(fileobj=fh, mode='r:*') return [x for x in [fasta_tar.extractfile(member) for member in fasta_tar.getmembers()] if x] -def _get_stream_readers_for_zip( fh, tmp_dir ): +def _get_stream_readers_for_zip(fh, tmp_dir): """ Unpacks all archived files in a zip file. Individual files will be concatenated (in _stream_fasta_to_file) """ - fasta_zip = zipfile.ZipFile( fh, 'r' ) + fasta_zip = zipfile.ZipFile(fh, 'r') rval = [] for member in fasta_zip.namelist(): - fasta_zip.extract( member, tmp_dir ) - rval.append( open( os.path.join( tmp_dir, member ), 'rb' ) ) + fasta_zip.extract(member, tmp_dir) + rval.append(open(os.path.join(tmp_dir, member), 'rb')) return rval -def _get_stream_readers_for_gzip( fh, tmp_dir ): - return [ gzip.GzipFile( fileobj=fh, mode='rb') ] +def _get_stream_readers_for_gzip(fh, tmp_dir): + return [gzip.GzipFile(fileobj=fh, mode='rb')] -def _get_stream_readers_for_bz2( fh, tmp_dir ): - return [ bz2.BZ2File( fh.name, 'rb') ] +def _get_stream_readers_for_bz2(fh, tmp_dir): + return [bz2.BZ2File(fh.name, 'rb')] -def sort_fasta( fasta_filename, sort_method, params ): +def sort_fasta(fasta_filename, sort_method, params): if sort_method is None: return - assert sort_method in SORTING_METHODS, ValueError( "%s is not a valid sorting option." % sort_method ) - return SORTING_METHODS[ sort_method ]( fasta_filename, params ) + assert sort_method in SORTING_METHODS, ValueError("%s is not a valid sorting option." % sort_method) + return SORTING_METHODS[sort_method](fasta_filename, params) -def _move_and_index_fasta_for_sorting( fasta_filename ): +def _move_and_index_fasta_for_sorting(fasta_filename): unsorted_filename = tempfile.NamedTemporaryFile().name - shutil.move( fasta_filename, unsorted_filename ) + shutil.move(fasta_filename, unsorted_filename) fasta_offsets = {} - unsorted_fh = open( unsorted_filename ) + unsorted_fh = open(unsorted_filename) while True: offset = unsorted_fh.tell() line = unsorted_fh.readline() if not line: break - if line.startswith( ">" ): - line = line.split( None, 1 )[0][1:] - fasta_offsets[ line ] = offset + if line.startswith(">"): + line = line.split(None, 1)[0][1:] + fasta_offsets[line] = offset unsorted_fh.close() - current_order = map( lambda x: x[1], sorted( map( lambda x: ( x[1], x[0] ), fasta_offsets.items() ) ) ) - return ( unsorted_filename, fasta_offsets, current_order ) + current_order = [_[1] for _ in sorted((_[1], _[0]) for _ in fasta_offsets.items())] + return (unsorted_filename, fasta_offsets, current_order) -def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ): - unsorted_fh = open( unsorted_fasta_filename ) - sorted_fh = open( sorted_fasta_filename, 'wb+' ) - +def _write_sorted_fasta(sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename): + unsorted_fh = open(unsorted_fasta_filename) + sorted_fh = open(sorted_fasta_filename, 'wb+') + for name in sorted_names: - offset = fasta_offsets[ name ] - unsorted_fh.seek( offset ) - sorted_fh.write( unsorted_fh.readline() ) + offset = fasta_offsets[name] + unsorted_fh.seek(offset) + sorted_fh.write(unsorted_fh.readline()) while True: line = unsorted_fh.readline() - if not line or line.startswith( ">" ): + if not line or line.startswith(">"): break - sorted_fh.write( line ) + sorted_fh.write(line) unsorted_fh.close() sorted_fh.close() -def _sort_fasta_as_is( fasta_filename, params ): +def _sort_fasta_as_is(fasta_filename, params): return -def _sort_fasta_lexicographical( fasta_filename, params ): - ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename ) - sorted_names = sorted( fasta_offsets.keys() ) + +def _sort_fasta_lexicographical(fasta_filename, params): + (unsorted_filename, fasta_offsets, current_order) = _move_and_index_fasta_for_sorting(fasta_filename) + sorted_names = sorted(fasta_offsets.keys()) if sorted_names == current_order: - shutil.move( unsorted_filename, fasta_filename ) + shutil.move(unsorted_filename, fasta_filename) else: - _write_sorted_fasta( sorted_names, fasta_offsets, fasta_filename, unsorted_filename ) + _write_sorted_fasta(sorted_names, fasta_offsets, fasta_filename, unsorted_filename) -def _sort_fasta_gatk( fasta_filename, params ): - #This method was added by reviewer request. - ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename ) - sorted_names = map( str, range( 1, 23 ) ) + [ 'X', 'Y' ] - #detect if we have chrN, or just N +def _sort_fasta_gatk(fasta_filename, params): + (unsorted_filename, fasta_offsets, current_order) = _move_and_index_fasta_for_sorting(fasta_filename) + sorted_names = list(map(str, range(1, 23))) + ['X', 'Y'] + # detect if we have chrN, or just N has_chr = False for chrom in sorted_names: if "chr%s" % chrom in current_order: has_chr = True break - + if has_chr: - sorted_names = map( lambda x: "chr%s" % x, sorted_names) - sorted_names.insert( 0, "chrM" ) + sorted_names = ["chr%s" % x for x in sorted_names] + sorted_names.insert(0, "chrM") else: - sorted_names.insert( 0, "MT" ) - sorted_names.extend( map( lambda x: "%s_random" % x, sorted_names ) ) - + sorted_names.insert(0, "MT") + sorted_names.extend("%s_random" % x for x in sorted_names) + existing_sorted_names = [] for name in sorted_names: if name in current_order: - existing_sorted_names.append( name ) + existing_sorted_names.append(name) for name in current_order: - #TODO: confirm that non-canonical names do not need to be sorted specially + # TODO: confirm that non-canonical names do not need to be sorted specially if name not in existing_sorted_names: - existing_sorted_names.append( name ) - + existing_sorted_names.append(name) + if existing_sorted_names == current_order: - shutil.move( unsorted_filename, fasta_filename ) + shutil.move(unsorted_filename, fasta_filename) else: - _write_sorted_fasta( existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename ) + _write_sorted_fasta(existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename) -def _sort_fasta_custom( fasta_filename, params ): - ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename ) +def _sort_fasta_custom(fasta_filename, params): + (unsorted_filename, fasta_offsets, current_order) = _move_and_index_fasta_for_sorting(fasta_filename) sorted_names = [] for id_repeat in params['param_dict']['sorting']['sequence_identifiers']: - sorted_names.append( id_repeat[ 'identifier' ] ) + sorted_names.append(id_repeat['identifier']) handle_not_listed = params['param_dict']['sorting']['handle_not_listed_selector'] - if handle_not_listed.startswith( 'keep' ): + if handle_not_listed.startswith('keep'): add_list = [] for name in current_order: if name not in sorted_names: - add_list.append( name ) + add_list.append(name) if add_list: if handle_not_listed == 'keep_append': - sorted_names.extend( add_list ) + sorted_names.extend(add_list) else: - add_list.extend( sorted_names ) + add_list.extend(sorted_names) sorted_names = add_list if sorted_names == current_order: - shutil.move( unsorted_filename, fasta_filename ) + shutil.move(unsorted_filename, fasta_filename) else: - _write_sorted_fasta( sorted_names, fasta_offsets, fasta_filename, unsorted_filename ) + _write_sorted_fasta(sorted_names, fasta_offsets, fasta_filename, unsorted_filename) def _download_file(start, fh): @@ -223,17 +224,17 @@ start_of_file = fh.read(CHUNK_SIZE) try: fh.seek(0) - except UnsupportedOperation: # This is if fh has been created by urlopen + except UnsupportedOperation: # This happens if fh has been created by urlopen fh = _download_file(start_of_file, fh) - for k,v in magic_dict.items(): - if start_of_file.startswith(k): - return v(fh, tmp_dir) try: # Check if file is tar file if tarfile.open(fileobj=StringIO(start_of_file)): return _get_stream_readers_for_tar(fh, tmp_dir) except tarfile.ReadError: pass - return fh + for k, v in magic_dict.items(): + if start_of_file.startswith(k): + return v(fh, tmp_dir) + return [fh] def _get_ucsc_download_address(params, dbkey): @@ -266,82 +267,126 @@ raise Exception('Unable to determine filename for UCSC Genome for %s: %s' % (ucsc_dbkey, path_contents)) -def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params): - for data_table_name, data_table_entry in _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ): - if data_table_entry: - _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name ) + +def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, **kwds): + fasta_filename = _stream_fasta_to_file(fasta_stream=fasta_readers, + target_directory=target_directory, + sequence_id=sequence_id) + sort_fasta(fasta_filename, params['param_dict']['sorting']['sort_selector'], params) + if dbkey_name: + add_dbkey_to_table(data_manager_dict=data_manager_dict, + target_directory=target_directory, + dbkey=dbkey, + dbkey_name=dbkey_name, + fasta_filename=fasta_filename) + _add_data_table_entry(data_manager_dict, + data_table_entry=dict(value=sequence_id, dbkey=dbkey, name=sequence_name, path=os.path.basename(fasta_filename)), + data_table_name='all_fasta') + return fasta_filename -def download_from_ucsc( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): - url = _get_ucsc_download_address(params, dbkey) - fasta_readers = get_stream_reader(urlopen(url), tmp_dir) - add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params) +def add_dbkey_to_table(data_manager_dict, target_directory, dbkey, dbkey_name, fasta_filename): + # do len calc here + len_base_name = "%s.len" % (dbkey) + compute_fasta_length(fasta_filename, os.path.join(target_directory, len_base_name), keep_first_word=True) + dbkey_dict = dict(value=dbkey, name=dbkey_name, len_path=len_base_name) + _add_data_table_entry(data_manager_dict, + data_table_entry=dbkey_dict, + data_table_name='__dbkeys__') -def download_from_ncbi( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): - NCBI_DOWNLOAD_URL = 'http://togows.dbcls.jp/entry/ncbi-nucleotide/%s.fasta' #FIXME: taken from dave's genome manager...why some japan site? +def download_from_ucsc(params, dbkey, tmp_dir, **kwds): + url = _get_ucsc_download_address(params, dbkey) + return get_stream_reader(urlopen(url), tmp_dir) + + +def download_from_ncbi(params, tmp_dir, **kwds): + NCBI_DOWNLOAD_URL = 'http://togows.dbcls.jp/entry/ncbi-nucleotide/%s.fasta' # FIXME: taken from dave's genome manager...why some japan site? requested_identifier = params['param_dict']['reference_source']['requested_identifier'] url = NCBI_DOWNLOAD_URL % requested_identifier - fasta_readers = get_stream_reader(urlopen(url), tmp_dir) - add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params) - - -def download_from_url( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): - urls = filter( bool, map( lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split( '\n' ) ) ) - fasta_readers = [ get_stream_reader(urlopen( url ), tmp_dir) for url in urls ] - add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params) + return get_stream_reader(urlopen(url), tmp_dir) -def download_from_history( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): - #TODO: allow multiple FASTA input files +def download_from_url(params, tmp_dir, **kwds): + """ + Download a file from a URL and return a list of filehandles from which to read the data. + + >>> url = 'https://github.com/mvdbeek/tools-devteam/raw/data_manager/data_managers/data_manager_fetch_genome_dbkeys_all_fasta/test-data/test.tar' + >>> params = {'param_dict': {'reference_source': {'user_url': url}}} + >>> tmp_dir = tempfile.mkdtemp() + >>> fh = download_from_url(params=params, tmp_dir=tmp_dir)[0][0] + >>> assert fh.readline().startswith('>FBtr0304171') + >>> url = 'https://github.com/mvdbeek/tools-devteam/raw/data_manager/data_managers/data_manager_fetch_genome_dbkeys_all_fasta/test-data/test.tar.bz2' + >>> params = {'param_dict': {'reference_source': {'user_url': url}}} + >>> fh = download_from_url(params=params, tmp_dir=tmp_dir)[0][0] + >>> assert fh.readline().startswith('>FBtr0304171') + >>> url = 'https://github.com/mvdbeek/tools-devteam/raw/data_manager/data_managers/data_manager_fetch_genome_dbkeys_all_fasta/test-data/test.tar.gz' + >>> params = {'param_dict': {'reference_source': {'user_url': url}}} + >>> fh = download_from_url(params=params, tmp_dir=tmp_dir)[0][0] + >>> assert fh.readline().startswith('>FBtr0304171') + >>> url = 'https://github.com/mvdbeek/tools-devteam/raw/data_manager/data_managers/data_manager_fetch_genome_dbkeys_all_fasta/test-data/test.zip' + >>> params = {'param_dict': {'reference_source': {'user_url': url}}} + >>> fh = download_from_url(params=params, tmp_dir=tmp_dir)[0][0] + >>> assert fh.readline().startswith('>FBtr0304171') + >>> url = 'https://raw.githubusercontent.com/galaxyproject/tools-devteam/master/data_managers/data_manager_fetch_genome_dbkeys_all_fasta/test-data/phiX174.fasta' + >>> params = {'param_dict': {'reference_source': {'user_url': url}}} + >>> fh = download_from_url(params=params, tmp_dir=tmp_dir)[0][0] + >>> assert fh.readline().startswith('>phiX174') + """ + urls = filter(bool, [x.strip() for x in params['param_dict']['reference_source']['user_url'].split('\n')]) + return [get_stream_reader(urlopen(url), tmp_dir) for url in urls] + + +def download_from_history(params, tmp_dir, **kwds): + # TODO: allow multiple FASTA input files input_filename = params['param_dict']['reference_source']['input_fasta'] - if isinstance( input_filename, list ): - fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ] + if isinstance(input_filename, list): + fasta_readers = [get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename] else: fasta_readers = get_stream_reader(open(input_filename), tmp_dir) - add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params) + return fasta_readers -def copy_from_directory( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): +def copy_from_directory(data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir): input_filename = params['param_dict']['reference_source']['fasta_filename'] create_symlink = params['param_dict']['reference_source']['create_symlink'] == 'create_symlink' if create_symlink: - data_table_entries = _create_symlink( input_filename, target_directory, dbkey, dbkey_name, sequence_id, sequence_name ) + data_table_entries = _create_symlink(input_filename, target_directory, dbkey, dbkey_name, sequence_id, sequence_name) else: - if isinstance( input_filename, list ): - fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ] + if isinstance(input_filename, list): + fasta_readers = [get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename] else: fasta_readers = get_stream_reader(open(input_filename), tmp_dir) - data_table_entries = _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ) + return fasta_readers for data_table_name, data_table_entry in data_table_entries: if data_table_entry: - _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name ) + _add_data_table_entry(data_manager_dict, data_table_entry, data_table_name) -def _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name ): - data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) - data_manager_dict['data_tables'][data_table_name] = data_manager_dict['data_tables'].get( 'all_fasta', [] ) - data_manager_dict['data_tables'][data_table_name].append( data_table_entry ) +def _add_data_table_entry(data_manager_dict, data_table_entry, data_table_name): + data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {}) + data_manager_dict['data_tables'][data_table_name] = data_manager_dict['data_tables'].get('all_fasta', []) + data_manager_dict['data_tables'][data_table_name].append(data_table_entry) return data_manager_dict -def _stream_fasta_to_file( fasta_stream, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, close_stream=True ): +def _stream_fasta_to_file(fasta_stream, target_directory, sequence_id, close_stream=True): fasta_base_filename = "%s.fa" % sequence_id - fasta_filename = os.path.join( target_directory, fasta_base_filename ) - with open( fasta_filename, 'wb+' ) as fasta_writer: + fasta_filename = os.path.join(target_directory, fasta_base_filename) + with open(fasta_filename, 'wb+') as fasta_writer: - if isinstance( fasta_stream, list ) and len( fasta_stream ) == 1: + if isinstance(fasta_stream, list) and len(fasta_stream) == 1: fasta_stream = fasta_stream[0] - if isinstance( fasta_stream, list ): + if isinstance(fasta_stream, list): last_char = None for fh in fasta_stream: - if last_char not in [ None, '\n', '\r', b'\n', b'\r' ]: - fasta_writer.write( b'\n' ) + if last_char not in [None, '\n', '\r', b'\n', b'\r']: + fasta_writer.write(b'\n') while True: - data = fh.read( CHUNK_SIZE ) + data = fh.read(CHUNK_SIZE) if data: - fasta_writer.write( data ) + fasta_writer.write(data) last_char = data[-1] else: break @@ -349,45 +394,34 @@ fh.close() else: while True: - data = fasta_stream.read( CHUNK_SIZE ) + data = fasta_stream.read(CHUNK_SIZE) if data: - fasta_writer.write( data ) + fasta_writer.write(data) else: break if close_stream: fasta_stream.close() - - sort_fasta( fasta_filename, params['param_dict']['sorting']['sort_selector'], params ) - - dbkey_dict = None - if dbkey_name: - #do len calc here - len_base_name = "%s.len" % ( dbkey ) - compute_fasta_length( fasta_filename, os.path.join( target_directory, len_base_name ), keep_first_word=True ) - dbkey_dict = dict( value=dbkey, name=dbkey_name, len_path=len_base_name ) - - return [ ( '__dbkeys__', dbkey_dict ), ( 'all_fasta', dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ] + return fasta_filename -def compute_fasta_length( fasta_file, out_file, keep_first_word=False ): - +def compute_fasta_length(fasta_file, out_file, keep_first_word=False): infile = fasta_file - out = open( out_file, 'w') + out = open(out_file, 'w') fasta_title = '' seq_len = 0 first_entry = True - for line in open( infile ): + for line in open(infile): line = line.strip() - if not line or line.startswith( '#' ): + if not line or line.startswith('#'): continue if line[0] == '>': - if first_entry == False: + if not first_entry: if keep_first_word: fasta_title = fasta_title.split()[0] - out.write( "%s\t%d\n" % ( fasta_title[ 1: ], seq_len ) ) + out.write("%s\t%d\n" % (fasta_title[1:], seq_len)) else: first_entry = False fasta_title = line @@ -398,57 +432,75 @@ # last fasta-entry if keep_first_word: fasta_title = fasta_title.split()[0] - out.write( "%s\t%d\n" % ( fasta_title[ 1: ], seq_len ) ) + out.write("%s\t%d\n" % (fasta_title[1:], seq_len)) out.close() -def _create_symlink( input_filename, target_directory, dbkey, dbkey_name, sequence_id, sequence_name ): +def _create_symlink(input_filename, target_directory, dbkey, dbkey_name, sequence_id, sequence_name): fasta_base_filename = "%s.fa" % sequence_id - fasta_filename = os.path.join( target_directory, fasta_base_filename ) - os.symlink( input_filename, fasta_filename ) - + fasta_filename = os.path.join(target_directory, fasta_base_filename) + os.symlink(input_filename, fasta_filename) + dbkey_dict = None if dbkey_name: - #do len calc here - len_base_name = "%s.len" % ( dbkey ) - compute_fasta_length( fasta_filename, os.path.join( target_directory, len_base_name ), keep_first_word=True ) - dbkey_dict = dict( value=dbkey, name=dbkey_name, len_path=len_base_name ) - - return [ ( '__dbkeys__', dbkey_dict ), ( 'all_fasta', dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ] + # do len calc here + len_base_name = "%s.len" % (dbkey) + compute_fasta_length(fasta_filename, os.path.join(target_directory, len_base_name), keep_first_word=True) + dbkey_dict = dict(value=dbkey, name=dbkey_name, len_path=len_base_name) + + return [('__dbkeys__', dbkey_dict), ('all_fasta', dict(value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename))] -REFERENCE_SOURCE_TO_DOWNLOAD = dict( ucsc=download_from_ucsc, ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, directory=copy_from_directory ) - -SORTING_METHODS = dict( as_is=_sort_fasta_as_is, lexicographical=_sort_fasta_lexicographical, gatk=_sort_fasta_gatk, custom=_sort_fasta_custom ) +REFERENCE_SOURCE_TO_DOWNLOAD = dict(ucsc=download_from_ucsc, ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, + directory=copy_from_directory) +SORTING_METHODS = dict(as_is=_sort_fasta_as_is, lexicographical=_sort_fasta_lexicographical, gatk=_sort_fasta_gatk, custom=_sort_fasta_custom) def main(): - #Parse Command Line parser = optparse.OptionParser() - parser.add_option( '-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description' ) + parser.add_option('-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description') (options, args) = parser.parse_args() - + filename = args[0] - - params = loads( open( filename ).read() ) - target_directory = params[ 'output_data' ][0]['extra_files_path'] - os.mkdir( target_directory ) + + params = loads(open(filename).read()) + target_directory = params['output_data'][0]['extra_files_path'] + os.mkdir(target_directory) data_manager_dict = {} - - dbkey, dbkey_name, sequence_id, sequence_name = get_dbkey_dbname_id_name( params, dbkey_description=options.dbkey_description ) - - if dbkey in [ None, '', '?' ]: - raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) ) + + dbkey, dbkey_name, sequence_id, sequence_name = get_dbkey_dbname_id_name(params, dbkey_description=options.dbkey_description) + + if dbkey in [None, '', '?']: + raise Exception('"%s" is not a valid dbkey. You must specify a valid dbkey.' % (dbkey)) # Create a tmp_dir, in case a zip file needs to be uncompressed tmp_dir = tempfile.mkdtemp() - #Fetch the FASTA + # Fetch the FASTA try: - REFERENCE_SOURCE_TO_DOWNLOAD[ params['param_dict']['reference_source']['reference_source_selector'] ]( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ) + reference_source = params['param_dict']['reference_source']['reference_source_selector'] + fasta_readers = REFERENCE_SOURCE_TO_DOWNLOAD[reference_source](data_manager_dict=data_manager_dict, + params=params, + target_directory=target_directory, + dbkey=dbkey, + dbkey_name=dbkey_name, + sequence_id=sequence_id, + sequence_name=sequence_name, + tmp_dir=tmp_dir) + if fasta_readers: + add_fasta_to_table(data_manager_dict=data_manager_dict, + fasta_readers=fasta_readers, + target_directory=target_directory, + dbkey=dbkey, + dbkey_name=dbkey_name, + sequence_id=sequence_id, + sequence_name=sequence_name, + params=params) + finally: cleanup_before_exit(tmp_dir) - #save info to json file - open( filename, 'wb' ).write( dumps( data_manager_dict ).encode() ) - + # save info to json file + open(filename, 'wb').write(dumps(data_manager_dict).encode()) + + if __name__ == "__main__": main()
--- a/data_manager/data_manager_fetch_genome_all_fasta_dbkeys.xml Fri Aug 26 12:46:47 2016 -0400 +++ b/data_manager/data_manager_fetch_genome_all_fasta_dbkeys.xml Tue Apr 04 17:13:31 2017 -0400 @@ -1,11 +1,12 @@ <tool id="data_manager_fetch_genome_all_fasta_dbkey" name="Create DBKey and Reference Genome" version="0.0.2" tool_type="manage_data"> <description>fetching</description> - <command><![CDATA[ - python "$__tool_directory__"/data_manager_fetch_genome_all_fasta_dbkeys.py "${out_file}" + <command detect_errors="exit_code"><![CDATA[ + python '$__tool_directory__/data_manager_fetch_genome_all_fasta_dbkeys.py' + '${out_file}' #if str( $dbkey_source.dbkey_source_selector ) == 'existing': - --dbkey_description ${ dbkey_source.dbkey.get_display_text() } + --dbkey_description '${ dbkey_source.dbkey.get_display_text() }' #else - --dbkey_description "${ dbkey_source.dbkey_name or $dbkey_source.dbkey }" + --dbkey_description '${ dbkey_source.dbkey_name or $dbkey_source.dbkey }' #end if ]]></command> <inputs> @@ -18,12 +19,12 @@ <param name="dbkey" type="genomebuild" label="DBKEY to assign to data" /> </when> <when value="new"> - <param type="text" name="dbkey" value="" label="dbkey" optional="False" /> - <param type="text" name="dbkey_name" value="" label="Display name for dbkey" /> + <param name="dbkey" type="text" value="" optional="false" label="dbkey" /> + <param name="dbkey_name" type="text" value="" label="Display name for dbkey" /> </when> </conditional> - <param type="text" name="sequence_name" value="" label="Name of sequence" /> - <param type="text" name="sequence_id" value="" label="ID for sequence" /> + <param name="sequence_name" type="text" value="" label="Name of sequence" /> + <param name="sequence_id" type="text" value="" label="ID for sequence" /> <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Choose the source for the reference genome"> <option value="ucsc" selected="True">UCSC</option> @@ -33,20 +34,20 @@ <option value="directory">Directory on Server</option> </param> <when value="ucsc"> - <param type="text" name="requested_dbkey" value="" label="UCSC's DBKEY for source FASTA" optional="False" /> + <param name="requested_dbkey" type="text" value="" optional="false" label="UCSC's DBKEY for source FASTA" /> </when> <when value="ncbi"> - <param type="text" name="requested_identifier" value="" label="NCBI identifier/accession" help="Identifiers (e.g 667699573) or accessions (e.g AC020606.7) may be used" optional="False" /> + <param name="requested_identifier" type="text" value="" optional="false" label="NCBI identifier/accession" help="Identifiers (e.g 667699573) or accessions (e.g AC020606.7) may be used" /> </when> <when value="url"> - <param type="text" area="True" name="user_url" value="http://" label="URLs" optional="False" /> + <param name="user_url" type="text" area="True" value="http://" optional="false" label="URLs" /> </when> <when value="history"> - <param name="input_fasta" type="data" format="fasta" label="FASTA File" multiple="False" optional="False" /> + <param name="input_fasta" type="data" format="fasta" label="FASTA file" /> </when> <when value="directory"> - <param type="text" name="fasta_filename" value="" label="Full path to FASTA File on disk" optional="False" /> - <param type="boolean" name="create_symlink" truevalue="create_symlink" falsevalue="copy_file" label="Create symlink to original data instead of copying" checked="False" /> + <param name="fasta_filename" type="text" value="" optional="false" label="Full path to FASTA file on disk" /> + <param name="create_symlink" type="boolean" truevalue="create_symlink" falsevalue="copy_file" label="Create symlink to original data instead of copying" /> </when> </conditional> <conditional name="sorting"> @@ -56,15 +57,12 @@ <option value="gatk">GATK</option> <option value="custom">Custom</option> </param> - <when value="as_is"> - </when> - <when value="lexicographical"> - </when> - <when value="gatk"> - </when> + <when value="as_is" /> + <when value="lexicographical" /> + <when value="gatk" /> <when value="custom"> <repeat name="sequence_identifiers" title="Sequence Identifiers" min="1" default="1"> - <param type="text" name="identifier" value="" label="Sequence Identifier" optional="False" /> + <param name="identifier" type="text" value="" optional="false" label="Sequence Identifier" /> </repeat> <param name="handle_not_listed_selector" type="select" label="How to handle non-specified Identifiers"> <option value="discard" selected="True">Discard</option> @@ -82,7 +80,6 @@ <test> <param name="dbkey" value="anoGam1"/> <param name="sequence_name" value=""/> - <param name="sequence_desc" value=""/> <param name="sequence_id" value=""/> <param name="reference_source_selector" value="history"/> <param name="input_fasta" value="phiX174.fasta"/> @@ -97,11 +94,8 @@ ------ - - .. class:: infomark **Notice:** If you leave name, description, or id blank, it will be generated automatically. - </help> </tool>