Mercurial > repos > rnateam > data_manager_sortmerna_database_downloader

comparison data_manager/data_manager_sortmerna_download.py @ 2:7d2252852f96 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_sortmerna_database_downloader commit 4241c1d4b05a177bd2c74f5a139f51d4f65e0b55
author rnateam
date Tue, 13 Jun 2017 12:03:08 -0400
parents 30bb49887172
children
comparison
equal deleted inserted replaced
1:30bb49887172 2:7d2252852f96
2 # Data manager for reference data for the SortMeRNA Galaxy tools 2 # Data manager for reference data for the SortMeRNA Galaxy tools
3 3
4 import argparse 4 import argparse
5 import json 5 import json
6 import os 6 import os
7 import shutil
7 import tarfile 8 import tarfile
8 import requests 9 import requests
9 import subprocess 10 import subprocess
10 11
11 12
124 file_dir = os.path.join(archive_content_path, "rRNA_databases") 125 file_dir = os.path.join(archive_content_path, "rRNA_databases")
125 for filename in os.listdir(file_dir): 126 for filename in os.listdir(file_dir):
126 if not filename.endswith("fasta"): 127 if not filename.endswith("fasta"):
127 continue 128 continue
128 input_filepath = os.path.join(file_dir, filename) 129 input_filepath = os.path.join(file_dir, filename)
129 output_filepath = os.path.join(target_dir, filename) 130 # Extract the db name
130 # Move file 131 db_name = os.path.splitext(filename)[0]
131 os.rename(input_filepath, output_filepath) 132 # Create the directory where to put the fasta files and indexed files
133 filedir = os.path.join(target_dir, db_name)
134 os.mkdir(filedir)
135 fasta_filepath = os.path.join(filedir, "%s.fasta" % db_name)
136 indexed_filepath = os.path.join(filedir, db_name)
137 # Move the fasta file
138 shutil.move(input_filepath, fasta_filepath)
132 # Index the file with indexdb_rna 139 # Index the file with indexdb_rna
133 command = "indexdb_rna --ref %s,%s" % ( 140 command = "indexdb_rna --ref %s,%s" % (
134 output_filepath, 141 fasta_filepath,
135 os.path.splitext(output_filepath)[0]) 142 indexed_filepath)
136 process = subprocess.call(command, shell=True ) 143 process = subprocess.call(command, shell=True )
137 # Add entry in the data table 144 # Add entry in the data table
138 db_name = os.path.splitext(filename)[0]
139 add_data_table_entry( 145 add_data_table_entry(
140 data_tables, 146 data_tables,
141 "rRNA_databases", 147 "rRNA_databases",
142 dict( 148 dict(
143 value=version, 149 value="%s-%s" %(version, db_name),
144 name=db_name, 150 name=db_name,
145 path=output_filepath)) 151 path=filedir))
146 152
147 153
148 def download_db(data_tables, version, target_dir): 154 def download_db(data_tables, version, target_dir):
149 """Download SortMeRNA database 155 """Download SortMeRNA database
150 156