# HG changeset patch # User crs4 # Date 1476094550 14400 # Node ID 7e66353ca9d0726690aa5abad89b710c38e89b26 # Parent c3a93255587edd817e3f806054b79b5895a3cbe6 Deleted selected files diff -r c3a93255587e -r 7e66353ca9d0 LICENSE --- a/LICENSE Thu Oct 06 12:39:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,28 +0,0 @@ -License note for "dorina.xml" ------------------------------ - -Copyright © 2015 Ricardo Wurmus -This file is part of Webdorina. - -Webdorina is free software; you can redistribute it and/or modify it -under the terms of the GNU General Public License as published by the -Free Software Foundation; either version 3 of the License, or (at your -option) any later version. - -Webdorina is distributed in the hope that it will be useful, but -WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -General Public License for more details. - -You should have received a copy of the GNU General Public License -along with Webdorina. If not, see . - -To enable combination with Galaxy, dorina.xml is also released under -the Academic Free License version 3.0. - - -License note for "data_source.py" ---------------------------------- - -As part of Galaxy, data_source.py is released under the Academic Free -License version 3.0. diff -r c3a93255587e -r 7e66353ca9d0 data_source.py --- a/data_source.py Thu Oct 06 12:39:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,113 +0,0 @@ -#!/usr/bin/env python -# Retrieves data from external data source applications and stores in a dataset file. -# Data source application parameters are temporarily stored in the dataset file. -import socket, urllib, sys, os -from galaxy import eggs #eggs needs to be imported so that galaxy.util can find docutils egg... -from json import loads, dumps -from galaxy.util import get_charset_from_http_headers -import galaxy.model # need to import model before sniff to resolve a circular import dependency -from galaxy.datatypes import sniff -from galaxy.datatypes.registry import Registry -from galaxy.jobs import TOOL_PROVIDED_JOB_METADATA_FILE - -assert sys.version_info[:2] >= ( 2, 4 ) - -def stop_err( msg ): - sys.stderr.write( msg ) - sys.exit() - -GALAXY_PARAM_PREFIX = 'GALAXY' -GALAXY_ROOT_DIR = os.path.realpath( os.path.join( os.path.split( os.path.realpath( __file__ ) )[0], '..', '..' ) ) -GALAXY_DATATYPES_CONF_FILE = os.path.join( GALAXY_ROOT_DIR, 'datatypes_conf.xml' ) - -def load_input_parameters( filename, erase_file = True ): - datasource_params = {} - try: - json_params = loads( open( filename, 'r' ).read() ) - datasource_params = json_params.get( 'param_dict' ) - except: - json_params = None - for line in open( filename, 'r' ): - try: - line = line.strip() - fields = line.split( '\t' ) - datasource_params[ fields[0] ] = fields[1] - except: - continue - if erase_file: - open( filename, 'w' ).close() #open file for writing, then close, removes params from file - return json_params, datasource_params - -def __main__(): - filename = sys.argv[1] - try: - max_file_size = int( sys.argv[2] ) - except: - max_file_size = 0 - - job_params, params = load_input_parameters( filename ) - - if job_params is None: #using an older tabular file - enhanced_handling = False - job_params = dict( param_dict = params ) - job_params[ 'output_data' ] = [ dict( out_data_name = 'output', - ext = 'data', - file_name = filename, - extra_files_path = None ) ] - job_params[ 'job_config' ] = dict( GALAXY_ROOT_DIR=GALAXY_ROOT_DIR, GALAXY_DATATYPES_CONF_FILE=GALAXY_DATATYPES_CONF_FILE, TOOL_PROVIDED_JOB_METADATA_FILE = TOOL_PROVIDED_JOB_METADATA_FILE ) - else: - enhanced_handling = True - json_file = open( job_params[ 'job_config' ][ 'TOOL_PROVIDED_JOB_METADATA_FILE' ], 'w' ) #specially named file for output junk to pass onto set metadata - - datatypes_registry = Registry() - datatypes_registry.load_datatypes( root_dir = job_params[ 'job_config' ][ 'GALAXY_ROOT_DIR' ], config = job_params[ 'job_config' ][ 'GALAXY_DATATYPES_CONF_FILE' ] ) - - URL = params.get( 'URL', None ) #using exactly URL indicates that only one dataset is being downloaded - URL_method = params.get( 'URL_method', None ) - - # The Python support for fetching resources from the web is layered. urllib uses the httplib - # library, which in turn uses the socket library. As of Python 2.3 you can specify how long - # a socket should wait for a response before timing out. By default the socket module has no - # timeout and can hang. Currently, the socket timeout is not exposed at the httplib or urllib2 - # levels. However, you can set the default timeout ( in seconds ) globally for all sockets by - # doing the following. - socket.setdefaulttimeout( 600 ) - - for data_dict in job_params[ 'output_data' ]: - cur_filename = data_dict.get( 'file_name', filename ) - cur_URL = params.get( '%s|%s|URL' % ( GALAXY_PARAM_PREFIX, data_dict[ 'out_data_name' ] ), URL ) - if not cur_URL: - open( cur_filename, 'w' ).write( "" ) - stop_err( 'The remote data source application has not sent back a URL parameter in the request.' ) - - # The following calls to urllib.urlopen() will use the above default timeout - try: - if not URL_method or URL_method == 'get': - page = urllib.urlopen( cur_URL ) - elif URL_method == 'post': - page = urllib.urlopen( cur_URL, urllib.urlencode( params ) ) - except Exception, e: - stop_err( 'The remote data source application may be off line, please try again later. Error: %s' % str( e ) ) - if max_file_size: - file_size = int( page.info().get( 'Content-Length', 0 ) ) - if file_size > max_file_size: - stop_err( 'The size of the data (%d bytes) you have requested exceeds the maximum allowed (%d bytes) on this server.' % ( file_size, max_file_size ) ) - #do sniff stream for multi_byte - try: - cur_filename, is_multi_byte = sniff.stream_to_open_named_file( page, os.open( cur_filename, os.O_WRONLY | os.O_CREAT ), cur_filename, source_encoding=get_charset_from_http_headers( page.headers ) ) - except Exception, e: - stop_err( 'Unable to fetch %s:\n%s' % ( cur_URL, e ) ) - - #here import checks that upload tool performs - if enhanced_handling: - try: - ext = sniff.handle_uploaded_dataset_file( filename, datatypes_registry, ext = data_dict[ 'ext' ], is_multi_byte = is_multi_byte ) - except Exception, e: - stop_err( str( e ) ) - info = dict( type = 'dataset', - dataset_id = data_dict[ 'dataset_id' ], - ext = ext) - - json_file.write( "%s\n" % dumps( info ) ) - -if __name__ == "__main__": __main__() diff -r c3a93255587e -r 7e66353ca9d0 dorina.xml --- a/dorina.xml Thu Oct 06 12:39:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,22 +0,0 @@ - - - DoRiNA data source - data_source.py $output $__app__.config.output_size_limit - - - go to DoRiNA search $GALAXY_URL - - - - - - - - - - - - - - -