details: http://www.bx.psu.edu/hg/galaxy/rev/d279017969cd changeset: 3148:d279017969cd user: Dan Blankenberg <dan@bx.psu.edu> date: Mon Dec 07 10:19:41 2009 -0500 description: Enhance tool parameter sanitization. Sanitization rules can now be defined on a per input parameter basis. Resolves ticket #38 and #142. Sanitization now occurs as part of the InputValueWrapper logic. Previously sanitization occurred as soon as parameter values were provided by the user via form submits, causing the sanitized values to be stored in the database. Now the original user specified values are stored in the database and sanitation happens when str is called on the InputValueWrapper, i.e. during command-line generation and when generating configfiles. Abstract out param name and value translations that are performed on data source tools. This changes some of the names of the tags used for these purposes (e.g. data_type_translation becomes value_translation) to reflect this generalization. The ToolConfigSyntax wiki page has been updated with these changes. Future Enhancement: Allow methods with arguments and keywords to be specified for sanitation and translation purposes. diffstat: lib/galaxy/datatypes/sequence.py | 36 +---- lib/galaxy/tools/__init__.py | 48 +------- lib/galaxy/tools/parameters/basic.py | 72 +++++++---- lib/galaxy/tools/parameters/input_translation.py | 106 +++++++++++++++++ lib/galaxy/tools/parameters/sanitize.py | 167 +++++++++++++++++++++++++++ lib/galaxy/util/__init__.py | 66 +---------- lib/galaxy/web/controllers/async.py | 2 +- lib/galaxy/web/controllers/root.py | 2 +- lib/galaxy/web/controllers/tool_runner.py | 9 +- test-data/2.tabular | 20 +- test-data/joiner_out3.bed | 32 ++-- tools/data_source/biomart.xml | 17 +- tools/data_source/biomart_test.xml | 17 +- tools/data_source/epigraph_import.xml | 3 +- tools/data_source/epigraph_import_test.xml | 3 +- tools/data_source/eupathdb.xml | 19 +- tools/data_source/flymine.xml | 3 +- tools/data_source/flymine_test.xml | 3 +- tools/data_source/gramene_mart.xml | 17 +- tools/data_source/modmine.xml | 3 +- tools/data_source/ratmine.xml | 3 +- tools/data_source/ucsc_tablebrowser.xml | 19 +- tools/data_source/ucsc_tablebrowser_archaea.xml | 23 ++- tools/data_source/ucsc_tablebrowser_test.xml | 23 ++- tools/data_source/wormbase.xml | 17 +- tools/data_source/wormbase_test.xml | 17 +- tools/emboss_5/emboss_fuzznuc.xml | 12 +- tools/filters/grep.py | 41 ++++-- tools/filters/grep.xml | 13 +- tools/filters/joiner.xml | 2 +- tools/plotting/xy_plot.xml | 7 +- 31 files changed, 526 insertions(+), 296 deletions(-) diffs (1446 lines): diff -r 81475cecea2c -r d279017969cd lib/galaxy/datatypes/sequence.py --- a/lib/galaxy/datatypes/sequence.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/datatypes/sequence.py Mon Dec 07 10:19:41 2009 -0500 @@ -309,35 +309,21 @@ return #this is not a MAF file dataset.metadata.species = species dataset.metadata.blocks = blocks - #only overwrite the contents if our newly determined chromosomes don't match stored + + #write species chromosomes to a file chrom_file = dataset.metadata.species_chromosomes - compare_chroms = {} - if chrom_file: - try: - for line in open( chrom_file.file_name ): - fields = line.split( "\t" ) - if fields: - spec = fields.pop( 0 ) - if spec: - compare_chroms[spec] = fields - except: - pass - #write out species chromosomes again only if values are different - if not species_chromosomes or compare_chroms != species_chromosomes: - tmp_file = tempfile.TemporaryFile( 'w+b' ) - for spec, chroms in species_chromosomes.items(): - tmp_file.write( "%s\t%s\n" % ( spec, "\t".join( chroms ) ) ) - - if not chrom_file: - chrom_file = dataset.metadata.spec['species_chromosomes'].param.new_file( dataset = dataset ) - tmp_file.seek( 0 ) - open( chrom_file.file_name, 'wb' ).write( tmp_file.read() ) - dataset.metadata.species_chromosomes = chrom_file - tmp_file.close() + if not chrom_file: + chrom_file = dataset.metadata.spec['species_chromosomes'].param.new_file( dataset = dataset ) + chrom_out = open( chrom_file.file_name, 'wb' ) + for spec, chroms in species_chromosomes.items(): + chrom_out.write( "%s\t%s\n" % ( spec, "\t".join( chroms ) ) ) + chrom_out.close() + dataset.metadata.species_chromosomes = chrom_file + index_file = dataset.metadata.maf_index if not index_file: index_file = dataset.metadata.spec['maf_index'].param.new_file( dataset = dataset ) - indexes.write( open( index_file.file_name, 'w' ) ) + indexes.write( open( index_file.file_name, 'wb' ) ) dataset.metadata.maf_index = index_file def set_peek( self, dataset, is_multi_byte=False ): if not dataset.dataset.purged: diff -r 81475cecea2c -r d279017969cd lib/galaxy/tools/__init__.py --- a/lib/galaxy/tools/__init__.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/tools/__init__.py Mon Dec 07 10:19:41 2009 -0500 @@ -17,6 +17,7 @@ from parameters import * from parameters.grouping import * from parameters.validation import LateValidationError +from parameters.input_translation import ToolInputTranslator from galaxy.util.expressions import ExpressionContext from galaxy.tools.test import ToolTestBuilder from galaxy.tools.actions import DefaultToolAction @@ -299,48 +300,11 @@ self.tool_type = root.get( "tool_type", None ) #Force history to fully refresh after job execution for this tool. Useful i.e. when an indeterminate number of outputs are created by a tool. self.force_history_refresh = util.string_as_bool( root.get( 'force_history_refresh', 'False' ) ) - # data_source tool - if self.tool_type == "data_source": - self.URL_method = root.get( "URL_method", "get" ) # get is the default - self.param_trans_dict = {} - req_param_trans = root.find( "request_param_translation" ) - if req_param_trans is not None: - for req_param in req_param_trans.findall( "request_param" ): - # req_param tags must look like <request_param galaxy_name="dbkey" remote_name="GENOME" missing="" /> - trans_list = [] - remote_name = req_param.get( "remote_name" ) - trans_list.append( req_param.get( "galaxy_name" ) ) - trans_list.append( req_param.get( "missing" ) ) - if req_param.get( "galaxy_name" ) == "data_type": - # The req_param tag for data_type is special in that it can contain another tag set like - # <data_type_translation> - # <format galaxy_format="tabular" remote_format="selectedFields" /> - # </data_type_translation> - format_trans = req_param.find( "data_type_translation" ) - if format_trans is not None: - format_trans_dict = {} - for format in format_trans.findall( "format" ): - remote_format = format.get( "remote_format" ) - galaxy_format = format.get( "galaxy_format" ) - format_trans_dict[ remote_format ] = galaxy_format - trans_list.append( format_trans_dict ) - elif req_param.get( "galaxy_name" ) == "URL": - # Some remote data sources ( e.g., Gbrowse ) send parameters back to - # Galaxy in the initial response that must be added to URL prior to - # Galaxy sending the secondary request to the URL. The tag set looks - # asomething like: - # <add_to_url> - # <param_from_source name="d" missing="" /> - # </add_to_url> - add_to_url = req_param.find( "add_to_url" ) - if add_to_url is not None: - add_to_url_dict = {} - for param_from_source in add_to_url.findall( "param_from_source" ): - name = param_from_source.get( "name" ) - value = param_from_source.get( "missing" ) # only used if the source doesn't send the param name - add_to_url_dict[ name ] = value - trans_list.append( add_to_url_dict ) - self.param_trans_dict[ remote_name ] = trans_list + self.param_trans_dict = {} #make this a property of all Tools, so don't need to check if tool is datasource, just if it is populated + #load input translator, used by datasource tools to change names/values of incoming parameters + self.input_translator = root.find( "request_param_translation" ) + if self.input_translator: + self.input_translator = ToolInputTranslator.from_element( self.input_translator ) # Command line (template). Optional for tools that do not invoke a local program command = root.find("command") if command is not None and command.text is not None: diff -r 81475cecea2c -r d279017969cd lib/galaxy/tools/parameters/basic.py --- a/lib/galaxy/tools/parameters/basic.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/tools/parameters/basic.py Mon Dec 07 10:19:41 2009 -0500 @@ -7,6 +7,8 @@ from galaxy import config, datatypes, util from galaxy.web import form_builder from galaxy.util.bunch import Bunch +from galaxy.util import string_as_bool, sanitize_param +from sanitize import ToolParameterSanitizer import validation, dynamic_options # For BaseURLToolParameter from galaxy.web import url_for @@ -28,7 +30,10 @@ self.type = param.get("type") self.label = util.xml_text(param, "label") self.help = util.xml_text(param, "help") - self.unsanitize = param.get( "unsanitize", None ) + self.unsanitize = param.get( "unsanitize", None ) ### This doesn't looked to be used anywhere... REMOVE ME? + self.sanitizer = param.find( "sanitizer" ) + if self.sanitizer is not None: + self.sanitizer = ToolParameterSanitizer.from_element( self.sanitizer ) self.html = "no html set" self.repeat = param.get("repeat", None) self.condition = param.get( "condition", None ) @@ -122,7 +127,13 @@ return value def to_param_dict_string( self, value, other_values={} ): - return str( value ) + value = str( value ) + if self.tool is None or self.tool.options.sanitize: + if self.sanitizer: + value = self.sanitizer.sanitize_param( value ) + else: + value = sanitize_param( value ) + return value def validate( self, value, history=None ): for validator in self.validators: @@ -154,7 +165,7 @@ self.name = elem.get( 'name' ) self.size = elem.get( 'size' ) self.value = elem.get( 'value' ) - self.area = str_bool( elem.get( 'area', False ) ) + self.area = string_as_bool( elem.get( 'area', False ) ) def get_html_field( self, trans=None, value=None, other_values={} ): if self.area: return form_builder.TextArea( self.name, self.size, value or self.value ) @@ -262,7 +273,7 @@ self.truevalue = elem.get( 'truevalue', 'true' ) self.falsevalue = elem.get( 'falsevalue', 'false' ) self.name = elem.get( 'name' ) - self.checked = str_bool( elem.get( 'checked' ) ) + self.checked = string_as_bool( elem.get( 'checked' ) ) def get_html_field( self, trans=None, value=None, other_values={} ): checked = self.checked if value: @@ -299,7 +310,7 @@ """ ToolParameter.__init__( self, tool, elem ) self.name = elem.get( 'name' ) - self.ajax = str_bool( elem.get( 'ajax-upload' ) ) + self.ajax = string_as_bool( elem.get( 'ajax-upload' ) ) def get_html_field( self, trans=None, value=None, other_values={} ): return form_builder.FileField( self.name, ajax = self.ajax, value = value ) def from_html( self, value, trans=None, other_values={} ): @@ -474,7 +485,7 @@ """ def __init__( self, tool, elem, context=None ): ToolParameter.__init__( self, tool, elem ) - self.multiple = str_bool( elem.get( 'multiple', False ) ) + self.multiple = string_as_bool( elem.get( 'multiple', False ) ) self.display = elem.get( 'display', None ) self.separator = elem.get( 'separator', ',' ) self.legal_values = set() @@ -492,7 +503,7 @@ for index, option in enumerate( elem.findall( "option" ) ): value = option.get( "value" ) self.legal_values.add( value ) - selected = str_bool( option.get( "selected", False ) ) + selected = string_as_bool( option.get( "selected", False ) ) self.static_options.append( ( option.text, value, selected ) ) self.is_dynamic = ( ( self.dynamic_options is not None ) or ( self.options is not None ) ) def get_options( self, trans, other_values ): @@ -571,11 +582,19 @@ if value is None: return "None" if isinstance( value, list ): - if not(self.repeat): + if not( self.repeat ): assert self.multiple, "Multiple values provided but parameter is not expecting multiple values" - return self.separator.join( map( str, value ) ) + value = map( str, value ) else: - return str(value) + value = str( value ) + if self.tool is None or self.tool.options.sanitize: + if self.sanitizer: + value = self.sanitizer.sanitize_param( value ) + else: + value = sanitize_param( value ) + if isinstance( value, list ): + value = self.separator.join( value ) + return value def value_to_basic( self, value, app ): if isinstance( value, UnvalidatedValue ): return { "__class__": "UnvalidatedValue", "value": value.value } @@ -741,9 +760,9 @@ def __init__( self, tool, elem ): SelectToolParameter.__init__( self, tool, elem ) self.tool = tool - self.numerical = str_bool( elem.get( "numerical", False )) - self.force_select = str_bool( elem.get( "force_select", True )) - self.accept_default = str_bool( elem.get( "accept_default", False )) + self.numerical = string_as_bool( elem.get( "numerical", False )) + self.force_select = string_as_bool( elem.get( "force_select", True )) + self.accept_default = string_as_bool( elem.get( "accept_default", False )) self.data_ref = elem.get( "data_ref", None ) self.is_dynamic = True def get_column_list( self, trans, other_values ): @@ -894,11 +913,11 @@ def __init__( self, tool, elem, context=None ): def recurse_option_elems( cur_options, option_elems ): for option_elem in option_elems: - selected = str_bool( option_elem.get( 'selected', False ) ) + selected = string_as_bool( option_elem.get( 'selected', False ) ) cur_options.append( { 'name':option_elem.get( 'name' ), 'value': option_elem.get( 'value'), 'options':[], 'selected':selected } ) recurse_option_elems( cur_options[-1]['options'], option_elem.findall( 'option' ) ) ToolParameter.__init__( self, tool, elem ) - self.multiple = str_bool( elem.get( 'multiple', False ) ) + self.multiple = string_as_bool( elem.get( 'multiple', False ) ) self.display = elem.get( 'display', None ) self.hierarchy = elem.get( 'hierarchy', 'exact' ) #exact or recurse self.separator = elem.get( 'separator', ',' ) @@ -1019,7 +1038,13 @@ if len( rval ) > 1: if not( self.repeat ): assert self.multiple, "Multiple values provided but parameter is not expecting multiple values" - return self.separator.join( rval ) + rval = self.separator.join( rval ) + if self.tool is None or self.tool.options.sanitize: + if self.sanitizer: + rval = self.sanitizer.sanitize_param( rval ) + else: + rval = sanitize_param( rval ) + return rval def get_initial_value( self, trans, context ): def recurse_options( initial_values, options ): @@ -1094,7 +1119,7 @@ def __init__( self, tool, elem ): ToolParameter.__init__( self, tool, elem ) # Add metadata validator - if not str_bool( elem.get( 'no_validation', False ) ): + if not string_as_bool( elem.get( 'no_validation', False ) ): self.validators.append( validation.MetadataValidator() ) # Build tuple of classes for supported data formats formats = [] @@ -1108,9 +1133,9 @@ else: formats.append( tool.app.datatypes_registry.get_datatype_by_extension( extension.lower() ).__class__ ) self.formats = tuple( formats ) - self.multiple = str_bool( elem.get( 'multiple', False ) ) + self.multiple = string_as_bool( elem.get( 'multiple', False ) ) # Optional DataToolParameters are used in tools like GMAJ and LAJ - self.optional = str_bool( elem.get( 'optional', False ) ) + self.optional = string_as_bool( elem.get( 'optional', False ) ) # TODO: Enhance dynamic options for DataToolParameters. Currently, # only the special case key='build' of type='data_meta' is # a valid filter @@ -1366,13 +1391,4 @@ runtime. """ pass - -def str_bool(in_str): - """ - returns true/false of a string, since bool(str), always returns true if string is not empty - default action is to return false - """ - if str(in_str).lower() == 'true' or str(in_str).lower() == 'yes': - return True - return False diff -r 81475cecea2c -r d279017969cd lib/galaxy/tools/parameters/input_translation.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib/galaxy/tools/parameters/input_translation.py Mon Dec 07 10:19:41 2009 -0500 @@ -0,0 +1,106 @@ +""" +Tool Input Translation. +""" + +import logging +from galaxy.util.bunch import Bunch + +log = logging.getLogger( __name__ ) + +class ToolInputTranslator( object ): + """ + Handles Tool input translation. + This is used for data source tools + + >>> from galaxy.util import Params + >>> from elementtree.ElementTree import XML + >>> translator = ToolInputTranslator.from_element( XML( + ... ''' + ... <request_param_translation> + ... <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> + ... <request_param galaxy_name="URL" remote_name="URL" missing="" > + ... <append_param separator="&" first_separator="?" join="="> + ... <value name="_export" missing="1" /> + ... <value name="GALAXY_URL" missing="0" /> + ... </append_param> + ... </request_param> + ... <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> + ... <request_param galaxy_name="organism" remote_name="org" missing="unknown species" /> + ... <request_param galaxy_name="table" remote_name="hgta_table" missing="unknown table" /> + ... <request_param galaxy_name="description" remote_name="hgta_regionType" missing="no description" /> + ... <request_param galaxy_name="data_type" remote_name="hgta_outputType" missing="tabular" > + ... <value_translation> + ... <value galaxy_value="tabular" remote_value="primaryTable" /> + ... <value galaxy_value="tabular" remote_value="selectedFields" /> + ... <value galaxy_value="wig" remote_value="wigData" /> + ... <value galaxy_value="interval" remote_value="tab" /> + ... <value galaxy_value="html" remote_value="hyperlinks" /> + ... <value galaxy_value="fasta" remote_value="sequence" /> + ... </value_translation> + ... </request_param> + ... </request_param_translation> + ... ''' ) ) + >>> params = Params( { 'db':'hg17', 'URL':'URL_value', 'org':'Human', 'hgta_outputType':'primaryTable' } ) + >>> translator.translate( params ) + >>> print params + {'hgta_outputType': 'primaryTable', 'data_type': 'tabular', 'table': 'unknown table', 'URL': 'URL_value?GALAXY_URL=0&_export=1', 'org': 'Human', 'URL_method': 'post', 'db': 'hg17', 'organism': 'Human', 'dbkey': 'hg17', 'description': 'no description'} + """ + @classmethod + def from_element( cls, elem ): + """Loads the proper filter by the type attribute of elem""" + rval = ToolInputTranslator() + for req_param in elem.findall( "request_param" ): + # req_param tags must look like <request_param galaxy_name="dbkey" remote_name="GENOME" missing="" /> + #trans_list = [] + remote_name = req_param.get( "remote_name" ) + galaxy_name = req_param.get( "galaxy_name" ) + missing = req_param.get( "missing" ) + value_trans = {} + append_param = None + + value_trans_elem = req_param.find( 'value_translation' ) + if value_trans_elem: + for value_elem in value_trans_elem.findall( 'value' ): + remote_value = value_elem.get( "remote_value" ) + galaxy_value = value_elem.get( "galaxy_value" ) + if None not in [ remote_value, galaxy_value ]: + value_trans[ remote_value ] = galaxy_value + + append_param_elem = req_param.find( "append_param" ) + if append_param_elem: + separator = append_param_elem.get( 'separator', ',' ) + first_separator = append_param_elem.get( 'first_separator', None ) + join_str = append_param_elem.get( 'join', '=' ) + append_dict = {} + for value_elem in append_param_elem.findall( 'value' ): + value_name = value_elem.get( 'name' ) + value_missing = value_elem.get( 'missing' ) + if None not in [ value_name, value_missing ]: + append_dict[ value_name ] = value_missing + append_param = Bunch( separator = separator, first_separator = first_separator, join_str = join_str, append_dict = append_dict ) + + rval.param_trans_dict[ remote_name ] = Bunch( galaxy_name = galaxy_name, missing = missing, value_trans = value_trans, append_param = append_param ) + + return rval + + def __init__( self ): + self.param_trans_dict = {} + + def translate( self, params ): + """ + update params in-place + """ + for remote_name, translator in self.param_trans_dict.iteritems(): + galaxy_name = translator.galaxy_name #NB: if a param by name galaxy_name is provided, it is always thrown away unless galaxy_name == remote_name + value = params.get( remote_name, translator.missing ) #get value from input params, or use default value specified in tool config + if translator.value_trans and value in translator.value_trans: + value = translator.value_trans[ value ] + if translator.append_param: + for param_name, missing_value in translator.append_param.append_dict.iteritems(): + param_value = params.get( param_name, missing_value ) + if translator.append_param.first_separator and translator.append_param.first_separator not in value: + sep = translator.append_param.first_separator + else: + sep = translator.append_param.separator + value += '%s%s%s%s' % ( sep, param_name, translator.append_param.join_str, param_value ) + params.update( { galaxy_name: value } ) diff -r 81475cecea2c -r d279017969cd lib/galaxy/tools/parameters/sanitize.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib/galaxy/tools/parameters/sanitize.py Mon Dec 07 10:19:41 2009 -0500 @@ -0,0 +1,167 @@ +""" +Tool Parameter specific sanitizing. +""" + +import logging +import string +import galaxy.util + +log = logging.getLogger( __name__ ) + +class ToolParameterSanitizer( object ): + """ + Handles tool parameter specific sanitizing. + + >>> from elementtree.ElementTree import XML + >>> sanitizer = ToolParameterSanitizer.from_element( XML( + ... ''' + ... <sanitizer invalid_char=""> + ... <valid initial="string.letters"/> + ... </sanitizer> + ... ''' ) ) + >>> sanitizer.sanitize_param( string.printable ) == string.letters + True + >>> slash = chr( 92 ) + >>> sanitizer = ToolParameterSanitizer.from_element( XML( + ... ''' + ... <sanitizer> + ... <valid initial="none"> + ... <add preset="string.printable"/> + ... <remove value="""/> + ... <remove value="%s"/> + ... </valid> + ... <mapping initial="none"> + ... <add source=""" target="%s""/> + ... <add source="%s" target="%s%s"/> + ... </mapping> + ... </sanitizer> + ... ''' % ( slash, slash, slash, slash, slash ) ) ) + >>> text = '%s"$rm&#!' % slash + >>> [ c for c in sanitizer.sanitize_param( text ) ] == [ slash, slash, slash, '"', '$', 'r', 'm', '&', '#', '!' ] + True + """ + + VALID_PRESET = { 'default':( string.letters + string.digits +" -=_.()/+*^,:?!" ), 'none':'' } + MAPPING_PRESET = { 'default':galaxy.util.mapped_chars, 'none':{} } + DEFAULT_INVALID_CHAR = 'X' + + #class methods + @classmethod + def from_element( cls, elem ): + """Loads the proper filter by the type attribute of elem""" + #TODO: Add ability to generically specify a method to use for sanitizing input via specification in tool XML + rval = ToolParameterSanitizer() + rval._invalid_char = elem.get( 'invalid_char', cls.DEFAULT_INVALID_CHAR ) + rval.sanitize = galaxy.util.string_as_bool( elem.get( 'sanitize', 'True' ) ) + for valid_elem in elem.findall( 'valid' ): + rval._valid_chars = rval.get_valid_by_name( valid_elem.get( 'initial', 'default' ) ) + for action_elem in valid_elem: + preset = rval.get_valid_by_name( action_elem.get( 'preset', 'none' ) ) + valid_value = [ val for val in action_elem.get( 'value', [] ) ] + if action_elem.tag.lower() == 'add': + for val in ( preset + valid_value ): + if val not in rval._valid_chars: + rval._valid_chars.append( val ) + elif action_elem.tag.lower() == 'remove': + for val in ( preset + valid_value ): + while val in rval._valid_chars: + rval._valid_chars.remove( val ) + else: + log.debug( 'Invalid action tag in valid: %s' % action_elem.tag ) + for mapping_elem in elem.findall( 'mapping' ): + rval._mapped_chars = rval.get_mapping_by_name( mapping_elem.get( 'initial', 'default' ) ) + for action_elem in mapping_elem: + map_source = action_elem.get( 'source', None ) + map_target = action_elem.get( 'target', None ) + preset = rval.get_mapping_by_name( action_elem.get( 'preset', 'none' ) ) + if action_elem.tag.lower() == 'add': + rval._mapped_chars.update( preset ) + if None not in [ map_source, map_target ]: + rval._mapped_chars[ map_source ] = map_target + elif action_elem.tag.lower() == 'remove': + for map_key in preset.keys(): + if map_key in rval._mapped_chars: + del rval._mapped_chars[ map_key ] + if map_source is not None and map_key in rval._mapped_chars: + del rval._mapped_chars[ map_key ] + else: + log.debug( 'Invalid action tag in mapping: %s' % action_elem.tag ) + return rval + + @classmethod + def get_valid_by_name( cls, name ): + rval = [] + for split_name in name.split( ',' ): + split_name = split_name.strip() + value = [] + if split_name.startswith( 'string.' ): + try: + value = eval( split_name ) + except NameError, e: + log.debug( 'Invalid string preset specified: %s' % e ) + elif split_name in cls.VALID_PRESET: + value = cls.VALID_PRESET[ split_name ] + else: + log.debug( 'Invalid preset name specified: %s' % split_name ) + rval.extend( [ val for val in value if val not in rval ] ) + return rval + + @classmethod + def get_mapping_by_name( cls, name ): + rval = {} + for split_name in name.split( ',' ): + split_name = split_name.strip() + if split_name in cls.MAPPING_PRESET: + rval.update( cls.MAPPING_PRESET[ split_name ] ) + else: + log.debug( 'Invalid preset name specified: %s' % split_name ) + return rval + #end class methods + + def __init__( self ): + self._valid_chars = [] #List of valid characters + self._mapped_chars = {} #Replace a char with a any number of characters + self._invalid_char = self.DEFAULT_INVALID_CHAR #Replace invalid characters with this character + self.sanitize = True #Simply pass back the passed in value + + def restore_text( self, text ): + """Restores sanitized text""" + if self.sanitize: + for key, value in self._mapped_chars.iteritems(): + text = text.replace( value, key ) + return text + + def restore_param( self, value ): + if self.sanitize: + if isinstance( value, basestring ): + return self.restore_text( value ) + elif isinstance( value, list ): + return map( self.restore_text, value ) + else: + raise Exception, 'Unknown parameter type (%s:%s)' % ( type( value ), value ) + return value + + def sanitize_text( self, text ): + """Restricts the characters that are allowed in a text""" + if not self.sanitize: + return text + rval = [] + for c in text: + if c in self._valid_chars: + rval.append( c ) + elif c in self._mapped_chars: + rval.append( self._mapped_chars[ c ] ) + else: + rval.append( self._invalid_char ) + return ''.join( rval ) + + def sanitize_param( self, value ): + """Clean incoming parameters (strings or lists)""" + if not self.sanitize: + return value + if isinstance( value, basestring ): + return self.sanitize_text( value ) + elif isinstance( value, list ): + return map( self.sanitize_text, value ) + else: + raise Exception, 'Unknown parameter type (%s:%s)' % ( type( value ), value ) diff -r 81475cecea2c -r d279017969cd lib/galaxy/util/__init__.py --- a/lib/galaxy/util/__init__.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/util/__init__.py Mon Dec 07 10:19:41 2009 -0500 @@ -174,70 +174,16 @@ [('status', 'on'), ('symbols', 'alpha'), ('symbols', '__lt____gt__'), ('symbols', 'XrmXX!')] """ - # HACK: Need top prevent sanitizing certain parameter types. The - # better solution I think is to more responsibility for - # sanitizing into the tool parameters themselves so that - # different parameters can be sanitized in different ways. + # is NEVER_SANITIZE required now that sanitizing for tool parameters can be controlled on a per parameter basis and occurs via InputValueWrappers? NEVER_SANITIZE = ['file_data', 'url_paste', 'URL', 'filesystem_paths'] - def __init__( self, params, safe=True, sanitize=True, tool=None ): - if safe: + def __init__( self, params, sanitize=True ): + if sanitize: for key, value in params.items(): - # Check to see if we should translate certain parameter names. For example, - # in data_source tools, the external data source application may send back - # parameter names like GENOME which is translated to dbkey in Galaxy. - # param_trans_dict looks like { "GENOME" : [ "dbkey" "?" ] } - new_key = key - new_value = value - if tool and tool.tool_type == 'data_source': - if key in tool.param_trans_dict: - new_key = tool.param_trans_dict[ key ][0] - if new_key == 'data_type': - try: - # The Galaxy "data_type entry is special in that it can include the ability - # to translate the format to a Galaxy supported format. In the dict, this entry - # looks something like: - # {'hgta_outputType': ['data_type', 'bed', {'selectedFields': 'tabular'}] } - format_trans_dict = tool.param_trans_dict[ key ][2] - if value in format_trans_dict: - new_value = format_trans_dict[ value ] - except: - pass - elif new_key == 'URL': - # As above, the URL can include a set of params from the remote data source - # that must be appended to the URL prior to the post. In this case, the - # dict entry would look something like: - # ['URL', '', {'q': '', 's': '', 'd': '', 'dbkey': '', 't': ''}] - try: - add_to_url_dict = tool.param_trans_dict[ key ][2] - if new_value.count( '?' ) == 0: - sep = '?' - else: - sep = '&' - for param_name, missing_value in add_to_url_dict.items(): - param_value = params.get( param_name, None ) - if not param_value and missing_value: - param_value = missing_value - if param_value: - new_value += '%s%s=%s' % ( sep, param_name, param_value ) - sep = '&' - except: - pass - if not value and not new_value: - new_value = tool.param_trans_dict[ key ][1] - if sanitize and not ( key in self.NEVER_SANITIZE or True in [ key.endswith( "|%s" % nonsanitize_parameter ) for nonsanitize_parameter in self.NEVER_SANITIZE ] ): #sanitize check both ungrouped and grouped parameters by name - self.__dict__[ new_key ] = sanitize_param( new_value ) + if key not in self.NEVER_SANITIZE and True not in [ key.endswith( "|%s" % nonsanitize_parameter ) for nonsanitize_parameter in self.NEVER_SANITIZE ]: #sanitize check both ungrouped and grouped parameters by name. Anything relying on NEVER_SANITIZE should be changed to not require this and NEVER_SANITIZE should be removed. + self.__dict__[ key ] = sanitize_param( value ) else: - self.__dict__[ new_key ] = new_value - if tool and tool.tool_type == 'data_source': - # Add the tool's URL_method to params - self.__dict__[ 'URL_method' ] = tool.URL_method - for key, value in tool.param_trans_dict.items(): - # Make sure that all translated values used in Galaxy are added to the params - galaxy_name = tool.param_trans_dict[ key ][0] - if galaxy_name not in self.__dict__: - # This will set the galaxy_name to the "missing" value - self.__dict__[ galaxy_name ] = tool.param_trans_dict[ key ][1] + self.__dict__[ key ] = value else: self.__dict__.update(params) diff -r 81475cecea2c -r d279017969cd lib/galaxy/web/controllers/async.py --- a/lib/galaxy/web/controllers/async.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/web/controllers/async.py Mon Dec 07 10:19:41 2009 -0500 @@ -32,7 +32,7 @@ return trans.response.send_redirect( "/index" ) history = trans.get_history( create=True ) - params = util.Params(kwd, safe=False) + params = util.Params(kwd, sanitize=False) STATUS = params.STATUS URL = params.URL data_id = params.data_id diff -r 81475cecea2c -r d279017969cd lib/galaxy/web/controllers/root.py --- a/lib/galaxy/web/controllers/root.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/web/controllers/root.py Mon Dec 07 10:19:41 2009 -0500 @@ -270,7 +270,7 @@ if trans.app.security_agent.can_access_dataset( roles, data.dataset ): if data.state == trans.model.Dataset.states.UPLOAD: return trans.show_error_message( "Please wait until this dataset finishes uploading before attempting to edit its metadata." ) - params = util.Params( kwd, safe=False ) + params = util.Params( kwd, sanitize=False ) if params.change: # The user clicked the Save button on the 'Change data type' form if data.datatype.allow_datatype_change and trans.app.datatypes_registry.get_datatype_by_extension( params.datatype ).allow_datatype_change: diff -r 81475cecea2c -r d279017969cd lib/galaxy/web/controllers/tool_runner.py --- a/lib/galaxy/web/controllers/tool_runner.py Fri Dec 04 20:24:09 2009 -0500 +++ b/lib/galaxy/web/controllers/tool_runner.py Mon Dec 07 10:19:41 2009 -0500 @@ -43,7 +43,10 @@ log.error( "index called with tool id '%s' but no such tool exists", tool_id ) trans.log_event( "Tool id '%s' does not exist" % tool_id ) return "Tool '%s' does not exist, kwd=%s " % (tool_id, kwd) - params = util.Params( kwd, sanitize=tool.options.sanitize, tool=tool ) + params = util.Params( kwd, sanitize = False ) #Sanitize parameters when substituting into command line via input wrappers + #do param translation here, used by datasource tools + if tool.input_translator: + tool.input_translator.translate( params ) history = trans.get_history() template, vars = tool.handle_input( trans, params.__dict__ ) if len(params) > 0: @@ -73,7 +76,7 @@ # Get the associated job, if any. If this hda was copied from another, # we need to find the job that created the origial hda job_hda = data - while job_hda.copied_from_history_dataset_association: + while job_hda.copied_from_history_dataset_association:#should this check library datasets as well? job_hda = job_hda.copied_from_history_dataset_association if not job_hda.creating_job_associations: error( "Could not find the job for this dataset" ) @@ -153,7 +156,7 @@ tool = self.get_toolbox().tools_by_id.get( tool_id, None ) if not tool: return False # bad tool_id - nonfile_params = util.Params( kwd, sanitize=tool.options.sanitize, tool=tool ) + nonfile_params = util.Params( kwd, sanitize=False ) if kwd.get( 'tool_state', None ) not in ( None, 'None' ): encoded_state = util.string_to_object( kwd["tool_state"] ) tool_state = DefaultToolState() diff -r 81475cecea2c -r d279017969cd test-data/2.tabular --- a/test-data/2.tabular Fri Dec 04 20:24:09 2009 -0500 +++ b/test-data/2.tabular Mon Dec 07 10:19:41 2009 -0500 @@ -1,10 +1,10 @@ -1 68 4.1 -2 71 4.6 -3 62 3.8 -4 75 4.4 -5 58 3.2 -6 60 3.1 -7 67 3.8 -8 68 4.1 -9 71 4.3 -10 69 3.7 +1 68 4.1 +2 71 4.6 +3 62 3.8 +4 75 4.4 +5 58 3.2 +6 60 3.1 +7 67 3.8 +8 68 4.1 +9 71 4.3 +10 69 3.7 diff -r 81475cecea2c -r d279017969cd test-data/joiner_out3.bed --- a/test-data/joiner_out3.bed Fri Dec 04 20:24:09 2009 -0500 +++ b/test-data/joiner_out3.bed Mon Dec 07 10:19:41 2009 -0500 @@ -6,46 +6,46 @@ chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - chr11 116124407 116124501 AK057832_cds_0_0_chr11_116124408_r 0 - chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + chr11 116206508 116206563 NM_000040_cds_1_0_chr11_116206509_f 0 + chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - chr11 116211733 116212337 BC005380_cds_0_0_chr11_116211734_r 0 - -chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + X X X X X X +chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + ~ ~ ~ ~ ~ ~ chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - chr12 38440094 38440321 NM_052885_cds_0_0_chr12_38440095_r 0 - chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + chr13 112381694 112381953 NM_207440_cds_1_0_chr13_112381695_f 0 + chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - chr14 98710240 98712285 NM_022898_cds_0_0_chr14_98710241_r 0 - chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - chr15 41486872 41487060 BX537418_cds_0_0_chr15_41486873_r 0 - chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + chr15 41673708 41673857 AK223365_cds_0_0_chr15_41673709_f 0 + chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - chr15 41679161 41679250 NM_153700_cds_0_0_chr15_41679162_r 0 - -chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + X X X X X X +chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + ~ ~ ~ ~ ~ ~ chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + chr16 142908 143003 NM_005332_cds_0_0_chr16_142909_f 0 + -chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - X X X X X X +chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - ~ ~ ~ ~ ~ ~ chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + chr16 244413 244681 AK057165_cds_2_0_chr16_244414_f 0 + chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - chr16 259268 259383 AB016929_cds_0_0_chr16_259269_r 0 - chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - chr18 23786114 23786321 NM_001792_cds_0_0_chr18_23786115_r 0 - chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + chr18 59406881 59407046 NM_012397_cds_1_0_chr18_59406882_f 0 + chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - chr18 59455932 59456337 AB046400_cds_0_0_chr18_59455933_r 0 - -chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + X X X X X X +chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + ~ ~ ~ ~ ~ ~ chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + chr19 59068595 59069564 BC013995_cds_1_0_chr19_59068596_f 0 + chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - chr19 59236026 59236146 NM_198481_cds_0_0_chr19_59236027_r 0 - chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + chr19 59297998 59298008 NM_004542_cds_0_0_chr19_59297999_f 0 + -chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - X X X X X X +chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - ~ ~ ~ ~ ~ ~ chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + chr2 118288583 118288668 NM_006773_cds_0_0_chr2_118288584_f 0 + -chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - X X X X X X -chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + X X X X X X +chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - ~ ~ ~ ~ ~ ~ +chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + ~ ~ ~ ~ ~ ~ chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - chr2 220229609 220230869 NM_024536_cds_0_0_chr2_220229610_r 0 - chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - chr20 33330413 33330423 NM_181466_cds_0_0_chr20_33330414_r 0 - chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + chr20 33513606 33513792 AF022655_cds_1_0_chr20_33513607_f 0 + -chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - X X X X X X -chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + X X X X X X -chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + X X X X X X +chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - ~ ~ ~ ~ ~ ~ +chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + ~ ~ ~ ~ ~ ~ +chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + ~ ~ ~ ~ ~ ~ chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - chr21 32869641 32870022 NM_018277_cds_3_0_chr21_32869642_r 0 - chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + chr21 33321040 33322012 NM_005806_cds_1_0_chr21_33321041_f 0 + -chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - X X X X X X +chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - ~ ~ ~ ~ ~ ~ chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + chr22 30120223 30120265 NM_004147_cds_0_0_chr22_30120224_f 0 + chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - chr22 30160419 30160661 BC032941_cds_0_0_chr22_30160420_r 0 - -chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + X X X X X X -chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - X X X X X X +chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + ~ ~ ~ ~ ~ ~ +chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - ~ ~ ~ ~ ~ ~ chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + chr5 131424298 131424460 NM_000588_cds_0_0_chr5_131424299_f 0 + chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - chr5 131556601 131556672 BC035813_cds_0_0_chr5_131556602_r 0 - chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + chr5 131621326 131621419 BC003096_cds_0_0_chr5_131621327_f 0 + -chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - X X X X X X +chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - ~ ~ ~ ~ ~ ~ chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - chr6 108299600 108299744 NM_007214_cds_0_0_chr6_108299601_r 0 - chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + chr6 108594662 108594687 NM_003269_cds_0_0_chr6_108594663_f 0 + chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - chr6 108640045 108640151 NM_003795_cds_0_0_chr6_108640046_r 0 - @@ -57,8 +57,8 @@ chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - chr8 118881131 118881317 NM_000127_cds_0_0_chr8_118881132_r 0 - chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + chr9 128764156 128764189 BC051300_cds_0_0_chr9_128764157_f 0 + chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - chr9 128787519 128789136 NM_014908_cds_0_0_chr9_128787520_r 0 - -chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + X X X X X X -chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - X X X X X X +chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + ~ ~ ~ ~ ~ ~ +chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - ~ ~ ~ ~ ~ ~ chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + chrX 122745047 122745924 NM_001167_cds_1_0_chrX_122745048_f 0 + chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - chrX 152648964 152649196 NM_000425_cds_0_0_chrX_152648965_r 0 - chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + chrX 152691446 152691471 AF101728_cds_0_0_chrX_152691447_f 0 + diff -r 81475cecea2c -r d279017969cd tools/data_source/biomart.xml --- a/tools/data_source/biomart.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/biomart.xml Mon Dec 07 10:19:41 2009 -0500 @@ -7,7 +7,7 @@ TODO: Hack to get biomart to work - the 'add_to_URL' param can be eliminated when the Biomart team encodes URL prior to sending, meanwhile everything including and beyond the first '&' is truncated from URL. They said they'll let us know when this is fixed at their end. --> -<tool name="BioMart" id="biomart" tool_type="data_source" URL_method="get" version="1.0.1"> +<tool name="BioMart" id="biomart" tool_type="data_source" version="1.0.1"> <description>Central server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://www.biomart.org/biomart/martview" check_values="false" method="get" target="_top"> @@ -16,16 +16,17 @@ </inputs> <request_param_translation> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="_export" missing="1" /> - <param_from_source name="GALAXY_URL" missing="0" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="_export" missing="1" /> + <value name="GALAXY_URL" missing="0" /> + </append_param> </request_param> <request_param galaxy_name="data_type" remote_name="exportView_outputformat" missing="tabular" > - <data_type_translation> - <format galaxy_format="tabular" remote_format="TSV" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="TSV" /> + </value_translation> </request_param> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="get" /> <request_param galaxy_name="dbkey" remote_name="dbkey" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> <request_param galaxy_name="table" remote_name="table" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/biomart_test.xml --- a/tools/data_source/biomart_test.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/biomart_test.xml Mon Dec 07 10:19:41 2009 -0500 @@ -7,7 +7,7 @@ TODO: Hack to get biomart to work - the 'add_to_URL' param can be eliminated when the Biomart team encodes URL prior to sending, meanwhile everything including and beyond the first '&' is truncated from URL. They said they'll let us know when this is fixed at their end. --> -<tool name="BioMart" id="biomart_test" tool_type="data_source" URL_method="get" version="1.0.1"> +<tool name="BioMart" id="biomart_test" tool_type="data_source" version="1.0.1"> <description>Test server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://test.biomart.org/biomart/martview" check_values="false" method="get" target="_top"> @@ -16,16 +16,17 @@ </inputs> <request_param_translation> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="_export" missing="1" /> - <param_from_source name="GALAXY_URL" missing="0" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="_export" missing="1" /> + <value name="GALAXY_URL" missing="0" /> + </append_param> </request_param> <request_param galaxy_name="data_type" remote_name="exportView_outputformat" missing="tabular" > - <data_type_translation> - <format galaxy_format="tabular" remote_format="TSV" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="TSV" /> + </value_translation> </request_param> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="get" /> <request_param galaxy_name="dbkey" remote_name="dbkey" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> <request_param galaxy_name="table" remote_name="table" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/epigraph_import.xml --- a/tools/data_source/epigraph_import.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/epigraph_import.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="EpiGRAPH" id="epigraph_import" tool_type="data_source" URL_method="get"> +<tool name="EpiGRAPH" id="epigraph_import" tool_type="data_source"> <description> server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://epigraph.mpi-inf.mpg.de/WebGRAPH/faces/Login.jsp" check_values="false" method="get"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=epigraph_import" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="get" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="GENOME" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/epigraph_import_test.xml --- a/tools/data_source/epigraph_import_test.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/epigraph_import_test.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="EpiGRAPH" id="epigraph_import_test" tool_type="data_source" URL_method="get"> +<tool name="EpiGRAPH" id="epigraph_import_test" tool_type="data_source"> <description> test server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://epigraph.mpi-inf.mpg.de/WebGRAPH_Public_Test/faces/Login.jsp" check_values="false" method="get"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=epigraph_import_test" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="get" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="GENOME" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/eupathdb.xml --- a/tools/data_source/eupathdb.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/eupathdb.xml Mon Dec 07 10:19:41 2009 -0500 @@ -3,7 +3,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="EuPathDB" id="eupathdb" tool_type="data_source" url_method="post"> +<tool name="EuPathDB" id="eupathdb" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://galaxy.eupathdb.org/eupathdb.galaxy/queries_tools.jsp" check_values="false" method="post"> @@ -11,15 +11,16 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=eupathdb" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="dbkey" missing="?" /> - <param_from_source name="wdk_history_id" missing="" /> - <param_from_source name="wdkReportFormat" missing="tabular" /> - <param_from_source name="selectedFields" missing="" /> - <param_from_source name="includeHeader" missing="yes" /> - <param_from_source name="downloadType" missing="plain" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="dbkey" missing="?" /> + <value name="wdk_history_id" missing="" /> + <value name="wdkReportFormat" missing="tabular" /> + <value name="selectedFields" missing="" /> + <value name="includeHeader" missing="yes" /> + <value name="downloadType" missing="plain" /> + </append_param> </request_param> <request_param galaxy_name="format" remote_name="wdkReportFormat" missing="tabular" /> <request_param galaxy_name="dbkey" remote_name="dbkey" missing="?" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/flymine.xml --- a/tools/data_source/flymine.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/flymine.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="Flymine" id="flymine" tool_type="data_source" URL_method="post"> +<tool name="Flymine" id="flymine" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://www.flymine.org" check_values="false" method="get" target="_top"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=flymine" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/flymine_test.xml --- a/tools/data_source/flymine_test.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/flymine_test.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="Flymine test" id="flymine_test" tool_type="data_source" URL_method="post"> +<tool name="Flymine test" id="flymine_test" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://preview.flymine.org/preview/begin.do" check_values="false" method="get" target="_top"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=flymine" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/gramene_mart.xml --- a/tools/data_source/gramene_mart.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/gramene_mart.xml Mon Dec 07 10:19:41 2009 -0500 @@ -7,7 +7,7 @@ TODO: Hack to get biomart to work - the 'add_to_URL' param can be eliminated when the Biomart team encodes URL prior to sending, meanwhile everything including and beyond the first '&' is truncated from URL. They said they'll let us know when this is fixed at their end. --> -<tool name="GrameneMart" id="gramenemart" tool_type="data_source" URL_method="get" version="1.0.1"> +<tool name="GrameneMart" id="gramenemart" tool_type="data_source" version="1.0.1"> <description> Central server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://www.gramene.org/biomart/martview" check_values="false" method="get" target="_top"> @@ -16,16 +16,17 @@ </inputs> <request_param_translation> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="_export" missing="1" /> - <param_from_source name="GALAXY_URL" missing="0" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="_export" missing="1" /> + <value name="GALAXY_URL" missing="0" /> + </append_param> </request_param> <request_param galaxy_name="data_type" remote_name="exportView_outputformat" missing="tabular"> - <data_type_translation> - <format galaxy_format="tabular" remote_format="TSV" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="TSV" /> + </value_translation> </request_param> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="get" /> <request_param galaxy_name="dbkey" remote_name="dbkey" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> <request_param galaxy_name="table" remote_name="table" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/modmine.xml --- a/tools/data_source/modmine.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/modmine.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="modMine" id="modmine" tool_type="data_source" URL_method="post"> +<tool name="modMine" id="modmine" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://intermine.modencode.org/" check_values="false" method="get" target="_top"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=modmine" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/ratmine.xml --- a/tools/data_source/ratmine.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/ratmine.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="Ratmine" id="ratmine" tool_type="data_source" URL_method="post"> +<tool name="Ratmine" id="ratmine" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://ratmine.mcw.edu/ratmine/begin.do" check_values="false" method="get" target="_top"> @@ -12,6 +12,7 @@ <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=ratmine" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="organism" missing="" /> diff -r 81475cecea2c -r d279017969cd tools/data_source/ucsc_tablebrowser.xml --- a/tools/data_source/ucsc_tablebrowser.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/ucsc_tablebrowser.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="UCSC Main" id="ucsc_table_direct1" tool_type="data_source" URL_method="post"> +<tool name="UCSC Main" id="ucsc_table_direct1" tool_type="data_source"> <description>table browser</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://genome.ucsc.edu/cgi-bin/hgTables" check_values="false" method="get"> @@ -16,20 +16,21 @@ <param name="hgta_outputType" type="hidden" value="bed" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="org" missing="unknown species" /> <request_param galaxy_name="table" remote_name="hgta_table" missing="unknown table" /> <request_param galaxy_name="description" remote_name="hgta_regionType" missing="no description" /> <request_param galaxy_name="data_type" remote_name="hgta_outputType" missing="tabular" > - <data_type_translation> - <format galaxy_format="tabular" remote_format="primaryTable" /> - <format galaxy_format="tabular" remote_format="selectedFields" /> - <format galaxy_format="wig" remote_format="wigData" /> - <format galaxy_format="interval" remote_format="tab" /> - <format galaxy_format="html" remote_format="hyperlinks" /> - <format galaxy_format="fasta" remote_format="sequence" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="primaryTable" /> + <value galaxy_value="tabular" remote_value="selectedFields" /> + <value galaxy_value="wig" remote_value="wigData" /> + <value galaxy_value="interval" remote_value="tab" /> + <value galaxy_value="html" remote_value="hyperlinks" /> + <value galaxy_value="fasta" remote_value="sequence" /> + </value_translation> </request_param> </request_param_translation> <uihints minwidth="800"/> diff -r 81475cecea2c -r d279017969cd tools/data_source/ucsc_tablebrowser_archaea.xml --- a/tools/data_source/ucsc_tablebrowser_archaea.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/ucsc_tablebrowser_archaea.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="UCSC Archaea" id="ucsc_table_direct_archaea1" tool_type="data_source" URL_method="post"> +<tool name="UCSC Archaea" id="ucsc_table_direct_archaea1" tool_type="data_source"> <description>table browser</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://archaea.ucsc.edu/cgi-bin/hgTables" check_values="false" method="get"> @@ -16,20 +16,21 @@ <param name="hgta_outputType" type="hidden" value="bed" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="org" missing="unknown species" /> - <request_param galaxy_name="table" remote_name="hgta_track" missing="" /> - <request_param galaxy_name="description" remote_name="hgta_regionType" missing="" /> + <request_param galaxy_name="table" remote_name="hgta_table" missing="unknown table" /> + <request_param galaxy_name="description" remote_name="hgta_regionType" missing="no description" /> <request_param galaxy_name="data_type" remote_name="hgta_outputType" missing="tabular" > - <data_type_translation> - <format galaxy_format="tabular" remote_format="primaryTable" /> - <format galaxy_format="tabular" remote_format="selectedFields" /> - <format galaxy_format="wig" remote_format="wigdata" /> - <format galaxy_format="interval" remote_format="tab" /> - <format galaxy_format="html" remote_format="hyperlinks" /> - <format galaxy_format="fasta" remote_format="sequence" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="primaryTable" /> + <value galaxy_value="tabular" remote_value="selectedFields" /> + <value galaxy_value="wig" remote_value="wigData" /> + <value galaxy_value="interval" remote_value="tab" /> + <value galaxy_value="html" remote_value="hyperlinks" /> + <value galaxy_value="fasta" remote_value="sequence" /> + </value_translation> </request_param> </request_param_translation> <uihints minwidth="800"/> diff -r 81475cecea2c -r d279017969cd tools/data_source/ucsc_tablebrowser_test.xml --- a/tools/data_source/ucsc_tablebrowser_test.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/ucsc_tablebrowser_test.xml Mon Dec 07 10:19:41 2009 -0500 @@ -4,7 +4,7 @@ the initial response. If value of 'URL_method' is 'post', any additional params coming back in the initial response ( in addition to 'URL' ) will be encoded and appended to URL and a post will be performed. --> -<tool name="UCSC Test" id="ucsc_table_direct_test1" tool_type="data_source" URL_method="post"> +<tool name="UCSC Test" id="ucsc_table_direct_test1" tool_type="data_source"> <description>table browser</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://genome-test.cse.ucsc.edu/cgi-bin/hgTables" check_values="false" method="get"> @@ -16,20 +16,21 @@ <param name="hgta_outputType" type="hidden" value="bed" /> </inputs> <request_param_translation> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="URL" remote_name="URL" missing="" /> <request_param galaxy_name="dbkey" remote_name="db" missing="?" /> <request_param galaxy_name="organism" remote_name="org" missing="unknown species" /> - <request_param galaxy_name="table" remote_name="hgta_track" missing="" /> - <request_param galaxy_name="description" remote_name="hgta_regionType" missing="" /> + <request_param galaxy_name="table" remote_name="hgta_table" missing="unknown table" /> + <request_param galaxy_name="description" remote_name="hgta_regionType" missing="no description" /> <request_param galaxy_name="data_type" remote_name="hgta_outputType" missing="tabular" > - <data_type_translation> - <format galaxy_format="tabular" remote_format="primaryTable" /> - <format galaxy_format="tabular" remote_format="selectedFields" /> - <format galaxy_format="wig" remote_format="wigdata" /> - <format galaxy_format="interval" remote_format="tab" /> - <format galaxy_format="html" remote_format="hyperlinks" /> - <format galaxy_format="fasta" remote_format="sequence" /> - </data_type_translation> + <value_translation> + <value galaxy_value="tabular" remote_value="primaryTable" /> + <value galaxy_value="tabular" remote_value="selectedFields" /> + <value galaxy_value="wig" remote_value="wigData" /> + <value galaxy_value="interval" remote_value="tab" /> + <value galaxy_value="html" remote_value="hyperlinks" /> + <value galaxy_value="fasta" remote_value="sequence" /> + </value_translation> </request_param> </request_param_translation> <uihints minwidth="800"/> diff -r 81475cecea2c -r d279017969cd tools/data_source/wormbase.xml --- a/tools/data_source/wormbase.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/wormbase.xml Mon Dec 07 10:19:41 2009 -0500 @@ -1,5 +1,5 @@ <?xml version="1.0"?> -<tool name="Wormbase" id="wormbase" tool_type="data_source" URL_method="post"> +<tool name="Wormbase" id="wormbase" tool_type="data_source"> <description>server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://www.wormbase.org/db/seq/gbgff/c_elegans/" check_values="false" target="_top"> @@ -8,14 +8,15 @@ </inputs> <request_param_translation> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="d" missing="" /> - <param_from_source name="dbkey" missing="" /> - <param_from_source name="q" missing="" /> - <param_from_source name="s" missing="" /> - <param_from_source name="t" missing="" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="d" missing="" /> + <value name="dbkey" missing="" /> + <value name="q" missing="" /> + <value name="s" missing="" /> + <value name="t" missing="" /> + </append_param> </request_param> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="data_type" remote_name="data_type" missing="txt" /> </request_param_translation> <uihints minwidth="800"/> diff -r 81475cecea2c -r d279017969cd tools/data_source/wormbase_test.xml --- a/tools/data_source/wormbase_test.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/data_source/wormbase_test.xml Mon Dec 07 10:19:41 2009 -0500 @@ -1,5 +1,5 @@ <?xml version="1.0"?> -<tool name="Wormbase" id="wormbase_test" tool_type="data_source" URL_method="post"> +<tool name="Wormbase" id="wormbase_test" tool_type="data_source"> <description>test server</description> <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> <inputs action="http://dev.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" target="_top"> @@ -8,14 +8,15 @@ </inputs> <request_param_translation> <request_param galaxy_name="URL" remote_name="URL" missing=""> - <add_to_url> - <param_from_source name="d" missing="" /> - <param_from_source name="dbkey" missing="" /> - <param_from_source name="q" missing="" /> - <param_from_source name="s" missing="" /> - <param_from_source name="t" missing="" /> - </add_to_url> + <append_param separator="&" first_separator="?" join="="> + <value name="d" missing="" /> + <value name="dbkey" missing="" /> + <value name="q" missing="" /> + <value name="s" missing="" /> + <value name="t" missing="" /> + </append_param> </request_param> + <request_param galaxy_name="URL_method" remote_name="URL_method" missing="post" /> <request_param galaxy_name="data_type" remote_name="data_type" missing="txt" /> </request_param_translation> <uihints minwidth="800"/> diff -r 81475cecea2c -r d279017969cd tools/emboss_5/emboss_fuzznuc.xml --- a/tools/emboss_5/emboss_fuzznuc.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/emboss_5/emboss_fuzznuc.xml Mon Dec 07 10:19:41 2009 -0500 @@ -1,12 +1,20 @@ -<tool id="EMBOSS: fuzznuc37" name="fuzznuc" version="5.0.0"> +<tool id="EMBOSS: fuzznuc37" name="fuzznuc" version="5.0.1"> <description>Nucleic acid pattern search</description> - <command>fuzznuc -sequence $input1 -outfile $out_file1 -pattern "$pattern" -pmismatch $mismatch -complement $complement -rformat2 $out_format1 -auto</command> + <command>fuzznuc -sequence $input1 -outfile $out_file1 -pattern '$pattern' -pmismatch $mismatch -complement $complement -rformat2 $out_format1 -auto</command> <inputs> <param format="fasta" name="input1" type="data"> <label>Sequences</label> </param> <param name="pattern" size="5" type="text" value=""> <label>Search pattern</label> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target=""/> + </mapping> + </sanitizer> </param> <param name="mismatch" size="5" type="text" value="0"> <label>Number of mismatches</label> diff -r 81475cecea2c -r d279017969cd tools/filters/grep.py --- a/tools/filters/grep.py Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/filters/grep.py Mon Dec 07 10:19:41 2009 -0500 @@ -13,9 +13,11 @@ # -v true or false (output NON-matching lines) import sys +import os import re import string import commands +from tempfile import NamedTemporaryFile # This function is exceedingly useful, perhaps package for reuse? def getopts(argv): @@ -72,17 +74,15 @@ '[' :'__ob__', ']' :'__cb__', '{' :'__oc__', - '}' :'__cc__', - + '}' :'__cc__' } - + + #with new sanitizing we only need to replace for single quote, but this needs to remain for backwards compatibility for key, value in mapped_chars.items(): pattern = pattern.replace(value, key) - - pattern = pattern.replace('\'', '') - - fileRegEx = re.compile("^[A-Za-z0-9./\-_]+$") - invertRegEx = re.compile("(true)|(false)") + + fileRegEx = re.compile("^[A-Za-z0-9./\-_]+$") #why? + invertRegEx = re.compile("(true)|(false)") #why? if not fileRegEx.match(outputfile): print "Illegal output filename." @@ -94,16 +94,29 @@ print "Illegal invert option." return -7 - # grep + # invert grep search? if invert == "true": - invertflag = " -v" + invertflag = " -v" + print "Not matching pattern: %s" % pattern else: - invertflag = "" - - commandline = "grep -E"+invertflag+" '"+pattern+"' "+inputfile+" > "+outputfile - + invertflag = "" + print "Matching pattern: %s" % pattern + + #Create temp file holding pattern + #By using a file to hold the pattern, we don't have worry about sanitizing grep commandline and can include single quotes in pattern + pattern_file_name = NamedTemporaryFile().name + open( pattern_file_name, 'w' ).write( pattern ) + + #generate grep command + commandline = "grep -E %s -f %s %s > %s" % ( invertflag, pattern_file_name, inputfile, outputfile ) + + #run grep errorcode, stdout = commands.getstatusoutput(commandline) + #remove temp pattern file + os.unlink( pattern_file_name ) + + #return error code return errorcode if __name__ == "__main__": diff -r 81475cecea2c -r d279017969cd tools/filters/grep.xml --- a/tools/filters/grep.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/filters/grep.xml Mon Dec 07 10:19:41 2009 -0500 @@ -1,4 +1,4 @@ -<tool id="Grep1" name="Select"> +<tool id="Grep1" name="Select" version="1.0.1"> <description>lines that match an expression</description> <command interpreter="python">grep.py -i $input -o $out_file1 -pattern '$pattern' -v $invert</command> <inputs> @@ -7,7 +7,16 @@ <option value="false">Matching</option> <option value="true">NOT Matching</option> </param> - <param name="pattern" size="40" type="text" value="^chr([0-9A-Za-z])+" label="the pattern" help="here you can enter text or regular expression (for syntax check lower part of this frame)"/> + <param name="pattern" size="40" type="text" value="^chr([0-9A-Za-z])+" label="the pattern" help="here you can enter text or regular expression (for syntax check lower part of this frame)"> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="__sq__"/> + </mapping> + </sanitizer> + </param> </inputs> <outputs> <data format="input" name="out_file1" metadata_source="input"/> diff -r 81475cecea2c -r d279017969cd tools/filters/joiner.xml --- a/tools/filters/joiner.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/filters/joiner.xml Mon Dec 07 10:19:41 2009 -0500 @@ -1,4 +1,4 @@ -<tool id="join1" name="Join two Queries" version="2.0.1"> +<tool id="join1" name="Join two Queries" version="2.0.2"> <description>side by side on a specified field</description> <command interpreter="python">join.py $input1 $input2 $field1 $field2 $out_file1 $unmatched $partial --index_depth=3 --buffer=50000000 --fill_options_file=$fill_options_file</command> <inputs> diff -r 81475cecea2c -r d279017969cd tools/plotting/xy_plot.xml --- a/tools/plotting/xy_plot.xml Fri Dec 04 20:24:09 2009 -0500 +++ b/tools/plotting/xy_plot.xml Mon Dec 07 10:19:41 2009 -0500 @@ -94,9 +94,7 @@ <outputs> <data format="pdf" name="out_file1" /> </outputs> - <!-- - TODO: figure out how to change the submit_form() method to correctly handle refreshing the - form when the input for refresh is within a repeat construct ( like this tool ) + <tests> <test> <param name="main" value="Example XY Plot"/> @@ -106,13 +104,12 @@ <param name="xcol" value="1"/> <param name="ycol" value="2"/> <param name="type" value="line"/> - <param name="lty" value="dashed"/> + <param name="lty" value="2"/> <param name="col" value="2"/> <param name="lwd" value="1.0"/> <output name="out_file1" file="XY_Plot_1_out.pdf"/> </test> </tests> - --> <help> .. class:: infomark