Mercurial > repos > devteam > cluster

comparison operation_filter.py @ 3:765ceb06c3e2 draft

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-devteam/tree/master/tool_collections/gops/cluster commit a1517c9d22029095120643bbe2c8fa53754dd2b7
author devteam
date Wed, 11 Nov 2015 12:47:24 -0500
parents d5677eecbad4
children 05696474ee89
comparison
equal deleted inserted replaced
2:520de69b107a 3:765ceb06c3e2
1 # runs after the job (and after the default post-filter) 1 # runs after the job (and after the default post-filter)
2 import os
3 from galaxy import eggs
4 from galaxy import jobs
5 from galaxy.tools.parameters import DataToolParameter 2 from galaxy.tools.parameters import DataToolParameter
6 3
7 from galaxy.jobs.handler import JOB_ERROR 4 from galaxy.jobs.handler import JOB_ERROR
8 5
9 # Older py compatibility 6 # Older py compatibility
10 try: 7 try:
11 set() 8 set()
12 except: 9 except:
13 from sets import Set as set 10 from sets import Set as set
14 11
15 #def exec_before_process(app, inp_data, out_data, param_dict, tool=None):
16 # """Sets the name of the data"""
17 # dbkeys = sets.Set( [data.dbkey for data in inp_data.values() ] )
18 # if len(dbkeys) != 1:
19 # raise Exception, '<p><font color="yellow">Both Queries must be from the same genome build</font></p>'
20 12
21 def validate_input( trans, error_map, param_values, page_param_map ): 13 def validate_input( trans, error_map, param_values, page_param_map ):
22 dbkeys = set() 14 dbkeys = set()
23 data_param_names = set() 15 data_param_names = set()
24 data_params = 0 16 data_params = 0
25 for name, param in page_param_map.iteritems(): 17 for name, param in page_param_map.iteritems():
26 if isinstance( param, DataToolParameter ): 18 if isinstance( param, DataToolParameter ):
27 # for each dataset parameter 19 # for each dataset parameter
28 if param_values.get(name, None) != None: 20 if param_values.get(name, None) is not None:
29 dbkeys.add( param_values[name].dbkey ) 21 dbkeys.add( param_values[name].dbkey )
30 data_params += 1 22 data_params += 1
31 # check meta data 23 # check meta data
32 try: 24 try:
33 param = param_values[name] 25 param = param_values[name]
34 if isinstance( param.datatype, trans.app.datatypes_registry.get_datatype_by_extension( 'gff' ).__class__ ): 26 if isinstance( param.datatype, trans.app.datatypes_registry.get_datatype_by_extension( 'gff' ).__class__ ):
35 # TODO: currently cannot validate GFF inputs b/c they are not derived from interval. 27 # TODO: currently cannot validate GFF inputs b/c they are not derived from interval.
36 pass 28 pass
37 else: # Validate interval datatype. 29 else: # Validate interval datatype.
38 startCol = int( param.metadata.startCol ) 30 int( param.metadata.startCol )
39 endCol = int( param.metadata.endCol ) 31 int( param.metadata.endCol )
40 chromCol = int( param.metadata.chromCol ) 32 int( param.metadata.chromCol )
41 if param.metadata.strandCol is not None: 33 if param.metadata.strandCol is not None:
42 strandCol = int ( param.metadata.strandCol ) 34 int( param.metadata.strandCol )
43 else:
44 strandCol = 0
45 except: 35 except:
46 error_msg = "The attributes of this dataset are not properly set. " + \ 36 error_msg = "The attributes of this dataset are not properly set. " + \
47 "Click the pencil icon in the history item to set the chrom, start, end and strand columns." 37 "Click the pencil icon in the history item to set the chrom, start, end and strand columns."
48 error_map[name] = error_msg 38 error_map[name] = error_msg
49 data_param_names.add( name ) 39 data_param_names.add( name )
50 if len( dbkeys ) > 1: 40 if len( dbkeys ) > 1:
51 for name in data_param_names: 41 for name in data_param_names:
52 error_map[name] = "All datasets must belong to same genomic build, " \ 42 error_map[name] = "All datasets must belong to same genomic build, " \
53 "this dataset is linked to build '%s'" % param_values[name].dbkey 43 "this dataset is linked to build '%s'" % param_values[name].dbkey
54 if data_params != len(data_param_names): 44 if data_params != len(data_param_names):
55 for name in data_param_names: 45 for name in data_param_names:
56 error_map[name] = "A dataset of the appropriate type is required" 46 error_map[name] = "A dataset of the appropriate type is required"
57 47
48
58 # Commented out by INS, 5/30/2007. What is the PURPOSE of this? 49 # Commented out by INS, 5/30/2007. What is the PURPOSE of this?
59 def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None): 50 def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
60 """Verify the output data after each run""" 51 """Verify the output data after each run"""
61 items = out_data.items() 52 for data in out_data.values():
62
63 for name, data in items:
64 try: 53 try:
65 if stderr and len( stderr ) > 0: 54 if stderr and len( stderr ) > 0:
66 raise Exception( stderr ) 55 raise Exception( stderr )
67 56
68 except Exception, exc: 57 except Exception:
69 data.blurb = JOB_ERROR 58 data.blurb = JOB_ERROR
70 data.state = JOB_ERROR 59 data.state = JOB_ERROR
71
72 ## def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
73 ## pass
74 60
75 61
76 def exec_after_merge(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None): 62 def exec_after_merge(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
77 exec_after_process( 63 exec_after_process(
78 app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr) 64 app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
79 65
80 # strip strand column if clusters were merged 66 # strip strand column if clusters were merged
81 items = out_data.items() 67 for data in out_data.values():
82 for name, data in items: 68 if param_dict['returntype'] is True:
83 if param_dict['returntype'] == True:
84 data.metadata.chromCol = 1 69 data.metadata.chromCol = 1
85 data.metadata.startCol = 2 70 data.metadata.startCol = 2
86 data.metadata.endCol = 3 71 data.metadata.endCol = 3
87 # merge always clobbers strand 72 # merge always clobbers strand
88 data.metadata.strandCol = None 73 data.metadata.strandCol = None
89 74
90 75
91 def exec_after_cluster(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None): 76 def exec_after_cluster(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
92 exec_after_process( 77 exec_after_process(
93 app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr) 78 app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
94 79
95 # strip strand column if clusters were merged 80 # strip strand column if clusters were merged
96 if param_dict["returntype"] == '1': 81 if param_dict["returntype"] == '1':
97 items = out_data.items() 82 for data in out_data.values():
98 for name, data in items:
99 data.metadata.strandCol = None 83 data.metadata.strandCol = None