4 from pprint import pprint
6 from htsworkflow.util.rdfhelp import \
18 TYPE_N = rdfNS['type']
19 CREATION_DATE = libraryOntology['date']
21 from encode_find import DBDIR
24 DEFAULT_OUTPUT='/tmp/submission_report.html'
26 def main(cmdline=None):
27 parser = make_parser()
28 args = parser.parse_args(cmdline)
29 model = get_model('encode', DBDIR)
30 report = what_have_we_done(model, genome=args.genome)
31 with open(DEFAULT_OUTPUT,'w') as stream:
35 parser = argparse.ArgumentParser()
36 parser.add_argument('--genome', default=DEFAULT_GENOME,
37 help='limit to one genome')
38 parser.add_argument('--output', default='/tmp/submission_report.html',
39 help="specify where to write to write report")
42 SUBMISSION_QUERY = """
43 PREFIX xsd:<http://www.w3.org/2001/XMLSchema#>
44 PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>
45 PREFIX ucscSubmission:<http://jumpgate.caltech.edu/wiki/UcscSubmissionOntology#>
46 PREFIX libraryOntology:<http://jumpgate.caltech.edu/wiki/LibraryOntology#>
47 PREFIX daf: <http://jumpgate.caltech.edu/wiki/UcscDaf#>
48 PREFIX ddf: <http://encodesubmit.ucsc.edu/pipeline/download_ddf#>
50 SELECT distinct ?assembly ?experiment ?library_urn ?library_name ?submission ?submission_status ?submission_name ?date
52 ?submission ucscSubmission:library_urn ?library_urn ;
53 ucscSubmission:has_status ?status ;
54 ucscSubmission:name ?submission_name ;
55 libraryOntology:date ?date .
56 ?status daf:assembly ?assembly ;
57 ucscSubmission:status ?submission_status .
58 OPTIONAL {{ ?library_urn libraryOntology:name ?library_name . }}
59 OPTIONAL {{ ?library_urn libraryOntology:experiment_type ?experiment . }}
60 FILTER(!regex(?submission_status, "revoked", "i"))
63 ORDER BY ?assembly ?experiment ?library_urn ?submission
66 SUBMISSION_TEMPLATE = '''
69 <style type="text/css">
70 table { border-width: 0 0 1px 1px; border-style: solid; }
71 th,td { border-width: 1px 1px 0 0; border-style: solid; margin: 0;}
72 .library { font-size: 18pt; background-color: #EEF; }
73 .submission { font-size: 12pt; background-color: #EFE;}
75 <title>Submission report for {{ genome }}</title>
78 <h1>Genome: {{ genome }}</h1>
79 {% for experiment in libraries %}
80 <h2>{{ experiment }}</h2>
85 <td colspan="3">Library Name</td>
87 <tr class="submission">
88 <td>Submission ID</td>
91 <td>Submission name</td>
95 {% for liburn, records in libraries[experiment]|dictsort %}
99 <a href="{{libraries[experiment][liburn].0.library_urn}}">
100 {{ libraries[experiment][liburn].0.library_urn | trim_rdf}}
103 <td colspan="3">{{ libraries[experiment][liburn].0.library_name }}</td>
105 {% for record in records|sort %}
106 <tr class="submission">
107 <td><a href="{{record.submission}}">{{record.submission|trim_rdf}}</a></td>
108 <td>{{ record.date|timestamp_to_date }}</td>
109 <td>{{ record.submission_status }}</td>
110 <td>{{ record.submission_name }}</td>
121 def what_have_we_done(model, genome):
123 assembly_filter = 'FILTER(regex(?assembly, "{0}", "i"))'.format(genome)
125 query = SUBMISSION_QUERY.format(
126 assembly_filter=assembly_filter
128 compiled_query = RDF.SPARQLQuery(query)
129 submissions = compiled_query.execute(model)
130 libraries = group_by_library(submissions)
131 environment = jinja2.Environment()
132 environment.filters['trim_rdf'] = trim_rdf
133 environment.filters['timestamp_to_date'] = timestamp_to_date
134 template = environment.from_string(SUBMISSION_TEMPLATE)
135 return template.render(libraries=libraries,
138 def group_by_library(submissions):
140 for record in submissions:
141 urn = str(record['library_urn'].uri)
142 experiment = str(record['experiment'])
143 libraries.setdefault(experiment, {}).setdefault(urn, []).append(record)
154 split_value = value.split('/')
155 if len(split_value) == 0:
157 return split_value[-1]
159 def timestamp_to_date(value):
160 datestamp, timestamp = str(value).split('T')
163 if __name__ == "__main__":