encode_submission/submission_report.py

   1 import argparse
   2 import RDF
   3 import jinja2
   4 from pprint import pprint
   5
   6 from htsworkflow.util.rdfhelp import \
   7      get_model, \
   8      get_serializer, \
   9      sparql_query, \
  10      libraryOntology, \
  11      load_into_model
  12 from htsworkflow.util.rdfns import *
  13 TYPE_N = rdfNS['type']
  14 CREATION_DATE = libraryOntology['date']
  15
  16 from encode_find import DBDIR
  17
  18 DEFAULT_GENOME='hg19'
  19 DEFAULT_OUTPUT='/tmp/submission_report.html'
  20
  21 def main(cmdline=None):
  22     parser = make_parser()
  23     args = parser.parse_args(cmdline)
  24     model = get_model('encode', DBDIR)
  25     report = what_have_we_done(model, genome=args.genome)
  26     with open(DEFAULT_OUTPUT,'w') as stream:
  27         stream.write(report)
  28
  29 def make_parser():
  30     parser = argparse.ArgumentParser()
  31     parser.add_argument('--genome', default=DEFAULT_GENOME,
  32                         help='limit to one genome')
  33     parser.add_argument('--output', default='/tmp/submission_report.html',
  34                         help="specify where to write to write report")
  35     return parser
  36
  37 SUBMISSION_QUERY = """
  38 PREFIX xsd:<http://www.w3.org/2001/XMLSchema#>
  39 PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>
  40 PREFIX ucscSubmission:<http://jumpgate.caltech.edu/wiki/UcscSubmissionOntology#>
  41 PREFIX libraryOntology:<http://jumpgate.caltech.edu/wiki/LibraryOntology#>
  42 PREFIX daf: <http://jumpgate.caltech.edu/wiki/UcscDaf#>
  43 PREFIX ddf: <http://encodesubmit.ucsc.edu/pipeline/download_ddf#>
  44
  45 SELECT distinct ?assembly ?experiment ?library_urn ?library_name ?submission ?submission_status ?submission_name ?date
  46 WHERE {{
  47   ?submission ucscSubmission:library_urn ?library_urn ;
  48               ucscSubmission:has_status ?status ;
  49               ucscSubmission:name ?submission_name ;
  50               libraryOntology:date ?date .
  51   ?status daf:assembly ?assembly ;
  52           ucscSubmission:status ?submission_status .
  53   OPTIONAL {{ ?library_urn libraryOntology:name ?library_name . }}
  54   OPTIONAL {{ ?library_urn libraryOntology:experiment_type ?experiment . }}
  55   FILTER(!regex(?submission_status, "revoked", "i"))
  56   {assembly_filter}
  57 }}
  58 ORDER BY ?assembly ?experiment ?library_urn ?submission
  59 """
  60
  61 SUBMISSION_TEMPLATE = '''
  62 <html>
  63 <head>
  64 <style type="text/css">
  65 table { border-width: 0 0 1px 1px; border-style: solid; }
  66 th,td { border-width: 1px 1px 0 0; border-style: solid; margin: 0;}
  67 .library { font-size: 18pt; background-color: #EEF; }
  68 .submission { font-size: 12pt; background-color: #EFE;}
  69 </style>
  70   <title>Submission report for {{ genome }}</title>
  71 </head>
  72 <body>
  73 <h1>Genome: {{ genome }}</h1>
  74 {% for experiment in libraries %}
  75   <h2>{{ experiment }}</h2>
  76   <table>
  77     <thead>
  78       <tr class="library">
  79       <td>Library ID</td>
  80       <td colspan="3">Library Name</td>
  81       </tr>
  82       <tr class="submission">
  83       <td>Submission ID</td>
  84       <td>Last Updated</td>
  85       <td>Status</td>
  86       <td>Submission name</td>
  87       </tr>
  88     </thead>
  89     <tbody>
  90       {% for liburn, records in libraries[experiment]|dictsort %}
  91       <!-- {{ liburn }} -->
  92       <tr class="library">
  93         <td>
  94           <a href="{{libraries[experiment][liburn].0.library_urn}}">
  95             {{ libraries[experiment][liburn].0.library_urn | trim_rdf}}
  96           </a>
  97         </td>
  98         <td colspan="3">{{ libraries[experiment][liburn].0.library_name }}</td>
  99       </tr>
 100       {% for record in records|sort %}
 101       <tr class="submission">
 102         <td><a href="{{record.submission}}">{{record.submission|trim_rdf}}</a></td>
 103         <td>{{ record.date|timestamp_to_date }}</td>
 104         <td>{{ record.submission_status }}</td>
 105         <td>{{ record.submission_name }}</td>
 106       </tr>
 107       {% endfor %}
 108     {% endfor %}
 109     </tbody>
 110   </table>
 111 {% endfor %}
 112   </body>
 113 </html>
 114 '''
 115
 116 def what_have_we_done(model, genome):
 117     assembly_filter = ''
 118     assembly_filter = 'FILTER(regex(?assembly, "{0}", "i"))'.format(genome)
 119
 120     query = SUBMISSION_QUERY.format(
 121         assembly_filter=assembly_filter
 122     )
 123     compiled_query = RDF.SPARQLQuery(query)
 124     submissions = compiled_query.execute(model)
 125     libraries = group_by_library(submissions)
 126     environment = jinja2.Environment()
 127     environment.filters['trim_rdf'] = trim_rdf
 128     environment.filters['timestamp_to_date'] = timestamp_to_date
 129     template = environment.from_string(SUBMISSION_TEMPLATE)
 130     return template.render(libraries=libraries,
 131                            genome=genome)
 132
 133 def group_by_library(submissions):
 134     libraries = {}
 135     for record in submissions:
 136         urn = str(record['library_urn'].uri)
 137         experiment = str(record['experiment'])
 138         libraries.setdefault(experiment, {}).setdefault(urn, []).append(record)
 139     return libraries
 140
 141 def trim_rdf(value):
 142     if value is None:
 143         return
 144     value = str(value)
 145     if len(value) == 0:
 146         return value
 147     if value[-1] == '/':
 148         value = value[:-1]
 149     split_value = value.split('/')
 150     if len(split_value) == 0:
 151         return value
 152     return split_value[-1]
 153
 154 def timestamp_to_date(value):
 155     datestamp, timestamp = str(value).split('T')
 156     return datestamp
 157
 158 if __name__ == "__main__":
 159     main()