encode_submission/submission_report.py

   1 import RDF
   2 import jinja2
   3
   4 from htsworkflow.util.rdfhelp import \
   5      dafTermOntology, \
   6      dublinCoreNS, \
   7      get_model, \
   8      get_serializer, \
   9      sparql_query, \
  10      submissionOntology, \
  11      libraryOntology, \
  12      load_into_model, \
  13      rdfNS, \
  14      rdfsNS, \
  15      xsdNS
  16 TYPE_N = rdfNS['type']
  17 CREATION_DATE = libraryOntology['date']
  18
  19 from encode_find import DBDIR
  20
  21 def main():
  22     model = get_model('encode', DBDIR)
  23     what_have_we_done(model)
  24
  25 SUBMISSION_QUERY = """
  26 PREFIX xsd:<http://www.w3.org/2001/XMLSchema#>
  27 PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>
  28 PREFIX ucscSubmission:<http://jumpgate.caltech.edu/wiki/UcscSubmissionOntology#>
  29 PREFIX libraryOntology:<http://jumpgate.caltech.edu/wiki/LibraryOntology#>
  30 PREFIX daf: <http://jumpgate.caltech.edu/wiki/UcscDaf#>
  31 PREFIX ddf: <http://encodesubmit.ucsc.edu/pipeline/download_ddf#>
  32
  33 SELECT distinct ?library_urn ?library_name ?assembly ?submission ?submission_status ?date
  34 WHERE {
  35   ?submission ucscSubmission:library_urn ?library_urn ;
  36               ucscSubmission:has_status ?status ;
  37               libraryOntology:date ?date .
  38   ?status daf:assembly ?assembly ;
  39           ucscSubmission:status ?submission_status .
  40   OPTIONAL { ?library_urn libraryOntology:name ?library_name . }
  41   FILTER(!regex(?submission_status, "revoked", "i"))
  42   FILTER(regex(?assembly, "mm9", "i"))
  43   #FILTER(!BOUND(?library_name))
  44 }
  45 ORDER BY ?library_urn ?submission
  46 """
  47
  48 SUBMISSION_TEMPLATE = """
  49 <html>
  50 <head>
  51 <style type="text/css">
  52 table { border-width: 0 0 1px 1px; border-style: solid; }
  53 th,td { border-width: 1px 1px 0 0; border-style: solid; margin: 0;}
  54 </style>
  55 </head>
  56 <body>
  57 <table>
  58 <thead>
  59   <tr>
  60   <td>Library ID</td><td>Submission ID</td><td>Last Updated</td><td>Status</td>
  61   <td>Library Name</td>
  62   </tr>
  63 </thead>
  64 <tbody>
  65 {% for record in submissions %}
  66   <tr>
  67     <td><a href="{{record.library_urn}}">{{ record.library_urn | trim_rdf}}</a></td>
  68     <td><a href="{{record.submission}}">{{record.submission|trim_rdf}}</a></td>
  69     <td>{{ record.date|timestamp_to_date }}</td>
  70     <td>{{ record.submission_status }}</td>
  71     <td>{{ record.library_name }}</td>
  72   </tr>
  73 {% endfor %}
  74 </tbody>
  75 </table>
  76 </body>
  77 </html>
  78 """
  79
  80 def what_have_we_done(model):
  81     compiled_query = RDF.SPARQLQuery(SUBMISSION_QUERY)
  82     submissions = compiled_query.execute(model)
  83     environment = jinja2.Environment()
  84     environment.filters['trim_rdf'] = trim_rdf
  85     environment.filters['timestamp_to_date'] = timestamp_to_date
  86     template = environment.from_string(SUBMISSION_TEMPLATE)
  87     print template.render(submissions = submissions)
  88
  89 def trim_rdf(value):
  90     if value is None:
  91         return
  92     value = str(value)
  93     if value[-1] == '/':
  94         value = value[:-1]
  95     split_value = value.split('/')
  96     if len(split_value) == 0:
  97         return value
  98     return split_value[-1]
  99
 100 def timestamp_to_date(value):
 101     datestamp, timestamp = str(value).split('T')
 102     return datestamp
 103
 104 if __name__ == "__main__":
 105     main()