X-Git-Url: http://woldlab.caltech.edu/gitweb/?a=blobdiff_plain;f=htsworkflow%2Fsubmission%2Fsubmission.py;h=897053fbc148477c108d232635958db45488dfc5;hb=1000ba383f47a9c3ab422f4552b3725038c96541;hp=3320f1caf3174e6d5636c4dd20841188771050d9;hpb=ad6adfee371e67084e55b94a1e5335263d6fb26b;p=htsworkflow.git

diff --git a/htsworkflow/submission/submission.py b/htsworkflow/submission/submission.py
index 3320f1c..897053f 100644
--- a/htsworkflow/submission/submission.py
+++ b/htsworkflow/submission/submission.py
@@ -8,16 +8,12 @@ import RDF
 
 from htsworkflow.util.rdfhelp import \
      blankOrUri, \
-     dafTermOntology, \
      dump_model, \
+     fromTypedNode, \
      get_model, \
-     libraryOntology, \
-     owlNS, \
-     rdfNS, \
-     submissionLog, \
-     submissionOntology, \
-     toTypedNode, \
-     fromTypedNode
+     strip_namespace, \
+     toTypedNode
+from htsworkflow.util.rdfns import *
 from htsworkflow.util.hashfile import make_md5sum
 from htsworkflow.submission.fastqname import FastqName
 from htsworkflow.submission.daf import \
@@ -25,6 +21,9 @@ from htsworkflow.submission.daf import \
      ModelException, \
      get_submission_uri
 
+from django.conf import settings
+from django.template import Context, Template, loader
+
 LOGGER = logging.getLogger(__name__)
 
 class Submission(object):
@@ -61,6 +60,13 @@ class Submission(object):
             pathname = os.path.abspath(os.path.join(analysis_dir, filename))
             self.construct_file_attributes(analysis_dir, libNode, pathname)
 
+    def analysis_nodes(self, result_map):
+        """Return an iterable of analysis nodes
+        """
+        for result_dir in result_map.values():
+            an_analysis = self.get_submission_node(result_dir)
+            yield an_analysis
+
     def construct_file_attributes(self, analysis_dir, libNode, pathname):
         """Looking for the best extension
         The 'best' is the longest match
@@ -118,6 +124,7 @@ class Submission(object):
         fileNode = self.make_file_node(pathname, an_analysis)
         self.add_md5s(filename, fileNode, analysis_dir)
         self.add_fastq_metadata(filename, fileNode)
+        self.add_label(file_type, fileNode, libNode)
         self.model.add_statement(
             RDF.Statement(fileNode,
                           rdfNS['type'],
@@ -126,7 +133,7 @@ class Submission(object):
             RDF.Statement(fileNode,
                           libraryOntology['library'],
                           libNode))
-                          
+
         LOGGER.debug("Done.")
 
     def make_file_node(self, pathname, submissionNode):
@@ -168,7 +175,7 @@ class Submission(object):
         except ValueError:
             # currently its just ignore it if the fastq name parser fails
             return
-        
+
         terms = [('flowcell', libraryOntology['flowcell_id']),
                  ('lib_id', libraryOntology['library_id']),
                  ('lane', libraryOntology['lane_number']),
@@ -180,6 +187,23 @@ class Submission(object):
                 s = RDF.Statement(fileNode, model_term, toTypedNode(value))
                 self.model.append(s)
 
+    def add_label(self, file_type, file_node, lib_node):
+        """Add rdfs:label to a file node
+        """
+        #template_term = libraryOntology['label_template']
+        template_term = libraryOntology['label_template']
+        label_template = self.model.get_target(file_type, template_term)
+        if label_template:
+            template = loader.get_template('submission_view_rdfs_label_metadata.sparql')
+            context = Context({
+                'library': str(lib_node.uri),
+                })
+            for r in self.execute_query(template, context):
+                context = Context(r)
+                label = Template(label_template).render(context)
+                s = RDF.Statement(file_node, rdfsNS['label'], unicode(label))
+                self.model.append(s)
+
     def _add_library_details_to_model(self, libNode):
         # attributes that can have multiple values
         set_attributes = set((libraryOntology['has_lane'],
@@ -324,6 +348,8 @@ class Submission(object):
                   'Small RNA (non-multiplexed)',]
         paired = ['Barcoded Illumina',
                   'Multiplexing',
+                  'NEBNext Multiplexed',
+                  'NEBNext Small RNA',
                   'Nextera',
                   'Paired End (non-multiplexed)',
                   'Dual Index Illumina',]
@@ -350,3 +376,21 @@ class Submission(object):
                 d[key] = fromTypedNode(value)
             results.append(d)
         return results
+
+
+def list_submissions(model):
+    """Return generator of submissions in this model.
+    """
+    query_body = """
+      PREFIX subns: <http://jumpgate.caltech.edu/wiki/UcscSubmissionOntology#>
+
+      select distinct ?submission
+      where { ?submission subns:has_submission ?library_dir }
+    """
+    query = RDF.SPARQLQuery(query_body)
+    rdfstream = query.execute(model)
+    for row in rdfstream:
+        s = strip_namespace(submissionLog, row['submission'])
+        if s[-1] in ['#', '/', '?']:
+            s = s[:-1]
+        yield s