Return species information as part of the flowcell json information.
[htsworkflow.git] / htsworkflow / frontend / experiments / experiments.py
index d11cda75a22d6652e4f35ec4363772eeea7db66d..331bdde59a2e57a42fd66d633eac580c40e1660b 100755 (executable)
@@ -1,14 +1,77 @@
 # some core functions of the exp tracker module
-from django.http import HttpResponse
-from datetime import datetime
-from string import *
+from datetime import datetime, timedelta
+try:
+    import json
+except ImportError, e:
+    import simplejson as json
+    
+import os
 import re
+
+from django.contrib.auth.decorators import login_required
+from django.core.exceptions import ObjectDoesNotExist
+from django.core.mail import send_mail, mail_admins
+from django.http import HttpResponse, Http404
+
 from htsworkflow.frontend import settings
 from htsworkflow.frontend.experiments.models import FlowCell, DataRun
 from htsworkflow.frontend.samples.models import Library
-from django.core.exceptions import ObjectDoesNotExist
-from django.core.mail import send_mail, mail_admins
+from htsworkflow.frontend.auth import require_api_key
+
+def flowcell_information(flowcell_id):
+    """
+    Return a dictionary describing a flowcell
+    """
+    try:
+        fc = FlowCell.objects.get(flowcell_id=flowcell_id)
+    except FlowCell.DoesNotExist, e:
+        return None
+
+    lane_set = {}
+    for lane in fc.lane_set.all():
+        lane_set[lane.lane_number] = {
+            'cluster_estimate': lane.cluster_estimate,
+            'comment': lane.comment,
+            'flowcell': lane.flowcell.flowcell_id,
+            'lane_number': int(lane.lane_number),
+            'library_name': lane.library.library_name,
+            'library_id': lane.library.library_id,
+            'library_species': lane.library.library_species.scientific_name,
+            'pM': float(lane.pM),
+        }
+    info = {
+        'advanced_run': fc.advanced_run,
+        'cluster_station_id': fc.cluster_station_id,
+        'cluster_station': fc.cluster_station.name,
+        'control_lane': int(fc.control_lane),
+        # 'datarun_set': how should this be represented?,
+        'flowcell_id': fc.flowcell_id,
+        'id': fc.id,
+        'lane_set': lane_set,
+        'notes': fc.notes,
+        'paired_end': fc.paired_end,
+        'read_length': fc.read_length,
+        'run_date': fc.run_date.isoformat(),
+        'sequencer_id': fc.sequencer_id,
+        'sequencer': fc.sequencer.name,
+    }
+    
+    return info
+
+def flowcell_json(request, fc_id):
+    """
+    Return a JSON blob containing enough information to generate a config file.
+    """
+    require_api_key(request)
+    
+    fc_dict = flowcell_information(fc_id)
 
+    if fc_dict is None:
+        raise Http404
+    
+    fc_json = json.dumps(fc_dict)
+    return HttpResponse(fc_json, mimetype = 'application/json')
+    
 def updStatus(request):
     output=''
     user = 'none'
@@ -17,30 +80,28 @@ def updStatus(request):
     fcid = 'none'
     runfolder = 'unknown'
     ClIP = request.META['REMOTE_ADDR']
-    granted = False    
 
-    if request.has_key('user'):
-      user = request['user']
-
-    #Check access permission 
-    if (user == 'rami' and settings.ALLOWED_IPS.has_key(ClIP)):  granted = True
-    if not granted: return HttpResponse("access denied.")
+    if hasattr(request, 'user'):
+      user = request.user
 
+    #Check access permission
+    if not (user.is_superuser and settings.ALLOWED_IPS.has_key(ClIP)): 
+        return HttpResponse("%s access denied from %s." % (user, ClIP))
 
     # ~~~~~~Parameters for the job ~~~~
-    if request.has_key('fcid'):
-      fcid = request['fcid']
+    if request.REQUEST.has_key('fcid'):
+      fcid = request.REQUEST['fcid']
     else:
       return HttpResponse('missing fcid')
     
-    if request.has_key('runf'):
-      runfolder = request['runf']
+    if request.REQUEST.has_key('runf'):
+      runfolder = request.REQUEST['runf']
     else:
       return HttpResponse('missing runf')
 
     
-    if request.has_key('updst'):
-      UpdatedStatus = request['updst']
+    if request.REQUEST.has_key('updst'):
+      UpdatedStatus = request.REQUEST['updst']
     else:
       return HttpResponse('missing status')
     
@@ -55,8 +116,8 @@ def updStatus(request):
       #if there's a message update that too
       mytimestamp = datetime.now().__str__()
       mytimestamp = re.sub(pattern=":[^:]*$",repl="",string=mytimestamp)
-      if request.has_key('msg'):
-        rec.run_note += ", "+request['msg']+" ("+mytimestamp+")"
+      if request.REQUEST.has_key('msg'):
+        rec.run_note += ", "+request.REQUEST['msg']+" ("+mytimestamp+")"
       else :
         if UpdatedStatus == '1':
           rec.run_note = "Started ("+mytimestamp+")"
@@ -81,55 +142,41 @@ def generateConfile(request,fcid):
 
     #if not granted: return HttpResponse("access denied.")
 
-    cnfgfile = 'READ_LENGTH 25\n'
-    cnfgfile += 'ANALYSIS eland\n'
-    cnfgfile += 'GENOME_FILE all_chr.fa\n'
-    cnfgfile += 'ELAND_MULTIPLE_INSTANCES 8\n'
+    config = ['READ_LENGTH 25']
+    config += ['ANALYSIS eland']
+    config += ['GENOME_FILE all_chr.fa']
+    config += ['ELAND_MULTIPLE_INSTANCES 8']
     genome_dir = 'GENOME_DIR /Volumes/Genomes/'
     eland_genome = 'ELAND_GENOME /Volumes/Genomes/'
     
     try:                                                                                                                                              
-      rec = FlowCell.objects.get(flowcell_id=fcid)
-      
-      cnfgfile += '1:'+genome_dir+rec.lane_1_library.library_species.use_genome_build+'\n'
-      cnfgfile += '1:'+eland_genome+rec.lane_1_library.library_species.use_genome_build+'\n'
-
-      cnfgfile += '2:'+genome_dir+rec.lane_2_library.library_species.use_genome_build+'\n'
-      cnfgfile += '2:'+eland_genome+rec.lane_2_library.library_species.use_genome_build+'\n'
-      cnfgfile += '3:'+genome_dir+rec.lane_3_library.library_species.use_genome_build+'\n'
-      cnfgfile += '3:'+eland_genome+rec.lane_3_library.library_species.use_genome_build+'\n'
-
-      cnfgfile += '4:'+genome_dir+rec.lane_4_library.library_species.use_genome_build+'\n'
-      cnfgfile += '4:'+eland_genome+rec.lane_4_library.library_species.use_genome_build+'\n'
+      fc = FlowCell.objects.get(flowcell_id=fcid)
+      for lane in fc.lane_set.all():
+          print dir(lane.library.library_species)
+          config += [ str(lane.lane_number) +":" + \
+                      genome_dir + lane.library.library_species.scientific_name ]
+          config += [ str(lane.lane_number) +":" + \
+                      eland_genome + lane.library.library_species.scientific_name ]
       
-      cnfgfile += '5:'+genome_dir+rec.lane_5_library.library_species.use_genome_build+'\n'
-      cnfgfile += '5:'+eland_genome+rec.lane_5_library.library_species.use_genome_build+'\n'
-
-      cnfgfile += '6:'+genome_dir+rec.lane_6_library.library_species.use_genome_build+'\n'
-      cnfgfile += '6:'+eland_genome+rec.lane_6_library.library_species.use_genome_build+'\n'
-
-      cnfgfile += '7:'+genome_dir+rec.lane_7_library.library_species.use_genome_build+'\n'
-      cnfgfile += '7:'+eland_genome+rec.lane_7_library.library_species.use_genome_build+'\n'
-
-      cnfgfile += '8:'+genome_dir+rec.lane_8_library.library_species.use_genome_build+'\n'
-      cnfgfile += '8:'+eland_genome+rec.lane_8_library.library_species.use_genome_build
-
     except ObjectDoesNotExist:
-      cnfgfile = 'Entry not found for fcid  = '+fcid
+      config = 'Entry not found for fcid  = '+fcid
 
-    return cnfgfile
+    return os.linesep.join(config)
 
-def getConfile(request):
+def getConfile(req):
     granted = False
-    ClIP = request.META['REMOTE_ADDR']
+    ClIP = req.META['REMOTE_ADDR']
     if (settings.ALLOWED_IPS.has_key(ClIP)):  granted = True
 
     if not granted: return HttpResponse("access denied. IP: "+ClIP)
 
     fcid = 'none'
-    cnfgfile = ''
+    cnfgfile = 'Nothing found'
     runfolder = 'unknown'
+    request = req.REQUEST
+    print request, dir(request)
+    print request['fcid'], request.has_key('fcid')
+    print request['runf']
     if request.has_key('fcid'):
       fcid = request['fcid']
       if request.has_key('runf'):
@@ -151,19 +198,20 @@ def getConfile(request):
         except ObjectDoesNotExist:
           cnfgfile = 'Entry not found for RunFolder = '+runfolder
 
-    return HttpResponse(cnfgfile)
+    return HttpResponse(cnfgfile, mimetype='text/plain')
 
-def getLaneLibs(request):
+def getLaneLibs(req):
     granted = False
-    ClIP = request.META['REMOTE_ADDR']
+    ClIP = req.META['REMOTE_ADDR']
     if (settings.ALLOWED_IPS.has_key(ClIP)):  granted = True
 
     if not granted: return HttpResponse("access denied.")
 
+    request = req.REQUEST
     fcid = 'none'
     outputfile = ''
     if request.has_key('fcid'):
-      fcid = request['fcid']                                                                                                      
+      fcid = request['fcid']
       try:                                
         rec = FlowCell.objects.get(flowcell_id=fcid)
         #Ex: 071211
@@ -191,4 +239,92 @@ def getLaneLibs(request):
         outputfile = 'Flowcell entry not found for: '+fcid
     else: outputfile = 'Missing input: flowcell id'
 
-    return HttpResponse(outputfile)
+    return HttpResponse(outputfile, mimetype='text/plain')
+
+def estimateFlowcellDuration(flowcell):
+    """
+    Attempt to estimate how long it will take to run a flowcell
+
+    """
+    # (3600 seconds * 1.5 hours per cycle )
+    sequencing_seconds_per_cycle= 3600 * 1.5
+    # 800 is a rough guess
+    pipeline_seconds_per_cycle = 800
+    
+    cycles = flowcell.read_length
+    if flowcell.paired_end:
+        cycles *= 2
+    sequencing_time = timedelta(0, cycles * sequencing_seconds_per_cycle)
+    analysis_time = timedelta(0, cycles * pipeline_seconds_per_cycle)
+    estimate_mid = sequencing_time + analysis_time
+    # floor estimate_mid
+    estimate_low = timedelta(estimate_mid.days, 0)
+    # floor estimate_mid and add a day
+    estimate_high = timedelta(estimate_mid.days+1, 0)
+    
+    return (estimate_low, estimate_high)
+    
+
+def makeUserLaneMap(flowcell):
+    """
+    Given a flowcell return a mapping of users interested in
+    the libraries on those lanes.
+    """
+    users = {}
+
+    for lane in flowcell.lane_set.all():
+        for affiliation in lane.library.affiliations.all():
+            for user in affiliation.users.all():
+                users.setdefault(user,[]).append(lane)
+
+    return users
+
+def getUsersForFlowcell(flowcell):
+    users = set()
+    
+    for lane in flowcell.lane_set.all():
+        for affiliation in lane.library.affiliations.all():
+            for user in affiliation.users.all():
+                users.add(user)
+                
+    return users
+    
+def makeUserLibraryMap(libraries):
+    """
+    Given an interable set of libraries return a mapping or
+    users interested in those libraries.
+    """
+    users = {}
+    
+    for library in libraries:
+        for affiliation in library.affiliations.all():
+            for user in affiliation.users.all():
+                users.setdefault(user,[]).append(library)
+                
+    return users
+
+def makeAffiliationLaneMap(flowcell):
+    affs = {}
+
+    for lane in flowcell.lane_set.all():
+        for affiliation in lane.library.affiliations.all():
+            affs.setdefault(affiliation,[]).append(lane)
+
+    return affs
+
+def makeEmailLaneMap(flowcell):
+    """
+    Create a list of email addresses and the lanes associated with those users.
+
+    The email addresses can come from both the "users" table and the "affiliations" table.
+    """
+    emails = {}
+    for lane in flowcell.lane_set.all():
+        for affiliation in lane.library.affiliations.all():
+            if affiliation.email is not None and len(affiliation.email) > 0:
+                emails.setdefault(affiliation.email,set()).add(lane)
+            for user in affiliation.users.all():
+                if user.email is not None and len(user.email) > 0:
+                    emails.setdefault(user.email,set()).add(lane)
+
+    return emails