When collecting files for a geo submission, group on library id
[htsworkflow.git] / htsworkflow / submission / geo.py
index 85947158390f699afa8a76cd719a0b1fadf26ebf..ef8d9457218a76ce53f0872f44efafd6d478dea1 100644 (file)
@@ -17,8 +17,8 @@ from django.template import Context, loader
 LOGGER = logging.getLogger(__name__)
 
 class GEOSubmission(Submission):
-    def __init__(self, name, model):
-        super(GEOSubmission, self).__init__(name, model)
+    def __init__(self, name, model, host):
+        super(GEOSubmission, self).__init__(name, model, host)
 
     def make_soft(self, result_map):
         samples = []
@@ -36,7 +36,7 @@ class GEOSubmission(Submission):
                 LOGGER.error(errmsg.format(str(an_analysis),))
                 continue
             elif len(metadata) > 1:
-                errmsg = 'Confused there are more than one samples for %s'
+                errmsg = 'Confused there are more than one sample for %s'
                 LOGGER.debug(errmsg % (str(an_analysis),))
             metadata = metadata[0]
             metadata['raw'] = self.get_raw_files(an_analysis)
@@ -131,10 +131,10 @@ class GEOSubmission(Submission):
             data = {}
             for k, v in row.items():
                 data[k] = v
-            lane = str(data['lane'])
-            lanes.setdefault(lane, []).append(data)
+            library = str(data['library'])
+            lanes.setdefault(library, []).append(data)
         result = []
-        for lane, files in lanes.items():
+        for library, files in lanes.items():
             if len(files) > 2:
                 errmsg = "Don't know what to do with more than 2 raw files"
                 raise ValueError(errmsg)
@@ -143,7 +143,7 @@ class GEOSubmission(Submission):
             elif len(files) == 1:
                 is_paired = False
             elif len(files) == 0:
-                raise RuntimeError("Empty lane list discovered")
+                raise RuntimeError("Empty library list discovered")
             files = self._format_filename(files, is_paired)
             files = self._format_flowcell_type(files, is_paired)
             files = self._format_read_length(files, is_paired)