break up functions and add tests

qiita_pet/handlers/study_handlers/listing_handlers.py

@@ -43,6 +43,41 @@ def _get_shared_links_for_study(study):
     return ", ".join(shared)
 
 
+def _build_single_study_info(study, info):
+    # Clean up and add to the study info for HTML purposes
+    PI = StudyPerson(info['principal_investigator_id'])
+    status = study.status
+    if info['pmid'] is not None:
+        info['pmid'] = ", ".join([pubmed_linkifier([p])
+                                  for p in info['pmid']])
+    else:
+        info['pmid'] = ""
+    if info["number_samples_collected"] is None:
+        info["number_samples_collected"] = 0
+    info["shared"] = _get_shared_links_for_study(study)
+    info["num_raw_data"] = len(study.raw_data())
+    info["status"] = status
+    info["study_id"] = study.id
+    info["pi"] = study_person_linkifier((PI.email, PI.name))
+    del info["principal_investigator_id"]
+    del info["email"]
+    return info
+
+
+def _build_proc_data_info(study, study_proc, proc_samples):
+    # Build the proc data info list for the child row in datatable
+    proc_data_info = []
+    for pid in study_proc[study.id]:
+        proc_data = ProcessedData(pid)
+        proc_info = proc_data.processing_info
+        proc_info['pid'] = pid
+        proc_info['data_type'] = proc_data.data_type()
+        proc_info['samples'] = sorted(proc_samples[pid])
+        proc_info['processed_date'] = str(proc_info['processed_date'])
+        proc_data_info.append(proc_info)
+    return proc_data_info
+
+
 def _build_study_info(user, study_proc=None, proc_samples=None):
     """builds list of dicts for studies table, with all html formatted
 
@@ -61,21 +96,22 @@ def _build_study_info(user, study_proc=None, proc_samples=None):
     -------
     infolist: list of dict of lists and dicts
         study and processed data info for JSON serialiation for datatables
+        Each dict in the list is a single study, and contains the text
 
     Notes
     -----
     Both study_proc and proc_samples must be passed, or neither passed.
     """
+    build_samples = False
     # Logic check to make sure both needed parts passed
-    build_info = False
     if study_proc is not None and proc_samples is None:
         raise IncompetentQiitaDeveloperError(
             'Must pass proc_samples when study_proc given')
     elif proc_samples is not None and study_proc is None:
         raise IncompetentQiitaDeveloperError(
             'Must pass study_proc when proc_samples given')
-    elif proc_samples is None:
-        build_info = True
+    elif study_proc is None:
+        build_samples = True
 
     # get list of studies for table
     study_set = user.user_studies.union(
@@ -93,48 +129,24 @@ def _build_study_info(user, study_proc=None, proc_samples=None):
     study_info = Study.get_info(study_set, cols)
 
     infolist = []
-    for row, info in enumerate(study_info):
+    for info in study_info:
         # Convert DictCursor to proper dict
         info = dict(info)
         study = Study(info['study_id'])
-        PI = StudyPerson(info['principal_investigator_id'])
-        status = study.status
-        # if needed, get all the proc data info since no search results passed
-        if build_info:
-            proc_data = study.processed_data()
-            proc_samples = {}
-            study_proc = {study.id: proc_data}
-            for pid in proc_data:
-                proc_samples[pid] = ProcessedData(pid).samples
-
-        # Clean up and add to the study info for HTML purposes
-        if info['pmid'] is not None:
-            info['pmid'] = ", ".join([pubmed_linkifier([p])
-                                      for p in info['pmid']])
-        else:
-            info['pmid'] = ""
-        if info["number_samples_collected"] is None:
-            info["number_samples_collected"] = 0
-        info["shared"] = _get_shared_links_for_study(study)
-        info["num_raw_data"] = len(study.raw_data())
-        info["status"] = status
-        info["study_id"] = study.id
-        info["pi"] = study_person_linkifier((PI.email, PI.name))
-        del info["principal_investigator_id"]
-        del info["email"]
+        # Build the processed data info for the study if none passed
+        if build_samples:
+                proc_data = study.processed_data()
+                proc_samples = {}
+                study_proc = {study.id: proc_data}
+                for pid in proc_data:
+                    proc_samples[pid] = ProcessedData(pid).samples
+
+        study_info = _build_single_study_info(study, info)
         # Build the proc data info list for the child row in datatable
-        proc_data_info = []
-        for pid in study_proc[study.id]:
-            proc_data = ProcessedData(pid)
-            proc_info = proc_data.processing_info
-            proc_info['pid'] = pid
-            proc_info['data_type'] = proc_data.data_type()
-            proc_info['samples'] = sorted(proc_samples[pid])
-            proc_info['processed_date'] = str(proc_info['processed_date'])
-            proc_data_info.append(proc_info)
-        info["proc_data_info"] = proc_data_info
-
-        infolist.append(info)
+        study_info["proc_data_info"] = _build_proc_data_info(study, study_proc,
+                                                             proc_samples)
+
+        infolist.append(study_info)
     return infolist
 
 

qiita_pet/test/test_study_handlers.py

@@ -7,13 +7,65 @@
 from qiita_db.util import get_count, check_count
 from qiita_db.user import User
 from qiita_pet.handlers.study_handlers.listing_handlers import (
-    _get_shared_links_for_study, _build_study_info)
+    _get_shared_links_for_study, _build_study_info, _build_single_study_info,
+    _build_proc_data_info)
 
 
 class TestHelpers(TestHandlerBase):
     database = True
 
     def setUp(self):
+        self.single_exp = {
+            'study_id': 1,
+            'status': 'private',
+            'study_abstract':
+                'This is a preliminary study to examine the microbiota '
+                'associated with the Cannabis plant. Soils samples '
+                'from the bulk soil, soil associated with the roots, '
+                'and the rhizosphere were extracted and the DNA '
+                'sequenced. Roots from three independent plants of '
+                'different strains were examined. These roots were '
+                'obtained November 11, 2011 from plants that had been '
+                'harvested in the summer. Future studies will attempt '
+                'to analyze the soils and rhizospheres from the same '
+                'location at different time points in the plant '
+                'lifecycle.',
+            'metadata_complete': True,
+            'study_title':
+                'Identification of the Microbiomes for Cannabis Soils',
+            'num_raw_data': 4,
+            'number_samples_collected': 27,
+            'shared':
+                '<a target="_blank" href="mailto:shared@foo.bar">Shared</a>',
+            'pmid': '<a target="_blank" href="http://www.ncbi.nlm.nih.gov/'
+                    'pubmed/123456">123456</a>, <a target="_blank" href="http:'
+                    '//www.ncbi.nlm.nih.gov/pubmed/7891011">7891011</a>',
+            'pi': '<a target="_blank" href="mailto:PI_dude@foo.bar">'
+                  'PIDude</a>'
+        }
+        self.proc_data_exp = [{
+            'pid': 1,
+            'processed_date': '2012-10-01 09:30:27',
+            'data_type': '18S',
+            'algorithm': 'uclust',
+            'reference_name': 'Greengenes',
+            'reference_version': '13_8',
+            'taxonomy_filepath': 'GreenGenes_13_8_97_otu_taxonomy.txt',
+            'sequence_filepath': 'GreenGenes_13_8_97_otus.fasta',
+            'tree_filepath': 'GreenGenes_13_8_97_otus.tree',
+            'similarity': 0.97,
+            'enable_rev_strand_match': True,
+            'suppress_new_clusters': True,
+            'samples': ['1.SKB1.640202', '1.SKB2.640194', '1.SKB3.640195',
+                        '1.SKB4.640189', '1.SKB5.640181', '1.SKB6.640176',
+                        '1.SKB7.640196', '1.SKB8.640193', '1.SKB9.640200',
+                        '1.SKD1.640179', '1.SKD2.640178', '1.SKD3.640198',
+                        '1.SKD4.640185', '1.SKD5.640186', '1.SKD6.640190',
+                        '1.SKD7.640191', '1.SKD8.640184', '1.SKD9.640182',
+                        '1.SKM1.640183', '1.SKM2.640199', '1.SKM3.640197',
+                        '1.SKM4.640180', '1.SKM5.640177', '1.SKM6.640187',
+                        '1.SKM7.640188', '1.SKM8.640201', '1.SKM9.640192']
+        }]
         self.exp = [{
             'study_id': 1,
             'status': 'public',
@@ -72,6 +124,42 @@ def test_get_shared_links_for_study(self):
         exp = '<a target="_blank" href="mailto:shared@foo.bar">Shared</a>'
         self.assertEqual(obs, exp)
 
+    def test_build_single_study_info(self):
+        study_info = {
+            'study_id': 1,
+            'email': 'test@foo.bar',
+            'principal_investigator_id': 3,
+            'pmid': ['123456', '7891011'],
+            'study_title':
+                'Identification of the Microbiomes for Cannabis Soils',
+            'metadata_complete': True,
+            'number_samples_collected': 27,
+            'study_abstract':
+                'This is a preliminary study to examine the microbiota '
+                'associated with the Cannabis plant. Soils samples '
+                'from the bulk soil, soil associated with the roots, '
+                'and the rhizosphere were extracted and the DNA '
+                'sequenced. Roots from three independent plants of '
+                'different strains were examined. These roots were '
+                'obtained November 11, 2011 from plants that had been '
+                'harvested in the summer. Future studies will attempt '
+                'to analyze the soils and rhizospheres from the same '
+                'location at different time points in the plant '
+                'lifecycle.'
+            }
+        obs = _build_single_study_info(Study(1), study_info)
+        for key, val in self.single_exp.iteritems():
+            if obs[key] != val:
+                print key
+                print obs[key], val
+        self.assertEqual(obs, self.single_exp)
+
+    def test_build_proc_data_info(self):
+        study_proc = {1: [1]}
+        proc_samples = {1: self.proc_data_exp[0]['samples']}
+        obs = _build_proc_data_info(Study(1), study_proc, proc_samples)
+        self.assertEqual(obs, self.proc_data_exp)
+
     def test_build_study_info(self):
         ProcessedData(1).status = 'public'
         obs = _build_study_info(User('test@foo.bar'))