Added counting

tests/importxls/test_from_collab.py

@@ -12,7 +12,7 @@ from tests.importxls.test_utils import get_value_list_from_row, process_data_typ
 class TestProjectsParser(TestCase):
     def test_export_from_collaborator(self):
         h = hashlib.md5()
-
+        count = 0
         for dirName, subdirList, fileList in os.walk(SHEETS_FOLDER):
             for fname in fileList:
                 if fname.startswith('from-collaborator'):
@@ -24,6 +24,7 @@ class TestProjectsParser(TestCase):
                     idx = 1
                     #print('----> {}'.format(full_file_path))
                     while idx < book.number_of_sheets():
+                        count+=1
                         sheet = book.sheet_by_index(idx)
                         dataset_data = {}
                         dataset_data['source_type'] = 'From_Collaborator'
@@ -39,6 +40,8 @@ class TestProjectsParser(TestCase):
 
                         if sheet[7, 2]:
                             dataset_data['samples_location'] = sheet[7, 2]
+                            if dataset_data['involves_samples'] == False:
+                                print('----> {}'.format('Inconsistent samples information' + full_file_path))
 
                         if sheet[8, 2]:
                             dataset_data['de_identification'] = sheet[8, 2]
@@ -143,3 +146,4 @@ class TestProjectsParser(TestCase):
                     with open('datasets-{}.json'.format(submission_id), 'w') as outfile:
                         json.dump(dataset_list, outfile, indent=4)
                         # print(json.dumps(dataset_list, indent=4))
+        print('Number of Collab Datasets  {} \n'.format(count))

tests/importxls/test_from_repo.py

@@ -13,6 +13,7 @@ class TestProjectsParser(TestCase):
     def test_export_from_repository(self):
 
         h = hashlib.md5()
+        count = 0
 
         for dirName, subdirList, fileList in os.walk(SHEETS_FOLDER):
             for fname in fileList:
@@ -25,6 +26,7 @@ class TestProjectsParser(TestCase):
                     idx = 1
                     # print('----> {}'.format(full_file_path))
                     while idx < book.number_of_sheets():
+                        count+=1
                         sheet = book.sheet_by_index(idx)
                         dataset_data = {}
                         dataset_data['source_type'] = 'From_Repository'
@@ -35,6 +37,9 @@ class TestProjectsParser(TestCase):
                         if sheet[4, 2]:
                             dataset_data['other_external_id'] = sheet[4, 2]
 
+                        if sheet[5, 2]:
+                            dataset_data['title'] = sheet[5, 2]
+
                         datatype_info = process_data_types(get_value_list_from_row(sheet, 7))
                         dataset_data['data_types'] = datatype_info[0]
                         if datatype_info[1]:
@@ -107,3 +112,5 @@ class TestProjectsParser(TestCase):
                     with open('datasets-{}.json'.format(submission_id), 'w') as outfile:
                         json.dump(dataset_list, outfile, indent=4)
                         # print(json.dumps(dataset_list, indent=4))
+
+        print('Number of Repo Datasets  {} \n'.format(count))

tests/importxls/test_own_cohort.py

@@ -13,6 +13,7 @@ class TestProjectsParser(TestCase):
     def test_export_own_cohort(self):
 
         h = hashlib.md5()
+        count = 0
 
         for dirName, subdirList, fileList in os.walk(SHEETS_FOLDER):
             for fname in fileList:
@@ -25,6 +26,7 @@ class TestProjectsParser(TestCase):
                     idx = 1
                     print('----> {}'.format(full_file_path))
                     while idx < book.number_of_sheets():
+                        count+=1
                         sheet = book.sheet_by_index(idx)
                         dataset_data = {}
                         dataset_data['source_type'] = 'Own_Cohort'
@@ -150,3 +152,5 @@ class TestProjectsParser(TestCase):
                     with open('datasets-{}.json'.format(submission_id), 'w') as outfile:
                         json.dump(dataset_list, outfile, indent=4)
                         # print(json.dumps(dataset_list, indent=4))
+
+        print('Number of Own-Cohort Datasets  {} \n'.format(count))
\ No newline at end of file

tests/importxls/test_projects.py

@@ -26,7 +26,7 @@ class TestProjectsParser(TestCase):
                     idx = 0
                     while idx < book.number_of_sheets():
                         if idx > 0 and fname.startswith('from-repository'):
-                            # print('---->{}'.format(fname))
+
                             prj_refs = set(get_value_list_from_row(book.sheet_by_index(idx),
                                                                    18) + get_value_list_from_row(
                                 book.sheet_by_index(idx), 19))
@@ -35,7 +35,7 @@ class TestProjectsParser(TestCase):
                                 print('Reference to undefined project(s): {} in file {}'.format(undefined_refs,
                                                                                                 full_file_path))
                         if idx > 0 and fname.startswith('from-collaborator'):
-                            # print('---->{}'.format(full_file_path))
+
                             prj_refs = set(get_value_list_from_row(book.sheet_by_index(idx),
                                                                    18) + get_value_list_from_row(
                                 book.sheet_by_index(idx), 26) + get_value_list_from_row(book.sheet_by_index(idx),
@@ -94,8 +94,10 @@ class TestProjectsParser(TestCase):
     def test_export_projects(self):
 
         projects_list = []
+        count = 0
         for acr, path, title, description, pi, start, end, personnel, HasUniLUERP, ERPNotes, HasCNER, CNERNotes, publications in collect_prj_info(
                 SHEETS_FOLDER):
+            count +=1
             prj_data = {}
             prj_data['acronym'] = acr
             prj_data['title'] = title
@@ -155,3 +157,4 @@ class TestProjectsParser(TestCase):
         with open('projects.json', 'w') as outfile:
             json.dump(projects_list, outfile, indent=4)
             # print(json.dumps(projects_list, indent=4))
+        print('Number of defined Projects   {} \n'.format(count))

tests/importxls/test_utils.py

@@ -52,7 +52,7 @@ def collect_prj_info(sheets_folder):
                 sheet = book.sheet_by_name('projects')
                 prj_acronyms = sheet.column[1]
                 numprojects = len(prj_acronyms) - 2
-                print('{}---> {} ----> {}'.format(fname, len(prj_acronyms), prj_acronyms))
+
                 if numprojects > 0:
                     for row in range(2, 2 + numprojects):
                         projects.append((sheet[row, 1], full_file_path, sheet[row, 2], sheet[row, 3], sheet[row, 4],