Merge pull request #110 from josenavas/MetadataBug

Metadata bug

Author: teravest

qiita_db/exceptions.py

@@ -54,3 +54,11 @@ def __init__(self, missing_id, table):
         super(QiitaDBUnknownIDError, self).__init__()
         self.args = ("The object with ID '%s' does not exists in table '%s'"
                      % (missing_id, table),)
+
+
+class QiitaDBDuplicateHeaderError(QiitaDBError):
+    """Exception for error when a MetadataTemplate has duplicate columns"""
+    def __init__(self):
+        super(QiitaDBDuplicateHeaderError, self).__init__()
+        self.args = ("Duplicate headers found in MetadataTemplate. Note "
+                     "that the headers are not case-sensitive",)

qiita_db/metadata_template.py

@@ -38,7 +38,8 @@
 
 from qiita_core.exceptions import IncompetentQiitaDeveloperError
 from .exceptions import (QiitaDBDuplicateError, QiitaDBColumnError,
-                         QiitaDBUnknownIDError, QiitaDBNotImplementedError)
+                         QiitaDBUnknownIDError, QiitaDBNotImplementedError,
+                         QiitaDBDuplicateHeaderError)
 from .base import QiitaObject
 from .sql_connection import SQLConnectionHandler
 from .util import exists_table, get_table_cols
@@ -582,6 +583,12 @@ def create(cls, md_template, obj):
         # We are going to modify the md_template. We create a copy so
         # we don't modify the user one
         md_template = deepcopy(md_template)
+        # In the database, all the column headers are lowercase
+        md_template.columns = [c.lower() for c in md_template.columns]
+
+        # Check that we don't have duplicate columns
+        if len(set(md_template.columns)) != len(md_template.columns):
+            raise QiitaDBDuplicateHeaderError()
 
         conn_handler = SQLConnectionHandler()
         # Check that md_template have the required columns

qiita_db/test/test_data.py

@@ -50,7 +50,8 @@ def setUp(self):
             f.write("\n")
 
     def tearDown(self):
-        map(remove, self._clean_up_files)
+        for f in self._clean_up_files:
+            remove(f)
 
     def test_create(self):
         """Correctly creates all the rows in the DB for the raw data"""
@@ -144,7 +145,8 @@ def setUp(self):
             f.write("\n")
 
     def tearDown(self):
-        map(remove, self._clean_up_files)
+        for f in self._clean_up_files:
+            remove(f)
 
     def test_create(self):
         """Correctly creates all the rows in the DB for preprocessed data"""
@@ -252,7 +254,8 @@ def setUp(self):
             f.write("\n")
 
     def tearDown(self):
-        map(remove, self._clean_up_files)
+        for f in self._clean_up_files:
+            remove(f)
 
     def test_create(self):
         """Correctly creates all the rows in the DB for the processed data"""

qiita_db/test/test_metadata_template.py

@@ -19,7 +19,8 @@
 from qiita_core.util import qiita_test_checker
 from qiita_core.exceptions import IncompetentQiitaDeveloperError
 from qiita_db.exceptions import (QiitaDBDuplicateError, QiitaDBUnknownIDError,
-                                 QiitaDBNotImplementedError)
+                                 QiitaDBNotImplementedError,
+                                 QiitaDBDuplicateHeaderError)
 from qiita_db.study import Study, StudyPerson
 from qiita_db.user import User
 from qiita_db.data import RawData
@@ -481,7 +482,7 @@ def setUp(self):
                         'collection_timestamp':
                         datetime(2014, 5, 29, 12, 24, 51),
                         'host_subject_id': 'NotIdentified',
-                        'description': 'Test Sample 1',
+                        'Description': 'Test Sample 1',
                         'str_column': 'Value for sample 1'},
             'Sample2': {'physical_location': 'location1',
                         'has_physical_specimen': True,
@@ -491,7 +492,7 @@ def setUp(self):
                         'collection_timestamp':
                         datetime(2014, 5, 29, 12, 24, 51),
                         'host_subject_id': 'NotIdentified',
-                        'description': 'Test Sample 2',
+                        'Description': 'Test Sample 2',
                         'str_column': 'Value for sample 2'},
             'Sample3': {'physical_location': 'location1',
                         'has_physical_specimen': True,
@@ -501,7 +502,7 @@ def setUp(self):
                         'collection_timestamp':
                         datetime(2014, 5, 29, 12, 24, 51),
                         'host_subject_id': 'NotIdentified',
-                        'description': 'Test Sample 3',
+                        'Description': 'Test Sample 3',
                         'str_column': 'Value for sample 3'}
             }
         self.metadata = pd.DataFrame.from_dict(metadata_dict, orient='index')
@@ -556,7 +557,14 @@ def test_create_duplicate(self):
         with self.assertRaises(QiitaDBDuplicateError):
             SampleTemplate.create(self.metadata, self.test_study)
 
-    def test_create_(self):
+    def test_create_duplicate_header(self):
+        """Create raises an error when duplicate headers are present"""
+        self.metadata['STR_COLUMN'] = pd.Series(['', '', ''],
+                                                index=self.metadata.index)
+        with self.assertRaises(QiitaDBDuplicateHeaderError):
+            SampleTemplate.create(self.metadata, self.new_study)
+
+    def test_create(self):
         """Creates a new SampleTemplate"""
         st = SampleTemplate.create(self.metadata, self.new_study)
         # The returned object has the correct id
@@ -750,21 +758,21 @@ def setUp(self):
                             'center_project_name': 'Test Project',
                             'ebi_submission_accession': None,
                             'ebi_study_accession': None,
-                            'emp_status_id': 1,
+                            'EMP_status_id': 1,
                             'data_type_id': 2,
                             'str_column': 'Value for sample 1'},
             'SKD8.640184': {'center_name': 'ANL',
                             'center_project_name': 'Test Project',
                             'ebi_submission_accession': None,
                             'ebi_study_accession': None,
-                            'emp_status_id': 1,
+                            'EMP_status_id': 1,
                             'data_type_id': 2,
                             'str_column': 'Value for sample 2'},
             'SKB7.640196': {'center_name': 'ANL',
                             'center_project_name': 'Test Project',
                             'ebi_submission_accession': None,
                             'ebi_study_accession': None,
-                            'emp_status_id': 1,
+                            'EMP_status_id': 1,
                             'data_type_id': 2,
                             'str_column': 'Value for sample 3'}
             }
@@ -822,6 +830,13 @@ def test_create_duplicate(self):
         with self.assertRaises(QiitaDBDuplicateError):
             PrepTemplate.create(self.metadata, self.test_raw_data)
 
+    def test_create_duplicate_header(self):
+        """Create raises an error when duplicate headers are present"""
+        self.metadata['STR_COLUMN'] = pd.Series(['', '', ''],
+                                                index=self.metadata.index)
+        with self.assertRaises(QiitaDBDuplicateHeaderError):
+            PrepTemplate.create(self.metadata, self.new_raw_data)
+
     def test_create(self):
         """Creates a new PrepTemplate"""
         pt = PrepTemplate.create(self.metadata, self.new_raw_data)