def sample_template_checks(study_id, user, check_exists=False): """Performs different checks and raises errors if any of the checks fail Parameters ---------- study_id : int The study id user : qiita_db.user.User The user trying to access the study check_exists : bool, optional If true, check if the sample template exists Raises ------ HTTPError 404 if the study does not exist 403 if the user does not have access to the study 404 if check_exists == True and the sample template doesn't exist """ try: study = Study(int(study_id)) except QiitaDBUnknownIDError: raise HTTPError(404, reason='Study does not exist') if not study.has_access(user): raise HTTPError(403, reason='User does not have access to study') # Check if the sample template exists if check_exists and not SampleTemplate.exists(study_id): raise HTTPError(404, reason="Study %s doesn't have sample information" % study_id)
def check_access(study_id, user_id): """Checks if user given has access to the study given Parameters ---------- study_id : int ID of the study to check access to user_id : str ID of the user to check access for Returns ------- dict Empty dict if access allowed, else a dict in the form {'status': 'error', 'message': reason for error} """ try: study = Study(int(study_id)) except QiitaDBUnknownIDError: return {'status': 'error', 'message': 'Study does not exist'} if not study.has_access(User(user_id)): return {'status': 'error', 'message': 'User does not have access to study'} return {}
def check_access(study_id, user_id): """Checks if user given has access to the study given Parameters ---------- study_id : int ID of the study to check access to user_id : str ID of the user to check access for Returns ------- dict Empty dict if access allowed, else a dict in the form {'status': 'error', 'message': reason for error} """ try: study = Study(int(study_id)) except QiitaDBUnknownIDError: return {'status': 'error', 'message': 'Study does not exist'} if not study.has_access(User(user_id)): return { 'status': 'error', 'message': 'User does not have access to study' } return {}
def get(self, arguments): study_id = int(self.get_argument('study_id')) # this block is tricky because you can either pass the sample or the # prep template and if none is passed then we will let an exception # be raised because template will not be declared for the logic below if self.get_argument('prep_template', None): template = PrepTemplate(int(self.get_argument('prep_template'))) if self.get_argument('sample_template', None): template = None tid = int(self.get_argument('sample_template')) try: template = SampleTemplate(tid) except QiitaDBUnknownIDError: raise HTTPError(404, "SampleTemplate %d does not exist" % tid) study = Study(template.study_id) # check whether or not the user has access to the requested information if not study.has_access(User(self.current_user)): raise HTTPError(403, "You do not have access to access this " "information.") df = dataframe_from_template(template) stats = stats_from_df(df) self.render('metadata_summary.html', user=self.current_user, study_title=study.title, stats=stats, study_id=study_id)
def get(self, arguments): study_id = int(self.get_argument('study_id')) # Get the arguments prep_template = self.get_argument('prep_template', None) sample_template = self.get_argument('sample_template', None) if prep_template and sample_template: raise HTTPError( 500, "You should provide either a sample template " "or a prep template, but not both") elif prep_template: # The prep template has been provided template = self._get_template(PrepTemplate, prep_template) back_button_path = ( "/study/description/%s?top_tab=raw_data_tab&sub_tab=%s" "&prep_tab=%s" % (study_id, template.raw_data, template.id)) elif sample_template: # The sample template has been provided template = self._get_template(SampleTemplate, sample_template) back_button_path = ("/study/description/%s" % study_id) else: # Neither a sample template or a prep template has been provided # Fail nicely raise HTTPError( 500, "You should provide either a sample template " "or a prep template") study = Study(template.study_id) # check whether or not the user has access to the requested information if not study.has_access(self.current_user): raise HTTPError( 403, "You do not have access to access this " "information.") df = dataframe_from_template(template) num_samples = df.shape[0] stats = stats_from_df(df) self.render('metadata_summary.html', study_title=study.title, stats=stats, num_samples=num_samples, back_button_path=back_button_path)
def get(self, arguments): study_id = int(self.get_argument('study_id')) # Get the arguments prep_template = self.get_argument('prep_template', None) sample_template = self.get_argument('sample_template', None) if prep_template and sample_template: raise HTTPError(500, "You should provide either a sample template " "or a prep template, but not both") elif prep_template: # The prep template has been provided template = self._get_template(PrepTemplate, prep_template) back_button_path = ( "/study/description/%s?top_tab=prep_template_tab&sub_tab=%s" % (study_id, template.id)) elif sample_template: # The sample template has been provided template = self._get_template(SampleTemplate, sample_template) back_button_path = ( "/study/description/%s" % study_id) else: # Neither a sample template or a prep template has been provided # Fail nicely raise HTTPError(500, "You should provide either a sample template " "or a prep template") study = Study(template.study_id) # check whether or not the user has access to the requested information if not study.has_access(self.current_user): raise HTTPError(403, "You do not have access to access this " "information.") df = template.to_dataframe() num_samples = df.shape[0] stats = stats_from_df(df) self.render('metadata_summary.html', study_title=study.title, stats=stats, num_samples=num_samples, back_button_path=back_button_path)
def study_get_req(study_id, user_id): """Returns information available for the given study Parameters ---------- study_id : int Study id to get prep template info for user_id : str User requesting the info Returns ------- dict Data types information in the form {'status': status, 'message': message, 'info': dict of objects status can be success, warning, or error depending on result message has the warnings or errors info contains study information seperated by data type, in the form {col_name: value, ...} with value being a string, int, or list of strings or ints """ access_error = check_access(study_id, user_id) if access_error: return access_error # Can only pass ids over API, so need to instantiate object study = Study(study_id) study_info = study.info # Add needed info that is not part of the initial info pull study_info['publication_doi'] = [] study_info['publication_pid'] = [] for pub, is_doi in study.publications: if is_doi: study_info['publication_doi'].append(pub) else: study_info['publication_pid'].append(pub) study_info['study_id'] = study.id study_info['study_title'] = study.title study_info['shared_with'] = [s.id for s in study.shared_with] study_info['status'] = study.status study_info['ebi_study_accession'] = study.ebi_study_accession study_info['ebi_submission_status'] = study.ebi_submission_status study_info['public_raw_download'] = study.public_raw_download study_info['notes'] = study.notes # Clean up StudyPerson objects to string for display pi = study_info['principal_investigator'] study_info['principal_investigator'] = { 'name': pi.name, 'email': pi.email, 'affiliation': pi.affiliation } lab_person = study_info['lab_person'] if lab_person: study_info['lab_person'] = { 'name': lab_person.name, 'email': lab_person.email, 'affiliation': lab_person.affiliation } samples = study.sample_template study_info['num_samples'] = 0 if samples is None else len(list(samples)) study_info['owner'] = study.owner.id # Study.has_access no_public=True, will return True only if the user_id is # the owner of the study or if the study is shared with the user_id; this # with study.public_raw_download will define has_access_to_raw_data study_info['has_access_to_raw_data'] = study.has_access( User(user_id), True) or study.public_raw_download study_info['show_biom_download_button'] = 'BIOM' in [ a.artifact_type for a in study.artifacts() ] study_info['show_raw_download_button'] = any( [True for pt in study.prep_templates() if pt.artifact is not None]) # getting study processing status from redis processing = False study_info['level'] = '' study_info['message'] = '' job_info = r_client.get(STUDY_KEY_FORMAT % study_id) if job_info: job_info = defaultdict(lambda: '', loads(job_info)) job_id = job_info['job_id'] job = ProcessingJob(job_id) job_status = job.status processing = job_status not in ('success', 'error') if processing: study_info['level'] = 'info' study_info['message'] = 'This study is currently being processed' elif job_status == 'error': study_info['level'] = 'danger' study_info['message'] = job.log.msg.replace('\n', '</br>') else: study_info['level'] = job_info['alert_type'] study_info['message'] = job_info['alert_msg'].replace( '\n', '</br>') return { 'status': 'success', 'message': '', 'study_info': study_info, 'editable': study.can_edit(User(user_id)) }
class TestStudy(TestCase): def setUp(self): self.study = Study(1) self.portal = qiita_config.portal self.info = { "timeseries_type_id": 1, "metadata_complete": True, "mixs_compliant": True, "number_samples_collected": 25, "number_samples_promised": 28, "study_alias": "FCM", "study_description": "Microbiome of people who eat nothing but " "fried chicken", "study_abstract": "Exploring how a high fat diet changes the " "gut microbiome", "emp_person_id": StudyPerson(2), "principal_investigator_id": StudyPerson(3), "lab_person_id": StudyPerson(1) } self.infoexp = { "timeseries_type_id": 1, "metadata_complete": True, "mixs_compliant": True, "number_samples_collected": 25, "number_samples_promised": 28, "study_alias": "FCM", "study_description": "Microbiome of people who eat nothing but " "fried chicken", "study_abstract": "Exploring how a high fat diet changes the " "gut microbiome", "emp_person_id": 2, "principal_investigator_id": 3, "lab_person_id": 1 } self.existingexp = { 'mixs_compliant': True, 'metadata_complete': True, 'reprocess': False, 'number_samples_promised': 27, 'emp_person_id': StudyPerson(2), 'funding': None, 'vamps_id': None, 'first_contact': datetime(2014, 5, 19, 16, 10), 'principal_investigator_id': StudyPerson(3), 'timeseries_type_id': 1, '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.", 'spatial_series': False, 'study_description': 'Analysis of the Cannabis Plant Microbiome', 'study_alias': 'Cannabis Soils', 'most_recent_contact': '2014-05-19 16:11', 'most_recent_contact': datetime(2014, 5, 19, 16, 11), 'lab_person_id': StudyPerson(1), 'number_samples_collected': 27} def tearDown(self): qiita_config.portal = self.portal def _change_processed_data_status(self, new_status): # Change the status of the studies by changing the status of their # processed data id_status = convert_to_id(new_status, 'processed_data_status') self.conn_handler.execute( "UPDATE qiita.processed_data SET processed_data_status_id = %s", (id_status,)) def test_get_info(self): # Test get all info for single study qiita_config.portal = 'QIITA' obs = Study.get_info([1]) self.assertEqual(len(obs), 1) obs = dict(obs[0]) exp = { 'mixs_compliant': True, 'metadata_complete': True, 'reprocess': False, 'timeseries_type': 'None', 'number_samples_promised': 27, 'emp_person_id': 2, 'funding': None, 'vamps_id': None, 'first_contact': datetime(2014, 5, 19, 16, 10), 'principal_investigator_id': 3, 'timeseries_type_id': 1, 'pmid': ['123456', '7891011'], 'study_alias': 'Cannabis Soils', 'spatial_series': False, '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.', 'study_description': 'Analysis of the Cannabis Plant Microbiome', 'intervention_type': 'None', 'email': '*****@*****.**', 'study_id': 1, 'most_recent_contact': datetime(2014, 5, 19, 16, 11), 'lab_person_id': 1, 'study_title': 'Identification of the Microbiomes for Cannabis ' 'Soils', 'number_samples_collected': 27} self.assertItemsEqual(obs, exp) # Test get specific keys for single study exp_keys = ['metadata_complete', 'reprocess', 'timeseries_type', 'pmid', 'study_title'] obs = Study.get_info([1], exp_keys) self.assertEqual(len(obs), 1) obs = dict(obs[0]) exp = { 'metadata_complete': True, 'reprocess': False, 'timeseries_type': 'None', 'pmid': ['123456', '7891011'], 'study_title': 'Identification of the Microbiomes for Cannabis ' 'Soils'} self.assertItemsEqual(obs, exp) # Test get specific keys for all studies info = { 'timeseries_type_id': 1, 'lab_person_id': None, 'principal_investigator_id': 3, 'metadata_complete': False, 'mixs_compliant': True, 'study_description': 'desc', 'study_alias': 'alias', 'study_abstract': 'abstract'} user = User('*****@*****.**') Study.create(user, 'test_study_1', efo=[1], info=info) obs = Study.get_info(info_cols=exp_keys) exp = [[True, ['123456', '7891011'], False, 'Identification of the Microbiomes for Cannabis Soils', 'None'], [False, None, False, 'test_study_1', 'None']] self.assertEqual(obs, exp) # test portal restriction working qiita_config.portal = 'EMP' with self.assertRaises(QiitaDBError): Study.get_info([1]) def test_has_access_public(self): self._change_processed_data_status('public') qiita_config.portal = 'QIITA' self.assertTrue(self.study.has_access(User("*****@*****.**"))) qiita_config.portal = 'EMP' with self.assertRaises(QiitaDBError): Study(1).has_access(User("*****@*****.**")) def test_has_access_no_public(self): self._change_processed_data_status('public') self.assertFalse(self.study.has_access(User("*****@*****.**"), True)) def test_owner(self): self.assertEqual(self.study.owner, "*****@*****.**") def test_share(self): # Clear all sharing associations self._change_processed_data_status('sandbox') self.conn_handler.execute("delete from qiita.study_users") self.assertEqual(self.study.shared_with, []) # Try to share with the owner, which should not work self.study.share(User("*****@*****.**")) self.assertEqual(self.study.shared_with, []) # Then share the study with [email protected] self.study.share(User("*****@*****.**")) self.assertEqual(self.study.shared_with, ["*****@*****.**"]) def test_unshare(self): self._change_processed_data_status('sandbox') self.study.unshare(User("*****@*****.**")) self.assertEqual(self.study.shared_with, []) def test_has_access_shared(self): self._change_processed_data_status('sandbox') self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_private(self): self._change_processed_data_status('sandbox') self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_admin(self): self._change_processed_data_status('sandbox') self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_no_access(self): self._change_processed_data_status('sandbox') self.assertFalse(self.study.has_access(User("*****@*****.**"))) def test_get_by_status(self): obs = Study.get_by_status('sandbox') self.assertEqual(obs, set()) Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) obs = Study.get_by_status('private') self.assertEqual(obs, {1}) obs = Study.get_by_status('sandbox') self.assertEqual(obs, {2}) obs = Study.get_by_status('public') self.assertEqual(obs, set()) obs = Study.get_by_status('awaiting_approval') self.assertEqual(obs, set()) def test_exists(self): self.assertTrue(Study.exists('Identification of the Microbiomes for ' 'Cannabis Soils')) self.assertFalse(Study.exists('Not Cannabis Soils')) def test_create_duplicate(self): with self.assertRaises(QiitaDBDuplicateError): Study.create( User('*****@*****.**'), 'Identification of the Microbiomes for Cannabis Soils', [1], self.info) def test_create_study_min_data(self): """Insert a study into the database""" before = datetime.now() obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info) after = datetime.now() self.assertEqual(obs.id, 2) exp = {'mixs_compliant': True, 'metadata_complete': True, 'reprocess': False, 'number_samples_promised': 28, 'emp_person_id': 2, 'funding': None, 'vamps_id': None, 'principal_investigator_id': 3, 'timeseries_type_id': 1, 'study_abstract': 'Exploring how a high fat diet changes the ' 'gut microbiome', 'email': '*****@*****.**', 'spatial_series': None, 'study_description': 'Microbiome of people who eat nothing but' ' fried chicken', 'study_alias': 'FCM', 'study_id': 2, 'most_recent_contact': None, 'lab_person_id': 1, 'study_title': 'Fried chicken microbiome', 'number_samples_collected': 25} obsins = self.conn_handler.execute_fetchall( "SELECT * FROM qiita.study WHERE study_id = 2") self.assertEqual(len(obsins), 1) obsins = dict(obsins[0]) # Check the timestamp separately, since it is set by the database # to the microsecond, and we can't predict it a priori ins_timestamp = obsins.pop('first_contact') self.assertTrue(before < ins_timestamp < after) self.assertEqual(obsins, exp) # make sure EFO went in to table correctly efo = self.conn_handler.execute_fetchall( "SELECT efo_id FROM qiita.study_experimental_factor " "WHERE study_id = 2") self.assertEqual(efo, [[1]]) def test_create_nonqiita_portal(self): qiita_config.portal = "EMP" Study.create(User('*****@*****.**'), "NEW!", [1], self.info, Investigation(1)) # make sure portal is associated obs = self.conn_handler.execute_fetchall( "SELECT * from qiita.study_portal WHERE study_id = 2") self.assertEqual(obs, [[2, 2], [2, 1]]) def test_create_study_with_investigation(self): """Insert a study into the database with an investigation""" obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info, Investigation(1)) self.assertEqual(obs.id, 2) # check the investigation was assigned obs = self.conn_handler.execute_fetchall( "SELECT * from qiita.investigation_study WHERE study_id = 2") self.assertEqual(obs, [[1, 2]]) def test_create_study_all_data(self): """Insert a study into the database with every info field""" self.info.update({ 'vamps_id': 'MBE_1111111', 'funding': 'FundAgency', 'spatial_series': True, 'metadata_complete': False, 'reprocess': True, 'first_contact': "10/24/2014 12:47PM", 'study_id': 3827 }) obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info) self.assertEqual(obs.id, 3827) exp = {'mixs_compliant': True, 'metadata_complete': False, 'reprocess': True, 'number_samples_promised': 28, 'emp_person_id': 2, 'funding': 'FundAgency', 'vamps_id': 'MBE_1111111', 'first_contact': datetime(2014, 10, 24, 12, 47), 'principal_investigator_id': 3, 'timeseries_type_id': 1, 'study_abstract': 'Exploring how a high fat diet changes the ' 'gut microbiome', 'email': '*****@*****.**', 'spatial_series': True, 'study_description': 'Microbiome of people who eat nothing ' 'but fried chicken', 'study_alias': 'FCM', 'study_id': 3827, 'most_recent_contact': None, 'lab_person_id': 1, 'study_title': 'Fried chicken microbiome', 'number_samples_collected': 25} obsins = self.conn_handler.execute_fetchall( "SELECT * FROM qiita.study WHERE study_id = 3827") self.assertEqual(len(obsins), 1) obsins = dict(obsins[0]) self.assertEqual(obsins, exp) # make sure EFO went in to table correctly obsefo = self.conn_handler.execute_fetchall( "SELECT efo_id FROM qiita.study_experimental_factor " "WHERE study_id = 3827") self.assertEqual(obsefo, [[1]]) def test_create_missing_required(self): """ Insert a study that is missing a required info key""" self.info.pop("study_alias") with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_create_empty_efo(self): """ Insert a study that is missing a required info key""" with self.assertRaises(IncompetentQiitaDeveloperError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [], self.info) def test_create_study_with_not_allowed_key(self): """Insert a study with key from _non_info present""" self.info.update({"email": "*****@*****.**"}) with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_create_unknown_db_col(self): """ Insert a study with an info key not in the database""" self.info["SHOULDNOTBEHERE"] = "BWAHAHAHAHAHA" with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_delete(self): title = "Fried chicken microbiome" # the study is assigned to investigation 1 study = Study.create(User('*****@*****.**'), title, [1], self.info, Investigation(1)) # sharing with other user study.share(User("*****@*****.**")) study.delete(study.id) self.assertFalse(study.exists(title)) with self.assertRaises(QiitaDBError): Study.delete(1) with self.assertRaises(QiitaDBUnknownIDError): Study.delete(41) def test_retrieve_title(self): self.assertEqual(self.study.title, 'Identification of the Microbiomes' ' for Cannabis Soils') def test_set_title(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.title = "Cannabis soils" self.assertEqual(new.title, "Cannabis soils") def test_get_efo(self): self.assertEqual(self.study.efo, [1]) def test_set_efo(self): """Set efo with list efo_id""" new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.efo = [3, 4] self.assertEqual(new.efo, [3, 4]) def test_set_efo_empty(self): """Set efo with list efo_id""" new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(IncompetentQiitaDeveloperError): new.efo = [] def test_set_efo_public(self): """Set efo on a public study""" with self.assertRaises(QiitaDBStatusError): self.study.efo = 6 def test_portals(self): self.assertEqual(self.study._portals, ['QIITA']) def test_retrieve_info(self): for key, val in viewitems(self.existingexp): if isinstance(val, QiitaObject): self.existingexp[key] = val.id self.assertEqual(self.study.info, self.existingexp) def test_set_info(self): """Set info in a study""" newinfo = { "timeseries_type_id": 2, "metadata_complete": False, "number_samples_collected": 28, "lab_person_id": StudyPerson(2), "vamps_id": 'MBE_111222', } self.info['first_contact'] = "6/11/2014" new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.infoexp.update(newinfo) new.info = newinfo # add missing table cols self.infoexp["funding"] = None self.infoexp["spatial_series"] = None self.infoexp["most_recent_contact"] = None self.infoexp["reprocess"] = False self.infoexp["lab_person_id"] = 2 self.infoexp["first_contact"] = datetime(2014, 6, 11) self.assertEqual(new.info, self.infoexp) def test_set_info_public(self): """Tests for fail if editing info of a public study""" self.study.info = {"vamps_id": "12321312"} def test_set_info_public_error(self): """Tests for fail if trying to modify timeseries of a public study""" with self.assertRaises(QiitaDBStatusError): self.study.info = {"timeseries_type_id": 2} def test_set_info_disallowed_keys(self): """Tests for fail if sending non-info keys in info dict""" new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(QiitaDBColumnError): new.info = {"email": "*****@*****.**"} def test_info_empty(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(IncompetentQiitaDeveloperError): new.info = {} def test_retrieve_status(self): self.assertEqual(self.study.status, "private") def test_retrieve_shared_with(self): self.assertEqual(self.study.shared_with, ['*****@*****.**']) def test_retrieve_pmids(self): exp = ['123456', '7891011'] self.assertEqual(self.study.pmids, exp) def test_retrieve_pmids_empty(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.pmids, []) def test_pmids_setter(self): exp = ['123456', '7891011'] self.assertEqual(self.study.pmids, exp) new_values = ['654321', '1101987'] self.study.pmids = new_values self.assertEqual(self.study.pmids, new_values) def test_pmids_setter_typeerror(self): with self.assertRaises(TypeError): self.study.pmids = '123456' def test_retrieve_investigation(self): self.assertEqual(self.study.investigation, 1) def test_retrieve_investigation_empty(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.investigation, None) def test_retrieve_sample_template(self): self.assertEqual(self.study.sample_template, 1) def test_retrieve_data_types(self): self.assertEqual(self.study.data_types, ['18S']) def test_retrieve_data_types_none(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.data_types, []) def test_retrieve_raw_data(self): self.assertEqual(self.study.raw_data(), [1]) def test_retrieve_raw_data_none(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.raw_data(), []) def test_retrieve_prep_templates(self): self.assertEqual(self.study.prep_templates(), [1]) def test_retrieve_prep_templates_none(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.prep_templates(), []) def test_retrieve_preprocessed_data(self): self.assertEqual(self.study.preprocessed_data(), [1, 2]) def test_retrieve_preprocessed_data_none(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.preprocessed_data(), []) def test_retrieve_processed_data(self): self.assertEqual(self.study.processed_data(), [1]) def test_retrieve_processed_data_none(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.processed_data(), []) def test_add_pmid(self): self._change_processed_data_status('sandbox') self.study.add_pmid('4544444') exp = ['123456', '7891011', '4544444'] self.assertEqual(self.study.pmids, exp) def test_environmental_packages(self): obs = self.study.environmental_packages exp = ['soil', 'plant-associated'] self.assertEqual(sorted(obs), sorted(exp)) def test_environmental_packages_setter(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) obs = new.environmental_packages exp = [] self.assertEqual(obs, exp) new_values = ['air', 'human-oral'] new.environmental_packages = new_values obs = new.environmental_packages self.assertEqual(sorted(obs), sorted(new_values)) def test_environmental_packages_setter_typeerror(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(TypeError): new.environmental_packages = 'air' def test_environmental_packages_setter_valueerror(self): new = Study.create(User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(ValueError): new.environmental_packages = ['air', 'not a package'] def test_environmental_packages_sandboxed(self): with self.assertRaises(QiitaDBStatusError): self.study.environmental_packages = ['air']
def study_get_req(study_id, user_id): """Returns information available for the given study Parameters ---------- study_id : int Study id to get prep template info for user_id : str User requesting the info Returns ------- dict Data types information in the form {'status': status, 'message': message, 'info': dict of objects status can be success, warning, or error depending on result message has the warnings or errors info contains study information seperated by data type, in the form {col_name: value, ...} with value being a string, int, or list of strings or ints """ access_error = check_access(study_id, user_id) if access_error: return access_error # Can only pass ids over API, so need to instantiate object study = Study(study_id) study_info = study.info # Add needed info that is not part of the initial info pull study_info['publication_doi'] = [] study_info['publication_pid'] = [] for pub, is_doi in study.publications: if is_doi: study_info['publication_doi'].append(pub) else: study_info['publication_pid'].append(pub) study_info['study_id'] = study.id study_info['study_title'] = study.title study_info['shared_with'] = [s.id for s in study.shared_with] study_info['status'] = study.status study_info['ebi_study_accession'] = study.ebi_study_accession study_info['ebi_submission_status'] = study.ebi_submission_status # Clean up StudyPerson objects to string for display pi = study_info['principal_investigator'] study_info['principal_investigator'] = { 'name': pi.name, 'email': pi.email, 'affiliation': pi.affiliation} lab_person = study_info['lab_person'] if lab_person: study_info['lab_person'] = { 'name': lab_person.name, 'email': lab_person.email, 'affiliation': lab_person.affiliation} samples = study.sample_template study_info['num_samples'] = 0 if samples is None else len(list(samples)) study_info['owner'] = study.owner.id # Study.has_access no_public=True, will return True only if the user_id is # the owner of the study or if the study is shared with the user_id study_info['has_access_to_raw_data'] = study.has_access( User(user_id), True) study_info['show_biom_download_button'] = 'BIOM' in [ a.artifact_type for a in study.artifacts()] study_info['show_raw_download_button'] = any([ True for pt in study.prep_templates() if pt.artifact is not None]) # getting study processing status from redis processing = False study_info['level'] = '' study_info['message'] = '' job_info = r_client.get(STUDY_KEY_FORMAT % study_id) if job_info: job_info = defaultdict(lambda: '', loads(job_info)) job_id = job_info['job_id'] job = ProcessingJob(job_id) job_status = job.status processing = job_status not in ('success', 'error') if processing: study_info['level'] = 'info' study_info['message'] = 'This study is currently being processed' elif job_status == 'error': study_info['level'] = 'danger' study_info['message'] = job.log.msg.replace('\n', '</br>') else: study_info['level'] = job_info['alert_type'] study_info['message'] = job_info['alert_msg'].replace( '\n', '</br>') return {'status': 'success', 'message': '', 'study_info': study_info, 'editable': study.can_edit(User(user_id))}
class TestStudy(TestCase): def setUp(self): self.study = Study(1) self.info = { "timeseries_type_id": 1, "metadata_complete": True, "mixs_compliant": True, "number_samples_collected": 25, "number_samples_promised": 28, "portal_type_id": 3, "study_alias": "FCM", "study_description": "Microbiome of people who eat nothing but " "fried chicken", "study_abstract": "Exploring how a high fat diet changes the " "gut microbiome", "emp_person_id": StudyPerson(2), "principal_investigator_id": StudyPerson(3), "lab_person_id": StudyPerson(1) } self.infoexp = { "timeseries_type_id": 1, "metadata_complete": True, "mixs_compliant": True, "number_samples_collected": 25, "number_samples_promised": 28, "portal_type_id": 3, "study_alias": "FCM", "study_description": "Microbiome of people who eat nothing but " "fried chicken", "study_abstract": "Exploring how a high fat diet changes the " "gut microbiome", "emp_person_id": 2, "principal_investigator_id": 3, "lab_person_id": 1 } self.existingexp = { 'mixs_compliant': True, 'metadata_complete': True, 'reprocess': False, 'number_samples_promised': 27, 'emp_person_id': StudyPerson(2), 'funding': None, 'vamps_id': None, 'first_contact': datetime(2014, 5, 19, 16, 10), 'principal_investigator_id': StudyPerson(3), 'timeseries_type_id': 1, '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.", 'spatial_series': False, 'study_description': 'Analysis of the Cannabis Plant Microbiome', 'portal_type_id': 2, 'study_alias': 'Cannabis Soils', 'most_recent_contact': '2014-05-19 16:11', 'most_recent_contact': datetime(2014, 5, 19, 16, 11), 'lab_person_id': StudyPerson(1), 'number_samples_collected': 27 } def _make_private(self): # make studies private self.conn_handler.execute("UPDATE qiita.study SET study_status_id = 4") def _make_sandbox(self): # make studies private self.conn_handler.execute("UPDATE qiita.study SET study_status_id = 1") def test_has_access_public(self): self.study.status = 'public' self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_no_public(self): self.study.status = 'public' self.assertFalse(self.study.has_access(User("*****@*****.**"), True)) def test_owner(self): self.assertEqual(self.study.owner, "*****@*****.**") def test_share(self): # Clear all sharing associations self._make_private() self.conn_handler.execute("delete from qiita.study_users") self.assertEqual(self.study.shared_with, []) # Try to share with the owner, which should not work self.study.share(User("*****@*****.**")) self.assertEqual(self.study.shared_with, []) # Then share the study with [email protected] self.study.share(User("*****@*****.**")) self.assertEqual(self.study.shared_with, ["*****@*****.**"]) def test_unshare(self): self._make_private() self.study.unshare(User("*****@*****.**")) self.assertEqual(self.study.shared_with, []) def test_has_access_shared(self): self._make_private() self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_private(self): self._make_private() self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_admin(self): self._make_private() self.assertTrue(self.study.has_access(User("*****@*****.**"))) def test_has_access_no_access(self): self._make_private() self.assertFalse(self.study.has_access(User("*****@*****.**"))) def test_get_by_status(self): Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) obs = Study.get_by_status('private') self.assertEqual(obs, [1]) def test_exists(self): self.assertTrue( Study.exists('Identification of the Microbiomes for ' 'Cannabis Soils')) self.assertFalse(Study.exists('Not Cannabis Soils')) def test_create_study_min_data(self): """Insert a study into the database""" before = datetime.now() obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info) after = datetime.now() self.assertEqual(obs.id, 2) exp = { 'mixs_compliant': True, 'metadata_complete': True, 'reprocess': False, 'study_status_id': 4, 'number_samples_promised': 28, 'emp_person_id': 2, 'funding': None, 'vamps_id': None, 'principal_investigator_id': 3, 'timeseries_type_id': 1, 'study_abstract': 'Exploring how a high fat diet changes the ' 'gut microbiome', 'email': '*****@*****.**', 'spatial_series': None, 'study_description': 'Microbiome of people who eat nothing but' ' fried chicken', 'portal_type_id': 3, 'study_alias': 'FCM', 'study_id': 2, 'most_recent_contact': None, 'lab_person_id': 1, 'study_title': 'Fried chicken microbiome', 'number_samples_collected': 25 } obsins = self.conn_handler.execute_fetchall( "SELECT * FROM qiita.study WHERE study_id = 2") self.assertEqual(len(obsins), 1) obsins = dict(obsins[0]) # Check the timestamp separately, since it is set by the database # to the microsecond, and we can't predict it a priori ins_timestamp = obsins.pop('first_contact') self.assertTrue(before < ins_timestamp < after) self.assertEqual(obsins, exp) # make sure EFO went in to table correctly efo = self.conn_handler.execute_fetchall( "SELECT efo_id FROM qiita.study_experimental_factor " "WHERE study_id = 2") self.assertEqual(efo, [[1]]) def test_create_study_with_investigation(self): """Insert a study into the database with an investigation""" obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info, Investigation(1)) self.assertEqual(obs.id, 2) # check the investigation was assigned obs = self.conn_handler.execute_fetchall( "SELECT * from qiita.investigation_study WHERE study_id = 2") self.assertEqual(obs, [[1, 2]]) def test_create_study_all_data(self): """Insert a study into the database with every info field""" self.info.update({ 'vamps_id': 'MBE_1111111', 'funding': 'FundAgency', 'spatial_series': True, 'metadata_complete': False, 'reprocess': True, 'first_contact': "10/24/2014 12:47PM", 'study_id': 3827 }) obs = Study.create(User('*****@*****.**'), "Fried chicken microbiome", [1], self.info) self.assertEqual(obs.id, 3827) exp = { 'mixs_compliant': True, 'metadata_complete': False, 'reprocess': True, 'study_status_id': 4, 'number_samples_promised': 28, 'emp_person_id': 2, 'funding': 'FundAgency', 'vamps_id': 'MBE_1111111', 'first_contact': datetime(2014, 10, 24, 12, 47), 'principal_investigator_id': 3, 'timeseries_type_id': 1, 'study_abstract': 'Exploring how a high fat diet changes the ' 'gut microbiome', 'email': '*****@*****.**', 'spatial_series': True, 'study_description': 'Microbiome of people who eat nothing ' 'but fried chicken', 'portal_type_id': 3, 'study_alias': 'FCM', 'study_id': 3827, 'most_recent_contact': None, 'lab_person_id': 1, 'study_title': 'Fried chicken microbiome', 'number_samples_collected': 25 } obsins = self.conn_handler.execute_fetchall( "SELECT * FROM qiita.study WHERE study_id = 3827") self.assertEqual(len(obsins), 1) obsins = dict(obsins[0]) self.assertEqual(obsins, exp) # make sure EFO went in to table correctly obsefo = self.conn_handler.execute_fetchall( "SELECT efo_id FROM qiita.study_experimental_factor " "WHERE study_id = 3827") self.assertEqual(obsefo, [[1]]) def test_create_missing_required(self): """ Insert a study that is missing a required info key""" self.info.pop("study_alias") with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_create_empty_efo(self): """ Insert a study that is missing a required info key""" with self.assertRaises(IncompetentQiitaDeveloperError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [], self.info) def test_create_study_with_not_allowed_key(self): """Insert a study with key from _non_info present""" self.info.update({"email": "*****@*****.**"}) with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_create_unknown_db_col(self): """ Insert a study with an info key not in the database""" self.info["SHOULDNOTBEHERE"] = "BWAHAHAHAHAHA" with self.assertRaises(QiitaDBColumnError): Study.create(User('*****@*****.**'), "Fried Chicken Microbiome", [1], self.info) def test_retrieve_title(self): self.assertEqual( self.study.title, 'Identification of the Microbiomes' ' for Cannabis Soils') def test_set_title(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.title = "Cannabis soils" self.assertEqual(new.title, "Cannabis soils") def test_get_efo(self): self.assertEqual(self.study.efo, [1]) def test_set_efo(self): """Set efo with list efo_id""" new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.efo = [3, 4] self.assertEqual(new.efo, [3, 4]) def test_set_efo_empty(self): """Set efo with list efo_id""" new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(IncompetentQiitaDeveloperError): new.efo = [] def test_set_efo_public(self): """Set efo on a public study""" with self.assertRaises(QiitaDBStatusError): self.study.efo = 6 def test_retrieve_info(self): for key, val in viewitems(self.existingexp): if isinstance(val, QiitaObject): self.existingexp[key] = val.id self.assertEqual(self.study.info, self.existingexp) def test_set_info(self): """Set info in a study""" newinfo = { "timeseries_type_id": 2, "metadata_complete": False, "number_samples_collected": 28, "lab_person_id": StudyPerson(2), "vamps_id": 'MBE_111222', } self.info['first_contact'] = "6/11/2014" new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.infoexp.update(newinfo) new.info = newinfo # add missing table cols self.infoexp["funding"] = None self.infoexp["spatial_series"] = None self.infoexp["most_recent_contact"] = None self.infoexp["reprocess"] = False self.infoexp["lab_person_id"] = 2 self.infoexp["first_contact"] = datetime(2014, 6, 11) self.assertEqual(new.info, self.infoexp) def test_set_info_public(self): """Tests for fail if editing info of a public study""" self.study.info = {"vamps_id": "12321312"} def test_set_info_public_error(self): """Tests for fail if trying to modify timeseries of a public study""" with self.assertRaises(QiitaDBStatusError): self.study.info = {"timeseries_type_id": 2} def test_set_info_disallowed_keys(self): """Tests for fail if sending non-info keys in info dict""" new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(QiitaDBColumnError): new.info = {"email": "*****@*****.**"} def test_info_empty(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(IncompetentQiitaDeveloperError): new.info = {} def test_retrieve_status(self): self.assertEqual(self.study.status, "private") def test_set_status(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.status = "private" self.assertEqual(new.status, "private") def test_retrieve_shared_with(self): self.assertEqual(self.study.shared_with, ['*****@*****.**']) def test_retrieve_pmids(self): exp = ['123456', '7891011'] self.assertEqual(self.study.pmids, exp) def test_retrieve_pmids_empty(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.pmids, []) def test_pmids_setter(self): exp = ['123456', '7891011'] self.assertEqual(self.study.pmids, exp) new_values = ['654321', '1101987'] self.study.pmids = new_values self.assertEqual(self.study.pmids, new_values) def test_pmids_setter_typeerror(self): with self.assertRaises(TypeError): self.study.pmids = '123456' def test_retrieve_investigation(self): self.assertEqual(self.study.investigation, 1) def test_retrieve_investigation_empty(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.investigation, None) def test_retrieve_sample_template(self): self.assertEqual(self.study.sample_template, 1) def test_retrieve_data_types(self): self.assertEqual(self.study.data_types, ['18S']) def test_retrieve_data_types_none(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.data_types, []) def test_retrieve_raw_data(self): self.assertEqual(self.study.raw_data(), [1, 2, 3, 4]) def test_retrieve_raw_data_none(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.raw_data(), []) def test_add_raw_data(self): self._make_sandbox() new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.add_raw_data([RawData(1), RawData(2)]) obs = self.conn_handler.execute_fetchall( "SELECT * FROM qiita.study_raw_data WHERE study_id=%s", (new.id, )) self.assertEqual(obs, [[new.id, 1], [new.id, 2]]) def test_add_raw_data_private(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) new.status = 'private' with self.assertRaises(QiitaDBStatusError): new.add_raw_data([RawData(2)]) def test_retrieve_preprocessed_data(self): self.assertEqual(self.study.preprocessed_data(), [1, 2]) def test_retrieve_preprocessed_data_none(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.preprocessed_data(), []) def test_retrieve_processed_data(self): self.assertEqual(self.study.processed_data(), [1]) def test_retrieve_processed_data_none(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) self.assertEqual(new.processed_data(), []) def test_add_pmid(self): self._make_private() self.study.add_pmid('4544444') exp = ['123456', '7891011', '4544444'] self.assertEqual(self.study.pmids, exp) def test_environmental_packages(self): obs = self.study.environmental_packages exp = ['soil', 'plant-associated'] self.assertEqual(sorted(obs), sorted(exp)) def test_environmental_packages_setter(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) obs = new.environmental_packages exp = [] self.assertEqual(obs, exp) new_values = ['air', 'human-oral'] new.environmental_packages = new_values obs = new.environmental_packages self.assertEqual(sorted(obs), sorted(new_values)) def test_environmental_packages_setter_typeerror(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(TypeError): new.environmental_packages = 'air' def test_environmental_packages_setter_valueerror(self): new = Study.create( User('*****@*****.**'), 'NOT Identification of the ' 'Microbiomes for Cannabis Soils', [1], self.info) with self.assertRaises(ValueError): new.environmental_packages = ['air', 'not a package'] def test_environmental_packages_sandboxed(self): with self.assertRaises(QiitaDBStatusError): self.study.environmental_packages = ['air']
def study_get_req(study_id, user_id): """Returns information available for the given study Parameters ---------- study_id : int Study id to get prep template info for user_id : str User requesting the info Returns ------- dict Data types information in the form {'status': status, 'message': message, 'info': dict of objects status can be success, warning, or error depending on result message has the warnings or errors info contains study information seperated by data type, in the form {col_name: value, ...} with value being a string, int, or list of strings or ints """ access_error = check_access(study_id, user_id) if access_error: return access_error # Can only pass ids over API, so need to instantiate object study = Study(study_id) study_info = study.info # Add needed info that is not part of the initial info pull study_info['publication_doi'] = [] study_info['publication_pid'] = [] for pub, is_doi in study.publications: if is_doi: study_info['publication_doi'].append(pub) else: study_info['publication_pid'].append(pub) study_info['study_id'] = study.id study_info['study_title'] = study.title study_info['shared_with'] = [s.id for s in study.shared_with] study_info['status'] = study.status study_info['ebi_study_accession'] = study.ebi_study_accession study_info['ebi_submission_status'] = study.ebi_submission_status # Clean up StudyPerson objects to string for display pi = study_info['principal_investigator'] study_info['principal_investigator'] = { 'name': pi.name, 'email': pi.email, 'affiliation': pi.affiliation} lab_person = study_info['lab_person'] if lab_person: study_info['lab_person'] = { 'name': lab_person.name, 'email': lab_person.email, 'affiliation': lab_person.affiliation} samples = study.sample_template study_info['num_samples'] = 0 if samples is None else len(list(samples)) study_info['owner'] = study.owner.id # Study.has_access no_public=True, will return True only if the user_id is # the owner of the study or if the study is shared with the user_id study_info['has_access_to_raw_data'] = study.has_access( User(user_id), True) study_info['show_biom_download_button'] = 'BIOM' in [ a.artifact_type for a in study.artifacts()] study_info['show_raw_download_button'] = any([ True for pt in study.prep_templates() if pt.artifact is not None]) return {'status': 'success', 'message': '', 'study_info': study_info, 'editable': study.can_edit(User(user_id))}
def get(self, study_id): study_id = int(study_id) # Check general access to study study_info = study_get_req(study_id, self.current_user.id) if study_info['status'] != 'success': raise HTTPError( 405, "%s: %s, %s" % (study_info['message'], self.current_user.email, str(study_id))) study = Study(study_id) user = self.current_user # Check "owner" access to the study if not study.has_access(user, True): raise HTTPError( 405, "%s: %s, %s" % ('No raw data access', self.current_user.email, str(study_id))) basedir = get_db_files_base_dir() basedir_len = len(basedir) + 1 # loop over artifacts and retrieve raw data (no parents) to_download = [] for a in study.artifacts(): if not a.parents: for i, (fid, path, data_type) in enumerate(a.filepaths): if data_type == 'directory': # If we have a directory, we actually need to list # all the files from the directory so NGINX can # actually download all of them for dp, _, fps in walk(path): for fname in fps: fullpath = join(dp, fname) spath = fullpath if fullpath.startswith(basedir): spath = fullpath[basedir_len:] to_download.append((fullpath, spath, spath)) elif path.startswith(basedir): spath = path[basedir_len:] to_download.append((path, spath, spath)) else: # We are not aware of any case that can trigger this # situation, but we wanted to be overly cautious # There is no test for this line cause we don't know # how to trigger it to_download.append((path, path, path)) for pt in a.prep_templates: qmf = pt.qiime_map_fp if qmf is not None: sqmf = qmf if qmf.startswith(basedir): sqmf = qmf[basedir_len:] to_download.append( (qmf, sqmf, 'mapping_files/%s_mapping_file.txt' % a.id)) # If we don't have nginx, write a file that indicates this # Note that this configuration will automatically create and download # ("on the fly") the zip file via the contents in all_files all_files = '\n'.join([ "- %s /protected/%s %s" % (getsize(fp), sfp, n) for fp, sfp, n in to_download ]) self.write("%s\n" % all_files) zip_fn = 'study_raw_data_%d_%s.zip' % ( study_id, datetime.now().strftime('%m%d%y-%H%M%S')) self.set_header('Content-Description', 'File Transfer') self.set_header('Expires', '0') self.set_header('Cache-Control', 'no-cache') self.set_header('X-Archive-Files', 'zip') self.set_header('Content-Disposition', 'attachment; filename=%s' % zip_fn) self.finish()