Reducing the rename_cols dict

josenavas · josenavas · commit 2d3df0820c42 · 2015-04-27T17:52:41.000-07:00
diff --git a/qiita_db/metadata_template/prep_template.py b/qiita_db/metadata_template/prep_template.py
@@ -417,9 +417,7 @@ def create_qiime_mapping_file(self):
         """
         rename_cols = {
             'barcode': 'BarcodeSequence',
-            'barcodesequence': 'BarcodeSequence',
             'primer': 'LinkerPrimerSequence',
-            'linkerprimersequence': 'LinkerPrimerSequence',
             'description': 'Description',
         }
 
diff --git a/qiita_db/metadata_template/test/test_prep_template.py b/qiita_db/metadata_template/test/test_prep_template.py
@@ -41,9 +41,9 @@ def setUp(self):
         self.sample_id = '1.SKB8.640193'
         self.tester = PrepSample(self.sample_id, self.prep_template)
         self.exp_categories = {'center_name', 'center_project_name',
-                               'emp_status', 'barcodesequence',
+                               'emp_status', 'barcode',
                                'library_construction_protocol',
-                               'linkerprimersequence', 'target_subfragment',
+                               'primer', 'target_subfragment',
                                'target_gene', 'run_center', 'run_prefix',
                                'run_date', 'experiment_center',
                                'experiment_design_description',
@@ -83,11 +83,11 @@ def test_add_setitem_queries_dynamic(self):
         conn_handler.create_queue(queue)
 
         self.tester.add_setitem_queries(
-            'barcodesequence', 'AAAAAAAAAAAA', conn_handler, queue)
+            'barcode', 'AAAAAAAAAAAA', conn_handler, queue)
 
         obs = conn_handler.queues[queue]
         sql = """UPDATE qiita.prep_1
-                 SET barcodesequence=%s
+                 SET barcode=%s
                  WHERE sample_id=%s"""
         exp = [(sql, ('AAAAAAAAAAAA', '1.SKB8.640193'))]
         self.assertEqual(obs, exp)
@@ -156,7 +156,7 @@ def test_getitem_dynamic(self):
         """
         self.assertEqual(self.tester['pcr_primers'],
                          'FWD:GTGCCAGCMGCCGCGGTAA; REV:GGACTACHVGGGTWTCTAAT')
-        self.assertEqual(self.tester['barcodesequence'], 'AGCGCTCACATC')
+        self.assertEqual(self.tester['barcode'], 'AGCGCTCACATC')
 
     def test_getitem_id_column(self):
         """Get item returns the correct metadata value from the changed column
@@ -176,8 +176,8 @@ def test_iter(self):
 
     def test_contains_true(self):
         """contains returns true if the category header exists"""
-        self.assertTrue('BarcodeSequence' in self.tester)
-        self.assertTrue('barcodesequence' in self.tester)
+        self.assertTrue('Barcode' in self.tester)
+        self.assertTrue('barcode' in self.tester)
 
     def test_contains_false(self):
         """contains returns false if the category header does not exists"""
@@ -218,7 +218,7 @@ def test_items(self):
         obs = self.tester.items()
         self.assertTrue(isinstance(obs, Iterable))
         exp = {('center_name', 'ANL'), ('center_project_name', None),
-               ('emp_status', 'EMP'), ('barcodesequence', 'AGCGCTCACATC'),
+               ('emp_status', 'EMP'), ('barcode', 'AGCGCTCACATC'),
                ('library_construction_protocol',
                 'This analysis was done as in Caporaso et al 2011 Genome '
                 'research. The PCR primers (F515/R806) were developed against '
@@ -231,7 +231,7 @@ def test_items(self):
                 'PCR primer is barcoded with a 12-base error-correcting Golay '
                 'code to facilitate multiplexing of up to 1,500 samples per '
                 'lane, and both PCR primers contain sequencer adapter '
-                'regions.'), ('linkerprimersequence', 'GTGCCAGCMGCCGCGGTAA'),
+                'regions.'), ('primer', 'GTGCCAGCMGCCGCGGTAA'),
                ('target_subfragment', 'V4'), ('target_gene', '16S rRNA'),
                ('run_center', 'ANL'), ('run_prefix', 's_G1_L001_sequences'),
                ('run_date', '8/1/12'), ('experiment_center', 'ANL'),
@@ -248,7 +248,7 @@ def test_items(self):
 
     def test_get(self):
         """get returns the correct sample object"""
-        self.assertEqual(self.tester.get('barcodesequence'), 'AGCGCTCACATC')
+        self.assertEqual(self.tester.get('barcode'), 'AGCGCTCACATC')
 
     def test_get_none(self):
         """get returns none if the sample id is not present"""
@@ -567,8 +567,8 @@ def test_to_dataframe(self):
 
         self.assertEqual(set(obs.columns), {
             u'center_name', u'center_project_name',
-            u'emp_status', u'barcodesequence',
-            u'library_construction_protocol', u'linkerprimersequence',
+            u'emp_status', u'barcode',
+            u'library_construction_protocol', u'primer',
             u'target_subfragment', u'target_gene', u'run_center',
             u'run_prefix', u'run_date', u'experiment_center',
             u'experiment_design_description', u'experiment_title', u'platform',
@@ -1260,23 +1260,23 @@ def test_status(self):
 
     def test_update_category(self):
         with self.assertRaises(QiitaDBUnknownIDError):
-            self.tester.update_category('barcodesequence', {"foo": "bar"})
+            self.tester.update_category('barcode', {"foo": "bar"})
 
         with self.assertRaises(QiitaDBColumnError):
             self.tester.update_category('missing column',
                                         {'1.SKB7.640196': 'bar'})
 
-        neg_test = self.tester['1.SKB7.640196']['barcodesequence']
+        neg_test = self.tester['1.SKB7.640196']['barcode']
         mapping = {'1.SKB8.640193': 'AAAAAAAAAAAA',
                    '1.SKD8.640184': 'CCCCCCCCCCCC'}
 
-        self.tester.update_category('barcodesequence', mapping)
+        self.tester.update_category('barcode', mapping)
 
-        self.assertEqual(self.tester['1.SKB7.640196']['barcodesequence'],
+        self.assertEqual(self.tester['1.SKB7.640196']['barcode'],
                          neg_test)
-        self.assertEqual(self.tester['1.SKB8.640193']['barcodesequence'],
+        self.assertEqual(self.tester['1.SKB8.640193']['barcode'],
                          'AAAAAAAAAAAA')
-        self.assertEqual(self.tester['1.SKD8.640184']['barcodesequence'],
+        self.assertEqual(self.tester['1.SKD8.640184']['barcode'],
                          'CCCCCCCCCCCC')
 
         neg_test = self.tester['1.SKB7.640196']['center_name']
diff --git a/qiita_db/support_files/populate_test_db.sql b/qiita_db/support_files/populate_test_db.sql
@@ -238,9 +238,9 @@ INSERT INTO qiita.prep_template_sample (prep_template_id, sample_id) VALUES
 -- Add raw data prep columns
 INSERT INTO qiita.prep_columns (prep_template_id, column_name, column_type) VALUES
 	(1, 'sample_id', 'varchar'),
-	(1, 'BarcodeSequence', 'varchar'),
+	(1, 'barcode', 'varchar'),
 	(1, 'LIBRARY_CONSTRUCTION_PROTOCOL', 'varchar'),
-	(1, 'LinkerPrimerSequence', 'varchar'),
+	(1, 'primer', 'varchar'),
 	(1, 'TARGET_SUBFRAGMENT', 'varchar'),
 	(1, 'target_gene', 'varchar'),
 	(1, 'RUN_CENTER', 'varchar'),
@@ -263,9 +263,9 @@ INSERT INTO qiita.prep_columns (prep_template_id, column_name, column_type) VALU
 -- Crate the prep_1 dynamic table
 CREATE TABLE qiita.prep_1 (
 	sample_id						varchar,
-	BarcodeSequence					varchar,
+	barcode							varchar,
 	LIBRARY_CONSTRUCTION_PROTOCOL	varchar,
-	LinkerPrimerSequence			varchar,
+	primer							varchar,
 	TARGET_SUBFRAGMENT				varchar,
 	target_gene						varchar,
 	RUN_CENTER						varchar,
@@ -288,7 +288,7 @@ CREATE TABLE qiita.prep_1 (
 );
 
 -- Populates the prep_1 dynamic table
-INSERT INTO qiita.prep_1 (sample_id, BarcodeSequence, LIBRARY_CONSTRUCTION_PROTOCOL, LinkerPrimerSequence, TARGET_SUBFRAGMENT, target_gene, RUN_CENTER, RUN_PREFIX, RUN_DATE, EXPERIMENT_CENTER, EXPERIMENT_DESIGN_DESCRIPTION, EXPERIMENT_TITLE, PLATFORM, SAMP_SIZE, SEQUENCING_METH, illumina_technology, SAMPLE_CENTER, pcr_primers, STUDY_CENTER, center_name, center_project_name, emp_status) VALUES
+INSERT INTO qiita.prep_1 (sample_id, barcode, LIBRARY_CONSTRUCTION_PROTOCOL, primer, TARGET_SUBFRAGMENT, target_gene, RUN_CENTER, RUN_PREFIX, RUN_DATE, EXPERIMENT_CENTER, EXPERIMENT_DESIGN_DESCRIPTION, EXPERIMENT_TITLE, PLATFORM, SAMP_SIZE, SEQUENCING_METH, illumina_technology, SAMPLE_CENTER, pcr_primers, STUDY_CENTER, center_name, center_project_name, emp_status) VALUES
 	('1.SKB1.640202', 'GTCCGCAAGTTA', 'This analysis was done as in Caporaso et al 2011 Genome research. The PCR primers (F515/R806) were developed against the V4 region of the 16S rRNA (both bacteria and archaea), which we determined would yield optimal community clustering with reads of this length using a procedure similar to that of ref. 15. [For reference, this primer pair amplifies the region 533_786 in the Escherichia coli strain 83972 sequence (greengenes accession no. prokMSA_id:470367).] The reverse PCR primer is barcoded with a 12-base error-correcting Golay code to facilitate multiplexing of up to 1,500 samples per lane, and both PCR primers contain sequencer adapter regions.', 'GTGCCAGCMGCCGCGGTAA', 'V4', '16S rRNA', 'ANL', 's_G1_L001_sequences', '8/1/12', 'ANL', 'micro biome of soil and rhizosphere of cannabis plants from CA', 'Cannabis Soil Microbiome', 'Illumina', '.25,g', 'Sequencing by synthesis', 'MiSeq', 'ANL', 'FWD:GTGCCAGCMGCCGCGGTAA; REV:GGACTACHVGGGTWTCTAAT', 'CCME', 'ANL', NULL, 'EMP'),
 	('1.SKB2.640194', 'CGTAGAGCTCTC', 'This analysis was done as in Caporaso et al 2011 Genome research. The PCR primers (F515/R806) were developed against the V4 region of the 16S rRNA (both bacteria and archaea), which we determined would yield optimal community clustering with reads of this length using a procedure similar to that of ref. 15. [For reference, this primer pair amplifies the region 533_786 in the Escherichia coli strain 83972 sequence (greengenes accession no. prokMSA_id:470367).] The reverse PCR primer is barcoded with a 12-base error-correcting Golay code to facilitate multiplexing of up to 1,500 samples per lane, and both PCR primers contain sequencer adapter regions.', 'GTGCCAGCMGCCGCGGTAA', 'V4', '16S rRNA', 'ANL', 's_G1_L001_sequences', '8/1/12', 'ANL', 'micro biome of soil and rhizosphere of cannabis plants from CA', 'Cannabis Soil Microbiome', 'Illumina', '.25,g', 'Sequencing by synthesis', 'MiSeq', 'ANL', 'FWD:GTGCCAGCMGCCGCGGTAA; REV:GGACTACHVGGGTWTCTAAT', 'CCME', 'ANL', NULL, 'EMP'),
 	('1.SKB3.640195', 'CCTCTGAGAGCT', 'This analysis was done as in Caporaso et al 2011 Genome research. The PCR primers (F515/R806) were developed against the V4 region of the 16S rRNA (both bacteria and archaea), which we determined would yield optimal community clustering with reads of this length using a procedure similar to that of ref. 15. [For reference, this primer pair amplifies the region 533_786 in the Escherichia coli strain 83972 sequence (greengenes accession no. prokMSA_id:470367).] The reverse PCR primer is barcoded with a 12-base error-correcting Golay code to facilitate multiplexing of up to 1,500 samples per lane, and both PCR primers contain sequencer adapter regions.', 'GTGCCAGCMGCCGCGGTAA', 'V4', '16S rRNA', 'ANL', 's_G1_L001_sequences', '8/1/12', 'ANL', 'micro biome of soil and rhizosphere of cannabis plants from CA', 'Cannabis Soil Microbiome', 'Illumina', '.25,g', 'Sequencing by synthesis', 'MiSeq', 'ANL', 'FWD:GTGCCAGCMGCCGCGGTAA; REV:GGACTACHVGGGTWTCTAAT', 'CCME', 'ANL', NULL, 'EMP'),

Original file line number	Diff line number	Diff line change
`@@ -417,9 +417,7 @@ def create_qiime_mapping_file(self):`
`417`	`417`	`"""`
`418`	`418`	`rename_cols = {`
`419`	`419`	`'barcode': 'BarcodeSequence',`
`420`		`- 'barcodesequence': 'BarcodeSequence',`
`421`	`420`	`'primer': 'LinkerPrimerSequence',`
`422`		`- 'linkerprimersequence': 'LinkerPrimerSequence',`
`423`	`421`	`'description': 'Description',`
`424`	`422`	`}`
`425`	`423`