Patch srst2 versions 0.1.6 and 0.2.0

recipes/srst2/0.1.6/build.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+$PYTHON setup.py install --single-version-externally-managed --record=record.txt
+

recipes/srst2/0.1.4.6/meta.yaml → recipes/srst2/0.1.6/meta.yaml

@@ -1,16 +1,17 @@
 package:
   name: srst2
-  version: 0.1.4.6
+  version: 0.1.6
 
 source:
   fn: v0.1.6.tar.gz
   url: https://github.com/katholt/srst2/archive/v0.1.6.tar.gz
   sha256: 24cbd03933d4cc14bbfa7f8a073c9b0caafb13d55afb3bfa25f8b093fc5bc615
   patches:
     - use_setuptools.patch
+    - srst_sample_name_v0.1.6.patch
 
 build:
-  number: 1
+  number: 0
   skip: True #[not py27 or osx]
 
 requirements:
@@ -29,8 +30,8 @@ requirements:
 
 test:
   commands:
-    - srst2 -h 2>&1 | grep 'SRST2 - Short Read Sequence Typer' > /dev/null
-    - getmlst.py -h 2>&1 | grep 'usage' > /dev/null
+    - srst2 -h 2>&1 | grep "SRST2 - Short Read Sequence Typer" > /dev/null
+    - getmlst.py -h 2>&1 | grep "usage" > /dev/null
 
 about:
   home: https://github.com/katholt/srst2

recipes/srst2/0.1.6/srst_sample_name_v0.1.6.patch

@@ -0,0 +1,63 @@
+diff --git a/scripts/srst2.py b/scripts/srst2.py
+index 67e48ae..916792e 100755
+--- a/scripts/srst2.py
++++ b/scripts/srst2.py
+@@ -233,7 +233,7 @@ def parse_fai(fai_file,db_type,delimiter):
+ 	return size, gene_clusters, unique_gene_symbols, unique_allele_symbols, gene_cluster_symbols
+
+
+-def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
++def read_pileup_data(pileup_file, size, prob_err, sample_name, consensus_file = ""):
+ 	with open(pileup_file) as pileup:
+ 		prob_success = 1 - prob_err	# Set by user, default is prob_err = 0.01
+ 		hash_alignment = {}
+@@ -372,7 +372,7 @@ def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
+ 				elif consensus_file.split(".")[-2] == "all_consensus_alleles":
+ 					consensus_type = "consensus"
+ 				with open(consensus_file, "a") as consensus_outfile:
+-					consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, pileup_file.split(".")[1].split("__")[1]))
++					consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, sample_name))
+ 					outstring = consensus_seq + "\n"
+ 					consensus_outfile.write(outstring)
+
+@@ -782,7 +782,7 @@ def create_allele_pileup(allele_name, all_pileup_file):
+ def parse_scores(run_type,args,scores, hash_edge_depth, 
+ 					avg_depth_allele, coverage_allele, mismatch_allele, indel_allele,  
+ 					missing_allele, size_allele, next_to_del_depth_allele,
+-					unique_cluster_symbols,unique_allele_symbols, pileup_file):
++					unique_cluster_symbols,unique_allele_symbols, pileup_file, sample_name):
+
+ 	# sort into hash for each gene locus
+ 	scores_by_gene = collections.defaultdict(dict) # key1 = gene, key2 = allele, value = score
+@@ -868,11 +868,11 @@ def parse_scores(run_type,args,scores, hash_edge_depth,
+ 			if args.report_new_consensus or args.report_all_consensus:
+ 				new_alleles_filename = args.output + ".new_consensus_alleles.fasta" 
+ 				allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
+-				read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
++				read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)
+ 		if args.report_all_consensus:
+ 			new_alleles_filename = args.output + ".all_consensus_alleles.fasta"
+ 			allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
+-			read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
++			read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)
+
+ 	return results # (allele, diffs, depth_problem, divergence)
+
+@@ -1265,7 +1265,7 @@ def map_fileSet_to_db(args,sample_name,fastq_inputs,db_name,fasta,size,gene_name
+ 		logging.info(' Processing SAMtools pileup...')
+ 		hash_alignment, hash_max_depth, hash_edge_depth, avg_depth_allele, coverage_allele, \
+ 				mismatch_allele, indel_allele, missing_allele, size_allele, next_to_del_depth_allele= \
+-				read_pileup_data(pileup_file, size, args.prob_err)
++				read_pileup_data(pileup_file, size, args.prob_err, sample_name)
+
+ 		# Generate scores for all alleles (prints these and associated info if verbose)
+ 		#   result = dict, with key=allele, value=score
+@@ -1283,7 +1283,7 @@ def map_fileSet_to_db(args,sample_name,fastq_inputs,db_name,fasta,size,gene_name
+ 	allele_scores = parse_scores(run_type, args, scores, \
+ 			hash_edge_depth, avg_depth_allele, coverage_allele, mismatch_allele,  \
+ 			indel_allele, missing_allele, size_allele, next_to_del_depth_allele,
+-			unique_gene_symbols, unique_allele_symbols, pileup_file)
++			unique_gene_symbols, unique_allele_symbols, pileup_file, sample_name)
+
+ 	# REPORT/RECORD RESULTS
+

recipes/srst2/build.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-python setup.py install
+$PYTHON setup.py install --single-version-externally-managed --record=record.txt

recipes/srst2/meta.yaml

@@ -8,9 +8,10 @@ source:
   sha256: 352c59bdf00039dfa5610a4b88049a0eb114d7c2a305d4924b6e605cc6d15123
   patches:
     - use_setuptools.patch
+    - srst_sample_name_v0.2.0.patch
 
 build:
-  number: 1
+  number: 2
   skip: True #[not py27]
 
 requirements:
@@ -29,8 +30,8 @@ requirements:
 
 test:
   commands:
-    - srst2 -h 2>&1 | grep 'SRST2 - Short Read Sequence Typer' > /dev/null
-    - getmlst.py -h 2>&1 | grep 'usage' > /dev/null
+    - srst2 -h 2>&1 | grep "SRST2 - Short Read Sequence Typer" > /dev/null
+    - getmlst.py -h 2>&1 | grep "usage" > /dev/null
 
 about:
   home: https://github.com/katholt/srst2

recipes/srst2/srst_sample_name_v0.2.0.patch

@@ -0,0 +1,74 @@
+From d9d617a67e432cabd768bac0cb06462aa8c87ec5 Mon Sep 17 00:00:00 2001
+From: Eric Enns <[email protected]>
+Date: Tue, 28 Nov 2017 11:12:31 -0600
+Subject: [PATCH] Remove sample name parsing which doesn't work when
+ directories have . in the name, instead just pass sample_name along to
+ functions requiring it.
+
+---
+ scripts/srst2.py | 14 +++++++-------
+ 1 file changed, 7 insertions(+), 7 deletions(-)
+
+diff --git a/scripts/srst2.py b/scripts/srst2.py
+index ac174ef..5c753e1 100755
+--- a/scripts/srst2.py
++++ b/scripts/srst2.py
+@@ -311,7 +311,7 @@ def parse_fai(fai_file,db_type,delimiter):
+ 	return size, gene_clusters, unique_gene_symbols, unique_allele_symbols, gene_cluster_symbols
+
+
+-def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
++def read_pileup_data(pileup_file, size, prob_err, sample_name, consensus_file = ""):
+ 	with open(pileup_file) as pileup:
+ 		prob_success = 1 - prob_err	# Set by user, default is prob_err = 0.01
+ 		hash_alignment = {}
+@@ -450,7 +450,7 @@ def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
+ 				elif consensus_file.split(".")[-2] == "all_consensus_alleles":
+ 					consensus_type = "consensus"
+ 				with open(consensus_file, "a") as consensus_outfile:
+-					consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, pileup_file.split(".")[1].split("__")[1]))
++					consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, sample_name))
+ 					outstring = consensus_seq + "\n"
+ 					consensus_outfile.write(outstring)
+
+@@ -942,7 +942,7 @@ def dict_of_dicts_inverted_ind(dd):
+ def parse_scores(run_type,args,scores, hash_edge_depth,
+ 					avg_depth_allele, coverage_allele, mismatch_allele, indel_allele,
+ 					missing_allele, size_allele, next_to_del_depth_allele,
+-					unique_cluster_symbols,unique_allele_symbols, pileup_file):
++					unique_cluster_symbols,unique_allele_symbols, pileup_file, sample_name):
+
+ 	# sort into hash for each gene locus
+ 	scores_by_gene = group_allele_dict_by_gene(dict( (allele,val) for (allele,val) in scores.items() \
+@@ -1018,11 +1018,11 @@ def parse_scores(run_type,args,scores, hash_edge_depth,
+ 			if args.report_new_consensus or args.report_all_consensus:
+ 				new_alleles_filename = args.output + ".new_consensus_alleles.fasta"
+ 				allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
+-				read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
++				read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)
+ 		if args.report_all_consensus:
+ 			new_alleles_filename = args.output + ".all_consensus_alleles.fasta"
+ 			allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
+-			read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
++			read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)
+
+ 	return results # (allele, diffs, depth_problem, divergence)
+
+@@ -1419,7 +1419,7 @@ def map_fileSet_to_db(args, sample_name, fastq_inputs, db_name, fasta, size, gen
+ 		logging.info(' Processing SAMtools pileup...')
+ 		hash_alignment, hash_max_depth, hash_edge_depth, avg_depth_allele, coverage_allele, \
+ 				mismatch_allele, indel_allele, missing_allele, size_allele, next_to_del_depth_allele= \
+-				read_pileup_data(pileup_file, size, args.prob_err)
++				read_pileup_data(pileup_file, size, args.prob_err, sample_name)
+
+ 		# Generate scores for all alleles (prints these and associated info if verbose)
+ 		#   result = dict, with key=allele, value=score
+@@ -1437,7 +1437,7 @@ def map_fileSet_to_db(args, sample_name, fastq_inputs, db_name, fasta, size, gen
+ 	allele_scores = parse_scores(run_type, args, scores, \
+ 			hash_edge_depth, avg_depth_allele, coverage_allele, mismatch_allele, \
+ 			indel_allele, missing_allele, size_allele, next_to_del_depth_allele,
+-			unique_gene_symbols, unique_allele_symbols, pileup_file)
++			unique_gene_symbols, unique_allele_symbols, pileup_file, sample_name)
+
+ 	# REPORT/RECORD RESULTS
+