Changes to vcf2scoary (#63)

Bug fixes in vcf2scoary: Should now split correctly even when there are commas in values.

CHANGELOG.md

@@ -1,4 +1,7 @@
 # CHANGELOG
+v1.6.16 (Aug 2017)
+- Bug fixes to vcf2scoary
+
 v1.6.15 (Jul 2017)
 - Apparently 1.6.14 did not fix the pip issue for all users. Deleted the function that seemed to cause the pip crash
 

README.md

@@ -32,20 +32,8 @@ Scoary is designed to take the gene_presence_absence.csv file from [Roary](https
 
 ## What's new?
 
-**LATEST VERSION - 1.6.15**
-- Some people still have problems with pip installs. Removed the readme() function from setup
-
-**1.6.14**
-- Fixed a bug where scoary could not be upgraded using pip
-
-**1.6.13**
-- Fixed bug where handling of converted VCF files would fail due to non-Roary column names
-- Fixed the ALL keyword used with --include_input_columns
-
-**1.6.12**
-- Convert VCF files to Roary/Scoary format, allowing analysis on a wide range of variants (SNPs, indels, structural variations etc)
-- Grab columns from the Roary input and put in the output (To get strain-specific protein names, for example)
-- Scoary now comes with a manual, located under docs/tex/scoary_manual.pdf
+**LATEST VERSION - 1.6.16**
+- Bug fixes to vcf2scoary
 
 All changes are logged in the [CHANGELOG](CHANGELOG.md)
 

scoary/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '1.6.15'
+__version__ = '1.6.16'
 __author__ = 'Ola Brynildsrud'
 __credits__ = ['Ola Brynildsrud']
 __license__ = 'GPL3'

scoary/vcf2scoary.py

@@ -101,7 +101,7 @@ def main():
         sys.exit("Unable to locate input file %s" % args.vcf)
 
     with open(args.vcf,'rU') as vcffile, open(args.out,'w') as outfile:
-        lines = csv.reader(vcffile, delimiter="\t")
+        lines = csv.reader(vcffile, delimiter='\t', quotechar='"')
         metainfo = {"##INFO" : {},
                     "##FILTER" : {},
                     "##FORMAT" : {},
@@ -125,7 +125,7 @@ def main():
                 # Capture list output for complex tags
                 if infoline[0] in metainfo:
                     ID=re.search(r'ID=(\w+)',infoline[1]).group(1)
-                    infolist = re.split(',',infoline[1].strip("<>"))
+                    infolist = re.split(',(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)',infoline[1].strip("<>"))
                     metainfo[infoline[0]][ID] = {}
                     # Enter all elements in infolist into appropriate dic
                     for e in infolist:
@@ -203,11 +203,18 @@ def writeLine(line, outfile):
 
 def fixdummy(line,c):
     newline = line[:]
-    for x in range(len(line)):
-        if int(line[x]) == c:
-            newline[x] = "1"
-        else:
-            newline[x] = "0"
+    try:
+        for x in range(len(line)):
+            if line[x] == ".":
+                # Missing data get entered as reference / no presence
+                newline[x] = "0"
+            elif int(line[x]) == c:
+                newline[x] = "1"
+            else:
+                newline[x] = "0"
+    except ValueError:
+        print(newline, c)
+        sys.exit(-1)
     return newline
 
 ########