bio-vcf 0.9.2 → 0.9.4

data/lib/bio-vcf/vcffile.rb

@@ -0,0 +1,46 @@
+module BioVcf
+    # This class abstracts a VCF file that can be iterated. 
+    # The VCF can be plain text or compressed with gzip
+    # Note that files compressed with bgzip will not work, as thie ruby implementation of Zlib don't allow concatenated files
+    class VCFfile
+    
+        def initialize(file: "", is_gz: true)
+            @file = file
+            @is_gz = is_gz
+        end
+    
+        def parseVCFheader(head_line="")
+            m=/##INFO=<ID=(.+),Number=(.+),Type=(.+),Description="(.+)">/.match(head_line)
+            {:id=>m[1],:number=>m[2],:type=>m[3],:desc=>m[4]}
+        end
+    
+    
+        #Returns an enum that can be used as an iterator. 
+        def each
+            return enum_for(:each) unless block_given? 
+            io = nil
+            if @is_gz
+                infile = open(@file)
+                io = Zlib::GzipReader.new(infile) 
+            else
+                io =  File.open(@file)
+            end
+            
+            header = BioVcf::VcfHeader.new 
+            io.each_line do |line|  
+                line.chomp!
+                if line =~ /^##fileformat=/
+                    header.add(line)  
+                    next
+                end
+                if line =~ /^#/
+                    header.add(line)
+                    next
+                end
+                fields = BioVcf::VcfLine.parse(line)
+                rec    = BioVcf::VcfRecord.new(fields,header)
+                yield rec
+            end
+        end
+    end
+end

data/lib/bio-vcf/vcfgenotypefield.rb

@@ -11,7 +11,7 @@ module BioVcf
     end
   end
 
-  # Helper class for a list of (variant) values, such as A,G. 
+  # Helper class for a list of (variant) values, such as A,G.
   # The [] function does the hard work. You can pass in an index (integer)
   # or nucleotide which translates to an index.
   # (see ./features for examples)
@@ -20,7 +20,7 @@ module BioVcf
       @alt = alt
       @list = list.split(/,/).map{|i| i.to_i}
     end
-  
+
     def [] idx
       if idx.kind_of?(Integer)
         # return a value
@@ -67,7 +67,7 @@ module BioVcf
       @alt = alt
       @list = list.split(/,/).map{|i| i.to_i}
     end
-  
+
     def [] idx
       if idx.kind_of?(Integer)
         @list[idx].to_i
@@ -87,15 +87,15 @@ module BioVcf
     end
 
     # Return the max value on the nucleotides in the list (typically rec.alt)
-    def max 
+    def max
       @list.reduce(0){ |memo,v| (v>memo ? v : memo) }
     end
 
-    def min 
+    def min
       @list.reduce(MAXINT){ |memo,v| (v<memo ? v : memo) }
     end
 
-    def sum 
+    def sum
       @list.reduce(0){ |memo,v| v+memo }
     end
   end
@@ -129,14 +129,14 @@ module BioVcf
       !empty?
     end
 
-    def dp4 
-      ilist('DP4') 
+    def dp4
+      ilist('DP4')
     end
-    def ad 
-      ilist('AD') 
+    def ad
+      ilist('AD')
     end
-    def pl 
-      ilist('PL') 
+    def pl
+      ilist('PL')
     end
 
     def bcount
@@ -154,7 +154,7 @@ module BioVcf
     def gti?
       not VcfValue::empty?(fetch_value("GT"))
     end
-    
+
     def gti
       gt.split(/[\/\|]/).map { |g| g.to_i }
     end
@@ -178,11 +178,11 @@ module BioVcf
       else
         v = values[fetch(m.to_s.upcase)]
         return nil if VcfValue::empty?(v)
-        v = v.to_i if v =~ /^\d+$/
-        v = v.to_f if v =~ /^\d+\.\d+$/
+        return v.to_i if v =~ /^\d+$/
+        return v.to_f if v =~ /^\d+\.\d+$/
         v
       end
-    end  
+    end
 
   private
 
@@ -200,7 +200,7 @@ module BioVcf
     def ilist name
       v = fetch_value(name)
       return nil if not v
-      v.split(',').map{|i| i.to_i} 
+      v.split(',').map{|i| i.to_i}
     end
 
   end
@@ -222,11 +222,11 @@ module BioVcf
         @samples[name] ||= VcfGenotypeField.new(@fields[@sample_index[name]],@format,@header,@ref,@alt)
       rescue TypeError
         $stderr.print "Unknown field name <#{name}> in record, did you mean r.info.#{name}?\n"
-        raise 
+        raise
       end
     end
 
-    def method_missing(m, *args, &block) 
+    def method_missing(m, *args, &block)
       name = m.to_s
       if name =~ /\?$/
         # test for valid sample
@@ -234,7 +234,7 @@ module BioVcf
       else
         @samples[name] ||= VcfGenotypeField.new(@fields[@sample_index[name]],@format,@header,@ref,@alt)
       end
-    end  
+    end
 
   end
 end

data/lib/bio-vcf/vcfheader.rb

@@ -39,6 +39,7 @@ module BioVcf
       @lines = []
       @field = {}
       @meta = nil
+      @cached_filter_index = {}
     end
 
     # Add a new field to the header
@@ -102,6 +103,34 @@ module BioVcf
       index
     end
 
+    # Give a list of samples (by index and/or name) and return 0-based index values
+    # The cache has to be able to hanle multiple lists - that is why it is a hash.
+    def sample_subset_index list
+      cached = @cached_filter_index[list]
+      if cached
+        l = cached
+      else
+        l = []
+        list = samples_index_array() if not list
+        list.each { |i|
+          value = 
+            begin 
+              Integer(i)
+            rescue
+              idx = samples.index(i)
+              if idx != nil
+                idx
+              else
+                raise "Unknown sample name '#{i}'"
+              end
+            end
+          l << value
+        }
+        @cached_filter_index[list] = l
+      end
+      l
+    end
+    
     # Look for a line in the header with the field name and return the
     # value, otherwise return nil
     def find_field name

data/lib/bio-vcf/vcfrecord.rb

@@ -199,15 +199,15 @@ module BioVcf
     end
 
     def sample_by_index i
-      # p @fields
       raise "Can not index sample on parameter <#{i}>" if not i.kind_of?(Integer)
       @sample_by_index[i] ||= VcfGenotypeField.new(@fields[i+9],format,@header,ref,alt)
     end
 
     # Walk the samples. list contains an Array of int (the index)
     def each_sample(list = nil)
-      list = @header.samples_index_array() if not list 
-      list.each { |i| yield VcfSample::Sample.new(self,sample_by_index(i.to_i)) }
+      @header.sample_subset_index(list).each { |i|
+        yield VcfSample::Sample.new(self,sample_by_index(i))
+      }
     end
 
     def samples
@@ -250,6 +250,7 @@ module BioVcf
           $stderr.print "RECORD ERROR!\n"
           $stderr.print [@fields],"\n"
           $stderr.print expr,"\n"
+          $stderr.print "To ignore this error use the -i switch!\n"
         end
         if ignore_missing_data
           $stderr.print e.message if not quiet
@@ -283,6 +284,7 @@ module BioVcf
           $stderr.print "RECORD ERROR!\n"
           $stderr.print [@fields],"\n"
           $stderr.print expr,"\n"
+          $stderr.print "To ignore this error use the -i switch!\n"
         end
         if ignore_missing_data
           $stderr.print e.message if not quiet

data/lib/bio-vcf/vcfsample.rb

@@ -3,7 +3,7 @@ module BioVcf
 
     # Check whether a sample is empty (on the raw string value)
     def VcfSample::empty? s
-      s==nil or s == './.' or s == '' or s[0..2]=='./.'
+      s==nil or s == './.' or s == '' or s[0..2]=='./.' or s[0..1] == '.:'
     end
 
     class Sample
@@ -40,6 +40,7 @@ module BioVcf
       # Split GT into index values
       def gti
         v = fetch_values("GT")
+        v = './.' if v == '.' #In case that you have a single missing value, make both as missing. 
         v.split(/[\/\|]/).map{ |v| (v=='.' ? nil : v.to_i) }
       end
 
@@ -47,6 +48,7 @@ module BioVcf
         v = fetch_values("GT")
         return case v
                when nil then nil
+               when '.' then nil
                when './.' then nil
                when '0/0' then 0
                when '0/1' then 1

data/test/data/input/empty.vcf

@@ -0,0 +1,2 @@
+##fileformat=VCFv4.0
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO

data/test/data/regression/empty-stderr.new

@@ -0,0 +1,12 @@
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Options: {:show_help=>false, :source=>"https://github.com/pjotrp/bioruby-vcf", :version=>"0.9.4 (Pjotr Prins)", :date=>"2020-12-22 11:30:38 +0000", :thread_lines=>40000, :timeout=>5}
+Waiting up to 5 seconds for pid=30726 to complete /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf
+OK pid=30726, processing starts of /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf
+Processing remaining output...
+Trying: [[30726, 1, "/tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf"]]
+Set lock on [[30726, 1, "/tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30724-19xxgvd/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30724-19xxgvd

data/test/data/regression/empty.new

@@ -0,0 +1,2 @@
+##fileformat=VCFv4.0
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO

data/test/data/regression/empty.ref

@@ -0,0 +1,2 @@
+##fileformat=VCFv4.0
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO

data/test/data/regression/eval_once-stderr.new

@@ -1,2 +1,2 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Removing dir /tmp/bio-vcf_20160122-9412-5yf2ot
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Removing dir /tmp/bio-vcf_20201222-30676-128vka8

data/test/data/regression/eval_r.info.dp-stderr.new

@@ -1,8 +1,10 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9378 to complete /tmp/bio-vcf_20160122-9376-640z88/000001-bio-vcf
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=30642 to complete /tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf
 Processing remaining output...
-Trying: [[9378, 1, "/tmp/bio-vcf_20160122-9376-640z88/000001-bio-vcf"]]
-Set lock on [[9378, 1, "/tmp/bio-vcf_20160122-9376-640z88/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9376-640z88/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9376-640z88/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9376-640z88
+Trying: [[30642, 1, "/tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf"]]
+Set lock on [[30642, 1, "/tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30640-gf6uns/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30640-gf6uns

data/test/data/regression/ifilter_s.dp-stderr.new

@@ -1,5 +1,5 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9369 to complete /tmp/bio-vcf_20160122-9367-zhp98h/000001-bio-vcf
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=30633 to complete /tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
 [:filter, "s.dp>100"]
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
@@ -25,8 +25,10 @@ Waiting up to 180 seconds for pid=9369 to complete /tmp/bio-vcf_20160122-9367-zh
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
 [:filter, "s.dp>100"]
 Processing remaining output...
-Trying: [[9369, 1, "/tmp/bio-vcf_20160122-9367-zhp98h/000001-bio-vcf"]]
-Set lock on [[9369, 1, "/tmp/bio-vcf_20160122-9367-zhp98h/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9367-zhp98h/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9367-zhp98h/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9367-zhp98h
+Trying: [[30633, 1, "/tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf"]]
+Set lock on [[30633, 1, "/tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30631-1lij1nd/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30631-1lij1nd

data/test/data/regression/pass1-stderr.new

@@ -1,8 +1,10 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9462 to complete /tmp/bio-vcf_20160122-9460-14lv2wl/000001-bio-vcf
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=30735 to complete /tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf
 Processing remaining output...
-Trying: [[9462, 1, "/tmp/bio-vcf_20160122-9460-14lv2wl/000001-bio-vcf"]]
-Set lock on [[9462, 1, "/tmp/bio-vcf_20160122-9460-14lv2wl/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9460-14lv2wl/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9460-14lv2wl/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9460-14lv2wl
+Trying: [[30735, 1, "/tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf"]]
+Set lock on [[30735, 1, "/tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30733-1xa4emu/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30733-1xa4emu

data/test/data/regression/r.info.dp-stderr.new

@@ -1,8 +1,4 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9246 to complete /tmp/bio-vcf_20160122-9244-jah911/000001-bio-vcf
-Processing remaining output...
-Trying: [[9246, 1, "/tmp/bio-vcf_20160122-9244-jah911/000001-bio-vcf"]]
-Set lock on [[9246, 1, "/tmp/bio-vcf_20160122-9244-jah911/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9244-jah911/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9244-jah911/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9244-jah911
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=31046 to complete /tmp/bio-vcf_20201222-31044-fq0sit/000001-bio-vcf
+ERROR: 
+Removing dir /tmp/bio-vcf_20201222-31044-fq0sit

data/test/data/regression/r.info.dp.new

@@ -112,36 +112,3 @@
 ##contig=<ID=GL000192.1,length=547496,assembly=b37>
 ##reference=file:human_g1k_v37.fasta
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Original	s1t1	s2t1	s3t1	s1t2	s2t2	s3t2
-1	10257	.	A	C	77.69	.	AC=1;AF=0.071;AN=14;BaseQRankSum=-0.066;DP=1518;Dels=0.00;FS=24.214;HaplotypeScore=226.5209;MLEAC=1;MLEAF=0.071;MQ=25.00;MQ0=329;MQRankSum=-1.744;QD=0.37;ReadPosRankSum=1.551	GT:AD:DP:GQ:PL	0/0:151,8:159:99:0,195,2282	0/0:219,22:242:99:0,197,2445	0/0:227,22:249:90:0,90,2339	0/0:226,22:249:99:0,159,2695	0/0:166,18:186:99:0,182,1989	0/1:185,27:212:99:111,0,2387	0/0:201,15:218:24:0,24,1972
-1	10291	.	C	T	1031.89	.	AC=7;AF=0.500;AN=14;BaseQRankSum=4.367;DP=1433;Dels=0.00;FS=0.696;HaplotypeScore=101.0885;MLEAC=7;MLEAF=0.500;MQ=26.96;MQ0=225;MQRankSum=0.087;QD=0.72;ReadPosRankSum=-1.640	GT:AD:DP:GQ:PL	0/1:145,16:165:23:23,0,491	0/1:218,26:249:29:29,0,611	0/1:214,30:249:99:145,0,801	0/1:213,32:247:20:20,0,1031	0/1:122,36:161:99:347,0,182	0/1:131,27:163:99:255,0,508	0/1:156,31:189:99:252,0,372
-1	10297	.	C	T	187.21	.	AC=5;AF=0.357;AN=14;BaseQRankSum=-2.778;DP=1440;Dels=0.00;FS=0.000;HaplotypeScore=123.6373;MLEAC=5;MLEAF=0.357;MQ=27.26;MQ0=217;MQRankSum=-2.914;QD=0.18;ReadPosRankSum=1.927	GT:AD:DP:GQ:PL	0/1:155,18:182:44:44,0,654	0/1:218,23:246:21:21,0,673	0/1:219,26:250:41:41,0,898	0/0:207,30:246:39:0,39,963	0/0:137,20:165:21:0,21,363	0/1:124,27:158:65:65,0,435	0/1:151,27:183:63:63,0,485
-1	10303	.	C	T	166.50	.	AC=3;AF=0.214;AN=14;BaseQRankSum=-3.960;DP=1460;Dels=0.00;FS=2.121;HaplotypeScore=138.0883;MLEAC=2;MLEAF=0.143;MQ=27.29;MQ0=220;MQRankSum=-2.873;QD=0.27;ReadPosRankSum=1.756	GT:AD:DP:GQ:PL	0/1:169,25:198:99:195,0,609	0/1:211,31:247:1:1,0,656	0/0:214,28:248:7:0,7,982	0/0:214,32:248:25:0,25,980	0/0:146,17:172:2:0,2,353	0/1:123,23:157:17:17,0,541	0/0:156,22:182:19:0,19,413
-1	10315	.	C	T	108.20	.	AC=3;AF=0.214;AN=14;BaseQRankSum=-3.769;DP=1500;Dels=0.01;FS=1.493;HaplotypeScore=169.3933;MLEAC=3;MLEAF=0.214;MQ=26.95;MQ0=241;MQRankSum=-4.511;QD=0.19;ReadPosRankSum=2.373	GT:AD:DP:GQ:PL	0/1:181,26:212:41:41,0,618	0/0:223,17:246:99:0,102,832	0/0:219,20:242:66:0,66,924	0/0:217,23:245:99:0,109,1384	0/1:155,27:190:97:97,0,328	0/1:130,20:157:10:10,0,531	0/0:163,24:189:5:0,5,450
-1	10321	.	C	T	106.30	.	AC=5;AF=0.357;AN=14;BaseQRankSum=3.045;DP=1537;Dels=0.01;FS=5.835;HaplotypeScore=220.1531;MLEAC=5;MLEAF=0.357;MQ=26.69;MQ0=258;MQRankSum=-4.870;QD=0.10;ReadPosRankSum=0.815	GT:AD:DP:GQ:PL	0/1:189,25:218:30:30,0,810	0/0:219,22:246:24:0,24,593	0/1:218,27:248:34:34,0,1134	0/0:220,22:248:56:0,56,1207	0/1:168,23:193:19:19,0,493	0/1:139,22:164:46:46,0,689	0/1:167,26:196:20:20,0,522
-1	10327	.	T	C	1215.15	.	AC=7;AF=0.500;AN=14;BaseQRankSum=3.585;DP=1641;Dels=0.02;FS=6.639;HaplotypeScore=237.4339;MLEAC=7;MLEAF=0.500;MQ=25.22;MQ0=321;MQRankSum=4.402;QD=0.74;ReadPosRankSum=3.957	GT:AD:DP:GQ:PL	0/1:178,56:237:99:178,0,848	0/1:178,60:238:99:320,0,575	0/1:185,40:229:99:236,0,679	0/1:184,52:237:99:358,0,544	0/1:165,43:209:57:57,0,726	0/1:151,31:183:9:9,0,780	0/1:164,46:210:96:96,0,550
-1	10583	.	G	A	699.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-4.714;DP=129;Dels=0.00;FS=7.556;HaplotypeScore=0.6677;MLEAC=7;MLEAF=0.500;MQ=41.33;MQ0=2;MQRankSum=-2.309;QD=5.43;ReadPosRankSum=-0.296	GT:AD:DP:GQ:PL	0/1:5,3:8:58:58,0,133	0/1:12,12:24:99:231,0,287	0/1:16,4:21:38:38,0,491	0/1:19,4:23:57:57,0,494	0/1:9,6:15:99:140,0,180	0/1:11,8:19:99:173,0,235	0/1:15,4:19:42:42,0,344
-1	12783	.	G	A	4330.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=12.671;DP=939;Dels=0.00;FS=0.000;HaplotypeScore=1.4998;MLEAC=7;MLEAF=0.500;MQ=14.64;MQ0=602;MQRankSum=-3.992;QD=4.61;ReadPosRankSum=0.195	GT:AD:DP:GQ:PL	0/1:24,34:58:82:174,0,82	0/1:80,84:164:99:658,0,433	0/1:59,85:144:99:670,0,407	0/1:68,114:182:99:1074,0,463	0/1:58,68:126:99:437,0,310	0/1:37,66:103:99:446,0,369	0/1:62,96:158:99:911,0,417
-1	13116	.	T	G	2592.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-5.563;DP=721;Dels=0.00;FS=381.256;HaplotypeScore=2.5606;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=222;MQRankSum=-14.896;QD=3.60;ReadPosRankSum=3.079	GT:AD:DP:GQ:PL	0/1:20,12:32:92:92,0,300	0/1:84,47:131:99:479,0,1548	0/1:65,37:102:99:441,0,1153	0/1:94,57:152:99:584,0,1993	0/1:61,43:104:99:360,0,1199	0/1:54,33:88:99:221,0,986	0/1:62,47:109:99:455,0,1128
-1	13118	.	A	G	2317.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-9.647;DP=703;Dels=0.00;FS=362.380;HaplotypeScore=2.3393;MLEAC=7;MLEAF=0.500;MQ=23.54;MQ0=228;MQRankSum=-14.592;QD=3.30;ReadPosRankSum=3.437	GT:AD:DP:GQ:PL	0/1:21,13:34:95:95,0,277	0/1:82,47:129:99:444,0,1445	0/1:65,36:101:99:412,0,1179	0/1:92,53:145:99:455,0,1989	0/1:58,40:99:99:312,0,1216	0/1:52,33:85:99:186,0,1000	0/1:61,47:108:99:453,0,1079
-1	13178	.	G	A	72.69	.	AC=2;AF=0.143;AN=14;BaseQRankSum=-2.194;DP=929;Dels=0.00;FS=8.154;HaplotypeScore=1.8585;MLEAC=2;MLEAF=0.143;MQ=13.49;MQ0=590;MQRankSum=-3.030;QD=0.38;ReadPosRankSum=-0.383	GT:AD:DP:GQ:PL	0/1:49,3:52:11:11,0,292	0/0:161,11:172:60:0,60,1328	0/1:122,15:137:99:99,0,936	0/0:164,8:172:99:0,112,1436	0/0:120,9:129:62:0,62,771	0/0:113,6:119:12:0,12,885	0/0:138,10:148:99:0,112,1596
-1	13302	.	C	T	1067.42	.	AC=6;AF=0.429;AN=14;BaseQRankSum=11.584;DP=692;Dels=0.00;FS=86.736;HaplotypeScore=2.8260;MLEAC=6;MLEAF=0.429;MQ=27.08;MQ0=150;MQRankSum=-14.794;QD=1.63;ReadPosRankSum=-9.193	GT:AD:DP:GQ:PL	0/0:26,10:36:41:0,41,616	0/1:91,45:136:99:183,0,2085	0/1:71,28:99:86:86,0,1557	0/1:96,50:146:99:333,0,2098	0/1:55,34:90:99:283,0,1321	0/1:47,18:65:99:157,0,943	0/1:89,28:117:67:67,0,1921
-1	13757	.	G	A	271.89	.	AC=2;AF=0.143;AN=14;BaseQRankSum=2.916;DP=1149;Dels=0.00;FS=11.172;HaplotypeScore=7.1466;MLEAC=2;MLEAF=0.143;MQ=18.17;MQ0=374;MQRankSum=3.990;QD=0.87;ReadPosRankSum=1.309	GT:AD:DP:GQ:PL	0/0:47,4:53:16:0,16,344	0/0:185,16:201:60:0,60,2690	0/1:157,24:181:99:162,0,2556	0/0:232,18:250:99:0,137,3600	0/0:139,13:152:15:0,15,2266	0/1:114,16:130:99:147,0,1525	0/0:168,14:182:2:0,2,2230
-1	13868	.	A	G	1481.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=2.036;DP=1108;Dels=0.00;FS=4.601;HaplotypeScore=6.7136;MLEAC=7;MLEAF=0.500;MQ=13.23;MQ0=622;MQRankSum=1.659;QD=1.34;ReadPosRankSum=0.283	GT:AD:DP:GQ:PL	0/1:60,15:75:80:80,0,568	0/1:146,46:192:99:289,0,1030	0/1:146,36:182:99:203,0,1001	0/1:172,52:224:99:222,0,1150	0/1:106,36:142:99:181,0,621	0/1:79,32:111:99:126,0,467	0/1:129,38:167:99:420,0,767
-1	13896	.	C	A	389.42	.	AC=6;AF=0.429;AN=14;BaseQRankSum=-0.743;DP=830;Dels=0.00;FS=0.000;HaplotypeScore=1.6931;MLEAC=6;MLEAF=0.429;MQ=11.88;MQ0=518;MQRankSum=-1.292;QD=0.54;ReadPosRankSum=0.433	GT:AD:DP:GQ:PL	0/1:50,12:62:99:107,0,367	0/1:107,28:135:40:40,0,660	0/1:120,23:143:37:37,0,675	0/1:144,31:175:99:172,0,690	0/0:98,14:112:42:0,42,577	0/1:65,16:81:34:34,0,290	0/1:102,19:121:41:41,0,677
-1	14354	.	C	A	109.72	.	AC=3;AF=0.250;AN=12;BaseQRankSum=-2.527;DP=764;Dels=0.00;FS=0.000;HaplotypeScore=0.3231;MLEAC=3;MLEAF=0.250;MQ=5.02;MQ0=710;MQRankSum=1.079;QD=0.47;ReadPosRankSum=-0.178	GT:AD:DP:GQ:PL	0/1:36,7:43:68:68,0,75	0/0:141,17:158:9:0,9,86	0/1:103,12:115:42:42,0,72	0/0:132,13:145:21:0,21,201	./.	0/1:62,10:72:38:38,0,117	0/0:108,11:119:9:0,9,86
-1	14464	.	A	T	3945.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=0.104;DP=809;Dels=0.00;FS=38.588;HaplotypeScore=5.8354;MLEAC=7;MLEAF=0.500;MQ=23.21;MQ0=241;MQRankSum=6.859;QD=4.88;ReadPosRankSum=-0.294	GT:AD:DP:GQ:PL	0/1:41,10:51:99:183,0,569	0/1:107,48:155:99:829,0,1388	0/1:99,42:141:99:691,0,1103	0/1:114,36:150:99:454,0,1544	0/1:48,35:83:99:781,0,561	0/1:64,25:89:99:409,0,781	0/1:102,38:140:99:638,0,1310
-1	14673	.	G	C	1012.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=3.674;DP=754;Dels=0.00;FS=115.496;HaplotypeScore=14.9167;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=268;MQRankSum=-1.459;QD=1.34;ReadPosRankSum=-3.039	GT:AD:DP:GQ:PL	0/1:28,8:36:34:34,0,409	0/1:117,25:142:99:125,0,1964	0/1:87,30:117:99:214,0,1506	0/1:130,27:157:99:193,0,2076	0/1:77,18:95:99:114,0,1273	0/1:49,27:76:99:200,0,719	0/1:103,28:131:99:172,0,1620
-1	14699	.	C	G	64.65	.	AC=2;AF=0.143;AN=14;BaseQRankSum=6.064;DP=719;Dels=0.00;FS=29.480;HaplotypeScore=5.5900;MLEAC=2;MLEAF=0.143;MQ=24.79;MQ0=233;MQRankSum=-8.066;QD=0.27;ReadPosRankSum=-0.696	GT:AD:DP:GQ:PL	0/0:35,6:43:51:0,51,720	0/1:91,37:128:59:59,0,1859	0/0:80,29:109:99:0,101,1700	0/0:113,34:147:14:0,14,1987	0/0:72,26:98:37:0,37,1319	0/0:53,25:78:78:0,78,1035	0/1:84,30:114:44:44,0,1326
-1	14907	.	A	G	9688.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=3.299;DP=1083;Dels=0.00;FS=20.983;HaplotypeScore=11.4413;MLEAC=7;MLEAF=0.500;MQ=33.27;MQ0=51;MQRankSum=1.076;QD=8.95;ReadPosRankSum=0.653	GT:AD:DP:GQ:PL	0/1:27,30:57:99:603,0,550	0/1:117,99:216:99:2024,0,2888	0/1:91,71:162:99:1489,0,1990	0/1:119,86:205:99:1876,0,2588	0/1:100,53:153:99:1001,0,2297	0/1:59,59:118:99:1240,0,1241	0/1:91,67:158:99:1495,0,2003
-1	14930	.	A	G	8665.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-13.760;DP=1092;Dels=0.00;FS=17.240;HaplotypeScore=20.0469;MLEAC=7;MLEAF=0.500;MQ=34.72;MQ0=22;MQRankSum=1.127;QD=7.94;ReadPosRankSum=0.785	GT:AD:DP:GQ:PL	0/1:32,36:68:99:609,0,659	0/1:123,92:216:99:1636,0,3225	0/1:92,78:170:99:1449,0,2202	0/1:123,86:210:99:1748,0,3028	0/1:85,50:136:99:802,0,2117	0/1:62,63:125:99:1072,0,1437	0/1:92,71:164:99:1389,0,2055
-1	14933	.	G	A	248.54	.	AC=3;AF=0.214;AN=14;BaseQRankSum=1.588;DP=1089;Dels=0.00;FS=14.333;HaplotypeScore=19.7793;MLEAC=3;MLEAF=0.214;MQ=34.91;MQ0=18;MQRankSum=1.439;QD=0.45;ReadPosRankSum=0.752	GT:AD:DP:GQ:PL	0/0:59,9:68:1:0,1,1361	0/1:192,24:216:99:125,0,4941	0/0:160,9:169:99:0,142,4118	0/1:191,21:212:39:39,0,4848	0/0:126,6:132:99:0,210,3367	0/1:113,15:128:99:124,0,2578	0/0:154,10:164:99:0,158,3934
-1	14948	.	G	A	570.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=9.167;DP=1050;Dels=0.00;FS=11.131;HaplotypeScore=6.4398;MLEAC=7;MLEAF=0.500;MQ=32.69;MQ0=53;MQRankSum=0.017;QD=0.54;ReadPosRankSum=-1.181	GT:AD:DP:GQ:PL	0/1:56,7:63:79:79,0,1134	0/1:168,24:192:70:70,0,3900	0/1:160,21:181:99:147,0,3515	0/1:188,23:211:57:57,0,4113	0/1:115,14:129:32:32,0,2406	0/1:103,18:121:99:173,0,2016	0/1:132,21:153:52:52,0,2861
-1	14976	.	G	A	195.07	.	AC=3;AF=0.214;AN=14;BaseQRankSum=7.340;DP=939;Dels=0.00;FS=32.492;HaplotypeScore=4.6786;MLEAC=3;MLEAF=0.214;MQ=27.87;MQ0=167;MQRankSum=1.477;QD=0.53;ReadPosRankSum=-0.560	GT:AD:DP:GQ:PL	0/1:50,6:56:12:12,0,929	0/0:152,14:166:81:0,81,3159	0/0:152,9:161:99:0,113,2885	0/1:174,22:196:99:127,0,3211	0/0:100,9:109:97:0,97,1900	0/1:103,13:116:97:97,0,1548	0/0:122,13:135:55:0,55,2246
-1	15118	.	A	G	2503.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-5.645;DP=1004;Dels=0.00;FS=0.313;HaplotypeScore=4.1078;MLEAC=7;MLEAF=0.500;MQ=21.49;MQ0=207;MQRankSum=-0.007;QD=2.49;ReadPosRankSum=-0.291	GT:AD:DP:GQ:PL	0/1:38,8:46:50:50,0,575	0/1:148,50:198:99:671,0,2598	0/1:97,32:129:99:358,0,1911	0/1:176,53:230:99:700,0,2989	0/1:91,19:113:99:146,0,1741	0/1:92,31:126:99:347,0,1543	0/1:126,30:158:99:271,0,2193
-1	15190	.	G	A	2564.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=11.094;DP=1090;Dels=0.00;FS=0.297;HaplotypeScore=4.3151;MLEAC=7;MLEAF=0.500;MQ=26.11;MQ0=187;MQRankSum=-0.724;QD=2.35;ReadPosRankSum=0.530	GT:AD:DP:GQ:PL	0/1:42,11:53:99:177,0,696	0/1:157,51:208:99:839,0,3145	0/1:142,28:170:91:91,0,2919	0/1:160,40:200:99:499,0,2815	0/1:109,17:126:99:167,0,2363	0/1:111,34:145:99:554,0,2268	0/1:141,38:179:99:277,0,2827
-1	15211	.	T	G	14032.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-11.292;DP=992;Dels=0.00;FS=0.281;HaplotypeScore=11.0809;MLEAC=7;MLEAF=0.500;MQ=27.20;MQ0=159;MQRankSum=3.859;QD=14.15;ReadPosRankSum=-1.972	GT:AD:DP:GQ:PL	0/1:19,35:54:99:858,0,183	0/1:63,120:183:99:2771,0,960	0/1:50,111:161:99:2213,0,740	0/1:58,113:171:99:2326,0,685	0/1:39,81:120:99:1707,0,678	0/1:38,96:134:99:2126,0,499	0/1:61,107:168:99:2071,0,895
-1	15274	.	A	G,T	8909.81	.	AC=7,7;AF=0.500,0.500;AN=14;BaseQRankSum=2.416;DP=636;Dels=0.00;FS=0.000;HaplotypeScore=5.1061;MLEAC=7,7;MLEAF=0.500,0.500;MQ=22.77;MQ0=195;MQRankSum=2.299;QD=14.01;ReadPosRankSum=1.707	GT:AD:DP:GQ:PL	1/2:1,14,22:37:99:717,494,467,224,0,170	1/2:1,45,75:121:99:1922,1334,1265,588,0,441	1/2:0,31,71:102:99:1960,1563,1515,396,0,222	1/2:1,59,77:137:99:2009,1376,1298,633,0,486	1/2:0,18,52:71:62:938,789,771,149,0,62	1/2:0,29,38:67:99:1141,883,853,258,0,162	1/2:0,38,60:98:99:1464,1064,1016,399,0,285
-1	15447	.	A	G	109.56	.	AC=3;AF=0.214;AN=14;BaseQRankSum=-9.704;DP=1213;Dels=0.00;FS=0.000;HaplotypeScore=16.4636;MLEAC=3;MLEAF=0.214;MQ=19.12;MQ0=346;MQRankSum=-0.997;QD=0.20;ReadPosRankSum=-1.088	GT:AD:DP:GQ:PL	0/0:42,4:46:34:0,34,690	0/0:220,22:242:99:0,99,3639	0/0:167,16:183:42:0,42,2582	0/1:201,25:226:78:78,0,2854	0/1:121,16:137:39:39,0,1877	0/0:160,13:173:99:0,139,2724	0/1:157,18:175:34:34,0,2472
-1	15688	.	C	T	54.29	.	AC=2;AF=0.143;AN=14;BaseQRankSum=-8.686;DP=904;Dels=0.00;FS=11.971;HaplotypeScore=3.1454;MLEAC=2;MLEAF=0.143;MQ=16.75;MQ0=361;MQRankSum=-0.069;QD=0.16;ReadPosRankSum=0.355	GT:AD:DP:GQ:PL	0/0:34,3:37:15:0,15,335	0/0:166,16:182:61:0,61,2190	0/1:131,16:147:69:69,0,1563	0/1:167,17:184:22:22,0,1894	0/0:88,12:100:15:0,15,1099	0/0:88,13:101:1:0,1,1126	0/0:132,16:148:18:0,18,1706
-1	16068	.	T	C	377.22	.	AC=4;AF=0.286;AN=14;BaseQRankSum=-7.618;DP=398;Dels=0.00;FS=12.349;HaplotypeScore=1.8069;MLEAC=4;MLEAF=0.286;MQ=26.64;MQ0=64;MQRankSum=-4.589;QD=1.80;ReadPosRankSum=-0.448	GT:AD:DP:GQ:PL	0/1:18,15:33:99:182,0,404	0/0:51,6:57:31:0,31,815	0/1:52,16:68:64:64,0,1101	0/0:68,13:81:99:0,99,1505	0/0:41,8:49:51:0,51,1010	0/1:40,9:49:21:21,0,702	0/1:38,19:58:99:153,0,760
-1	16103	.	T	G	2348.85	.	AC=7;AF=0.500;AN=14;BaseQRankSum=-1.646;DP=526;Dels=0.00;FS=2.577;HaplotypeScore=0.9645;MLEAC=7;MLEAF=0.500;MQ=26.64;MQ0=82;MQRankSum=-2.736;QD=4.47;ReadPosRankSum=-2.044	GT:AD:DP:GQ:PL	0/1:21,29:50:99:504,0,450	0/1:55,24:79:99:209,0,838	0/1:49,37:86:99:456,0,1002	0/1:74,32:106:99:193,0,1519	0/1:41,19:60:99:141,0,740	0/1:38,23:61:99:257,0,548	0/1:38,46:84:99:628,0,641

data/test/data/regression/rewrite.info.sample-stderr.new

@@ -1,8 +1,10 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9405 to complete /tmp/bio-vcf_20160122-9403-3mhvpb/000001-bio-vcf
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=30669 to complete /tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf
 Processing remaining output...
-Trying: [[9405, 1, "/tmp/bio-vcf_20160122-9403-3mhvpb/000001-bio-vcf"]]
-Set lock on [[9405, 1, "/tmp/bio-vcf_20160122-9403-3mhvpb/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9403-3mhvpb/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9403-3mhvpb/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9403-3mhvpb
+Trying: [[30669, 1, "/tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf"]]
+Set lock on [[30669, 1, "/tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30667-hcdvz2/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30667-hcdvz2

data/test/data/regression/s.dp-stderr.new

@@ -1,5 +1,5 @@
-bio-vcf 0.9.2 (biogem Ruby 2.2.4 with pcows) by Pjotr Prins 2015
-Waiting up to 180 seconds for pid=9360 to complete /tmp/bio-vcf_20160122-9358-zf1vnp/000001-bio-vcf
+bio-vcf 0.9.4 (biogem Ruby 2.5.5 with pcows) by Pjotr Prins 2015-2020
+Waiting up to 180 seconds for pid=30624 to complete /tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
 [:filter, "s.dp>20"]
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
@@ -9,8 +9,10 @@ Waiting up to 180 seconds for pid=9360 to complete /tmp/bio-vcf_20160122-9358-zf
 [:format, {"GT"=>0, "AD"=>1, "DP"=>2, "GQ"=>3, "PL"=>4}, :sample, ["./."]]
 [:filter, "s.dp>20"]
 Processing remaining output...
-Trying: [[9360, 1, "/tmp/bio-vcf_20160122-9358-zf1vnp/000001-bio-vcf"]]
-Set lock on [[9360, 1, "/tmp/bio-vcf_20160122-9358-zf1vnp/000001-bio-vcf"]]
-Processing output file /tmp/bio-vcf_20160122-9358-zf1vnp/000001-bio-vcf (blocking)
-Removing /tmp/bio-vcf_20160122-9358-zf1vnp/000001-bio-vcf
-Removing dir /tmp/bio-vcf_20160122-9358-zf1vnp
+Trying: [[30624, 1, "/tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf"]]
+Set lock on [[30624, 1, "/tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf"]]
+Processing output file /tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf (blocking)
+Checking for output_lock on existing /tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf
+Trying to remove /tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf.keep
+Removing /tmp/bio-vcf_20201222-30622-9czlqz/000001-bio-vcf.keep
+Removing dir /tmp/bio-vcf_20201222-30622-9czlqz