added qual_valid? method to Seq.rb

[biopieces.git] / code_ruby / lib / maasha / seq.rb

diff --git a/code_ruby/lib/maasha/seq.rb b/code_ruby/lib/maasha/seq.rb
index 45c13fe6ded1fe1d20771b8003a58596f5ab41b1..f2d93d1fc5bbf86b6611e56e9eb9ce98d9185795 100644 (file)
--- a/code_ruby/lib/maasha/seq.rb
+++ b/code_ruby/lib/maasha/seq.rb
@@ -538,13 +538,30 @@ class Seq
   # Method that determines if a quality score string can be
   # absolutely identified as base 33.
   def qual_base33?
-    self.qual.match(/[!-:]/)
+    self.qual.match(/[!-:]/) ? true : false
   end
 
   # Method that determines if a quality score string can be
   # absolutely identified as base 64.
   def qual_base64?
-    self.qual.match(/[K-h]/)
+    self.qual.match(/[K-h]/) ? true : false
+  end
+
+  # Method to determine if a quality score is valid.
+  def qual_valid?(encoding)
+    raise SeqError, "Missing qual" if self.qual.nil?
+
+    case encoding.downcase
+    when "sanger"     then return true if self.qual.match(/^[!-I]*$/)
+    when "454"        then return true if self.qual.match(/^[@-h]*$/)
+    when "solexa"     then return true if self.qual.match(/^[;-h]*$/)
+    when "illumina13" then return true if self.qual.match(/^[@-h]*$/)
+    when "illumina15" then return true if self.qual.match(/^[@-h]*$/)
+    when "illumina18" then return true if self.qual.match(/^[!-J]*$/)
+    else raise SeqError, "unknown quality score encoding: #{encoding}"
+    end
+
+    false
   end
 
   # Method to convert quality scores inbetween formats.
@@ -552,7 +569,7 @@ class Seq
   # 454        base 64, range  0-40 
   # Solexa     base 64, range -5-40 
   # Illumina13 base 64, range  0-40 
-  # Illumina15 base 64, range  3-40 
+  # Illumina15 base 64, range  0-40 
   # Illumina18 base 33, range  0-41 
   def convert_scores!(from, to)
     unless from == to