From 700bfa35e4032ef19a9cab2fb4bdda1fb7e1f0a6 Mon Sep 17 00:00:00 2001 From: bow <bow@bow.web.id> Date: Sun, 15 Feb 2015 23:36:13 +0100 Subject: [PATCH] Precompile regex for splitting read IDs --- .../src/main/scala/nl/lumc/sasc/biopet/tools/FastqSync.scala | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSync.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSync.scala index 43ac955e4..b16e205e7 100644 --- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSync.scala +++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSync.scala @@ -90,9 +90,12 @@ class FastqSync(val root: Configurable) extends BiopetJavaCommandLineFunction { object FastqSync extends ToolCommand { + /** Regex for capturing read ID ~ taking into account its read pair mark (if present) */ + private val idRegex = "[_/][12]\\s??|\\s".r + /** Implicit class to allow for lazy retrieval of FastqRecord ID without any read pair mark */ private implicit class FastqPair(fq: FastqRecord) { - lazy val fragId = fq.getReadHeader.split("[_/][12]\\s??|\\s")(0) + lazy val fragId = idRegex.split(fq.getReadHeader)(0) } /** -- GitLab