From 512afe0cf0679a7109e6335119b4b538da797172 Mon Sep 17 00:00:00 2001
From: Jacques Dainat <jacques.dainat@nbis.se>
Date: Thu, 7 Nov 2019 15:29:36 +0100
Subject: [PATCH] update information and cases for benchmark

---
 .../Handler/Benchmark/gff_file_type_benchmark/1_test.gff | 1 +
 .../Benchmark/gff_file_type_benchmark/1a_test.gff        | 1 +
 .../Handler/Benchmark/gff_file_type_benchmark/2_test.gff | 1 +
 .../Benchmark/gff_file_type_benchmark/2a_test.gff        | 9 +++++++++
 .../Benchmark/gff_file_type_benchmark/2b_test.gff        | 9 +++++++++
 5 files changed, 21 insertions(+)
 create mode 100644 annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2a_test.gff
 create mode 100644 annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2b_test.gff

diff --git a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1_test.gff b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1_test.gff
index 52cb1ac70..946903f0d 100644
--- a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1_test.gff
+++ b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1_test.gff
@@ -1,3 +1,4 @@
+#GFF1 with attribute "tag value tag value"
 scaffold_5	JGI	exon	442603	443344	.	+	.	gene_id "e_gw1.5.2.1" transcript_id 335995
 scaffold_5	JGI	CDS	442603	443344	.	+	0	gene_id "e_gw1.5.2.1" protein_id 335805 exonNumber 1
 scaffold_5	JGI	start_codon	442603	442605	.	+	0	gene_id "e_gw1.5.2.1"
diff --git a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1a_test.gff b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1a_test.gff
index a301172c7..607c3ab8b 100644
--- a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1a_test.gff
+++ b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/1a_test.gff
@@ -1,3 +1,4 @@
+# GFF1 only one value as attribute
 scaffold_5	JGI	exon	442603	443344	.	+	.	geneA
 scaffold_5	JGI	CDS	442603	443344	.	+	0	geneA
 scaffold_5	JGI	start_codon	442603	442605	.	+	0	geneA
diff --git a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2_test.gff b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2_test.gff
index 21eb4db64..2fca952d4 100644
--- a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2_test.gff
+++ b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2_test.gff
@@ -1,3 +1,4 @@
+# GFF2
 scaffold_5	JGI	exon	442603	443344	.	+	.	gene_id "e_gw1.5.2.1"; transcript_id 335995
 scaffold_5	JGI	CDS	442603	443344	.	+	0	gene_id "e_gw1.5.2.1"; protein_id 335805; exonNumber 1
 scaffold_5	JGI	start_codon	442603	442605	.	+	0	gene_id "e_gw1.5.2.1"
diff --git a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2a_test.gff b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2a_test.gff
new file mode 100644
index 000000000..d08acd8bc
--- /dev/null
+++ b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2a_test.gff
@@ -0,0 +1,9 @@
+#GFF2 as we see often with space before semicolon
+scaffold_5	JGI	exon	442603	443344	.	+	.	gene_id "e_gw1.5.2.1" ; transcript_id 335995
+scaffold_5	JGI	CDS	442603	443344	.	+	0	gene_id "e_gw1.5.2.1" ; protein_id 335805; exonNumber 1
+scaffold_5	JGI	start_codon	442603	442605	.	+	0	gene_id "e_gw1.5.2.1"
+scaffold_5	JGI	exon	443530	443531	.	+	.	gene_id "e_gw1.5.2.1" ; transcript_id 335995
+scaffold_5	JGI	CDS	443530	443531	.	+	2	gene_id "e_gw1.5.2.1" ; protein_id 335805; exonNumber 2
+scaffold_5	JGI	exon	443569	445653	.	+	.	gene_id "e_gw1.5.2.1" ; transcript_id 335995
+scaffold_5	JGI	CDS	443569	445653	.	+	0	gene_id "e_gw1.5.2.1" ; protein_id 335805; exonNumber 3
+scaffold_5	JGI	stop_codon	445651	445653	.	+	0	gene_id "e_gw1.5.2.1"
diff --git a/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2b_test.gff b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2b_test.gff
new file mode 100644
index 000000000..79e20127d
--- /dev/null
+++ b/annotation/BILS/Handler/Benchmark/gff_file_type_benchmark/2b_test.gff
@@ -0,0 +1,9 @@
+#GTF2 GFF2.5 as GFF2 but with semicolon at the end
+scaffold_5	JGI	exon	442603	443344	.	+	.	gene_id "e_gw1.5.2.1"; transcript_id 335995;
+scaffold_5	JGI	CDS	442603	443344	.	+	0	gene_id "e_gw1.5.2.1"; protein_id 335805; exonNumber 1;
+scaffold_5	JGI	start_codon	442603	442605	.	+	0	gene_id "e_gw1.5.2.1";
+scaffold_5	JGI	exon	443530	443531	.	+	.	gene_id "e_gw1.5.2.1"; transcript_id 335995;
+scaffold_5	JGI	CDS	443530	443531	.	+	2	gene_id "e_gw1.5.2.1"; protein_id 335805; exonNumber 2;
+scaffold_5	JGI	exon	443569	445653	.	+	.	gene_id "e_gw1.5.2.1"; transcript_id 335995;
+scaffold_5	JGI	CDS	443569	445653	.	+	0	gene_id "e_gw1.5.2.1"; protein_id 335805; exonNumber 3;
+scaffold_5	JGI	stop_codon	445651	445653	.	+	0	gene_id "e_gw1.5.2.1";