From 07c462e36f361ff3049280f6588693c5d45ac887 Mon Sep 17 00:00:00 2001
From: Sam Horsfield <57448593+samhorsfield96@users.noreply.github.com>
Date: Tue, 16 Jul 2024 11:09:25 +0100
Subject: [PATCH 1/2] Update indexing.cpp

Corrects potential out of range error
---
 src/indexing.cpp | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/src/indexing.cpp b/src/indexing.cpp
index b903eb4..17291fa 100644
--- a/src/indexing.cpp
+++ b/src/indexing.cpp
@@ -458,16 +458,18 @@ void calculate_genome_paths(const std::vector<Kmer>& head_kmer_arr,
                     }
                 }
 
-                // map to last entry and assign end-contig
-                auto um_pair = get_um_data(ccdbg, head_kmer_arr, prev_head);
-                auto& um_data = um_pair.second;
-
-                um_data->set_end_contig(colour_ID, nb_colours);
-
-                // add delimiter between contigs
-                genome_path += contig_path;
-                genome_path += ";";
-                contig_ID++;
+                if (prev_head != 0) {
+                    // map to last entry and assign end-contig
+                    auto um_pair = get_um_data(ccdbg, head_kmer_arr, prev_head);
+                    auto& um_data = um_pair.second;
+    
+                    um_data->set_end_contig(colour_ID, nb_colours);
+    
+                    // add delimiter between contigs
+                    genome_path += contig_path;
+                    genome_path += ";";
+                    contig_ID++;
+                }
             }
         }
     }
@@ -585,4 +587,4 @@ NodeColourVector index_graph(std::vector<Kmer>& head_kmer_arr,
 
     // return node_colour vector
     return node_colour_vector;
-}
\ No newline at end of file
+}

From 0f0acd39d574ce722f8ee7bb03dcbab84bc7cd30 Mon Sep 17 00:00:00 2001
From: Sam Horsfield <57448593+samhorsfield96@users.noreply.github.com>
Date: Wed, 17 Jul 2024 09:19:37 +0100
Subject: [PATCH 2/2] Adds comment for changes

---
 src/indexing.cpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/indexing.cpp b/src/indexing.cpp
index 17291fa..7aa3ceb 100644
--- a/src/indexing.cpp
+++ b/src/indexing.cpp
@@ -458,6 +458,8 @@ void calculate_genome_paths(const std::vector<Kmer>& head_kmer_arr,
                     }
                 }
 
+                // in case where whole contig removed, do not add to FM index
+                // otherwise causes out of range error with head_kmer_arr as k-mer not present
                 if (prev_head != 0) {
                     // map to last entry and assign end-contig
                     auto um_pair = get_um_data(ccdbg, head_kmer_arr, prev_head);