From df992acd73df8906ae681d9624f1819a7415206f Mon Sep 17 00:00:00 2001
From: chuan-wang <chuan.wang@scilifelab.se>
Date: Fri, 15 Mar 2024 15:12:24 +0100
Subject: [PATCH] Fix cases that MiSeq samplesheet misses index or index2

---
 VERSIONLOG.md                  | 4 ++++
 taca/analysis/analysis.py      | 2 +-
 taca/illumina/Runs.py          | 4 ++++
 taca/illumina/Standard_Runs.py | 4 ++++
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/VERSIONLOG.md b/VERSIONLOG.md
index bca6360e..4d464718 100644
--- a/VERSIONLOG.md
+++ b/VERSIONLOG.md
@@ -1,5 +1,9 @@
 # TACA Version Log
 
+## 20240315.1
+
+Fix cases that MiSeq samplesheet misses index or index2
+
 ## 20240304.1
 
 - Make sure TACA can handle runs that generate NO sequencing data at all
diff --git a/taca/analysis/analysis.py b/taca/analysis/analysis.py
index f9418f46..ffacfb27 100755
--- a/taca/analysis/analysis.py
+++ b/taca/analysis/analysis.py
@@ -115,7 +115,7 @@ def _upload_to_statusdb(run):
     # Check if I have NoIndex lanes
     for element in parser.obj["samplesheet_csv"]:
         if (
-            "NoIndex" in element["index"] or not element["index"]
+            "NoIndex" in element.get("index", "") or not element.get("index")
         ):  # NoIndex in the case of HiSeq, empty in the case of HiSeqX
             lane = element["Lane"]  # This is a lane with NoIndex
             # In this case PF Cluster is the number of undetermined reads
diff --git a/taca/illumina/Runs.py b/taca/illumina/Runs.py
index 2bd33e3c..876ed1eb 100644
--- a/taca/illumina/Runs.py
+++ b/taca/illumina/Runs.py
@@ -453,6 +453,10 @@ def _classify_lanes(self, samplesheets):
         # Prepare a list for lanes with NoIndex samples
         noindex_lanes = []
         for entry in self.runParserObj.samplesheet.data:
+            if not entry.get("index"):
+                entry["index"] = ""
+            if not entry.get("index2"):
+                entry["index2"] = ""
             if entry["index"].upper() == "NOINDEX" or (
                 entry["index"] == "" and entry["index2"] == ""
             ):
diff --git a/taca/illumina/Standard_Runs.py b/taca/illumina/Standard_Runs.py
index a7f9a2d9..08d6fdbc 100755
--- a/taca/illumina/Standard_Runs.py
+++ b/taca/illumina/Standard_Runs.py
@@ -131,6 +131,10 @@ def _classify_samples(self, indexfile, ssparser, runSetup):
             sample_name = sample.get("Sample_Name") or sample.get("SampleName")
             umi_length = [0, 0]
             read_length = read_cycles
+            if not sample.get("index"):
+                sample["index"] = ""
+            if not sample.get("index2"):
+                sample["index2"] = ""
             # Read the length of read 1 and read 2 from the field Recipe
             if sample.get("Recipe") and RECIPE_PAT.findall(sample.get("Recipe")):
                 ss_read_length = [