Add check for sample names with space

This fixes issue #27

README.md

@@ -96,6 +96,8 @@ cases, this can be a csv file with one line per read-pair, as can be seen
 Any number of samples can be processed in a single execution, and each sample
 may have any number of read pairs, and HAMLET will handle those properly.
 
+**Note that spaces in sample names are not supported**
+
 ## Execution
 If running in a cluster, you may also want to define the resource configurations in another YAML file. Read more about
 this type of configuration on the official [Snakemake

common.smk

@@ -6,6 +6,11 @@ pepfile: config["pepfile"]
 
 samples = pep.sample_table["sample_name"]
 
+for s in samples:
+    if " " in s:
+        raise RuntimeError(f'Spaces in samples are not supported ("{s}")')
+
+
 containers = {
     "hamlet-scripts": "docker://quay.io/redmar_van_den_berg/hamlet-scripts:0.3",
     "multiqc": "docker://quay.io/biocontainers/multiqc:1.22.1--pyhdfd78af_0",

includes/fusion/Snakefile

@@ -1,11 +1,6 @@
 include: "common.smk"
 
 
-# Put each sample name in a SimpleNamespace to mimic Snakemake wildcard usage
-# (e.g {wildcards.sample}). This is only used in the 'all' rule.
-samples = [SimpleNamespace(sample=sample) for sample in pep.sample_table["sample_name"]]
-
-
 rule all:
     input:
         arriba=[module_output.arriba(sample) for sample in samples],

includes/fusion/common.smk

@@ -4,6 +4,15 @@ from types import SimpleNamespace
 pepfile: config["pepfile"]
 
 
+# Put each sample name in a SimpleNamespace to mimic Snakemake wildcard usage
+# (e.g {wildcards.sample}). This is only used in the 'all' rule.
+samples = [SimpleNamespace(sample=sample) for sample in pep.sample_table["sample_name"]]
+
+for s in samples:
+    if " " in s.sample:
+        raise RuntimeError(f'Spaces in samples are not supported ("{s.sample}")')
+
+
 containers = {
     "arriba": "docker://quay.io/biocontainers/arriba:2.4.0--h0033a41_2",
     "poppler": "docker://quay.io/biocontainers/keggcharter:0.6.0--hdfd78af_0",

includes/itd/common.smk

@@ -4,6 +4,15 @@ from types import SimpleNamespace
 pepfile: config["pepfile"]
 
 
+# Put each sample name in a SimpleNamespace to mimic Snakemake wildcard usage
+# (e.g {wildcards.sample}). This is only used in the 'all' rule.
+samples = [SimpleNamespace(sample=sample) for sample in pep.sample_table["sample_name"]]
+
+for s in samples:
+    if " " in s.sample:
+        raise RuntimeError(f'Spaces in samples are not supported ("{s.sample}")')
+
+
 containers = {
     "bwa-0.7.17-samtools-1.3.1-picard-2.9.2": "docker://quay.io/biocontainers/mulled-v2-1c6be8ad49e4dfe8ab70558e8fb200d7b2fd7509:5900b4e68c4051137fffd99165b00e98f810acae-0",
     "rose": "docker://quay.io/redmar_van_den_berg/rose-dt:0.4",

includes/qc-seq/common.smk

@@ -14,6 +14,10 @@ pepfile: config["pepfile"]
 # (e.g {wildcards.sample}). This is only used in the 'all' rule.
 samples = [SimpleNamespace(sample=sample) for sample in pep.sample_table["sample_name"]]
 
+for s in samples:
+    if " " in s.sample:
+        raise RuntimeError(f'Spaces in samples are not supported ("{s.sample}")')
+
 
 def get_input_fastq(sample, pair):
     """Get all fastq files for the specified sample"""

includes/snv-indels/common.smk

@@ -20,6 +20,10 @@ containers = {
 # (e.g {wildcards.sample}). This is only used in the 'all' rule.
 samples = [SimpleNamespace(sample=sample) for sample in pep.sample_table["sample_name"]]
 
+for s in samples:
+    if " " in s.sample:
+        raise RuntimeError(f'Spaces in samples are not supported ("{s.sample}")')
+
 
 def get_forward(wildcards):
     return pep.sample_table.loc[wildcards.sample, "R1"]

test/pep/invalid.csv

@@ -0,0 +1,3 @@
+sample_name,R1,R2
+SRR 8615687,test/data/fastq/SRR8615687_flt3_1.fastq.gz,test/data/fastq/SRR8615687_flt3_2.fastq.gz
+SRR 8616218,test/data/fastq/SRR8616218_KMT2A_1.fastq.gz,test/data/fastq/SRR8616218_KMT2A_2.fastq.gz

test/test_fusion.yml

@@ -89,3 +89,18 @@
     - sanity
     - fusion
   command: snakefmt --check includes/fusion
+
+- name: test-fusion-sample-with-space
+  tags:
+    - sanity
+    - fusion
+  command: >
+    snakemake
+    --snakefile includes/fusion/Snakefile
+    --workflow-profile test
+    --configfile test/data/config/fusion.json
+    --config pepfile=test/pep/invalid.csv
+  exit_code: 1
+  stderr:
+    contains:
+      - 'RuntimeError: Spaces in samples are not supported ("SRR 8615687")'

test/test_hamlet.yml

@@ -170,3 +170,18 @@
     - sanity
     - hamlet
   command: snakefmt --check .
+
+- name: test-sample-with-space
+  tags:
+    - sanity
+    - hamlet
+  command: >
+    snakemake
+    --snakefile Snakefile
+    --workflow-profile test
+    --configfile test/data/config/hamlet-dry.json
+    --config pepfile=test/pep/invalid.csv
+  exit_code: 1
+  stderr:
+    contains:
+      - 'RuntimeError: Spaces in samples are not supported ("SRR 8615687")'

test/test_itd.yml

@@ -45,6 +45,7 @@
     contains_regex:
       - "singularity(-ce)? version 3"
 
+
 # ITD pipeline should run successfully and actually create the specified files
 - name: test-itd
   tags:
@@ -165,3 +166,18 @@
     - sanity
     - itd
   command: snakefmt --check includes/itd
+
+- name: test-itd-sample-with-space
+  tags:
+    - sanity
+    - itd
+  command: >
+    snakemake
+    --snakefile includes/itd/Snakefile
+    --workflow-profile test
+    --configfile test/data/config/itd.json
+    --config pepfile=test/pep/invalid.csv
+  exit_code: 1
+  stderr:
+    contains:
+      - 'RuntimeError: Spaces in samples are not supported ("SRR 8615687")'

test/test_qc_seq.yml

@@ -92,3 +92,18 @@
     - sanity
     - qc-seq
   command: snakefmt --check includes/qc-seq/
+
+- name: test-qc-seq-sample-with-space
+  tags:
+    - sanity
+    - qc-seq
+  command: >
+    snakemake
+    --snakefile includes/qc-seq/Snakefile
+    --workflow-profile test
+    --configfile test/data/config/qc-seq.json
+    --config pepfile=test/pep/invalid.csv
+  exit_code: 1
+  stderr:
+    contains:
+      - 'RuntimeError: Spaces in samples are not supported ("SRR 8615687")'

test/test_snv_indels.yml

@@ -188,3 +188,18 @@
     - sanity
     - snv-indels
   command: snakefmt --check includes/snv-indels/
+
+- name: test-snv-indels-sample-with-space
+  tags:
+    - sanity
+    - snv-indels
+  command: >
+    snakemake
+    --snakefile includes/snv-indels/Snakefile
+    --workflow-profile test
+    --configfile test/data/config/snv-indels.json
+    --config pepfile=test/pep/invalid.csv
+  exit_code: 1
+  stderr:
+    contains:
+      - 'RuntimeError: Spaces in samples are not supported ("SRR 8615687")'