feat: make it possible to set input as files or dirs to multiqc (#488)

* feat: make it possible to set input as files or dirs to multiqc

make it possible to use the actual input from the rule as input to multiqc, instead of converting it to dirs that are then searched.

* Update bio/multiqc/test/Snakefile

Co-authored-by: Filipe G. Vieira <fgarrettvieira@gmail.com>

* feat: change params variable name

* Update Snakefile

* doc: update documentation

* Update bio/multiqc/meta.yaml

Co-authored-by: Filipe G. Vieira <fgarrettvieira@gmail.com>

Co-authored-by: Filipe G. Vieira <fgarrettvieira@gmail.com>

bio/multiqc/meta.yaml

@@ -1,9 +1,12 @@
 name: multiqc
 description: |
   Generate qc report using multiqc.
+url: https://multiqc.info/
 authors:
   - Julian de Ruiter
 input:
-  - input directory containing qc files
+  - input directory containing qc files, default behaviour is to extract folder path from the provided files or parent folder if a folder is provided.
+params:
+  - use_input_files_only: if this variable is set to True input will be used as it is, i.e no folder will be extract from provided file names
 output:
   - qc report (html)

bio/multiqc/test/Snakefile

@@ -1,10 +1,23 @@
-rule multiqc:
+rule multiqc_dir:
     input:
         expand("samtools_stats/{sample}.txt", sample=["a", "b"])
     output:
         "qc/multiqc.html"
     params:
-        ""  # Optional: extra parameters for multiqc.
+        extra=""  # Optional: extra parameters for multiqc.
+    log:
+        "logs/multiqc.log"
+    wrapper:
+        "master/bio/multiqc"
+
+rule multiqc_file:
+    input:
+        expand("samtools_stats/{sample}.txt", sample=["a"])
+    output:
+        "qc/multiqc_a.html"
+    params:
+        extra="",  # Optional: extra parameters for multiqc.
+        use_input_files_only=True, # Optional, use only a.txt and don't search folder samtools_stats for files
     log:
         "logs/multiqc.log"
     wrapper:

bio/multiqc/wrapper.py

@@ -11,17 +11,26 @@
 from snakemake.shell import shell
 
 
-input_dirs = set(path.dirname(fp) for fp in snakemake.input)
+extra = snakemake.params.get("extra", "")
+# Set this to False if multiqc should use the actual input directly
+# instead of parsing the folders where the provided files are located
+use_input_files_only = snakemake.params.get("use_input_files_only", False)
+
+if not use_input_files_only:
+    input_data = set(path.dirname(fp) for fp in snakemake.input)
+else:
+    input_data = set(snakemake.input)
+
 output_dir = path.dirname(snakemake.output[0])
 output_name = path.basename(snakemake.output[0])
 log = snakemake.log_fmt_shell(stdout=True, stderr=True)
 
 shell(
     "multiqc"
-    " {snakemake.params}"
+    " {extra}"
     " --force"
     " -o {output_dir}"
     " -n {output_name}"
-    " {input_dirs}"
+    " {input_data}"
     " {log}"
 )

test.py

@@ -2132,6 +2132,12 @@ def test_multiqc():
         ["snakemake", "--cores", "1", "qc/multiqc.html", "--use-conda", "-F"],
     )
 
+@skip_if_not_modified
+def test_multiqc_a():
+    run(
+        "bio/multiqc",
+        ["snakemake", "--cores", "1", "qc/multiqc_a.html", "--use-conda", "-F"],
+    )
 
 @skip_if_not_modified
 def test_muscle_clw():