Merge pull request #777 from dfm/snakemake

Adding support for Snakemake, #777
AlDanial · Oct 20, 2023 · b7e76ec · b7e76ec
2 parents 713d067 + 523f733
commit b7e76ec
Show file tree

Hide file tree

Showing 4 changed files with 98 additions and 0 deletions.
diff --git a/Unix/t/00_C.t b/Unix/t/00_C.t
@@ -1006,6 +1006,11 @@ my @Tests = (
                     'ref'  => '../tests/outputs/captcha.cs.yaml',
                     'args' => '../tests/inputs/captcha.cs',
                 },
+                {
+                    'name' => 'Snakemake',
+                    'ref'  => '../tests/outputs/Snakefile.yaml',
+                    'args' => '../tests/inputs/Snakefile',
+                },
                 {
                     'name' => 'Smarty',
                     'ref'  => '../tests/outputs/guestbook.tpl.yaml',

diff --git a/cloc b/cloc
@@ -8806,6 +8806,8 @@ sub set_constants {                          # {{{1
             'data.sql'    => 'SQL Data'              ,
             'sss'         => 'SugarSS'               ,
             'st'          => 'Smalltalk'             ,
+            'rules'       => 'Snakemake'             ,
+            'smk'         => 'Snakemake'             ,
             'styl'        => 'Stylus'                ,
             'i'           => 'SWIG'                  ,
             'svelte'      => 'Svelte'                ,
@@ -9111,6 +9113,7 @@ sub set_constants {                          # {{{1
             'pom.xml'           => 'Maven/XML'          ,
             'Rakefile'          => 'Ruby'               ,
             'rakefile'          => 'Ruby'               ,
+            'Snakefile'         => 'Snakemake'          ,
             'Dockerfile'        => 'Dockerfile'         ,
             'Dockerfile.m4'     => 'Dockerfile'         ,
             'Dockerfile.cmake'  => 'Dockerfile'         ,
@@ -10338,6 +10341,12 @@ sub set_constants {                          # {{{1
                                 [ 'smarty_to_C'                    ],
                                 [ 'call_regexp_common'  , 'C'      ],
                             ],
+    'Snakemake'          => [
+                                [ 'remove_matches'      , '^\s*#'  ],
+                                [ 'docstring_to_C'                 ],
+                                [ 'call_regexp_common'  , 'C'      ],
+                                [ 'remove_inline'       , '#.*$'   ],
+                            ],
     'Standard ML'        => [
                                 [ 'remove_between_general', '(*', '*)' ],
                             ],
@@ -10762,6 +10771,7 @@ sub set_constants {                          # {{{1
     'kvlang'             =>     '\\\\$'         ,
     'Kermit'             =>     '\\\\$'         ,
     'Korn Shell'         =>     '\\\\$'         ,
+    'Snakemake'          =>     '\\\\$'         ,
     'Starlark'           =>     '\\\\$'         ,
     'Solidity'           =>     '\\\\$'         ,
     'Stata'              =>     '///$'          ,
@@ -11263,6 +11273,7 @@ sub set_constants {                          # {{{1
     'PHP'                          => 3.50,
     'Jupyter Notebook'             => 4.20,
     'Python'                       => 4.20,
+    'Snakemake'                    => 4.20,
     'RapydScript'                  => 4.20,
     'Starlark'                     => 4.20,
     'BizTalk Pipeline'             => 1.00,

diff --git a/tests/inputs/Snakefile b/tests/inputs/Snakefile
@@ -0,0 +1,63 @@
+"""
+A sample Snakefile for testing line counting
+"""
+
+SAMPLES = ["A", "B"]
+
+
+# This is a
+# multiline
+# comment
+rule all:
+    input:
+        "plots/quals.svg"
+
+
+rule bwa_map:
+    input:
+        "data/genome.fa",  # Inline comments are also supported
+        "data/samples/{sample}.fastq"
+    output:
+        "mapped_reads/{sample}.bam"
+    shell:
+        "bwa mem {input} | samtools view -Sb - > {output}"
+
+
+rule samtools_sort:
+    input:
+        "mapped_reads/{sample}.bam"
+    output:
+        "sorted_reads/{sample}.bam"
+    shell:
+        "samtools sort -T sorted_reads/{wildcards.sample} "
+        "-O bam {input} > {output}"
+
+
+rule samtools_index:
+    input:
+        "sorted_reads/{sample}.bam"
+    output:
+        "sorted_reads/{sample}.bam.bai"
+    shell:
+        "samtools index {input}"
+
+
+rule bcftools_call:
+    input:
+        fa="data/genome.fa",
+        bam=expand("sorted_reads/{sample}.bam", sample=SAMPLES),
+        bai=expand("sorted_reads/{sample}.bam.bai", sample=SAMPLES)
+    output:
+        "calls/all.vcf"
+    shell:
+        "bcftools mpileup -f {input.fa} {input.bam} | "
+        "bcftools call -mv - > {output}"
+
+
+rule plot_quals:
+    input:
+        "calls/all.vcf"
+    output:
+        "plots/quals.svg"
+    script:
+        "scripts/plot-quals.py"
diff --git a/tests/outputs/Snakefile.yaml b/tests/outputs/Snakefile.yaml
@@ -0,0 +1,19 @@
+# github.com/AlDanial/cloc
+header :
+  cloc_url           : github.com/AlDanial/cloc
+  cloc_version       : 1.99
+  elapsed_seconds    : 0.039093017578125
+  n_files            : 1
+  n_lines            : 63
+  files_per_second   : 25.5800156128025
+  lines_per_second   : 1611.54098360656
+'Snakemake' :
+  nFiles: 1
+  blank: 13
+  comment: 6
+  code: 44
+SUM:
+  blank: 13
+  comment: 6
+  code: 44
+  nFiles: 1