Skip to content

Commit

Permalink
New module: RIPGREP (nf-core#7275)
Browse files Browse the repository at this point in the history 
* Add ska/fasta module

* Update modules/nf-core/ska/fasta/main.nf

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>

* Update modules/nf-core/ska/fasta/main.nf

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>

* Update modules/nf-core/ska/fasta/main.nf

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>

* Update modules/nf-core/ska/fasta/meta.yml

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>

* Update modules/nf-core/ska/fasta/tests/main.nf.test

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>

* Tweak tests for unstable md5

* Update modules/nf-core/ska/fasta/meta.yml

Co-authored-by: Sateesh_Peri <[email protected]>

* Update modules/nf-core/ska/fasta/meta.yml

Co-authored-by: Sateesh_Peri <[email protected]>

* Update modules/nf-core/ska/fasta/meta.yml

Co-authored-by: Sateesh_Peri <[email protected]>

* Update modules/nf-core/ska/fasta/meta.yml

Co-authored-by: Sateesh_Peri <[email protected]>

* Delete nxf-tmp.xaQb2l

* Update modules/nf-core/ska/fasta/main.nf

Co-authored-by: Sateesh_Peri <[email protected]>

* Add ripgrep module

* Fix meta

* Add name safety, add compression to stub

---------

Co-authored-by: Jose Espinosa-Carrasco <[email protected]>
Co-authored-by: Sateesh_Peri <[email protected]>
  • Loading branch information
@itrujnara @JoseEspinosa
@sateeshperi @fellen31
3 people authored and fellen31 committed Jan 10, 2025
1 parent 560dfdf commit 78e9e2c
Show file tree
Hide file tree
Showing 5 changed files with 312 additions and 0 deletions.
7 changes: 7 additions & 0 deletions modules/nf-core/ripgrep/environment.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
channels:
- conda-forge
- bioconda

dependencies:
- conda-forge::pigz=2.8
- conda-forge::ripgrep=14.1.1
55 changes: 55 additions & 0 deletions modules/nf-core/ripgrep/main.nf
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
process RIPGREP {
tag "$meta.id"
label 'process_low'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/de/deecf2e0aab3f4ba7c04eb24724f5c80550e39bec80760b18c7b52f8efa8e6b3/data':
'community.wave.seqera.io/library/pigz_ripgrep:94e5407412b666ab' }"

input:
tuple val(meta), path(files)
val pattern
val compress

output:
tuple val(meta), path("*.txt{.gz,}"), emit: txt
path "versions.yml" , emit: versions

when:
task.ext.when == null || task.ext.when

script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def write_output = compress ? " | pigz -cp ${task.cpus} > ${prefix}.txt.gz" : "> ${prefix}.txt"
if (!compress && files.contains("${prefix}.txt") || compress && files.contains("${prefix}.txt.gz")) {
error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
}
"""
rg \\
$args \\
--threads $task.cpus \\
$pattern \\
$files \\
$write_output
cat <<-END_VERSIONS > versions.yml
"${task.process}":
ripgrep: \$(rg --version |& sed '1!d ; s/ripgrep //')
END_VERSIONS
"""

stub:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def write_output = compress ? "touch ${prefix}.txt.gz" : "touch ${prefix}.txt"
"""
$write_output
cat <<-END_VERSIONS > versions.yml
"${task.process}":
ripgrep: \$(rg --version |& sed '1!d ; s/ripgrep //')
END_VERSIONS
"""
}
59 changes: 59 additions & 0 deletions modules/nf-core/ripgrep/meta.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
name: "ripgrep"
description: ripgrep recursively searches directories for a regex pattern
keywords:
- search
- regex
- patterns
tools:
- "ripgrep":
description: "ripgrep recursively searches directories for a regex pattern"
homepage: "https://github.com/BurntSushi/ripgrep"
documentation: "https://github.com/BurntSushi/ripgrep"
tool_dev_url: "https://github.com/BurntSushi/ripgrep"
licence: ["MIT", "UNLICENSE"]
identifier: ""
- "pigz":
description: "Parallel implementation of the gzip algorithm."
homepage: "https://zlib.net/pigz/"
documentation: "https://zlib.net/pigz/pigz.pdf"

identifier: ""
input:
- - meta:
type: map
description: |
Groovy Map containing sample information
e.g. `[ id:'sample1' ]`
- files:
type: file
description: File(s) to be searched

- - pattern:
type: string
description: Regex pattern to search for

- - compress:
type: boolean
description: Compress the output file using pigz
default: false

output:
- txt:
- meta:
type: map
description: Groovy map containing sample information
- "*.txt{.gz,}":
type: file
description: Output file containing the search results
pattern: "*.txt{.gz,}"
- versions:
- versions.yml:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@itrujnara"
maintainers:
- "@itrujnara"
90 changes: 90 additions & 0 deletions modules/nf-core/ripgrep/tests/main.nf.test
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,90 @@
nextflow_process {

name "Test Process RIPGREP"
script "../main.nf"
process "RIPGREP"

tag "modules"
tag "modules_nfcore"
tag "ripgrep"

test("generic - csv") {

when {
process {
"""
input[0] = [
[ id:'test' ], // meta map
file(params.modules_testdata_base_path + 'generic/csv/test.csv', checkIfExists: true),
]
input[1] = 'Robert' // pattern
input[2] = false // compress
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}

}

test("generic - csv - compress") {

when {
process {
"""
input[0] = [
[ id:'test' ], // meta map
file(params.modules_testdata_base_path + 'generic/csv/test.csv', checkIfExists: true),
]
input[1] = 'Robert' // pattern
input[2] = true // compress
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}
}

test("generic - csv - stub") {

options "-stub"

when {
process {
"""
input[0] = [
[ id:'test' ], // meta map
file(params.modules_testdata_base_path + 'generic/csv/test.csv', checkIfExists: true),
]
input[1] = 'Robert' // pattern
input[2] = false // compress
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}

}

}
101 changes: 101 additions & 0 deletions modules/nf-core/ripgrep/tests/main.nf.test.snap
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,101 @@
{
"generic - csv": {
"content": [
{
"0": [
[
{
"id": "test"
},
"test.txt:md5,5f32b160f4f228e7abfda2cd988eb164"
]
],
"1": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
],
"txt": [
[
{
"id": "test"
},
"test.txt:md5,5f32b160f4f228e7abfda2cd988eb164"
]
],
"versions": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
]
}
],
"meta": {
"nf-test": "0.9.2",
"nextflow": "24.10.3"
},
"timestamp": "2025-01-08T13:04:56.719646"
},
"generic - csv - stub": {
"content": [
{
"0": [
[
{
"id": "test"
},
"test.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"1": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
],
"txt": [
[
{
"id": "test"
},
"test.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
]
}
],
"meta": {
"nf-test": "0.9.2",
"nextflow": "24.10.3"
},
"timestamp": "2025-01-08T13:05:05.816873"
},
"generic - csv - compress": {
"content": [
{
"0": [
[
{
"id": "test"
},
"test.txt.gz:md5,5f32b160f4f228e7abfda2cd988eb164"
]
],
"1": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
],
"txt": [
[
{
"id": "test"
},
"test.txt.gz:md5,5f32b160f4f228e7abfda2cd988eb164"
]
],
"versions": [
"versions.yml:md5,d8a13e6037909fd47164f64bcdd8afa3"
]
}
],
"meta": {
"nf-test": "0.9.2",
"nextflow": "24.10.3"
},
"timestamp": "2025-01-08T13:10:17.112725"
}
}

0 comments on commit 78e9e2c

Please sign in to comment.