Build branch main with version main (781f668)

Build pipeline: viash-hub.craftbox.main-5sjkz

Source commit: 781f668839

Source message: FEAT: add untar (#3)

* FEAT: add untar

* Use meta_executable
This commit is contained in:
CI
2024-06-26 12:30:50 +00:00
commit a0733101ff
27 changed files with 12414 additions and 0 deletions

0
target/.build.yaml Normal file
View File

View File

@@ -0,0 +1,248 @@
name: "csv2fasta"
version: "main"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "CSV file to be processed."
info: null
example:
- "barcodes.csv"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--header"
description: "Parse the first line of the CSV file as a header.\n"
info: null
direction: "input"
- name: "CSV dialect options"
description: "Options that can be used to override the automatically detected\n\
dialect of the CSV file.\n"
arguments:
- type: "string"
name: "--delimiter"
description: "Overwrite the column delimiter character.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quote_character"
description: "Overwrite the character used to denote the start and end of a quoted\
\ item.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "CSV column arguments"
description: "Parameters for the selection of columns from the CSV file.\nOnly required\
\ when your CSV file contains more than 2 columns,\notherwise the first column\
\ will be used for the FASTA header\nand the second for the FASTA nucleotide sequences.\
\ This default\ncan still be overwritten by using the options below.\n"
arguments:
- type: "string"
name: "--sequence_column"
description: "Name of the column containing the sequences. Implies 'header'.\n\
Cannot be used together with 'sequence_column_index'.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--name_column"
description: "Name of the column describing the FASTA headers. Implies 'header'.\n\
Cannot be used together with 'name_column_index'.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--sequence_column_index"
description: "Index of the column to use as the FASTA sequences, counter from\
\ the left and\nstarting from 0. Cannot be used in combination with the 'sequence_column'\
\ argument.\n"
info: null
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--name_column_index"
description: "Index of the column to use as the FASTA headers, counter from the\
\ left and\nstarting from 0. Cannot be used in combination with 'name_column'.\n"
info: null
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output fasta file."
info: null
example:
- "barcodes.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
description: "Convert two columns from a CSV file to FASTA entries. The CSV file can\n\
contain an optional header and each row (other than the header) becomes\na single\
\ FASTA record. One of the two columns will be used as the names\nfor the FASTA\
\ entries, while the other become the sequences. The sequences\ncolumn must only\
\ contain characters that are valid IUPAC notation for \nnucleotides or a group\
\ thereof (wildcard characters).\n"
test_resources:
- type: "python_script"
path: "test_csv2fasta.py"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/craftbox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "python:slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "dnaio"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "pytest"
- "viashpy"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/csv2fasta/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/csv2fasta"
executable: "target/executable/csv2fasta/csv2fasta"
viash_version: "0.9.0-RC6"
git_commit: "781f66883977e37a849f228ee1dffddbb7acdf32"
git_remote: "https://github.com/viash-hub/craftbox"
package_config:
name: "craftbox"
version: "main"
description: "A collection of custom-tailored scripts and applied tools.\n"
info: null
viash_version: "0.9.0-RC6"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "scripts"
- "custom"
- "implementations"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/craftbox"
issue_tracker: "https://github.com/viash-hub/craftbox/issues"

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,173 @@
name: "untar"
version: "main"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--input"
description: "Tarball file to be unpacked."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output arguments"
arguments:
- type: "file"
name: "--output"
description: "Directory to write the contents of the .tar file to."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Other arguments"
arguments:
- type: "string"
name: "--exclude"
alternatives:
- "-e"
description: "Prevents any file or member whose name matches the shell wildcard\
\ (pattern) from being extracted."
info: null
example:
- "docs/figures"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Unpack a .tar file. When the contents of the .tar file is just a single\
\ directory,\nput the contents of the directory into the output folder instead of\
\ that directory.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/craftbox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/untar/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/untar"
executable: "target/executable/untar/untar"
viash_version: "0.9.0-RC6"
git_commit: "781f66883977e37a849f228ee1dffddbb7acdf32"
git_remote: "https://github.com/viash-hub/craftbox"
package_config:
name: "craftbox"
version: "main"
description: "A collection of custom-tailored scripts and applied tools.\n"
info: null
viash_version: "0.9.0-RC6"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "scripts"
- "custom"
- "implementations"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/craftbox"
issue_tracker: "https://github.com/viash-hub/craftbox/issues"

1111
target/executable/untar/untar Executable file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,248 @@
name: "csv2fasta"
version: "main"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "CSV file to be processed."
info: null
example:
- "barcodes.csv"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--header"
description: "Parse the first line of the CSV file as a header.\n"
info: null
direction: "input"
- name: "CSV dialect options"
description: "Options that can be used to override the automatically detected\n\
dialect of the CSV file.\n"
arguments:
- type: "string"
name: "--delimiter"
description: "Overwrite the column delimiter character.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quote_character"
description: "Overwrite the character used to denote the start and end of a quoted\
\ item.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "CSV column arguments"
description: "Parameters for the selection of columns from the CSV file.\nOnly required\
\ when your CSV file contains more than 2 columns,\notherwise the first column\
\ will be used for the FASTA header\nand the second for the FASTA nucleotide sequences.\
\ This default\ncan still be overwritten by using the options below.\n"
arguments:
- type: "string"
name: "--sequence_column"
description: "Name of the column containing the sequences. Implies 'header'.\n\
Cannot be used together with 'sequence_column_index'.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--name_column"
description: "Name of the column describing the FASTA headers. Implies 'header'.\n\
Cannot be used together with 'name_column_index'.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--sequence_column_index"
description: "Index of the column to use as the FASTA sequences, counter from\
\ the left and\nstarting from 0. Cannot be used in combination with the 'sequence_column'\
\ argument.\n"
info: null
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--name_column_index"
description: "Index of the column to use as the FASTA headers, counter from the\
\ left and\nstarting from 0. Cannot be used in combination with 'name_column'.\n"
info: null
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output fasta file."
info: null
example:
- "barcodes.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
description: "Convert two columns from a CSV file to FASTA entries. The CSV file can\n\
contain an optional header and each row (other than the header) becomes\na single\
\ FASTA record. One of the two columns will be used as the names\nfor the FASTA\
\ entries, while the other become the sequences. The sequences\ncolumn must only\
\ contain characters that are valid IUPAC notation for \nnucleotides or a group\
\ thereof (wildcard characters).\n"
test_resources:
- type: "python_script"
path: "test_csv2fasta.py"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/craftbox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "python:slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "dnaio"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "pytest"
- "viashpy"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/csv2fasta/config.vsh.yaml"
runner: "nextflow"
engine: "docker|native"
output: "target/nextflow/csv2fasta"
executable: "target/nextflow/csv2fasta/main.nf"
viash_version: "0.9.0-RC6"
git_commit: "781f66883977e37a849f228ee1dffddbb7acdf32"
git_remote: "https://github.com/viash-hub/craftbox"
package_config:
name: "craftbox"
version: "main"
description: "A collection of custom-tailored scripts and applied tools.\n"
info: null
viash_version: "0.9.0-RC6"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "scripts"
- "custom"
- "implementations"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/craftbox"
issue_tracker: "https://github.com/viash-hub/craftbox/issues"

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,125 @@
manifest {
name = 'csv2fasta'
mainScript = 'main.nf'
nextflowVersion = '!>=20.12.1-edge'
version = 'main'
description = 'Convert two columns from a CSV file to FASTA entries. The CSV file can\ncontain an optional header and each row (other than the header) becomes\na single FASTA record. One of the two columns will be used as the names\nfor the FASTA entries, while the other become the sequences. The sequences\ncolumn must only contain characters that are valid IUPAC notation for \nnucleotides or a group thereof (wildcard characters).\n'
}
process.container = 'nextflow/bash:latest'
// detect tempdir
tempDir = java.nio.file.Paths.get(
System.getenv('NXF_TEMP') ?:
System.getenv('VIASH_TEMP') ?:
System.getenv('TEMPDIR') ?:
System.getenv('TMPDIR') ?:
'/tmp'
).toAbsolutePath()
profiles {
no_publish {
process {
withName: '.*' {
publishDir = [
enabled: false
]
}
}
}
mount_temp {
docker.temp = tempDir
podman.temp = tempDir
charliecloud.temp = tempDir
}
docker {
docker.enabled = true
// docker.userEmulation = true
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
singularity {
singularity.enabled = true
singularity.autoMounts = true
docker.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
podman {
podman.enabled = true
docker.enabled = false
singularity.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
shifter {
shifter.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
charliecloud.enabled = false
}
charliecloud {
charliecloud.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
}
}
process{
withLabel: mem1gb { memory = 1000000000.B }
withLabel: mem2gb { memory = 2000000000.B }
withLabel: mem5gb { memory = 5000000000.B }
withLabel: mem10gb { memory = 10000000000.B }
withLabel: mem20gb { memory = 20000000000.B }
withLabel: mem50gb { memory = 50000000000.B }
withLabel: mem100gb { memory = 100000000000.B }
withLabel: mem200gb { memory = 200000000000.B }
withLabel: mem500gb { memory = 500000000000.B }
withLabel: mem1tb { memory = 1000000000000.B }
withLabel: mem2tb { memory = 2000000000000.B }
withLabel: mem5tb { memory = 5000000000000.B }
withLabel: mem10tb { memory = 10000000000000.B }
withLabel: mem20tb { memory = 20000000000000.B }
withLabel: mem50tb { memory = 50000000000000.B }
withLabel: mem100tb { memory = 100000000000000.B }
withLabel: mem200tb { memory = 200000000000000.B }
withLabel: mem500tb { memory = 500000000000000.B }
withLabel: mem1gib { memory = 1073741824.B }
withLabel: mem2gib { memory = 2147483648.B }
withLabel: mem4gib { memory = 4294967296.B }
withLabel: mem8gib { memory = 8589934592.B }
withLabel: mem16gib { memory = 17179869184.B }
withLabel: mem32gib { memory = 34359738368.B }
withLabel: mem64gib { memory = 68719476736.B }
withLabel: mem128gib { memory = 137438953472.B }
withLabel: mem256gib { memory = 274877906944.B }
withLabel: mem512gib { memory = 549755813888.B }
withLabel: mem1tib { memory = 1099511627776.B }
withLabel: mem2tib { memory = 2199023255552.B }
withLabel: mem4tib { memory = 4398046511104.B }
withLabel: mem8tib { memory = 8796093022208.B }
withLabel: mem16tib { memory = 17592186044416.B }
withLabel: mem32tib { memory = 35184372088832.B }
withLabel: mem64tib { memory = 70368744177664.B }
withLabel: mem128tib { memory = 140737488355328.B }
withLabel: mem256tib { memory = 281474976710656.B }
withLabel: mem512tib { memory = 562949953421312.B }
withLabel: cpu1 { cpus = 1 }
withLabel: cpu2 { cpus = 2 }
withLabel: cpu5 { cpus = 5 }
withLabel: cpu10 { cpus = 10 }
withLabel: cpu20 { cpus = 20 }
withLabel: cpu50 { cpus = 50 }
withLabel: cpu100 { cpus = 100 }
withLabel: cpu200 { cpus = 200 }
withLabel: cpu500 { cpus = 500 }
withLabel: cpu1000 { cpus = 1000 }
}

View File

@@ -0,0 +1,194 @@
{
"$schema": "http://json-schema.org/draft-07/schema",
"title": "csv2fasta",
"description": "Convert two columns from a CSV file to FASTA entries. The CSV file can\ncontain an optional header and each row (other than the header) becomes\na single FASTA record. One of the two columns will be used as the names\nfor the FASTA entries, while the other become the sequences. The sequences\ncolumn must only contain characters that are valid IUPAC notation for \nnucleotides or a group thereof (wildcard characters).\n",
"type": "object",
"definitions": {
"inputs" : {
"title": "Inputs",
"type": "object",
"description": "No description",
"properties": {
"input": {
"type":
"string",
"description": "Type: `file`, required, example: `barcodes.csv`. CSV file to be processed",
"help_text": "Type: `file`, required, example: `barcodes.csv`. CSV file to be processed."
}
,
"header": {
"type":
"boolean",
"description": "Type: `boolean_true`, default: `false`. Parse the first line of the CSV file as a header",
"help_text": "Type: `boolean_true`, default: `false`. Parse the first line of the CSV file as a header.\n"
,
"default": "False"
}
}
},
"outputs" : {
"title": "Outputs",
"type": "object",
"description": "No description",
"properties": {
"output": {
"type":
"string",
"description": "Type: `file`, default: `$id.$key.output.fasta`, example: `barcodes.fasta`. Output fasta file",
"help_text": "Type: `file`, default: `$id.$key.output.fasta`, example: `barcodes.fasta`. Output fasta file."
,
"default": "$id.$key.output.fasta"
}
}
},
"csv dialect options" : {
"title": "CSV dialect options",
"type": "object",
"description": "Options that can be used to override the automatically detected\ndialect of the CSV file.\n",
"properties": {
"delimiter": {
"type":
"string",
"description": "Type: `string`. Overwrite the column delimiter character",
"help_text": "Type: `string`. Overwrite the column delimiter character.\n"
}
,
"quote_character": {
"type":
"string",
"description": "Type: `string`. Overwrite the character used to denote the start and end of a quoted item",
"help_text": "Type: `string`. Overwrite the character used to denote the start and end of a quoted item.\n"
}
}
},
"csv column arguments" : {
"title": "CSV column arguments",
"type": "object",
"description": "Parameters for the selection of columns from the CSV file.\nOnly required when your CSV file contains more than 2 columns,\notherwise the first column will be used for the FASTA header\nand the second for the FASTA nucleotide sequences. This default\ncan still be overwritten by using the options below.\n",
"properties": {
"sequence_column": {
"type":
"string",
"description": "Type: `string`. Name of the column containing the sequences",
"help_text": "Type: `string`. Name of the column containing the sequences. Implies \u0027header\u0027.\nCannot be used together with \u0027sequence_column_index\u0027.\n"
}
,
"name_column": {
"type":
"string",
"description": "Type: `string`. Name of the column describing the FASTA headers",
"help_text": "Type: `string`. Name of the column describing the FASTA headers. Implies \u0027header\u0027.\nCannot be used together with \u0027name_column_index\u0027.\n"
}
,
"sequence_column_index": {
"type":
"integer",
"description": "Type: `integer`. Index of the column to use as the FASTA sequences, counter from the left and\nstarting from 0",
"help_text": "Type: `integer`. Index of the column to use as the FASTA sequences, counter from the left and\nstarting from 0. Cannot be used in combination with the \u0027sequence_column\u0027 argument.\n"
}
,
"name_column_index": {
"type":
"integer",
"description": "Type: `integer`. Index of the column to use as the FASTA headers, counter from the left and\nstarting from 0",
"help_text": "Type: `integer`. Index of the column to use as the FASTA headers, counter from the left and\nstarting from 0. Cannot be used in combination with \u0027name_column\u0027.\n"
}
}
},
"nextflow input-output arguments" : {
"title": "Nextflow input-output arguments",
"type": "object",
"description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.",
"properties": {
"publish_dir": {
"type":
"string",
"description": "Type: `string`, required, example: `output/`. Path to an output directory",
"help_text": "Type: `string`, required, example: `output/`. Path to an output directory."
}
,
"param_list": {
"type":
"string",
"description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel",
"help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/inputs"
},
{
"$ref": "#/definitions/outputs"
},
{
"$ref": "#/definitions/csv dialect options"
},
{
"$ref": "#/definitions/csv column arguments"
},
{
"$ref": "#/definitions/nextflow input-output arguments"
}
]
}

View File

@@ -0,0 +1,173 @@
name: "untar"
version: "main"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--input"
description: "Tarball file to be unpacked."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output arguments"
arguments:
- type: "file"
name: "--output"
description: "Directory to write the contents of the .tar file to."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Other arguments"
arguments:
- type: "string"
name: "--exclude"
alternatives:
- "-e"
description: "Prevents any file or member whose name matches the shell wildcard\
\ (pattern) from being extracted."
info: null
example:
- "docs/figures"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Unpack a .tar file. When the contents of the .tar file is just a single\
\ directory,\nput the contents of the directory into the output folder instead of\
\ that directory.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/craftbox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/untar/config.vsh.yaml"
runner: "nextflow"
engine: "docker|native"
output: "target/nextflow/untar"
executable: "target/nextflow/untar/main.nf"
viash_version: "0.9.0-RC6"
git_commit: "781f66883977e37a849f228ee1dffddbb7acdf32"
git_remote: "https://github.com/viash-hub/craftbox"
package_config:
name: "craftbox"
version: "main"
description: "A collection of custom-tailored scripts and applied tools.\n"
info: null
viash_version: "0.9.0-RC6"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "scripts"
- "custom"
- "implementations"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/craftbox"
issue_tracker: "https://github.com/viash-hub/craftbox/issues"

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,125 @@
manifest {
name = 'untar'
mainScript = 'main.nf'
nextflowVersion = '!>=20.12.1-edge'
version = 'main'
description = 'Unpack a .tar file. When the contents of the .tar file is just a single directory,\nput the contents of the directory into the output folder instead of that directory.\n'
}
process.container = 'nextflow/bash:latest'
// detect tempdir
tempDir = java.nio.file.Paths.get(
System.getenv('NXF_TEMP') ?:
System.getenv('VIASH_TEMP') ?:
System.getenv('TEMPDIR') ?:
System.getenv('TMPDIR') ?:
'/tmp'
).toAbsolutePath()
profiles {
no_publish {
process {
withName: '.*' {
publishDir = [
enabled: false
]
}
}
}
mount_temp {
docker.temp = tempDir
podman.temp = tempDir
charliecloud.temp = tempDir
}
docker {
docker.enabled = true
// docker.userEmulation = true
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
singularity {
singularity.enabled = true
singularity.autoMounts = true
docker.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
podman {
podman.enabled = true
docker.enabled = false
singularity.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
shifter {
shifter.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
charliecloud.enabled = false
}
charliecloud {
charliecloud.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
}
}
process{
withLabel: mem1gb { memory = 1000000000.B }
withLabel: mem2gb { memory = 2000000000.B }
withLabel: mem5gb { memory = 5000000000.B }
withLabel: mem10gb { memory = 10000000000.B }
withLabel: mem20gb { memory = 20000000000.B }
withLabel: mem50gb { memory = 50000000000.B }
withLabel: mem100gb { memory = 100000000000.B }
withLabel: mem200gb { memory = 200000000000.B }
withLabel: mem500gb { memory = 500000000000.B }
withLabel: mem1tb { memory = 1000000000000.B }
withLabel: mem2tb { memory = 2000000000000.B }
withLabel: mem5tb { memory = 5000000000000.B }
withLabel: mem10tb { memory = 10000000000000.B }
withLabel: mem20tb { memory = 20000000000000.B }
withLabel: mem50tb { memory = 50000000000000.B }
withLabel: mem100tb { memory = 100000000000000.B }
withLabel: mem200tb { memory = 200000000000000.B }
withLabel: mem500tb { memory = 500000000000000.B }
withLabel: mem1gib { memory = 1073741824.B }
withLabel: mem2gib { memory = 2147483648.B }
withLabel: mem4gib { memory = 4294967296.B }
withLabel: mem8gib { memory = 8589934592.B }
withLabel: mem16gib { memory = 17179869184.B }
withLabel: mem32gib { memory = 34359738368.B }
withLabel: mem64gib { memory = 68719476736.B }
withLabel: mem128gib { memory = 137438953472.B }
withLabel: mem256gib { memory = 274877906944.B }
withLabel: mem512gib { memory = 549755813888.B }
withLabel: mem1tib { memory = 1099511627776.B }
withLabel: mem2tib { memory = 2199023255552.B }
withLabel: mem4tib { memory = 4398046511104.B }
withLabel: mem8tib { memory = 8796093022208.B }
withLabel: mem16tib { memory = 17592186044416.B }
withLabel: mem32tib { memory = 35184372088832.B }
withLabel: mem64tib { memory = 70368744177664.B }
withLabel: mem128tib { memory = 140737488355328.B }
withLabel: mem256tib { memory = 281474976710656.B }
withLabel: mem512tib { memory = 562949953421312.B }
withLabel: cpu1 { cpus = 1 }
withLabel: cpu2 { cpus = 2 }
withLabel: cpu5 { cpus = 5 }
withLabel: cpu10 { cpus = 10 }
withLabel: cpu20 { cpus = 20 }
withLabel: cpu50 { cpus = 50 }
withLabel: cpu100 { cpus = 100 }
withLabel: cpu200 { cpus = 200 }
withLabel: cpu500 { cpus = 500 }
withLabel: cpu1000 { cpus = 1000 }
}

View File

@@ -0,0 +1,119 @@
{
"$schema": "http://json-schema.org/draft-07/schema",
"title": "untar",
"description": "Unpack a .tar file. When the contents of the .tar file is just a single directory,\nput the contents of the directory into the output folder instead of that directory.\n",
"type": "object",
"definitions": {
"input arguments" : {
"title": "Input arguments",
"type": "object",
"description": "No description",
"properties": {
"input": {
"type":
"string",
"description": "Type: `file`, required. Tarball file to be unpacked",
"help_text": "Type: `file`, required. Tarball file to be unpacked."
}
}
},
"output arguments" : {
"title": "Output arguments",
"type": "object",
"description": "No description",
"properties": {
"output": {
"type":
"string",
"description": "Type: `file`, required, default: `$id.$key.output.output`. Directory to write the contents of the ",
"help_text": "Type: `file`, required, default: `$id.$key.output.output`. Directory to write the contents of the .tar file to."
,
"default": "$id.$key.output.output"
}
}
},
"other arguments" : {
"title": "Other arguments",
"type": "object",
"description": "No description",
"properties": {
"exclude": {
"type":
"string",
"description": "Type: `string`, example: `docs/figures`. Prevents any file or member whose name matches the shell wildcard (pattern) from being extracted",
"help_text": "Type: `string`, example: `docs/figures`. Prevents any file or member whose name matches the shell wildcard (pattern) from being extracted."
}
}
},
"nextflow input-output arguments" : {
"title": "Nextflow input-output arguments",
"type": "object",
"description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.",
"properties": {
"publish_dir": {
"type":
"string",
"description": "Type: `string`, required, example: `output/`. Path to an output directory",
"help_text": "Type: `string`, required, example: `output/`. Path to an output directory."
}
,
"param_list": {
"type":
"string",
"description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel",
"help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input arguments"
},
{
"$ref": "#/definitions/output arguments"
},
{
"$ref": "#/definitions/other arguments"
},
{
"$ref": "#/definitions/nextflow input-output arguments"
}
]
}