CI
a0733101ff
Build pipeline: viash-hub.craftbox.main-5sjkz
Source commit: 781f668839
Source message: FEAT: add untar (#3)
* FEAT: add untar
* Use meta_executable
195 lines
7.8 KiB
JSON
195 lines
7.8 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema",
|
|
"title": "csv2fasta",
|
|
"description": "Convert two columns from a CSV file to FASTA entries. The CSV file can\ncontain an optional header and each row (other than the header) becomes\na single FASTA record. One of the two columns will be used as the names\nfor the FASTA entries, while the other become the sequences. The sequences\ncolumn must only contain characters that are valid IUPAC notation for \nnucleotides or a group thereof (wildcard characters).\n",
|
|
"type": "object",
|
|
"definitions": {
|
|
|
|
|
|
|
|
"inputs" : {
|
|
"title": "Inputs",
|
|
"type": "object",
|
|
"description": "No description",
|
|
"properties": {
|
|
|
|
|
|
"input": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, required, example: `barcodes.csv`. CSV file to be processed",
|
|
"help_text": "Type: `file`, required, example: `barcodes.csv`. CSV file to be processed."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"header": {
|
|
"type":
|
|
"boolean",
|
|
"description": "Type: `boolean_true`, default: `false`. Parse the first line of the CSV file as a header",
|
|
"help_text": "Type: `boolean_true`, default: `false`. Parse the first line of the CSV file as a header.\n"
|
|
,
|
|
"default": "False"
|
|
}
|
|
|
|
|
|
}
|
|
},
|
|
|
|
|
|
"outputs" : {
|
|
"title": "Outputs",
|
|
"type": "object",
|
|
"description": "No description",
|
|
"properties": {
|
|
|
|
|
|
"output": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, default: `$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"
|
|
}
|
|
]
|
|
}
|