From ef4cabdceee524f3a2dc6efe91977cc22704c80b Mon Sep 17 00:00:00 2001 From: CI Date: Fri, 25 Jul 2025 08:53:08 +0000 Subject: [PATCH] Build branch main with version main (a3b7ae3) Build pipeline: viash-hub.htrnaseq.main-fmznz Source commit: https://github.com/viash-hub/htrnaseq/commit/a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957 Source message: update biobox and craftbox versions (#60) * update biobox and craftbox versions * update changelog --- CHANGELOG.md | 4 + src/workflows/htrnaseq/config.vsh.yaml | 2 +- .../well_demultiplex/config.vsh.yaml | 4 +- .../nextflow/cutadapt/.config.vsh.yaml | 34 +- .../nextflow/cutadapt/main.nf | 486 ++- .../nextflow/cutadapt/nextflow.config | 2 +- .../nextflow/cutadapt/nextflow_schema.json | 0 .../nextflow/concat_text/.config.vsh.yaml | 216 + .../v0.2.0/nextflow/concat_text/main.nf | 3868 +++++++++++++++++ .../nextflow/concat_text/nextflow.config | 126 + .../nextflow/concat_text/nextflow_schema.json | 106 + .../eset/create_eset/.config.vsh.yaml | 4 +- .../executable/eset/create_eset/create_eset | 4 +- .../eset/create_fdata/.config.vsh.yaml | 4 +- .../executable/eset/create_fdata/create_fdata | 4 +- .../eset/create_pdata/.config.vsh.yaml | 4 +- .../executable/eset/create_pdata/create_pdata | 4 +- .../htrnaseq/check_eset/.config.vsh.yaml | 4 +- .../htrnaseq/check_eset/check_eset | 4 +- .../check_cutadapt_output/.config.vsh.yaml | 4 +- .../check_cutadapt_output | 4 +- .../io/publish_fastqs/.config.vsh.yaml | 4 +- .../io/publish_fastqs/publish_fastqs | 4 +- .../io/publish_results/.config.vsh.yaml | 4 +- .../io/publish_results/publish_results | 4 +- .../executable/parallel_map/.config.vsh.yaml | 4 +- target/executable/parallel_map/parallel_map | 4 +- .../report/create_report/.config.vsh.yaml | 4 +- .../report/create_report/create_report | 4 +- .../stats/combine_star_logs/.config.vsh.yaml | 4 +- .../stats/combine_star_logs/combine_star_logs | 4 +- .../generate_pool_statistics/.config.vsh.yaml | 4 +- .../generate_pool_statistics | 4 +- .../generate_well_statistics/.config.vsh.yaml | 4 +- .../generate_well_statistics | 4 +- .../utils/save_params/.config.vsh.yaml | 4 +- .../executable/utils/save_params/save_params | 4 +- .../eset/create_eset/.config.vsh.yaml | 4 +- target/nextflow/eset/create_eset/main.nf | 4 +- .../eset/create_eset/nextflow_schema.json | 174 +- .../eset/create_fdata/.config.vsh.yaml | 4 +- target/nextflow/eset/create_fdata/main.nf | 4 +- .../eset/create_fdata/nextflow_schema.json | 122 +- .../eset/create_pdata/.config.vsh.yaml | 4 +- target/nextflow/eset/create_pdata/main.nf | 4 +- .../eset/create_pdata/nextflow_schema.json | 139 +- .../htrnaseq/check_eset/.config.vsh.yaml | 4 +- .../htrnaseq/check_eset/main.nf | 4 +- .../htrnaseq/check_eset/nextflow_schema.json | 124 +- .../check_cutadapt_output/.config.vsh.yaml | 4 +- .../check_cutadapt_output/main.nf | 4 +- .../nextflow_schema.json | 145 +- .../io/publish_fastqs/.config.vsh.yaml | 4 +- target/nextflow/io/publish_fastqs/main.nf | 4 +- .../io/publish_fastqs/nextflow_schema.json | 147 +- .../io/publish_results/.config.vsh.yaml | 4 +- target/nextflow/io/publish_results/main.nf | 4 +- .../io/publish_results/nextflow_schema.json | 281 +- target/nextflow/parallel_map/.config.vsh.yaml | 4 +- target/nextflow/parallel_map/main.nf | 4 +- .../parallel_map/nextflow_schema.json | 317 +- .../report/create_report/.config.vsh.yaml | 4 +- target/nextflow/report/create_report/main.nf | 4 +- .../report/create_report/nextflow_schema.json | 125 +- .../stats/combine_star_logs/.config.vsh.yaml | 4 +- .../nextflow/stats/combine_star_logs/main.nf | 4 +- .../combine_star_logs/nextflow_schema.json | 183 +- .../generate_pool_statistics/.config.vsh.yaml | 4 +- .../stats/generate_pool_statistics/main.nf | 4 +- .../nextflow_schema.json | 82 - .../generate_well_statistics/.config.vsh.yaml | 4 +- .../stats/generate_well_statistics/main.nf | 4 +- .../nextflow_schema.json | 222 +- .../utils/concatRuns/.config.vsh.yaml | 4 +- target/nextflow/utils/concatRuns/main.nf | 4 +- .../utils/concatRuns/nextflow_schema.json | 184 +- .../utils/listInputDir/.config.vsh.yaml | 4 +- target/nextflow/utils/listInputDir/main.nf | 4 +- .../utils/listInputDir/nextflow_schema.json | 207 +- .../utils/save_params/.config.vsh.yaml | 4 +- target/nextflow/utils/save_params/main.nf | 4 +- .../utils/save_params/nextflow_schema.json | 157 +- .../workflows/htrnaseq/.config.vsh.yaml | 6 +- target/nextflow/workflows/htrnaseq/main.nf | 6 +- .../workflows/htrnaseq/nextflow_schema.json | 404 +- .../workflows/runner/.config.vsh.yaml | 4 +- target/nextflow/workflows/runner/main.nf | 4 +- .../workflows/runner/nextflow_schema.json | 370 +- .../well_demultiplex/.config.vsh.yaml | 16 +- .../workflows/well_demultiplex/main.nf | 16 +- .../well_demultiplex/nextflow_schema.json | 212 +- .../workflows/well_metadata/.config.vsh.yaml | 4 +- .../nextflow/workflows/well_metadata/main.nf | 4 +- .../well_metadata/nextflow_schema.json | 300 +- 94 files changed, 6367 insertions(+), 2660 deletions(-) rename target/dependencies/vsh/vsh/biobox/{v0.3.0 => v0.3.1}/nextflow/cutadapt/.config.vsh.yaml (94%) rename target/dependencies/vsh/vsh/biobox/{v0.3.0 => v0.3.1}/nextflow/cutadapt/main.nf (91%) rename target/dependencies/vsh/vsh/biobox/{v0.3.0 => v0.3.1}/nextflow/cutadapt/nextflow.config (99%) rename target/dependencies/vsh/vsh/biobox/{v0.3.0 => v0.3.1}/nextflow/cutadapt/nextflow_schema.json (100%) create mode 100644 target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/.config.vsh.yaml create mode 100644 target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/main.nf create mode 100644 target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow.config create mode 100644 target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow_schema.json diff --git a/CHANGELOG.md b/CHANGELOG.md index 92cf11cf..753790c4 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,6 +8,10 @@ * Moved the test resources to their new location (PR #47). +## Minor changes + +* Bump `biobox` and `craftbox` dependencies to versions `0.3.1` and `0.2.0`, respectively (PR #60). + # htrnaseq v0.8.0 ## New functionality diff --git a/src/workflows/htrnaseq/config.vsh.yaml b/src/workflows/htrnaseq/config.vsh.yaml index 3340f328..cfba9f55 100644 --- a/src/workflows/htrnaseq/config.vsh.yaml +++ b/src/workflows/htrnaseq/config.vsh.yaml @@ -135,7 +135,7 @@ repositories: - name: bb type: vsh repo: biobox - tag: v0.1.0 + tag: v0.3.1 runners: - type: nextflow diff --git a/src/workflows/well_demultiplex/config.vsh.yaml b/src/workflows/well_demultiplex/config.vsh.yaml index 4873d848..bec78d8a 100644 --- a/src/workflows/well_demultiplex/config.vsh.yaml +++ b/src/workflows/well_demultiplex/config.vsh.yaml @@ -65,11 +65,11 @@ repositories: - name: bb type: vsh repo: biobox - tag: v0.3.0 + tag: v0.3.1 - name: cb type: vsh repo: craftbox - tag: v0.1.0 + tag: v0.2.0 runners: - type: nextflow diff --git a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/.config.vsh.yaml similarity index 94% rename from target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/.config.vsh.yaml index 793bdbbc..91567579 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/.config.vsh.yaml @@ -1,5 +1,5 @@ name: "cutadapt" -version: "v0.3.0" +version: "v0.3.1" authors: - name: "Toni Verbeiren" roles: @@ -633,6 +633,9 @@ test_resources: is_executable: true info: null status: "enabled" +scope: + image: "public" + target: "public" requirements: commands: - "ps" @@ -718,7 +721,7 @@ engines: id: "docker" image: "python:3.12" target_registry: "images.viash-hub.com" - target_tag: "v0.3.0" + target_tag: "v0.3.1" namespace_separator: "/" setup: - type: "python" @@ -739,23 +742,34 @@ build_info: engine: "docker|native" output: "target/nextflow/cutadapt" executable: "target/nextflow/cutadapt/main.nf" - viash_version: "0.9.0" - git_commit: "d86bd5cf62104af02caa852aacd352b1aa97ed60" - git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" - git_tag: "v0.2.0-29-gd86bd5c" + viash_version: "0.9.4" + git_commit: "98a5f3cc745525a65c10263d25cf414eb1093223" + git_remote: "https://github.com/viash-hub/biobox" + git_tag: "v0.3.0-8-g98a5f3c" package_config: name: "biobox" - version: "v0.3.0" - description: "A collection of bioinformatics tools for working with sequence data.\n" + version: "v0.3.1" + summary: "A curated collection of high-quality, standalone bioinformatics components\ + \ built with [Viash](https://viash.io).\n" + description: "`biobox` offers a suite of reliable bioinformatics components, similar\ + \ to [nf-core/modules](https://github.com/nf-core/modules) and [snakemake-wrappers/bio](https://github.com/snakemake/snakemake-wrappers/tree/master/bio),\ + \ but built using the [Viash](https://viash.io) framework.\n\nThis approach emphasizes\ + \ **reusability**, **reproducibility**, and adherence to **best practices**. Key\ + \ features of `biobox` components include:\n\n* **Standalone & Nextflow Ready:**\ + \ Run components directly via the command line or seamlessly integrate them into\ + \ Nextflow workflows.\n* **High Quality Standards:**\n * Comprehensive documentation\ + \ for components and parameters.\n * Full exposure of underlying tool arguments.\n\ + \ * Containerized (Docker) for dependency management and reproducibility.\n\ + \ * Unit tested for verified functionality.\n" info: null - viash_version: "0.9.0" + viash_version: "0.9.4" 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 := 'v0.3.0'" + - ".engines[.type == 'docker'].target_tag := 'v0.3.1'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/main.nf b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/main.nf similarity index 91% rename from target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/main.nf rename to target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/main.nf index 4e413804..949e4972 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/main.nf +++ b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/main.nf @@ -1,6 +1,6 @@ -// cutadapt v0.3.0 +// cutadapt v0.3.1 // -// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data // Intuitive. // @@ -85,64 +85,56 @@ def _checkArgumentType(String stage, Map par, Object value, String errorIdentifi foundClass = "List[${e.foundClass}]" } } else if (par.type == "string") { - // cast to string if need be + // cast to string if need be. only cast if the value is a GString if (value instanceof GString) { - value = value.toString() + value = value as String } expectedClass = value instanceof String ? null : "String" } else if (par.type == "integer") { // cast to integer if need be - if (value instanceof String) { + if (value !instanceof Integer) { try { - value = value.toInteger() + value = value as Integer } catch (NumberFormatException e) { - // do nothing + expectedClass = "Integer" } } - if (value instanceof java.math.BigInteger) { - value = value.intValue() - } - expectedClass = value instanceof Integer ? null : "Integer" } else if (par.type == "long") { // cast to long if need be - if (value instanceof String) { + if (value !instanceof Long) { try { - value = value.toLong() + value = value as Long } catch (NumberFormatException e) { - // do nothing + expectedClass = "Long" } } - if (value instanceof Integer) { - value = value.toLong() - } - expectedClass = value instanceof Long ? null : "Long" } else if (par.type == "double") { // cast to double if need be - if (value instanceof String) { + if (value !instanceof Double) { try { - value = value.toDouble() + value = value as Double } catch (NumberFormatException e) { - // do nothing + expectedClass = "Double" } } - if (value instanceof java.math.BigDecimal) { - value = value.doubleValue() + } else if (par.type == "float") { + // cast to float if need be + if (value !instanceof Float) { + try { + value = value as Float + } catch (NumberFormatException e) { + expectedClass = "Float" + } } - if (value instanceof Float) { - value = value.toDouble() - } - expectedClass = value instanceof Double ? null : "Double" } else if (par.type == "boolean" | par.type == "boolean_true" | par.type == "boolean_false") { // cast to boolean if need be - if (value instanceof String) { - def valueLower = value.toLowerCase() - if (valueLower == "true") { - value = true - } else if (valueLower == "false") { - value = false + if (value !instanceof Boolean) { + try { + value = value as Boolean + } catch (Exception e) { + expectedClass = "Boolean" } } - expectedClass = value instanceof Boolean ? null : "Boolean" } else if (par.type == "file" && (par.direction == "input" || stage == "output")) { // cast to path if need be if (value instanceof String) { @@ -154,10 +146,13 @@ def _checkArgumentType(String stage, Map par, Object value, String errorIdentifi expectedClass = value instanceof Path ? null : "Path" } else if (par.type == "file" && stage == "input" && par.direction == "output") { // cast to string if need be - if (value instanceof GString) { - value = value.toString() + if (value !instanceof String) { + try { + value = value as String + } catch (Exception e) { + expectedClass = "String" + } } - expectedClass = value instanceof String ? null : "String" } else { // didn't find a match for par.type expectedClass = par.type @@ -176,7 +171,7 @@ def _checkArgumentType(String stage, Map par, Object value, String errorIdentifi Map _processInputValues(Map inputs, Map config, String id, String key) { if (!workflow.stubRun) { config.allArguments.each { arg -> - if (arg.required) { + if (arg.required && arg.direction == "input") { assert inputs.containsKey(arg.plainName) && inputs.get(arg.plainName) != null : "Error in module '${key}' id '${id}': required input argument '${arg.plainName}' is missing" } @@ -195,15 +190,8 @@ Map _processInputValues(Map inputs, Map config, String id, String key) { } // helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processOutputValues.nf' -Map _processOutputValues(Map outputs, Map config, String id, String key) { +Map _checkValidOutputArgument(Map outputs, Map config, String id, String key) { if (!workflow.stubRun) { - config.allArguments.each { arg -> - if (arg.direction == "output" && arg.required) { - assert outputs.containsKey(arg.plainName) && outputs.get(arg.plainName) != null : - "Error in module '${key}' id '${id}': required output argument '${arg.plainName}' is missing" - } - } - outputs = outputs.collectEntries { name, value -> def par = config.allArguments.find { it.plainName == name && it.direction == "output" } assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid output argument" @@ -216,6 +204,16 @@ Map _processOutputValues(Map outputs, Map config, String id, String key) { return outputs } +void _checkAllRequiredOuputsPresent(Map outputs, Map config, String id, String key) { + if (!workflow.stubRun) { + config.allArguments.each { arg -> + if (arg.direction == "output" && arg.required) { + assert outputs.containsKey(arg.plainName) && outputs.get(arg.plainName) != null : + "Error in module '${key}' id '${id}': required output argument '${arg.plainName}' is missing" + } + } + } +} // helper file: 'src/main/resources/io/viash/runners/nextflow/channel/IDChecker.nf' class IDChecker { final def items = [] as Set @@ -1669,6 +1667,162 @@ def joinStates(Closure apply_) { } return joinStatesWf } +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishFiles.nf' +def publishFiles(Map args) { + def key_ = args.get("key") + + assert key_ != null : "publishFiles: key must be specified" + + workflow publishFilesWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] + + // the input files and the target output filenames + def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() + def inputFiles_ = inputoutputFilenames_[0] + def outputFilenames_ = inputoutputFilenames_[1] + + [id_, inputFiles_, outputFilenames_] + } + | publishFilesProc + emit: input_ch + } + return publishFilesWf +} + +process publishFilesProc { + // todo: check publishpath? + publishDir path: "${getPublishDir()}/", mode: "copy" + tag "$id" + input: + tuple val(id), path(inputFiles, stageAs: "_inputfile?/*"), val(outputFiles) + output: + tuple val(id), path{outputFiles} + script: + def copyCommands = [ + inputFiles instanceof List ? inputFiles : [inputFiles], + outputFiles instanceof List ? outputFiles : [outputFiles] + ] + .transpose() + .collectMany{infile, outfile -> + if (infile.toString() != outfile.toString()) { + [ + "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"", + "cp -r '${infile.toString()}' '${outfile.toString()}'" + ] + } else { + // no need to copy if infile is the same as outfile + [] + } + } + """ + echo "Copying output files to destination folder" + ${copyCommands.join("\n ")} + """ +} + + +// this assumes that the state contains no other values other than those specified in the config +def publishFilesByConfig(Map args) { + def config = args.get("config") + assert config != null : "publishFilesByConfig: config must be specified" + + def key_ = args.get("key", config.name) + assert key_ != null : "publishFilesByConfig: key must be specified" + + workflow publishFilesSimpleWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] // e.g. [output: new File("myoutput.h5ad"), k: 10] + def origState_ = tup[2] // e.g. [output: '$id.$key.foo.h5ad'] + + + // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where + // - key is a String + // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) + // - inputPath is a List[Path] + // - outputFilename is a List[String] + // - (inputPath, outputFilename) are the files that will be copied from src to dest (relative to the state.yaml) + def processedState = + config.allArguments + .findAll { it.direction == "output" } + .collectMany { par -> + def plainName_ = par.plainName + // if the state does not contain the key, it's an + // optional argument for which the component did + // not generate any output OR multiple channels were emitted + // and the output was just not added to using the channel + // that is now being parsed + if (!state_.containsKey(plainName_)) { + return [] + } + def value = state_[plainName_] + // if the parameter is not a file, it should be stored + // in the state as-is, but is not something that needs + // to be copied from the source path to the dest path + if (par.type != "file") { + return [[inputPath: [], outputFilename: []]] + } + // if the orig state does not contain this filename, + // it's an optional argument for which the user specified + // that it should not be returned as a state + if (!origState_.containsKey(plainName_)) { + return [] + } + def filenameTemplate = origState_[plainName_] + // if the pararameter is multiple: true, fetch the template + if (par.multiple && filenameTemplate instanceof List) { + filenameTemplate = filenameTemplate[0] + } + // instantiate the template + def filename = filenameTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + if (par.multiple) { + // if the parameter is multiple: true, the filename + // should contain a wildcard '*' that is replaced with + // the index of the file + assert filename.contains("*") : "Module '${key_}' id '${id_}': Multiple output files specified, but no wildcard '*' in the filename: ${filename}" + def outputPerFile = value.withIndex().collect{ val, ix -> + def filename_ix = filename.replace("*", ix.toString()) + def inputPath = val instanceof File ? val.toPath() : val + [inputPath: inputPath, outputFilename: filename_ix] + } + def transposedOutputs = ["inputPath", "outputFilename"].collectEntries{ key -> + [key, outputPerFile.collect{dic -> dic[key]}] + } + return [[key: plainName_] + transposedOutputs] + } else { + def value_ = java.nio.file.Paths.get(filename) + def inputPath = value instanceof File ? value.toPath() : value + return [[inputPath: [inputPath], outputFilename: [filename]]] + } + } + + def inputPaths = processedState.collectMany{it.inputPath} + def outputFilenames = processedState.collectMany{it.outputFilename} + + + [id_, inputPaths, outputFilenames] + } + | publishFilesProc + emit: input_ch + } + return publishFilesSimpleWf +} + + + + // helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishStates.nf' def collectFiles(obj) { if (obj instanceof java.io.File || obj instanceof Path) { @@ -1726,8 +1880,6 @@ def publishStates(Map args) { // the input files and the target output filenames def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() - def inputFiles_ = inputoutputFilenames_[0] - def outputFilenames_ = inputoutputFilenames_[1] def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) @@ -1740,7 +1892,7 @@ def publishStates(Map args) { // convert state to yaml blob def yamlBlob_ = toRelativeTaggedYamlBlob([id: id_] + state_, java.nio.file.Paths.get(yamlFilename)) - [id_, yamlBlob_, yamlFilename, inputFiles_, outputFilenames_] + [id_, yamlBlob_, yamlFilename] } | publishStatesProc emit: input_ch @@ -1752,33 +1904,17 @@ process publishStatesProc { publishDir path: "${getPublishDir()}/", mode: "copy" tag "$id" input: - tuple val(id), val(yamlBlob), val(yamlFile), path(inputFiles, stageAs: "_inputfile?/*"), val(outputFiles) + tuple val(id), val(yamlBlob), val(yamlFile) output: - tuple val(id), path{[yamlFile] + outputFiles} + tuple val(id), path{[yamlFile]} script: - def copyCommands = [ - inputFiles instanceof List ? inputFiles : [inputFiles], - outputFiles instanceof List ? outputFiles : [outputFiles] - ] - .transpose() - .collectMany{infile, outfile -> - if (infile.toString() != outfile.toString()) { - [ - "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"", - "cp -r '${infile.toString()}' '${outfile.toString()}'" - ] - } else { - // no need to copy if infile is the same as outfile - [] - } - } """ -mkdir -p "\$(dirname '${yamlFile}')" -echo "Storing state as yaml" -echo '${yamlBlob}' > '${yamlFile}' -echo "Copying output files to destination folder" -${copyCommands.join("\n ")} -""" + mkdir -p "\$(dirname '${yamlFile}')" + echo "Storing state as yaml" + cat > '${yamlFile}' << HERE +${yamlBlob} +HERE + """ } @@ -1809,13 +1945,10 @@ def publishStatesByConfig(Map args) { .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() - // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where + // the processed state is a list of [key, value] tuples, where // - key is a String // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) - // - inputPath is a List[Path] - // - outputFilename is a List[String] // - (key, value) are the tuples that will be saved to the state.yaml file - // - (inputPath, outputFilename) are the files that will be copied from src to dest (relative to the state.yaml) def processedState = config.allArguments .findAll { it.direction == "output" } @@ -1832,7 +1965,7 @@ def publishStatesByConfig(Map args) { // in the state as-is, but is not something that needs // to be copied from the source path to the dest path if (par.type != "file") { - return [[key: plainName_, value: value, inputPath: [], outputFilename: []]] + return [[key: plainName_, value: value]] } // if the orig state does not contain this filename, // it's an optional argument for which the user specified @@ -1863,13 +1996,9 @@ def publishStatesByConfig(Map args) { if (yamlDir != null) { value_ = yamlDir.relativize(value_) } - def inputPath = val instanceof File ? val.toPath() : val - [value: value_, inputPath: inputPath, outputFilename: filename_ix] + return value_ } - def transposedOutputs = ["value", "inputPath", "outputFilename"].collectEntries{ key -> - [key, outputPerFile.collect{dic -> dic[key]}] - } - return [[key: plainName_] + transposedOutputs] + return [["key": plainName_, "value": outputPerFile]] } else { def value_ = java.nio.file.Paths.get(filename) // if id contains a slash @@ -1877,18 +2006,17 @@ def publishStatesByConfig(Map args) { value_ = yamlDir.relativize(value_) } def inputPath = value instanceof File ? value.toPath() : value - return [[key: plainName_, value: value_, inputPath: [inputPath], outputFilename: [filename]]] + return [["key": plainName_, value: value_]] } } + def updatedState_ = processedState.collectEntries{[it.key, it.value]} - def inputPaths = processedState.collectMany{it.inputPath} - def outputFilenames = processedState.collectMany{it.outputFilename} // convert state to yaml blob def yamlBlob_ = toTaggedYamlBlob([id: id_] + updatedState_) - [id_, yamlBlob_, yamlFilename, inputPaths, outputFilenames] + [id_, yamlBlob_, yamlFilename] } | publishStatesProc emit: input_ch @@ -2562,7 +2690,8 @@ def _debug(workflowArgs, debugKey) { def workflowFactory(Map args, Map defaultWfArgs, Map meta) { def workflowArgs = processWorkflowArgs(args, defaultWfArgs, meta) def key_ = workflowArgs["key"] - + def multipleArgs = meta.config.allArguments.findAll{ it.multiple }.collect{it.plainName} + workflow workflowInstance { take: input_ @@ -2719,12 +2848,36 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { } // TODO: move some of the _meta.join_id wrangling to the safeJoin() function. - def chInitialOutput = chArgsWithDefaults + def chInitialOutputMulti = chArgsWithDefaults | _debug(workflowArgs, "processed") // run workflow | innerWorkflowFactory(workflowArgs) - // check output tuple - | map { id_, output_ -> + def chInitialOutputList = chInitialOutputMulti instanceof List ? chInitialOutputMulti : [chInitialOutputMulti] + assert chInitialOutputList.size() > 0: "should have emitted at least one output channel" + // Add a channel ID to the events, which designates the channel the event was emitted from as a running number + // This number is used to sort the events later when the events are gathered from across the channels. + def chInitialOutputListWithIndexedEvents = chInitialOutputList.withIndex().collect{channel, channelIndex -> + def newChannel = channel + | map {tuple -> + assert tuple instanceof List : + "Error in module '${key_}': element in output channel should be a tuple [id, data, ...otherargs...]\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: List. Found: tuple.getClass() is ${tuple.getClass()}" + + def newEvent = [channelIndex] + tuple + return newEvent + } + return newChannel + } + // Put the events into 1 channel, cover case where there is only one channel is emitted + def chInitialOutput = chInitialOutputList.size() > 1 ? \ + chInitialOutputListWithIndexedEvents[0].mix(*chInitialOutputListWithIndexedEvents.tail()) : \ + chInitialOutputListWithIndexedEvents[0] + def chInitialOutputProcessed = chInitialOutput + | map { tuple -> + def channelId = tuple[0] + def id_ = tuple[1] + def output_ = tuple[2] // see if output map contains metadata def meta_ = @@ -2737,19 +2890,94 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { output_ = output_.findAll{k, v -> k != "_meta"} // check value types - output_ = _processOutputValues(output_, meta.config, id_, key_) + output_ = _checkValidOutputArgument(output_, meta.config, id_, key_) - // simplify output if need be - if (workflowArgs.auto.simplifyOutput && output_.size() == 1) { - output_ = output_.values()[0] - } - - [join_id, id_, output_] + [join_id, channelId, id_, output_] } // | view{"chInitialOutput: ${it.take(3)}"} + // join the output [prev_id, channel_id, new_id, output] with the previous state [prev_id, state, ...] + def chPublishWithPreviousState = safeJoin(chInitialOutputProcessed, chRunFiltered, key_) + // input tuple format: [join_id, channel_id, id, output, prev_state, ...] + // output tuple format: [join_id, channel_id, id, new_state, ...] + | map{ tup -> + def new_state = workflowArgs.toState(tup.drop(2).take(3)) + tup.take(3) + [new_state] + tup.drop(5) + } + if (workflowArgs.auto.publish == "state") { + def chPublishFiles = chPublishWithPreviousState + // input tuple format: [join_id, channel_id, id, new_state, ...] + // output tuple format: [join_id, channel_id, id, new_state] + | map{ tup -> + tup.take(4) + } + + safeJoin(chPublishFiles, chArgsWithDefaults, key_) + // input tuple format: [join_id, channel_id, id, new_state, orig_state, ...] + // output tuple format: [id, new_state, orig_state] + | map { tup -> + tup.drop(2).take(3) + } + | publishFilesByConfig(key: key_, config: meta.config) + } + // Join the state from the events that were emitted from different channels + def chJoined = chInitialOutputProcessed + | map {tuple -> + def join_id = tuple[0] + def channel_id = tuple[1] + def id = tuple[2] + def other = tuple.drop(3) + // Below, groupTuple is used to join the events. To make sure resuming a workflow + // keeps working, the output state must be deterministic. This means the state needs to be + // sorted with groupTuple's has a 'sort' argument. This argument can be set to 'hash', + // but hashing the state when it is large can be problematic in terms of performance. + // Therefore, a custom comparator function is provided. We add the channel ID to the + // states so that we can use the channel ID to sort the items. + def stateWithChannelID = [[channel_id] * other.size(), other].transpose() + // A comparator that is provided to groupTuple's 'sort' argument is applied + // to all elements of the event tuple (that is not the 'id'). The comparator + // closure that is used below expects the input to be List. So the join_id and + // channel_id must also be wrapped in a list. + [[join_id], [channel_id], id] + stateWithChannelID + } + | groupTuple(by: 2, sort: {a, b -> a[0] <=> b[0]}, size: chInitialOutputList.size(), remainder: true) + | map {join_ids, _, id, statesWithChannelID -> + // Remove the channel IDs from the states + def states = statesWithChannelID.collect{it[1]} + def newJoinId = join_ids.flatten().unique{a, b -> a <=> b} + assert newJoinId.size() == 1: "Multiple events were emitted for '$id'." + def newJoinIdUnique = newJoinId[0] + + // Merge the states from the different channels + def newState = states.inject([:]){ old_state, state_to_add -> + return old_state + state_to_add.collectEntries{k, v -> + if (!multipleArgs.contains(k)) { + // if the key is not a multiple argument, we expect only one value + if (old_state.containsKey(k)) { + assert old_state[k] == v : "ID $id: multiple entries for argument $k were emitted." + } + [k, v] + } else { + // if the key is a multiple argument, append the different values into one list + def prevValue = old_state.getOrDefault(k, []) + def prevValueAsList = prevValue instanceof List ? prevValue : [prevValue] + [k, prevValueAsList + v] + } + } + } + + _checkAllRequiredOuputsPresent(newState, meta.config, id, key_) + + // simplify output if need be + if (workflowArgs.auto.simplifyOutput && newState.size() == 1) { + newState = newState.values()[0] + } + + return [newJoinIdUnique, id, newState] + } + // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) + def chNewState = safeJoin(chJoined, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2758,23 +2986,21 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { } if (workflowArgs.auto.publish == "state") { - def chPublish = chNewState + def chPublishStates = chNewState // input tuple format: [join_id, id, new_state, ...] // output tuple format: [join_id, id, new_state] | map{ tup -> tup.take(3) } - safeJoin(chPublish, chArgsWithDefaults, key_) + safeJoin(chPublishStates, chArgsWithDefaults, key_) // input tuple format: [join_id, id, new_state, orig_state, ...] // output tuple format: [id, new_state, orig_state] | map { tup -> tup.drop(1).take(3) - } + } | publishStatesByConfig(key: key_, config: meta.config) } - - // remove join_id and meta chReturn = chNewState | map { tup -> // input tuple format: [join_id, id, new_state, ...] @@ -2808,7 +3034,7 @@ meta = [ "resources_dir": moduleDir.toRealPath().normalize(), "config": processConfig(readJsonBlob('''{ "name" : "cutadapt", - "version" : "v0.3.0", + "version" : "v0.3.1", "authors" : [ { "name" : "Toni Verbeiren", @@ -3488,6 +3714,10 @@ meta = [ } ], "status" : "enabled", + "scope" : { + "image" : "public", + "target" : "public" + }, "requirements" : { "commands" : [ "ps" @@ -3589,7 +3819,7 @@ meta = [ "id" : "docker", "image" : "python:3.12", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.3.0", + "target_tag" : "v0.3.1", "namespace_separator" : "/", "setup" : [ { @@ -3618,23 +3848,24 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/cutadapt", - "viash_version" : "0.9.0", - "git_commit" : "d86bd5cf62104af02caa852aacd352b1aa97ed60", - "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", - "git_tag" : "v0.2.0-29-gd86bd5c" + "viash_version" : "0.9.4", + "git_commit" : "98a5f3cc745525a65c10263d25cf414eb1093223", + "git_remote" : "https://github.com/viash-hub/biobox", + "git_tag" : "v0.3.0-8-g98a5f3c" }, "package_config" : { "name" : "biobox", - "version" : "v0.3.0", - "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0", + "version" : "v0.3.1", + "summary" : "A curated collection of high-quality, standalone bioinformatics components built with [Viash](https://viash.io).\n", + "description" : "`biobox` offers a suite of reliable bioinformatics components, similar to [nf-core/modules](https://github.com/nf-core/modules) and [snakemake-wrappers/bio](https://github.com/snakemake/snakemake-wrappers/tree/master/bio), but built using the [Viash](https://viash.io) framework.\n\nThis approach emphasizes **reusability**, **reproducibility**, and adherence to **best practices**. Key features of `biobox` components include:\n\n* **Standalone & Nextflow Ready:** Run components directly via the command line or seamlessly integrate them into Nextflow workflows.\n* **High Quality Standards:**\n * Comprehensive documentation for components and parameters.\n * Full exposure of underlying tool arguments.\n * Containerized (Docker) for dependency management and reproducibility.\n * Unit tested for verified functionality.\n", + "viash_version" : "0.9.4", "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 := 'v0.3.0'" + ".engines[.type == 'docker'].target_tag := 'v0.3.1'" ], "keywords" : [ "bioinformatics", @@ -4320,7 +4551,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { // create process from temp file def binding = new nextflow.script.ScriptBinding([:]) def session = nextflow.Nextflow.getSession() - def parser = new nextflow.script.ScriptParser(session) + def parser = _getScriptLoader(session) .setModule(true) .setBinding(binding) def moduleScript = parser.runScript(tempFile) @@ -4334,6 +4565,27 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { return scriptMeta.getProcess(procKey) } +// use Reflection to get a ScriptParser / ScriptLoader +// <25.02.0-edge: new nextflow.script.ScriptParser(session) +// >=25.02.0-edge: nextflow.script.ScriptLoaderFactory.create(session) +def _getScriptLoader(nextflow.Session session) { + // try using the old method + try { + Class scriptParserClass = Class.forName('nextflow.script.ScriptParser') + return scriptParserClass.getDeclaredConstructor(nextflow.Session).newInstance(session) + } catch (ClassNotFoundException e) { + // else try with the new method + try { + Class scriptLoaderFactoryClass = Class.forName('nextflow.script.ScriptLoaderFactory') + def createMethod = scriptLoaderFactoryClass.getDeclaredMethod('create', nextflow.Session) + return createMethod.invoke(null, session) // null because create is static + } catch (ClassNotFoundException | NoSuchMethodException | IllegalAccessException | java.lang.reflect.InvocationTargetException e2) { + // Handle the case where neither class is found + throw new Exception("Neither nextflow.script.ScriptParser nor nextflow.script.ScriptLoaderFactory could be found. Is this a compatible Nextflow version?", e2) + } + } +} + // defaults meta["defaults"] = [ // key to be used to trace the process and determine output names @@ -4347,7 +4599,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/cutadapt", - "tag" : "v0.3.0" + "tag" : "v0.3.1" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/nextflow.config b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/nextflow.config similarity index 99% rename from target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/nextflow.config rename to target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/nextflow.config index 49626c1f..09aff55b 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/nextflow.config @@ -2,7 +2,7 @@ manifest { name = 'cutadapt' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.3.0' + version = 'v0.3.1' description = 'Cutadapt removes adapter sequences from high-throughput sequencing reads.\n' author = 'Toni Verbeiren' } diff --git a/target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/nextflow_schema.json similarity index 100% rename from target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/nextflow_schema.json rename to target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/nextflow_schema.json diff --git a/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/.config.vsh.yaml b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/.config.vsh.yaml new file mode 100644 index 00000000..1e11e7ba --- /dev/null +++ b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/.config.vsh.yaml @@ -0,0 +1,216 @@ +name: "concat_text" +version: "v0.2.0" +authors: +- name: "Toni Verbeiren" + roles: + - "author" + - "maintainer" + info: + links: + github: "tverbeiren" + linkedin: "verbeiren" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist and CEO" +- name: "Dries Schaumont" + roles: + - "reviewer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +argument_groups: +- name: "Input arguments" + arguments: + - type: "file" + name: "--input" + description: "A list of (gzipped) text files." + info: null + example: + - "input?.txt.gz" + must_exist: true + create_parent: true + required: true + direction: "input" + multiple: true + multiple_sep: ";" +- name: "Output arguments" + arguments: + - type: "boolean_true" + name: "--gzip_output" + description: "Should the output be zipped?" + info: null + direction: "input" + - type: "file" + name: "--output" + description: "File to write the output to, optionally gzipped." + info: null + example: + - "output.txt" + must_exist: true + create_parent: true + required: false + direction: "output" + multiple: false + multiple_sep: ";" +resources: +- type: "bash_script" + path: "script.sh" + is_executable: true +summary: "Concatenate a number of text files" +description: "Concatenate a number of text files, handle gzipped text files gracefully\ + \ and\noptionally gzip the output text file.\n\nThis component is useful for concatening\ + \ fastq files from different lanes, for instance.\n" +test_resources: +- type: "bash_script" + path: "test.sh" + is_executable: true +info: + improvements: "This component could be improved in 2 ways:\n 1. Allow for a mix\ + \ of zipped and plain input files\n 2. Allow to specify a compression algorithm\ + \ for the output\n" +status: "enabled" +scope: + image: "public" + target: "public" +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: "alpine:latest" + target_registry: "images.viash-hub.com" + target_tag: "v0.2.0" + namespace_separator: "/" + setup: + - type: "apk" + packages: + - "bash" + - "procps" + - "file" + entrypoint: [] + cmd: null +- type: "native" + id: "native" +build_info: + config: "src/concat_text/config.vsh.yaml" + runner: "nextflow" + engine: "docker|native" + output: "target/nextflow/concat_text" + executable: "target/nextflow/concat_text/main.nf" + viash_version: "0.9.4" + git_commit: "1c1b0a4a1aff891ab678072b0ba915ac3ac71610" + git_remote: "https://github.com/viash-hub/craftbox" + git_tag: "v0.1.0-8-g1c1b0a4" +package_config: + name: "craftbox" + version: "v0.2.0" + summary: "A collection of custom-tailored scripts and applied utilities built with\ + \ Viash.\n" + description: "`craftbox` is a curated collection of custom scripts and utilities\ + \ designed to tackle context-specific tasks.\n\nEmphasizing the Viash principles,\ + \ `craftbox` components aim for **reusability**, **reproducibility**, and adherence\ + \ to **best practices**. Key features generally include:\n\n* **Standalone & Nextflow\ + \ Ready:** Components are built to run directly via the command line or be smoothly\ + \ integrated into Nextflow workflows.\n* **Custom Implementations:** Contains\ + \ scripts and tools developed for particular tasks that may not be found in broader\ + \ collections.\n* **High Quality Standards (promoted by Viash):**\n * Clear\ + \ documentation for components and their parameters.\n * Full exposure of underlying\ + \ script/tool arguments for fine-grained control.\n * Containerized (Docker)\ + \ to ensure dependency management and a consistent, reproducible runtime environment.\n\ + \ * Unit tested where applicable to ensure components function as expected.\n" + info: null + viash_version: "0.9.4" + 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 := 'v0.2.0'" + keywords: + - "scripts" + - "custom" + - "implementations" + - "utilities" + license: "MIT" + organization: "vsh" + links: + repository: "https://github.com/viash-hub/craftbox" + issue_tracker: "https://github.com/viash-hub/craftbox/issues" diff --git a/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/main.nf b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/main.nf new file mode 100644 index 00000000..ad5e2baa --- /dev/null +++ b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/main.nf @@ -0,0 +1,3868 @@ +// concat_text v0.2.0 +// +// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. +// +// The component may contain files which fall under a different license. The +// authors of this component should specify the license in the header of such +// files, or include a separate license file detailing the licenses of all included +// files. +// +// Component authors: +// * Toni Verbeiren (author, maintainer) +// * Dries Schaumont (reviewer) + +//////////////////////////// +// VDSL3 helper functions // +//////////////////////////// + +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_checkArgumentType.nf' +class UnexpectedArgumentTypeException extends Exception { + String errorIdentifier + String stage + String plainName + String expectedClass + String foundClass + + // ${key ? " in module '$key'" : ""}${id ? " id '$id'" : ""} + UnexpectedArgumentTypeException(String errorIdentifier, String stage, String plainName, String expectedClass, String foundClass) { + super("Error${errorIdentifier ? " $errorIdentifier" : ""}:${stage ? " $stage" : "" } argument '${plainName}' has the wrong type. " + + "Expected type: ${expectedClass}. Found type: ${foundClass}") + this.errorIdentifier = errorIdentifier + this.stage = stage + this.plainName = plainName + this.expectedClass = expectedClass + this.foundClass = foundClass + } +} + +/** + * Checks if the given value is of the expected type. If not, an exception is thrown. + * + * @param stage The stage of the argument (input or output) + * @param par The parameter definition + * @param value The value to check + * @param errorIdentifier The identifier to use in the error message + * @return The value, if it is of the expected type + * @throws UnexpectedArgumentTypeException If the value is not of the expected type +*/ +def _checkArgumentType(String stage, Map par, Object value, String errorIdentifier) { + // expectedClass will only be != null if value is not of the expected type + def expectedClass = null + def foundClass = null + + // todo: split if need be + + if (!par.required && value == null) { + expectedClass = null + } else if (par.multiple) { + if (value !instanceof Collection) { + value = [value] + } + + // split strings + value = value.collectMany{ val -> + if (val instanceof String) { + // collect() to ensure that the result is a List and not simply an array + val.split(par.multiple_sep).collect() + } else { + [val] + } + } + + // process globs + if (par.type == "file" && par.direction == "input") { + value = value.collect{ it instanceof String ? file(it, hidden: true) : it }.flatten() + } + + // check types of elements in list + try { + value = value.collect { listVal -> + _checkArgumentType(stage, par + [multiple: false], listVal, errorIdentifier) + } + } catch (UnexpectedArgumentTypeException e) { + expectedClass = "List[${e.expectedClass}]" + foundClass = "List[${e.foundClass}]" + } + } else if (par.type == "string") { + // cast to string if need be. only cast if the value is a GString + if (value instanceof GString) { + value = value as String + } + expectedClass = value instanceof String ? null : "String" + } else if (par.type == "integer") { + // cast to integer if need be + if (value !instanceof Integer) { + try { + value = value as Integer + } catch (NumberFormatException e) { + expectedClass = "Integer" + } + } + } else if (par.type == "long") { + // cast to long if need be + if (value !instanceof Long) { + try { + value = value as Long + } catch (NumberFormatException e) { + expectedClass = "Long" + } + } + } else if (par.type == "double") { + // cast to double if need be + if (value !instanceof Double) { + try { + value = value as Double + } catch (NumberFormatException e) { + expectedClass = "Double" + } + } + } else if (par.type == "float") { + // cast to float if need be + if (value !instanceof Float) { + try { + value = value as Float + } catch (NumberFormatException e) { + expectedClass = "Float" + } + } + } else if (par.type == "boolean" | par.type == "boolean_true" | par.type == "boolean_false") { + // cast to boolean if need be + if (value !instanceof Boolean) { + try { + value = value as Boolean + } catch (Exception e) { + expectedClass = "Boolean" + } + } + } else if (par.type == "file" && (par.direction == "input" || stage == "output")) { + // cast to path if need be + if (value instanceof String) { + value = file(value, hidden: true) + } + if (value instanceof File) { + value = value.toPath() + } + expectedClass = value instanceof Path ? null : "Path" + } else if (par.type == "file" && stage == "input" && par.direction == "output") { + // cast to string if need be + if (value !instanceof String) { + try { + value = value as String + } catch (Exception e) { + expectedClass = "String" + } + } + } else { + // didn't find a match for par.type + expectedClass = par.type + } + + if (expectedClass != null) { + if (foundClass == null) { + foundClass = value.getClass().getName() + } + throw new UnexpectedArgumentTypeException(errorIdentifier, stage, par.plainName, expectedClass, foundClass) + } + + return value +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processInputValues.nf' +Map _processInputValues(Map inputs, Map config, String id, String key) { + if (!workflow.stubRun) { + config.allArguments.each { arg -> + if (arg.required && arg.direction == "input") { + assert inputs.containsKey(arg.plainName) && inputs.get(arg.plainName) != null : + "Error in module '${key}' id '${id}': required input argument '${arg.plainName}' is missing" + } + } + + inputs = inputs.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid input argument" + + value = _checkArgumentType("input", par, value, "in module '$key' id '$id'") + + [ name, value ] + } + } + return inputs +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processOutputValues.nf' +Map _checkValidOutputArgument(Map outputs, Map config, String id, String key) { + if (!workflow.stubRun) { + outputs = outputs.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && it.direction == "output" } + assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid output argument" + + value = _checkArgumentType("output", par, value, "in module '$key' id '$id'") + + [ name, value ] + } + } + return outputs +} + +void _checkAllRequiredOuputsPresent(Map outputs, Map config, String id, String key) { + if (!workflow.stubRun) { + config.allArguments.each { arg -> + if (arg.direction == "output" && arg.required) { + assert outputs.containsKey(arg.plainName) && outputs.get(arg.plainName) != null : + "Error in module '${key}' id '${id}': required output argument '${arg.plainName}' is missing" + } + } + } +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/IDChecker.nf' +class IDChecker { + final def items = [] as Set + + @groovy.transform.WithWriteLock + boolean observe(String item) { + if (items.contains(item)) { + return false + } else { + items << item + return true + } + } + + @groovy.transform.WithReadLock + boolean contains(String item) { + return items.contains(item) + } + + @groovy.transform.WithReadLock + Set getItems() { + return items.clone() + } +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_checkUniqueIds.nf' + +/** + * Check if the ids are unique across parameter sets + * + * @param parameterSets a list of parameter sets. + */ +private void _checkUniqueIds(List>> parameterSets) { + def ppIds = parameterSets.collect{it[0]} + assert ppIds.size() == ppIds.unique().size() : "All argument sets should have unique ids. Detected ids: $ppIds" +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_getChild.nf' + +// helper functions for reading params from file // +def _getChild(parent, child) { + if (child.contains("://") || java.nio.file.Paths.get(child).isAbsolute()) { + child + } else { + def parentAbsolute = java.nio.file.Paths.get(parent).toAbsolutePath().toString() + parentAbsolute.replaceAll('/[^/]*$', "/") + child + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_parseParamList.nf' +/** + * Figure out the param list format based on the file extension + * + * @param param_list A String containing the path to the parameter list file. + * + * @return A String containing the format of the parameter list file. + */ +def _paramListGuessFormat(param_list) { + if (param_list !instanceof String) { + "asis" + } else if (param_list.endsWith(".csv")) { + "csv" + } else if (param_list.endsWith(".json") || param_list.endsWith(".jsn")) { + "json" + } else if (param_list.endsWith(".yaml") || param_list.endsWith(".yml")) { + "yaml" + } else { + "yaml_blob" + } +} + + +/** + * Read the param list + * + * @param param_list One of the following: + * - A String containing the path to the parameter list file (csv, json or yaml), + * - A yaml blob of a list of maps (yaml_blob), + * - Or a groovy list of maps (asis). + * @param config A Map of the Viash configuration. + * + * @return A List of Maps containing the parameters. + */ +def _parseParamList(param_list, Map config) { + // first determine format by extension + def paramListFormat = _paramListGuessFormat(param_list) + + def paramListPath = (paramListFormat != "asis" && paramListFormat != "yaml_blob") ? + file(param_list, hidden: true) : + null + + // get the correct parser function for the detected params_list format + def paramSets = [] + if (paramListFormat == "asis") { + paramSets = param_list + } else if (paramListFormat == "yaml_blob") { + paramSets = readYamlBlob(param_list) + } else if (paramListFormat == "yaml") { + paramSets = readYaml(paramListPath) + } else if (paramListFormat == "json") { + paramSets = readJson(paramListPath) + } else if (paramListFormat == "csv") { + paramSets = readCsv(paramListPath) + } else { + error "Format of provided --param_list not recognised.\n" + + "Found: '$paramListFormat'.\n" + + "Expected: a csv file, a json file, a yaml file,\n" + + "a yaml blob or a groovy list of maps." + } + + // data checks + assert paramSets instanceof List: "--param_list should contain a list of maps" + for (value in paramSets) { + assert value instanceof Map: "--param_list should contain a list of maps" + } + + // id is argument + def idIsArgument = config.allArguments.any{it.plainName == "id"} + + // Reformat from List to List> by adding the ID as first element of a Tuple2 + paramSets = paramSets.collect({ data -> + def id = data.id + if (!idIsArgument) { + data = data.findAll{k, v -> k != "id"} + } + [id, data] + }) + + // Split parameters with 'multiple: true' + paramSets = paramSets.collect({ id, data -> + data = _splitParams(data, config) + [id, data] + }) + + // The paths of input files inside a param_list file may have been specified relatively to the + // location of the param_list file. These paths must be made absolute. + if (paramListPath) { + paramSets = paramSets.collect({ id, data -> + def new_data = data.collectEntries{ parName, parValue -> + def par = config.allArguments.find{it.plainName == parName} + if (par && par.type == "file" && par.direction == "input") { + if (parValue instanceof Collection) { + parValue = parValue.collectMany{path -> + def x = _resolveSiblingIfNotAbsolute(path, paramListPath) + x instanceof Collection ? x : [x] + } + } else { + parValue = _resolveSiblingIfNotAbsolute(parValue, paramListPath) + } + } + [parName, parValue] + } + [id, new_data] + }) + } + + return paramSets +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_splitParams.nf' +/** + * Split parameters for arguments that accept multiple values using their separator + * + * @param paramList A Map containing parameters to split. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A Map of parameters where the parameter values have been split into a list using + * their seperator. + */ +Map _splitParams(Map parValues, Map config){ + def parsedParamValues = parValues.collectEntries { parName, parValue -> + def parameterSettings = config.allArguments.find({it.plainName == parName}) + + if (!parameterSettings) { + // if argument is not found, do not alter + return [parName, parValue] + } + if (parameterSettings.multiple) { // Check if parameter can accept multiple values + if (parValue instanceof Collection) { + parValue = parValue.collect{it instanceof String ? it.split(parameterSettings.multiple_sep) : it } + } else if (parValue instanceof String) { + parValue = parValue.split(parameterSettings.multiple_sep) + } else if (parValue == null) { + parValue = [] + } else { + parValue = [ parValue ] + } + parValue = parValue.flatten() + } + // For all parameters check if multiple values are only passed for + // arguments that allow it. Quietly simplify lists of length 1. + if (!parameterSettings.multiple && parValue instanceof Collection) { + assert parValue.size() == 1 : + "Error: argument ${parName} has too many values.\n" + + " Expected amount: 1. Found: ${parValue.size()}" + parValue = parValue[0] + } + [parName, parValue] + } + return parsedParamValues +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/channelFromParams.nf' +/** + * Parse nextflow parameters based on settings defined in a viash config. + * Return a list of parameter sets, each parameter set corresponding to + * an event in a nextflow channel. The output from this function can be used + * with Channel.fromList to create a nextflow channel with Vdsl3 formatted + * events. + * + * This function performs: + * - A filtering of the params which can be found in the config file. + * - Process the params_list argument which allows a user to to initialise + * a Vsdl3 channel with multiple parameter sets. Possible formats are + * csv, json, yaml, or simply a yaml_blob. A csv should have column names + * which correspond to the different arguments of this pipeline. A json or a yaml + * file should be a list of maps, each of which has keys corresponding to the + * arguments of the pipeline. A yaml blob can also be passed directly as a parameter. + * When passing a csv, json or yaml, relative path names are relativized to the + * location of the parameter file. + * - Combine the parameter sets into a vdsl3 Channel. + * + * @param params Input parameters. Can optionaly contain a 'param_list' key that + * provides a list of arguments that can be split up into multiple events + * in the output channel possible formats of param_lists are: a csv file, + * json file, a yaml file or a yaml blob. Each parameters set (event) must + * have a unique ID. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A list of parameters with the first element of the event being + * the event ID and the second element containing a map of the parsed parameters. + */ + +private List>> _paramsToParamSets(Map params, Map config){ + // todo: fetch key from run args + def key_ = config.name + + /* parse regular parameters (not in param_list) */ + /*************************************************/ + def globalParams = config.allArguments + .findAll { params.containsKey(it.plainName) } + .collectEntries { [ it.plainName, params[it.plainName] ] } + def globalID = params.get("id", null) + + /* process params_list arguments */ + /*********************************/ + def paramList = params.containsKey("param_list") && params.param_list != null ? + params.param_list : [] + // if (paramList instanceof String) { + // paramList = [paramList] + // } + // def paramSets = paramList.collectMany{ _parseParamList(it, config) } + // TODO: be able to process param_list when it is a list of strings + def paramSets = _parseParamList(paramList, config) + if (paramSets.isEmpty()) { + paramSets = [[null, [:]]] + } + + /* combine arguments into channel */ + /**********************************/ + def processedParams = paramSets.indexed().collect{ index, tup -> + // Process ID + def id = tup[0] ?: globalID + + if (workflow.stubRun && !id) { + // if stub run, explicitly add an id if missing + id = "stub${index}" + } + assert id != null: "Each parameter set should have at least an 'id'" + + // Process params + def parValues = globalParams + tup[1] + // // Remove parameters which are null, if the default is also null + // parValues = parValues.collectEntries{paramName, paramValue -> + // parameterSettings = config.functionality.allArguments.find({it.plainName == paramName}) + // if ( paramValue != null || parameterSettings.get("default", null) != null ) { + // [paramName, paramValue] + // } + // } + parValues = parValues.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + assert par != null : "Error in module '${key_}' id '${id}': '${name}' is not a valid input argument" + + if (par == null) { + return [:] + } + value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") + + [ name, value ] + } + + [id, parValues] + } + + // Check if ids (first element of each list) is unique + _checkUniqueIds(processedParams) + return processedParams +} + +/** + * Parse nextflow parameters based on settings defined in a viash config + * and return a nextflow channel. + * + * @param params Input parameters. Can optionaly contain a 'param_list' key that + * provides a list of arguments that can be split up into multiple events + * in the output channel possible formats of param_lists are: a csv file, + * json file, a yaml file or a yaml blob. Each parameters set (event) must + * have a unique ID. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A nextflow Channel with events. Events are formatted as a tuple that contains + * first contains the ID of the event and as second element holds a parameter map. + * + * + */ +def channelFromParams(Map params, Map config) { + def processedParams = _paramsToParamSets(params, config) + return Channel.fromList(processedParams) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/checkUniqueIds.nf' +def checkUniqueIds(Map args) { + def stopOnError = args.stopOnError == null ? args.stopOnError : true + + def idChecker = new IDChecker() + + return filter { tup -> + if (!idChecker.observe(tup[0])) { + if (stopOnError) { + error "Duplicate id: ${tup[0]}" + } else { + log.warn "Duplicate id: ${tup[0]}, removing duplicate entry" + return false + } + } + return true + } +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/preprocessInputs.nf' +// This helper file will be deprecated soon +preprocessInputsDeprecationWarningPrinted = false + +def preprocessInputsDeprecationWarning() { + if (!preprocessInputsDeprecationWarningPrinted) { + preprocessInputsDeprecationWarningPrinted = true + System.err.println("Warning: preprocessInputs() is deprecated and will be removed in Viash 0.9.0.") + } +} + +/** + * Generate a nextflow Workflow that allows processing a channel of + * Vdsl3 formatted events and apply a Viash config to them: + * - Gather default parameters from the Viash config and make + * sure that they are correctly formatted (see applyConfig method). + * - Format the input parameters (also using the applyConfig method). + * - Apply the default parameter to the input parameters. + * - Do some assertions: + * ~ Check if the event IDs in the channel are unique. + * + * The events in the channel are formatted as tuples, with the + * first element of the tuples being a unique id of the parameter set, + * and the second element containg the the parameters themselves. + * Optional extra elements of the tuples will be passed to the output as is. + * + * @param args A map that must contain a 'config' key that points + * to a parsed config (see readConfig()). Optionally, a + * 'key' key can be provided which can be used to create a unique + * name for the workflow process. + * + * @return A workflow that allows processing a channel of Vdsl3 formatted events + * and apply a Viash config to them. + */ +def preprocessInputs(Map args) { + preprocessInputsDeprecationWarning() + + def config = args.config + assert config instanceof Map : + "Error in preprocessInputs: config must be a map. " + + "Expected class: Map. Found: config.getClass() is ${config.getClass()}" + def key_ = args.key ?: config.name + + // Get different parameter types (used throughout this function) + def defaultArgs = config.allArguments + .findAll { it.containsKey("default") } + .collectEntries { [ it.plainName, it.default ] } + + map { tup -> + def id = tup[0] + def data = tup[1] + def passthrough = tup.drop(2) + + def new_data = (defaultArgs + data).collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + + if (par != null) { + value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") + } + + [ name, value ] + } + + [ id, new_data ] + passthrough + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runComponents.nf' +/** + * Run a list of components on a stream of data. + * + * @param components: list of Viash VDSL3 modules to run + * @param fromState: a closure, a map or a list of keys to extract from the input data. + * If a closure, it will be called with the id, the data and the component config. + * @param toState: a closure, a map or a list of keys to extract from the output data + * If a closure, it will be called with the id, the output data, the old state and the component config. + * @param filter: filter function to apply to the input. + * It will be called with the id, the data and the component config. + * @param id: id to use for the output data + * If a closure, it will be called with the id, the data and the component config. + * @param auto: auto options to pass to the components + * + * @return: a workflow that runs the components + **/ +def runComponents(Map args) { + log.warn("runComponents is deprecated, use runEach instead") + assert args.components: "runComponents should be passed a list of components to run" + + def components_ = args.components + if (components_ !instanceof List) { + components_ = [ components_ ] + } + assert components_.size() > 0: "pass at least one component to runComponents" + + def fromState_ = args.fromState + def toState_ = args.toState + def filter_ = args.filter + def id_ = args.id + + workflow runComponentsWf { + take: input_ch + main: + + // generate one channel per method + out_chs = components_.collect{ comp_ -> + def comp_config = comp_.config + + def filter_ch = filter_ + ? input_ch | filter{tup -> + filter_(tup[0], tup[1], comp_config) + } + : input_ch + def id_ch = id_ + ? filter_ch | map{tup -> + // def new_id = id_(tup[0], tup[1], comp_config) + def new_id = tup[0] + if (id_ instanceof String) { + new_id = id_ + } else if (id_ instanceof Closure) { + new_id = id_(new_id, tup[1], comp_config) + } + [new_id] + tup.drop(1) + } + : filter_ch + def data_ch = id_ch | map{tup -> + def new_data = tup[1] + if (fromState_ instanceof Map) { + new_data = fromState_.collectEntries{ key0, key1 -> + [key0, new_data[key1]] + } + } else if (fromState_ instanceof List) { + new_data = fromState_.collectEntries{ key -> + [key, new_data[key]] + } + } else if (fromState_ instanceof Closure) { + new_data = fromState_(tup[0], new_data, comp_config) + } + tup.take(1) + [new_data] + tup.drop(1) + } + def out_ch = data_ch + | comp_.run( + auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] + ) + def post_ch = toState_ + ? out_ch | map{tup -> + def output = tup[1] + def old_state = tup[2] + def new_state = null + if (toState_ instanceof Map) { + new_state = old_state + toState_.collectEntries{ key0, key1 -> + [key0, output[key1]] + } + } else if (toState_ instanceof List) { + new_state = old_state + toState_.collectEntries{ key -> + [key, output[key]] + } + } else if (toState_ instanceof Closure) { + new_state = toState_(tup[0], output, old_state, comp_config) + } + [tup[0], new_state] + tup.drop(3) + } + : out_ch + + post_ch + } + + // mix all results + output_ch = + (out_chs.size == 1) + ? out_chs[0] + : out_chs[0].mix(*out_chs.drop(1)) + + emit: output_ch + } + + return runComponentsWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runEach.nf' +/** + * Run a list of components on a stream of data. + * + * @param components: list of Viash VDSL3 modules to run + * @param fromState: a closure, a map or a list of keys to extract from the input data. + * If a closure, it will be called with the id, the data and the component itself. + * @param toState: a closure, a map or a list of keys to extract from the output data + * If a closure, it will be called with the id, the output data, the old state and the component itself. + * @param filter: filter function to apply to the input. + * It will be called with the id, the data and the component itself. + * @param id: id to use for the output data + * If a closure, it will be called with the id, the data and the component itself. + * @param auto: auto options to pass to the components + * + * @return: a workflow that runs the components + **/ +def runEach(Map args) { + assert args.components: "runEach should be passed a list of components to run" + + def components_ = args.components + if (components_ !instanceof List) { + components_ = [ components_ ] + } + assert components_.size() > 0: "pass at least one component to runEach" + + def fromState_ = args.fromState + def toState_ = args.toState + def filter_ = args.filter + def runIf_ = args.runIf + def id_ = args.id + + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + + workflow runEachWf { + take: input_ch + main: + + // generate one channel per method + out_chs = components_.collect{ comp_ -> + def filter_ch = filter_ + ? input_ch | filter{tup -> + filter_(tup[0], tup[1], comp_) + } + : input_ch + def id_ch = id_ + ? filter_ch | map{tup -> + def new_id = id_ + if (new_id instanceof Closure) { + new_id = new_id(tup[0], tup[1], comp_) + } + assert new_id instanceof String : "Error in runEach: id should be a String or a Closure that returns a String. Expected: id instanceof String. Found: ${new_id.getClass()}" + [new_id] + tup.drop(1) + } + : filter_ch + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> + def new_data = tup[1] + if (fromState_ instanceof Map) { + new_data = fromState_.collectEntries{ key0, key1 -> + [key0, new_data[key1]] + } + } else if (fromState_ instanceof List) { + new_data = fromState_.collectEntries{ key -> + [key, new_data[key]] + } + } else if (fromState_ instanceof Closure) { + new_data = fromState_(tup[0], new_data, comp_) + } + tup.take(1) + [new_data] + tup.drop(1) + } + def out_ch = data_ch + | comp_.run( + auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] + ) + def post_ch = toState_ + ? out_ch | map{tup -> + def output = tup[1] + def old_state = tup[2] + def new_state = null + if (toState_ instanceof Map) { + new_state = old_state + toState_.collectEntries{ key0, key1 -> + [key0, output[key1]] + } + } else if (toState_ instanceof List) { + new_state = old_state + toState_.collectEntries{ key -> + [key, output[key]] + } + } else if (toState_ instanceof Closure) { + new_state = toState_(tup[0], output, old_state, comp_) + } + [tup[0], new_state] + tup.drop(3) + } + : out_ch + + def return_ch = post_ch + | concat(chPassthrough) + + return_ch + } + + // mix all results + output_ch = + (out_chs.size == 1) + ? out_chs[0] + : out_chs[0].mix(*out_chs.drop(1)) + + emit: output_ch + } + + return runEachWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/safeJoin.nf' +/** + * Join sourceChannel to targetChannel + * + * This function joins the sourceChannel to the targetChannel. + * However, each id in the targetChannel must be present in the + * sourceChannel. If _meta.join_id exists in the targetChannel, that is + * used as an id instead. If the id doesn't match any id in the sourceChannel, + * an error is thrown. + */ + +def safeJoin(targetChannel, sourceChannel, key) { + def sourceIDs = new IDChecker() + + def sourceCheck = sourceChannel + | map { tup -> + sourceIDs.observe(tup[0]) + tup + } + def targetCheck = targetChannel + | map { tup -> + def id = tup[0] + + if (!sourceIDs.contains(id)) { + error ( + "Error in module '${key}' when merging output with original state.\n" + + " Reason: output with id '${id}' could not be joined with source channel.\n" + + " If the IDs in the output channel differ from the input channel,\n" + + " please set `tup[1]._meta.join_id to the original ID.\n" + + " Original IDs in input channel: ['${sourceIDs.getItems().join("', '")}'].\n" + + " Unexpected ID in the output channel: '${id}'.\n" + + " Example input event: [\"id\", [input: file(...)]],\n" + + " Example output event: [\"newid\", [output: file(...), _meta: [join_id: \"id\"]]]" + ) + } + // TODO: add link to our documentation on how to fix this + + tup + } + + sourceCheck.cross(targetChannel) + | map{ left, right -> + right + left.drop(1) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/_processArgument.nf' +def _processArgument(arg) { + arg.multiple = arg.multiple != null ? arg.multiple : false + arg.required = arg.required != null ? arg.required : false + arg.direction = arg.direction != null ? arg.direction : "input" + arg.multiple_sep = arg.multiple_sep != null ? arg.multiple_sep : ";" + arg.plainName = arg.name.replaceAll("^-*", "") + + if (arg.type == "file") { + arg.must_exist = arg.must_exist != null ? arg.must_exist : true + arg.create_parent = arg.create_parent != null ? arg.create_parent : true + } + + // add default values to output files which haven't already got a default + if (arg.type == "file" && arg.direction == "output" && arg.default == null) { + def mult = arg.multiple ? "_*" : "" + def extSearch = "" + if (arg.default != null) { + extSearch = arg.default + } else if (arg.example != null) { + extSearch = arg.example + } + if (extSearch instanceof List) { + extSearch = extSearch[0] + } + def extSearchResult = extSearch.find("\\.[^\\.]+\$") + def ext = extSearchResult != null ? extSearchResult : "" + arg.default = "\$id.\$key.${arg.plainName}${mult}${ext}" + if (arg.multiple) { + arg.default = [arg.default] + } + } + + if (!arg.multiple) { + if (arg.default != null && arg.default instanceof List) { + arg.default = arg.default[0] + } + if (arg.example != null && arg.example instanceof List) { + arg.example = arg.example[0] + } + } + + if (arg.type == "boolean_true") { + arg.default = false + } + if (arg.type == "boolean_false") { + arg.default = true + } + + arg +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/addGlobalParams.nf' +def addGlobalArguments(config) { + def localConfig = [ + "argument_groups": [ + [ + "name": "Nextflow input-output arguments", + "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.", + "arguments" : [ + [ + 'name': '--publish_dir', + 'required': true, + 'type': 'string', + 'description': 'Path to an output directory.', + 'example': 'output/', + 'multiple': false + ], + [ + 'name': '--param_list', + 'required': false, + 'type': 'string', + 'description': '''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. + | + |* 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: [ ['id': 'foo', 'input': 'foo.txt'], ['id': 'bar', 'input': 'bar.txt'] ]`. + |* 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`. + |* 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 `[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]`. + |* A yaml blob can also be passed directly as a string. Example: `--param_list "[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]"`. + | + |When 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.'''.stripMargin(), + 'example': 'my_params.yaml', + 'multiple': false, + 'hidden': true + ] + // TODO: allow multiple: true in param_list? + // TODO: allow to specify a --param_list_regex to filter the param_list? + // TODO: allow to specify a --param_list_from_state to remap entries in the param_list? + ] + ] + ] + ] + + return processConfig(_mergeMap(config, localConfig)) +} + +def _mergeMap(Map lhs, Map rhs) { + return rhs.inject(lhs.clone()) { map, entry -> + if (map[entry.key] instanceof Map && entry.value instanceof Map) { + map[entry.key] = _mergeMap(map[entry.key], entry.value) + } else if (map[entry.key] instanceof Collection && entry.value instanceof Collection) { + map[entry.key] += entry.value + } else { + map[entry.key] = entry.value + } + return map + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/generateHelp.nf' +def _generateArgumentHelp(param) { + // alternatives are not supported + // def names = param.alternatives ::: List(param.name) + + def unnamedProps = [ + ["required parameter", param.required], + ["multiple values allowed", param.multiple], + ["output", param.direction.toLowerCase() == "output"], + ["file must exist", param.type == "file" && param.must_exist] + ].findAll{it[1]}.collect{it[0]} + + def dflt = null + if (param.default != null) { + if (param.default instanceof List) { + dflt = param.default.join(param.multiple_sep != null ? param.multiple_sep : ", ") + } else { + dflt = param.default.toString() + } + } + def example = null + if (param.example != null) { + if (param.example instanceof List) { + example = param.example.join(param.multiple_sep != null ? param.multiple_sep : ", ") + } else { + example = param.example.toString() + } + } + def min = param.min?.toString() + def max = param.max?.toString() + + def escapeChoice = { choice -> + def s1 = choice.replaceAll("\\n", "\\\\n") + def s2 = s1.replaceAll("\"", """\\\"""") + s2.contains(",") || s2 != choice ? "\"" + s2 + "\"" : s2 + } + def choices = param.choices == null ? + null : + "[ " + param.choices.collect{escapeChoice(it.toString())}.join(", ") + " ]" + + def namedPropsStr = [ + ["type", ([param.type] + unnamedProps).join(", ")], + ["default", dflt], + ["example", example], + ["choices", choices], + ["min", min], + ["max", max] + ] + .findAll{it[1]} + .collect{"\n " + it[0] + ": " + it[1].replaceAll("\n", "\\n")} + .join("") + + def descStr = param.description == null ? + "" : + _paragraphWrap("\n" + param.description.trim(), 80 - 8).join("\n ") + + "\n --" + param.plainName + + namedPropsStr + + descStr +} + +// Based on Helper.generateHelp() in Helper.scala +def _generateHelp(config) { + def fun = config + + // PART 1: NAME AND VERSION + def nameStr = fun.name + + (fun.version == null ? "" : " " + fun.version) + + // PART 2: DESCRIPTION + def descrStr = fun.description == null ? + "" : + "\n\n" + _paragraphWrap(fun.description.trim(), 80).join("\n") + + // PART 3: Usage + def usageStr = fun.usage == null ? + "" : + "\n\nUsage:\n" + fun.usage.trim() + + // PART 4: Options + def argGroupStrs = fun.allArgumentGroups.collect{argGroup -> + def name = argGroup.name + def descriptionStr = argGroup.description == null ? + "" : + "\n " + _paragraphWrap(argGroup.description.trim(), 80-4).join("\n ") + "\n" + def arguments = argGroup.arguments.collect{arg -> + arg instanceof String ? fun.allArguments.find{it.plainName == arg} : arg + }.findAll{it != null} + def argumentStrs = arguments.collect{param -> _generateArgumentHelp(param)} + + "\n\n$name:" + + descriptionStr + + argumentStrs.join("\n") + } + + // FINAL: combine + def out = nameStr + + descrStr + + usageStr + + argGroupStrs.join("") + + return out +} + +// based on Format._paragraphWrap +def _paragraphWrap(str, maxLength) { + def outLines = [] + str.split("\n").each{par -> + def words = par.split("\\s").toList() + + def word = null + def line = words.pop() + while(!words.isEmpty()) { + word = words.pop() + if (line.length() + word.length() + 1 <= maxLength) { + line = line + " " + word + } else { + outLines.add(line) + line = word + } + } + if (words.isEmpty()) { + outLines.add(line) + } + } + return outLines +} + +def helpMessage(config) { + if (params.containsKey("help") && params.help) { + def mergedConfig = addGlobalArguments(config) + def helpStr = _generateHelp(mergedConfig) + println(helpStr) + exit 0 + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/processConfig.nf' +def processConfig(config) { + // set defaults for arguments + config.arguments = + (config.arguments ?: []).collect{_processArgument(it)} + + // set defaults for argument_group arguments + config.argument_groups = + (config.argument_groups ?: []).collect{grp -> + grp.arguments = (grp.arguments ?: []).collect{_processArgument(it)} + grp + } + + // create combined arguments list + config.allArguments = + config.arguments + + config.argument_groups.collectMany{it.arguments} + + // add missing argument groups (based on Functionality::allArgumentGroups()) + def argGroups = config.argument_groups + if (argGroups.any{it.name.toLowerCase() == "arguments"}) { + argGroups = argGroups.collect{ grp -> + if (grp.name.toLowerCase() == "arguments") { + grp = grp + [ + arguments: grp.arguments + config.arguments + ] + } + grp + } + } else { + argGroups = argGroups + [ + name: "Arguments", + arguments: config.arguments + ] + } + config.allArgumentGroups = argGroups + + config +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/readConfig.nf' + +def readConfig(file) { + def config = readYaml(file ?: moduleDir.resolve("config.vsh.yaml")) + processConfig(config) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_resolveSiblingIfNotAbsolute.nf' +/** + * Resolve a path relative to the current file. + * + * @param str The path to resolve, as a String. + * @param parentPath The path to resolve relative to, as a Path. + * + * @return The path that may have been resovled, as a Path. + */ +def _resolveSiblingIfNotAbsolute(str, parentPath) { + if (str !instanceof String) { + return str + } + if (!_stringIsAbsolutePath(str)) { + return parentPath.resolveSibling(str) + } else { + return file(str, hidden: true) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_stringIsAbsolutePath.nf' +/** + * Check whether a path as a string is absolute. + * + * In the past, we tried using `file(., relative: true).isAbsolute()`, + * but the 'relative' option was added in 22.10.0. + * + * @param path The path to check, as a String. + * + * @return Whether the path is absolute, as a boolean. + */ +def _stringIsAbsolutePath(path) { + def _resolve_URL_PROTOCOL = ~/^([a-zA-Z][a-zA-Z0-9]*:)?\\/.+/ + + assert path instanceof String + return _resolve_URL_PROTOCOL.matcher(path).matches() +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/collectTraces.nf' +class CustomTraceObserver implements nextflow.trace.TraceObserver { + List traces + + CustomTraceObserver(List traces) { + this.traces = traces + } + + @Override + void onProcessComplete(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { + def trace2 = trace.store.clone() + trace2.script = null + traces.add(trace2) + } + + @Override + void onProcessCached(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { + def trace2 = trace.store.clone() + trace2.script = null + traces.add(trace2) + } +} + +def collectTraces() { + def traces = Collections.synchronizedList([]) + + // add custom trace observer which stores traces in the traces object + session.observers.add(new CustomTraceObserver(traces)) + + traces +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/deepClone.nf' +/** + * Performs a deep clone of the given object. + * @param x an object + */ +def deepClone(x) { + iterateMap(x, {it instanceof Cloneable ? it.clone() : it}) +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getPublishDir.nf' +def getPublishDir() { + return params.containsKey("publish_dir") ? params.publish_dir : + params.containsKey("publishDir") ? params.publishDir : + null +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getRootDir.nf' + +// Recurse upwards until we find a '.build.yaml' file +def _findBuildYamlFile(pathPossiblySymlink) { + def path = pathPossiblySymlink.toRealPath() + def child = path.resolve(".build.yaml") + if (java.nio.file.Files.isDirectory(path) && java.nio.file.Files.exists(child)) { + return child + } else { + def parent = path.getParent() + if (parent == null) { + return null + } else { + return _findBuildYamlFile(parent) + } + } +} + +// get the root of the target folder +def getRootDir() { + def dir = _findBuildYamlFile(meta.resources_dir) + assert dir != null: "Could not find .build.yaml in the folder structure" + dir.getParent() +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/iterateMap.nf' +/** + * Recursively apply a function over the leaves of an object. + * @param obj The object to iterate over. + * @param fun The function to apply to each value. + * @return The object with the function applied to each value. + */ +def iterateMap(obj, fun) { + if (obj instanceof List && obj !instanceof String) { + return obj.collect{item -> + iterateMap(item, fun) + } + } else if (obj instanceof Map) { + return obj.collectEntries{key, item -> + [key.toString(), iterateMap(item, fun)] + } + } else { + return fun(obj) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/niceView.nf' +/** + * A view for printing the event of each channel as a YAML blob. + * This is useful for debugging. + */ +def niceView() { + workflow niceViewWf { + take: input + main: + output = input + | view{toYamlBlob(it)} + emit: output + } + return niceViewWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readCsv.nf' + +def readCsv(file_path) { + def output = [] + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + + // todo: allow escaped quotes in string + // todo: allow single quotes? + def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''') + def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''') + + def br = java.nio.file.Files.newBufferedReader(inputFile) + + def row = -1 + def header = null + while (br.ready() && header == null) { + def line = br.readLine() + row++ + if (!line.startsWith("#")) { + header = splitRegex.split(line, -1).collect{field -> + m = removeQuote.matcher(field) + m.find() ? m.replaceFirst('$1') : field + } + } + } + assert header != null: "CSV file should contain a header" + + while (br.ready()) { + def line = br.readLine() + row++ + if (line == null) { + br.close() + break + } + + if (!line.startsWith("#")) { + def predata = splitRegex.split(line, -1) + def data = predata.collect{field -> + if (field == "") { + return null + } + def m = removeQuote.matcher(field) + if (m.find()) { + return m.replaceFirst('$1') + } else { + return field + } + } + assert header.size() == data.size(): "Row $row should contain the same number as fields as the header" + + def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null} + output.add(dataMap) + } + } + + output +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJson.nf' +def readJson(file_path) { + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + def jsonSlurper = new groovy.json.JsonSlurper() + jsonSlurper.parse(inputFile) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJsonBlob.nf' +def readJsonBlob(str) { + def jsonSlurper = new groovy.json.JsonSlurper() + jsonSlurper.parseText(str) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readTaggedYaml.nf' +// Custom constructor to modify how certain objects are parsed from YAML +class CustomConstructor extends org.yaml.snakeyaml.constructor.Constructor { + Path root + + class ConstructPath extends org.yaml.snakeyaml.constructor.AbstractConstruct { + public Object construct(org.yaml.snakeyaml.nodes.Node node) { + String filename = (String) constructScalar(node); + if (root != null) { + return root.resolve(filename); + } + return java.nio.file.Paths.get(filename); + } + } + + CustomConstructor(org.yaml.snakeyaml.LoaderOptions options, Path root) { + super(options) + this.root = root + // Handling !file tag and parse it back to a File type + this.yamlConstructors.put(new org.yaml.snakeyaml.nodes.Tag("!file"), new ConstructPath()) + } +} + +def readTaggedYaml(Path path) { + def options = new org.yaml.snakeyaml.LoaderOptions() + def constructor = new CustomConstructor(options, path.getParent()) + def yaml = new org.yaml.snakeyaml.Yaml(constructor) + return yaml.load(path.text) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYaml.nf' +def readYaml(file_path) { + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + def yamlSlurper = new org.yaml.snakeyaml.Yaml() + yamlSlurper.load(inputFile) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYamlBlob.nf' +def readYamlBlob(str) { + def yamlSlurper = new org.yaml.snakeyaml.Yaml() + yamlSlurper.load(str) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toJsonBlob.nf' +String toJsonBlob(data) { + return groovy.json.JsonOutput.toJson(data) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toTaggedYamlBlob.nf' +// Custom representer to modify how certain objects are represented in YAML +class CustomRepresenter extends org.yaml.snakeyaml.representer.Representer { + Path relativizer + + class RepresentPath implements org.yaml.snakeyaml.representer.Represent { + public String getFileName(Object obj) { + if (obj instanceof File) { + obj = ((File) obj).toPath(); + } + if (obj !instanceof Path) { + throw new IllegalArgumentException("Object: " + obj + " is not a Path or File"); + } + def path = (Path) obj; + + if (relativizer != null) { + return relativizer.relativize(path).toString() + } else { + return path.toString() + } + } + + public org.yaml.snakeyaml.nodes.Node representData(Object data) { + String filename = getFileName(data); + def tag = new org.yaml.snakeyaml.nodes.Tag("!file"); + return representScalar(tag, filename); + } + } + CustomRepresenter(org.yaml.snakeyaml.DumperOptions options, Path relativizer) { + super(options) + this.relativizer = relativizer + this.representers.put(sun.nio.fs.UnixPath, new RepresentPath()) + this.representers.put(Path, new RepresentPath()) + this.representers.put(File, new RepresentPath()) + } +} + +String toTaggedYamlBlob(data) { + return toRelativeTaggedYamlBlob(data, null) +} +String toRelativeTaggedYamlBlob(data, Path relativizer) { + def options = new org.yaml.snakeyaml.DumperOptions() + options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) + def representer = new CustomRepresenter(options, relativizer) + def yaml = new org.yaml.snakeyaml.Yaml(representer, options) + return yaml.dump(data) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toYamlBlob.nf' +String toYamlBlob(data) { + def options = new org.yaml.snakeyaml.DumperOptions() + options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) + options.setPrettyFlow(true) + def yaml = new org.yaml.snakeyaml.Yaml(options) + def cleanData = iterateMap(data, { it instanceof Path ? it.toString() : it }) + return yaml.dump(cleanData) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeJson.nf' +void writeJson(data, file) { + assert data: "writeJson: data should not be null" + assert file: "writeJson: file should not be null" + file.write(toJsonBlob(data)) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeYaml.nf' +void writeYaml(data, file) { + assert data: "writeYaml: data should not be null" + assert file: "writeYaml: file should not be null" + file.write(toYamlBlob(data)) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/findStates.nf' +def findStates(Map params, Map config) { + def auto_config = deepClone(config) + def auto_params = deepClone(params) + + auto_config = auto_config.clone() + // override arguments + auto_config.argument_groups = [] + auto_config.arguments = [ + [ + type: "string", + name: "--id", + description: "A dummy identifier", + required: false + ], + [ + type: "file", + name: "--input_states", + example: "/path/to/input/directory/**/state.yaml", + description: "Path to input directory containing the datasets to be integrated.", + required: true, + multiple: true, + multiple_sep: ";" + ], + [ + type: "string", + name: "--filter", + example: "foo/.*/state.yaml", + description: "Regex to filter state files by path.", + required: false + ], + // to do: make this a yaml blob? + [ + type: "string", + name: "--rename_keys", + example: ["newKey1:oldKey1", "newKey2:oldKey2"], + description: "Rename keys in the detected input files. This is useful if the input files do not match the set of input arguments of the workflow.", + required: false, + multiple: true, + multiple_sep: ";" + ], + [ + type: "string", + name: "--settings", + example: '{"output_dataset": "dataset.h5ad", "k": 10}', + description: "Global arguments as a JSON glob to be passed to all components.", + required: false + ] + ] + if (!(auto_params.containsKey("id"))) { + auto_params["id"] = "auto" + } + + // run auto config through processConfig once more + auto_config = processConfig(auto_config) + + workflow findStatesWf { + helpMessage(auto_config) + + output_ch = + channelFromParams(auto_params, auto_config) + | flatMap { autoId, args -> + + def globalSettings = args.settings ? readYamlBlob(args.settings) : [:] + + // look for state files in input dir + def stateFiles = args.input_states + + // filter state files by regex + if (args.filter) { + stateFiles = stateFiles.findAll{ stateFile -> + def stateFileStr = stateFile.toString() + def matcher = stateFileStr =~ args.filter + matcher.matches()} + } + + // read in states + def states = stateFiles.collect { stateFile -> + def state_ = readTaggedYaml(stateFile) + [state_.id, state_] + } + + // construct renameMap + if (args.rename_keys) { + def renameMap = args.rename_keys.collectEntries{renameString -> + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" + split + } + + // rename keys in state, only let states through which have all keys + // also add global settings + states = states.collectMany{id, state -> + def newState = [:] + + for (key in renameMap.keySet()) { + def origKey = renameMap[key] + if (!(state.containsKey(origKey))) { + return [] + } + newState[key] = state[origKey] + } + + [[id, globalSettings + newState]] + } + } + + states + } + emit: + output_ch + } + + return findStatesWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/joinStates.nf' +def joinStates(Closure apply_) { + workflow joinStatesWf { + take: input_ch + main: + output_ch = input_ch + | toSortedList + | filter{ it.size() > 0 } + | map{ tups -> + def ids = tups.collect{it[0]} + def states = tups.collect{it[1]} + apply_(ids, states) + } + + emit: output_ch + } + return joinStatesWf +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishFiles.nf' +def publishFiles(Map args) { + def key_ = args.get("key") + + assert key_ != null : "publishFiles: key must be specified" + + workflow publishFilesWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] + + // the input files and the target output filenames + def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() + def inputFiles_ = inputoutputFilenames_[0] + def outputFilenames_ = inputoutputFilenames_[1] + + [id_, inputFiles_, outputFilenames_] + } + | publishFilesProc + emit: input_ch + } + return publishFilesWf +} + +process publishFilesProc { + // todo: check publishpath? + publishDir path: "${getPublishDir()}/", mode: "copy" + tag "$id" + input: + tuple val(id), path(inputFiles, stageAs: "_inputfile?/*"), val(outputFiles) + output: + tuple val(id), path{outputFiles} + script: + def copyCommands = [ + inputFiles instanceof List ? inputFiles : [inputFiles], + outputFiles instanceof List ? outputFiles : [outputFiles] + ] + .transpose() + .collectMany{infile, outfile -> + if (infile.toString() != outfile.toString()) { + [ + "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"", + "cp -r '${infile.toString()}' '${outfile.toString()}'" + ] + } else { + // no need to copy if infile is the same as outfile + [] + } + } + """ + echo "Copying output files to destination folder" + ${copyCommands.join("\n ")} + """ +} + + +// this assumes that the state contains no other values other than those specified in the config +def publishFilesByConfig(Map args) { + def config = args.get("config") + assert config != null : "publishFilesByConfig: config must be specified" + + def key_ = args.get("key", config.name) + assert key_ != null : "publishFilesByConfig: key must be specified" + + workflow publishFilesSimpleWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] // e.g. [output: new File("myoutput.h5ad"), k: 10] + def origState_ = tup[2] // e.g. [output: '$id.$key.foo.h5ad'] + + + // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where + // - key is a String + // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) + // - inputPath is a List[Path] + // - outputFilename is a List[String] + // - (inputPath, outputFilename) are the files that will be copied from src to dest (relative to the state.yaml) + def processedState = + config.allArguments + .findAll { it.direction == "output" } + .collectMany { par -> + def plainName_ = par.plainName + // if the state does not contain the key, it's an + // optional argument for which the component did + // not generate any output OR multiple channels were emitted + // and the output was just not added to using the channel + // that is now being parsed + if (!state_.containsKey(plainName_)) { + return [] + } + def value = state_[plainName_] + // if the parameter is not a file, it should be stored + // in the state as-is, but is not something that needs + // to be copied from the source path to the dest path + if (par.type != "file") { + return [[inputPath: [], outputFilename: []]] + } + // if the orig state does not contain this filename, + // it's an optional argument for which the user specified + // that it should not be returned as a state + if (!origState_.containsKey(plainName_)) { + return [] + } + def filenameTemplate = origState_[plainName_] + // if the pararameter is multiple: true, fetch the template + if (par.multiple && filenameTemplate instanceof List) { + filenameTemplate = filenameTemplate[0] + } + // instantiate the template + def filename = filenameTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + if (par.multiple) { + // if the parameter is multiple: true, the filename + // should contain a wildcard '*' that is replaced with + // the index of the file + assert filename.contains("*") : "Module '${key_}' id '${id_}': Multiple output files specified, but no wildcard '*' in the filename: ${filename}" + def outputPerFile = value.withIndex().collect{ val, ix -> + def filename_ix = filename.replace("*", ix.toString()) + def inputPath = val instanceof File ? val.toPath() : val + [inputPath: inputPath, outputFilename: filename_ix] + } + def transposedOutputs = ["inputPath", "outputFilename"].collectEntries{ key -> + [key, outputPerFile.collect{dic -> dic[key]}] + } + return [[key: plainName_] + transposedOutputs] + } else { + def value_ = java.nio.file.Paths.get(filename) + def inputPath = value instanceof File ? value.toPath() : value + return [[inputPath: [inputPath], outputFilename: [filename]]] + } + } + + def inputPaths = processedState.collectMany{it.inputPath} + def outputFilenames = processedState.collectMany{it.outputFilename} + + + [id_, inputPaths, outputFilenames] + } + | publishFilesProc + emit: input_ch + } + return publishFilesSimpleWf +} + + + + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishStates.nf' +def collectFiles(obj) { + if (obj instanceof java.io.File || obj instanceof Path) { + return [obj] + } else if (obj instanceof List && obj !instanceof String) { + return obj.collectMany{item -> + collectFiles(item) + } + } else if (obj instanceof Map) { + return obj.collectMany{key, item -> + collectFiles(item) + } + } else { + return [] + } +} + +/** + * Recurse through a state and collect all input files and their target output filenames. + * @param obj The state to recurse through. + * @param prefix The prefix to prepend to the output filenames. + */ +def collectInputOutputPaths(obj, prefix) { + if (obj instanceof File || obj instanceof Path) { + def path = obj instanceof Path ? obj : obj.toPath() + def ext = path.getFileName().toString().find("\\.[^\\.]+\$") ?: "" + def newFilename = prefix + ext + return [[obj, newFilename]] + } else if (obj instanceof List && obj !instanceof String) { + return obj.withIndex().collectMany{item, ix -> + collectInputOutputPaths(item, prefix + "_" + ix) + } + } else if (obj instanceof Map) { + return obj.collectMany{key, item -> + collectInputOutputPaths(item, prefix + "." + key) + } + } else { + return [] + } +} + +def publishStates(Map args) { + def key_ = args.get("key") + def yamlTemplate_ = args.get("output_state", args.get("outputState", '$id.$key.state.yaml')) + + assert key_ != null : "publishStates: key must be specified" + + workflow publishStatesWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] + + // the input files and the target output filenames + def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() + + def yamlFilename = yamlTemplate_ + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + + // TODO: do the pathnames in state_ match up with the outputFilenames_? + + // convert state to yaml blob + def yamlBlob_ = toRelativeTaggedYamlBlob([id: id_] + state_, java.nio.file.Paths.get(yamlFilename)) + + [id_, yamlBlob_, yamlFilename] + } + | publishStatesProc + emit: input_ch + } + return publishStatesWf +} +process publishStatesProc { + // todo: check publishpath? + publishDir path: "${getPublishDir()}/", mode: "copy" + tag "$id" + input: + tuple val(id), val(yamlBlob), val(yamlFile) + output: + tuple val(id), path{[yamlFile]} + script: + """ + mkdir -p "\$(dirname '${yamlFile}')" + echo "Storing state as yaml" + cat > '${yamlFile}' << HERE +${yamlBlob} +HERE + """ +} + + +// this assumes that the state contains no other values other than those specified in the config +def publishStatesByConfig(Map args) { + def config = args.get("config") + assert config != null : "publishStatesByConfig: config must be specified" + + def key_ = args.get("key", config.name) + assert key_ != null : "publishStatesByConfig: key must be specified" + + workflow publishStatesSimpleWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] // e.g. [output: new File("myoutput.h5ad"), k: 10] + def origState_ = tup[2] // e.g. [output: '$id.$key.foo.h5ad'] + + // TODO: allow overriding the state.yaml template + // TODO TODO: if auto.publish == "state", add output_state as an argument + def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' + def yamlFilename = yamlTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() + + // the processed state is a list of [key, value] tuples, where + // - key is a String + // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) + // - (key, value) are the tuples that will be saved to the state.yaml file + def processedState = + config.allArguments + .findAll { it.direction == "output" } + .collectMany { par -> + def plainName_ = par.plainName + // if the state does not contain the key, it's an + // optional argument for which the component did + // not generate any output + if (!state_.containsKey(plainName_)) { + return [] + } + def value = state_[plainName_] + // if the parameter is not a file, it should be stored + // in the state as-is, but is not something that needs + // to be copied from the source path to the dest path + if (par.type != "file") { + return [[key: plainName_, value: value]] + } + // if the orig state does not contain this filename, + // it's an optional argument for which the user specified + // that it should not be returned as a state + if (!origState_.containsKey(plainName_)) { + return [] + } + def filenameTemplate = origState_[plainName_] + // if the pararameter is multiple: true, fetch the template + if (par.multiple && filenameTemplate instanceof List) { + filenameTemplate = filenameTemplate[0] + } + // instantiate the template + def filename = filenameTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + if (par.multiple) { + // if the parameter is multiple: true, the filename + // should contain a wildcard '*' that is replaced with + // the index of the file + assert filename.contains("*") : "Module '${key_}' id '${id_}': Multiple output files specified, but no wildcard '*' in the filename: ${filename}" + def outputPerFile = value.withIndex().collect{ val, ix -> + def filename_ix = filename.replace("*", ix.toString()) + def value_ = java.nio.file.Paths.get(filename_ix) + // if id contains a slash + if (yamlDir != null) { + value_ = yamlDir.relativize(value_) + } + return value_ + } + return [["key": plainName_, "value": outputPerFile]] + } else { + def value_ = java.nio.file.Paths.get(filename) + // if id contains a slash + if (yamlDir != null) { + value_ = yamlDir.relativize(value_) + } + def inputPath = value instanceof File ? value.toPath() : value + return [["key": plainName_, value: value_]] + } + } + + + def updatedState_ = processedState.collectEntries{[it.key, it.value]} + + // convert state to yaml blob + def yamlBlob_ = toTaggedYamlBlob([id: id_] + updatedState_) + + [id_, yamlBlob_, yamlFilename] + } + | publishStatesProc + emit: input_ch + } + return publishStatesSimpleWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/setState.nf' +def setState(fun) { + assert fun instanceof Closure || fun instanceof Map || fun instanceof List : + "Error in setState: Expected process argument to be a Closure, a Map, or a List. Found: class ${fun.getClass()}" + + // if fun is a List, convert to map + if (fun instanceof List) { + // check whether fun is a list[string] + assert fun.every{it instanceof CharSequence} : "Error in setState: argument is a List, but not all elements are Strings" + fun = fun.collectEntries{[it, it]} + } + + // if fun is a map, convert to closure + if (fun instanceof Map) { + // check whether fun is a map[string, string] + assert fun.values().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all values are Strings" + assert fun.keySet().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all keys are Strings" + def funMap = fun.clone() + // turn the map into a closure to be used later on + fun = { id_, state_ -> + assert state_ instanceof Map : "Error in setState: the state is not a Map" + funMap.collectMany{newkey, origkey -> + if (state_.containsKey(origkey)) { + [[newkey, state_[origkey]]] + } else { + [] + } + }.collectEntries() + } + } + + map { tup -> + def id = tup[0] + def state = tup[1] + def unfilteredState = fun(id, state) + def newState = unfilteredState.findAll{key, val -> val != null} + [id, newState] + tup.drop(2) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processAuto.nf' +// TODO: unit test processAuto +def processAuto(Map auto) { + // remove null values + auto = auto.findAll{k, v -> v != null} + + // check for unexpected keys + def expectedKeys = ["simplifyInput", "simplifyOutput", "transcript", "publish"] + def unexpectedKeys = auto.keySet() - expectedKeys + assert unexpectedKeys.isEmpty(), "unexpected keys in auto: '${unexpectedKeys.join("', '")}'" + + // check auto.simplifyInput + assert auto.simplifyInput instanceof Boolean, "auto.simplifyInput must be a boolean" + + // check auto.simplifyOutput + assert auto.simplifyOutput instanceof Boolean, "auto.simplifyOutput must be a boolean" + + // check auto.transcript + assert auto.transcript instanceof Boolean, "auto.transcript must be a boolean" + + // check auto.publish + assert auto.publish instanceof Boolean || auto.publish == "state", "auto.publish must be a boolean or 'state'" + + return auto.subMap(expectedKeys) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processDirectives.nf' +def assertMapKeys(map, expectedKeys, requiredKeys, mapName) { + assert map instanceof Map : "Expected argument '$mapName' to be a Map. Found: class ${map.getClass()}" + map.forEach { key, val -> + assert key in expectedKeys : "Unexpected key '$key' in ${mapName ? mapName + " " : ""}map" + } + requiredKeys.forEach { requiredKey -> + assert map.containsKey(requiredKey) : "Missing required key '$key' in ${mapName ? mapName + " " : ""}map" + } +} + +// TODO: unit test processDirectives +def processDirectives(Map drctv) { + // remove null values + drctv = drctv.findAll{k, v -> v != null} + + // check for unexpected keys + def expectedKeys = [ + "accelerator", "afterScript", "beforeScript", "cache", "conda", "container", "containerOptions", "cpus", "disk", "echo", "errorStrategy", "executor", "machineType", "maxErrors", "maxForks", "maxRetries", "memory", "module", "penv", "pod", "publishDir", "queue", "label", "scratch", "storeDir", "stageInMode", "stageOutMode", "tag", "time" + ] + def unexpectedKeys = drctv.keySet() - expectedKeys + assert unexpectedKeys.isEmpty() : "Unexpected keys in process directive: '${unexpectedKeys.join("', '")}'" + + /* DIRECTIVE accelerator + accepted examples: + - [ limit: 4, type: "nvidia-tesla-k80" ] + */ + if (drctv.containsKey("accelerator")) { + assertMapKeys(drctv["accelerator"], ["type", "limit", "request", "runtime"], [], "accelerator") + } + + /* DIRECTIVE afterScript + accepted examples: + - "source /cluster/bin/cleanup" + */ + if (drctv.containsKey("afterScript")) { + assert drctv["afterScript"] instanceof CharSequence + } + + /* DIRECTIVE beforeScript + accepted examples: + - "source /cluster/bin/setup" + */ + if (drctv.containsKey("beforeScript")) { + assert drctv["beforeScript"] instanceof CharSequence + } + + /* DIRECTIVE cache + accepted examples: + - true + - false + - "deep" + - "lenient" + */ + if (drctv.containsKey("cache")) { + assert drctv["cache"] instanceof CharSequence || drctv["cache"] instanceof Boolean + if (drctv["cache"] instanceof CharSequence) { + assert drctv["cache"] in ["deep", "lenient"] : "Unexpected value for cache" + } + } + + /* DIRECTIVE conda + accepted examples: + - "bwa=0.7.15" + - "bwa=0.7.15 fastqc=0.11.5" + - ["bwa=0.7.15", "fastqc=0.11.5"] + */ + if (drctv.containsKey("conda")) { + if (drctv["conda"] instanceof List) { + drctv["conda"] = drctv["conda"].join(" ") + } + assert drctv["conda"] instanceof CharSequence + } + + /* DIRECTIVE container + accepted examples: + - "foo/bar:tag" + - [ registry: "reg", image: "im", tag: "ta" ] + is transformed to "reg/im:ta" + - [ image: "im" ] + is transformed to "im:latest" + */ + if (drctv.containsKey("container")) { + assert drctv["container"] instanceof Map || drctv["container"] instanceof CharSequence + if (drctv["container"] instanceof Map) { + def m = drctv["container"] + assertMapKeys(m, [ "registry", "image", "tag" ], ["image"], "container") + def part1 = + System.getenv('OVERRIDE_CONTAINER_REGISTRY') ? System.getenv('OVERRIDE_CONTAINER_REGISTRY') + "/" : + params.containsKey("override_container_registry") ? params["override_container_registry"] + "/" : // todo: remove? + m.registry ? m.registry + "/" : + "" + def part2 = m.image + def part3 = m.tag ? ":" + m.tag : ":latest" + drctv["container"] = part1 + part2 + part3 + } + } + + /* DIRECTIVE containerOptions + accepted examples: + - "--foo bar" + - ["--foo bar", "-f b"] + */ + if (drctv.containsKey("containerOptions")) { + if (drctv["containerOptions"] instanceof List) { + drctv["containerOptions"] = drctv["containerOptions"].join(" ") + } + assert drctv["containerOptions"] instanceof CharSequence + } + + /* DIRECTIVE cpus + accepted examples: + - 1 + - 10 + */ + if (drctv.containsKey("cpus")) { + assert drctv["cpus"] instanceof Integer + } + + /* DIRECTIVE disk + accepted examples: + - "1 GB" + - "2TB" + - "3.2KB" + - "10.B" + */ + if (drctv.containsKey("disk")) { + assert drctv["disk"] instanceof CharSequence + // assert drctv["disk"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") + // ^ does not allow closures + } + + /* DIRECTIVE echo + accepted examples: + - true + - false + */ + if (drctv.containsKey("echo")) { + assert drctv["echo"] instanceof Boolean + } + + /* DIRECTIVE errorStrategy + accepted examples: + - "terminate" + - "finish" + */ + if (drctv.containsKey("errorStrategy")) { + assert drctv["errorStrategy"] instanceof CharSequence + assert drctv["errorStrategy"] in ["terminate", "finish", "ignore", "retry"] : "Unexpected value for errorStrategy" + } + + /* DIRECTIVE executor + accepted examples: + - "local" + - "sge" + */ + if (drctv.containsKey("executor")) { + assert drctv["executor"] instanceof CharSequence + assert drctv["executor"] in ["local", "sge", "uge", "lsf", "slurm", "pbs", "pbspro", "moab", "condor", "nqsii", "ignite", "k8s", "awsbatch", "google-pipelines"] : "Unexpected value for executor" + } + + /* DIRECTIVE machineType + accepted examples: + - "n1-highmem-8" + */ + if (drctv.containsKey("machineType")) { + assert drctv["machineType"] instanceof CharSequence + } + + /* DIRECTIVE maxErrors + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxErrors")) { + assert drctv["maxErrors"] instanceof Integer + } + + /* DIRECTIVE maxForks + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxForks")) { + assert drctv["maxForks"] instanceof Integer + } + + /* DIRECTIVE maxRetries + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxRetries")) { + assert drctv["maxRetries"] instanceof Integer + } + + /* DIRECTIVE memory + accepted examples: + - "1 GB" + - "2TB" + - "3.2KB" + - "10.B" + */ + if (drctv.containsKey("memory")) { + assert drctv["memory"] instanceof CharSequence + // assert drctv["memory"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") + // ^ does not allow closures + } + + /* DIRECTIVE module + accepted examples: + - "ncbi-blast/2.2.27" + - "ncbi-blast/2.2.27:t_coffee/10.0" + - ["ncbi-blast/2.2.27", "t_coffee/10.0"] + */ + if (drctv.containsKey("module")) { + if (drctv["module"] instanceof List) { + drctv["module"] = drctv["module"].join(":") + } + assert drctv["module"] instanceof CharSequence + } + + /* DIRECTIVE penv + accepted examples: + - "smp" + */ + if (drctv.containsKey("penv")) { + assert drctv["penv"] instanceof CharSequence + } + + /* DIRECTIVE pod + accepted examples: + - [ label: "key", value: "val" ] + - [ annotation: "key", value: "val" ] + - [ env: "key", value: "val" ] + - [ [label: "l", value: "v"], [env: "e", value: "v"]] + */ + if (drctv.containsKey("pod")) { + if (drctv["pod"] instanceof Map) { + drctv["pod"] = [ drctv["pod"] ] + } + assert drctv["pod"] instanceof List + drctv["pod"].forEach { pod -> + assert pod instanceof Map + // TODO: should more checks be added? + // See https://www.nextflow.io/docs/latest/process.html?highlight=directives#pod + // e.g. does it contain 'label' and 'value', or 'annotation' and 'value', or ...? + } + } + + /* DIRECTIVE publishDir + accepted examples: + - [] + - [ [ path: "foo", enabled: true ], [ path: "bar", enabled: false ] ] + - "/path/to/dir" + is transformed to [[ path: "/path/to/dir" ]] + - [ path: "/path/to/dir", mode: "cache" ] + is transformed to [[ path: "/path/to/dir", mode: "cache" ]] + */ + // TODO: should we also look at params["publishDir"]? + if (drctv.containsKey("publishDir")) { + def pblsh = drctv["publishDir"] + + // check different options + assert pblsh instanceof List || pblsh instanceof Map || pblsh instanceof CharSequence + + // turn into list if not already so + // for some reason, 'if (!pblsh instanceof List) pblsh = [ pblsh ]' doesn't work. + pblsh = pblsh instanceof List ? pblsh : [ pblsh ] + + // check elements of publishDir + pblsh = pblsh.collect{ elem -> + // turn into map if not already so + elem = elem instanceof CharSequence ? [ path: elem ] : elem + + // check types and keys + assert elem instanceof Map : "Expected publish argument '$elem' to be a String or a Map. Found: class ${elem.getClass()}" + assertMapKeys(elem, [ "path", "mode", "overwrite", "pattern", "saveAs", "enabled" ], ["path"], "publishDir") + + // check elements in map + assert elem.containsKey("path") + assert elem["path"] instanceof CharSequence + if (elem.containsKey("mode")) { + assert elem["mode"] instanceof CharSequence + assert elem["mode"] in [ "symlink", "rellink", "link", "copy", "copyNoFollow", "move" ] + } + if (elem.containsKey("overwrite")) { + assert elem["overwrite"] instanceof Boolean + } + if (elem.containsKey("pattern")) { + assert elem["pattern"] instanceof CharSequence + } + if (elem.containsKey("saveAs")) { + assert elem["saveAs"] instanceof CharSequence //: "saveAs as a Closure is currently not supported. Surround your closure with single quotes to get the desired effect. Example: '\{ foo \}'" + } + if (elem.containsKey("enabled")) { + assert elem["enabled"] instanceof Boolean + } + + // return final result + elem + } + // store final directive + drctv["publishDir"] = pblsh + } + + /* DIRECTIVE queue + accepted examples: + - "long" + - "short,long" + - ["short", "long"] + */ + if (drctv.containsKey("queue")) { + if (drctv["queue"] instanceof List) { + drctv["queue"] = drctv["queue"].join(",") + } + assert drctv["queue"] instanceof CharSequence + } + + /* DIRECTIVE label + accepted examples: + - "big_mem" + - "big_cpu" + - ["big_mem", "big_cpu"] + */ + if (drctv.containsKey("label")) { + if (drctv["label"] instanceof CharSequence) { + drctv["label"] = [ drctv["label"] ] + } + assert drctv["label"] instanceof List + drctv["label"].forEach { label -> + assert label instanceof CharSequence + // assert label.matches("[a-zA-Z0-9]([a-zA-Z0-9_]*[a-zA-Z0-9])?") + // ^ does not allow closures + } + } + + /* DIRECTIVE scratch + accepted examples: + - true + - "/path/to/scratch" + - '$MY_PATH_TO_SCRATCH' + - "ram-disk" + */ + if (drctv.containsKey("scratch")) { + assert drctv["scratch"] == true || drctv["scratch"] instanceof CharSequence + } + + /* DIRECTIVE storeDir + accepted examples: + - "/path/to/storeDir" + */ + if (drctv.containsKey("storeDir")) { + assert drctv["storeDir"] instanceof CharSequence + } + + /* DIRECTIVE stageInMode + accepted examples: + - "copy" + - "link" + */ + if (drctv.containsKey("stageInMode")) { + assert drctv["stageInMode"] instanceof CharSequence + assert drctv["stageInMode"] in ["copy", "link", "symlink", "rellink"] + } + + /* DIRECTIVE stageOutMode + accepted examples: + - "copy" + - "link" + */ + if (drctv.containsKey("stageOutMode")) { + assert drctv["stageOutMode"] instanceof CharSequence + assert drctv["stageOutMode"] in ["copy", "move", "rsync"] + } + + /* DIRECTIVE tag + accepted examples: + - "foo" + - '$id' + */ + if (drctv.containsKey("tag")) { + assert drctv["tag"] instanceof CharSequence + } + + /* DIRECTIVE time + accepted examples: + - "1h" + - "2days" + - "1day 6hours 3minutes 30seconds" + */ + if (drctv.containsKey("time")) { + assert drctv["time"] instanceof CharSequence + // todo: validation regex? + } + + return drctv +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processWorkflowArgs.nf' +def processWorkflowArgs(Map args, Map defaultWfArgs, Map meta) { + // override defaults with args + def workflowArgs = defaultWfArgs + args + + // check whether 'key' exists + assert workflowArgs.containsKey("key") : "Error in module '${meta.config.name}': key is a required argument" + + // if 'key' is a closure, apply it to the original key + if (workflowArgs["key"] instanceof Closure) { + workflowArgs["key"] = workflowArgs["key"](meta.config.name) + } + def key = workflowArgs["key"] + assert key instanceof CharSequence : "Expected process argument 'key' to be a String. Found: class ${key.getClass()}" + assert key ==~ /^[a-zA-Z_]\w*$/ : "Error in module '$key': Expected process argument 'key' to consist of only letters, digits or underscores. Found: ${key}" + + // check for any unexpected keys + def expectedKeys = ["key", "directives", "auto", "map", "mapId", "mapData", "mapPassthrough", "filter", "runIf", "fromState", "toState", "args", "renameKeys", "debug"] + def unexpectedKeys = workflowArgs.keySet() - expectedKeys + assert unexpectedKeys.isEmpty() : "Error in module '$key': unexpected arguments to the '.run()' function: '${unexpectedKeys.join("', '")}'" + + // check whether directives exists and apply defaults + assert workflowArgs.containsKey("directives") : "Error in module '$key': directives is a required argument" + assert workflowArgs["directives"] instanceof Map : "Error in module '$key': Expected process argument 'directives' to be a Map. Found: class ${workflowArgs['directives'].getClass()}" + workflowArgs["directives"] = processDirectives(defaultWfArgs.directives + workflowArgs["directives"]) + + // check whether directives exists and apply defaults + assert workflowArgs.containsKey("auto") : "Error in module '$key': auto is a required argument" + assert workflowArgs["auto"] instanceof Map : "Error in module '$key': Expected process argument 'auto' to be a Map. Found: class ${workflowArgs['auto'].getClass()}" + workflowArgs["auto"] = processAuto(defaultWfArgs.auto + workflowArgs["auto"]) + + // auto define publish, if so desired + if (workflowArgs.auto.publish == true && (workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : [:]).isEmpty()) { + // can't assert at this level thanks to the no_publish profile + // assert params.containsKey("publishDir") || params.containsKey("publish_dir") : + // "Error in module '${workflowArgs['key']}': if auto.publish is true, params.publish_dir needs to be defined.\n" + + // " Example: params.publish_dir = \"./output/\"" + def publishDir = getPublishDir() + + if (publishDir != null) { + workflowArgs.directives.publishDir = [[ + path: publishDir, + saveAs: "{ it.startsWith('.') ? null : it }", // don't publish hidden files, by default + mode: "copy" + ]] + } + } + + // auto define transcript, if so desired + if (workflowArgs.auto.transcript == true) { + // can't assert at this level thanks to the no_publish profile + // assert params.containsKey("transcriptsDir") || params.containsKey("transcripts_dir") || params.containsKey("publishDir") || params.containsKey("publish_dir") : + // "Error in module '${workflowArgs['key']}': if auto.transcript is true, either params.transcripts_dir or params.publish_dir needs to be defined.\n" + + // " Example: params.transcripts_dir = \"./transcripts/\"" + def transcriptsDir = + params.containsKey("transcripts_dir") ? params.transcripts_dir : + params.containsKey("transcriptsDir") ? params.transcriptsDir : + params.containsKey("publish_dir") ? params.publish_dir + "/_transcripts" : + params.containsKey("publishDir") ? params.publishDir + "/_transcripts" : + null + if (transcriptsDir != null) { + def timestamp = nextflow.Nextflow.getSession().getWorkflowMetadata().start.format('yyyy-MM-dd_HH-mm-ss') + def transcriptsPublishDir = [ + path: "$transcriptsDir/$timestamp/\${task.process.replaceAll(':', '-')}/\${id}/", + saveAs: "{ it.startsWith('.') ? it.replaceAll('^.', '') : null }", + mode: "copy" + ] + def publishDirs = workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : null ? workflowArgs.directives.publishDir : [] + workflowArgs.directives.publishDir = publishDirs + transcriptsPublishDir + } + } + + // if this is a stubrun, remove certain directives? + if (workflow.stubRun) { + workflowArgs.directives.keySet().removeAll(["publishDir", "cpus", "memory", "label"]) + } + + for (nam in ["map", "mapId", "mapData", "mapPassthrough", "filter", "runIf"]) { + if (workflowArgs.containsKey(nam) && workflowArgs[nam]) { + assert workflowArgs[nam] instanceof Closure : "Error in module '$key': Expected process argument '$nam' to be null or a Closure. Found: class ${workflowArgs[nam].getClass()}" + } + } + + // TODO: should functions like 'map', 'mapId', 'mapData', 'mapPassthrough' be deprecated as well? + for (nam in ["map", "mapData", "mapPassthrough", "renameKeys"]) { + if (workflowArgs.containsKey(nam) && workflowArgs[nam] != null) { + log.warn "module '$key': workflow argument '$nam' is deprecated and will be removed in Viash 0.9.0. Please use 'fromState' and 'toState' instead." + } + } + + // check fromState + workflowArgs["fromState"] = _processFromState(workflowArgs.get("fromState"), key, meta.config) + + // check toState + workflowArgs["toState"] = _processToState(workflowArgs.get("toState"), key, meta.config) + + // return output + return workflowArgs +} + +def _processFromState(fromState, key_, config_) { + assert fromState == null || fromState instanceof Closure || fromState instanceof Map || fromState instanceof List : + "Error in module '$key_': Expected process argument 'fromState' to be null, a Closure, a Map, or a List. Found: class ${fromState.getClass()}" + if (fromState == null) { + return null + } + + // if fromState is a List, convert to map + if (fromState instanceof List) { + // check whether fromstate is a list[string] + assert fromState.every{it instanceof CharSequence} : "Error in module '$key_': fromState is a List, but not all elements are Strings" + fromState = fromState.collectEntries{[it, it]} + } + + // if fromState is a map, convert to closure + if (fromState instanceof Map) { + // check whether fromstate is a map[string, string] + assert fromState.values().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all values are Strings" + assert fromState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all keys are Strings" + def fromStateMap = fromState.clone() + def requiredInputNames = meta.config.allArguments.findAll{it.required && it.direction == "Input"}.collect{it.plainName} + // turn the map into a closure to be used later on + fromState = { it -> + def state = it[1] + assert state instanceof Map : "Error in module '$key_': the state is not a Map" + def data = fromStateMap.collectMany{newkey, origkey -> + // check whether newkey corresponds to a required argument + if (state.containsKey(origkey)) { + [[newkey, state[origkey]]] + } else if (!requiredInputNames.contains(origkey)) { + [] + } else { + throw new Exception("Error in module '$key_': fromState key '$origkey' not found in current state") + } + }.collectEntries() + data + } + } + + return fromState +} + +def _processToState(toState, key_, config_) { + if (toState == null) { + toState = { tup -> tup[1] } + } + + // toState should be a closure, map[string, string], or list[string] + assert toState instanceof Closure || toState instanceof Map || toState instanceof List : + "Error in module '$key_': Expected process argument 'toState' to be a Closure, a Map, or a List. Found: class ${toState.getClass()}" + + // if toState is a List, convert to map + if (toState instanceof List) { + // check whether toState is a list[string] + assert toState.every{it instanceof CharSequence} : "Error in module '$key_': toState is a List, but not all elements are Strings" + toState = toState.collectEntries{[it, it]} + } + + // if toState is a map, convert to closure + if (toState instanceof Map) { + // check whether toState is a map[string, string] + assert toState.values().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all values are Strings" + assert toState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all keys are Strings" + def toStateMap = toState.clone() + def requiredOutputNames = config_.allArguments.findAll{it.required && it.direction == "Output"}.collect{it.plainName} + // turn the map into a closure to be used later on + toState = { it -> + def output = it[1] + def state = it[2] + assert output instanceof Map : "Error in module '$key_': the output is not a Map" + assert state instanceof Map : "Error in module '$key_': the state is not a Map" + def extraEntries = toStateMap.collectMany{newkey, origkey -> + // check whether newkey corresponds to a required argument + if (output.containsKey(origkey)) { + [[newkey, output[origkey]]] + } else if (!requiredOutputNames.contains(origkey)) { + [] + } else { + throw new Exception("Error in module '$key_': toState key '$origkey' not found in current output") + } + }.collectEntries() + state + extraEntries + } + } + + return toState +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/workflowFactory.nf' +def _debug(workflowArgs, debugKey) { + if (workflowArgs.debug) { + view { "process '${workflowArgs.key}' $debugKey tuple: $it" } + } else { + map { it } + } +} + +// depends on: innerWorkflowFactory +def workflowFactory(Map args, Map defaultWfArgs, Map meta) { + def workflowArgs = processWorkflowArgs(args, defaultWfArgs, meta) + def key_ = workflowArgs["key"] + def multipleArgs = meta.config.allArguments.findAll{ it.multiple }.collect{it.plainName} + + workflow workflowInstance { + take: input_ + + main: + def chModified = input_ + | checkUniqueIds([:]) + | _debug(workflowArgs, "input") + | map { tuple -> + tuple = deepClone(tuple) + + if (workflowArgs.map) { + tuple = workflowArgs.map(tuple) + } + if (workflowArgs.mapId) { + tuple[0] = workflowArgs.mapId(tuple[0]) + } + if (workflowArgs.mapData) { + tuple[1] = workflowArgs.mapData(tuple[1]) + } + if (workflowArgs.mapPassthrough) { + tuple = tuple.take(2) + workflowArgs.mapPassthrough(tuple.drop(2)) + } + + // check tuple + assert tuple instanceof List : + "Error in module '${key_}': element in channel should be a tuple [id, data, ...otherargs...]\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: List. Found: tuple.getClass() is ${tuple.getClass()}" + assert tuple.size() >= 2 : + "Error in module '${key_}': expected length of tuple in input channel to be two or greater.\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Found: tuple.size() == ${tuple.size()}" + + // check id field + if (tuple[0] instanceof GString) { + tuple[0] = tuple[0].toString() + } + assert tuple[0] instanceof CharSequence : + "Error in module '${key_}': first element of tuple in channel should be a String\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Found: ${tuple[0]}" + + // match file to input file + if (workflowArgs.auto.simplifyInput && (tuple[1] instanceof Path || tuple[1] instanceof List)) { + def inputFiles = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + + assert inputFiles.size() == 1 : + "Error in module '${key_}' id '${tuple[0]}'.\n" + + " Anonymous file inputs are only allowed when the process has exactly one file input.\n" + + " Expected: inputFiles.size() == 1. Found: inputFiles.size() is ${inputFiles.size()}" + + tuple[1] = [[ inputFiles[0].plainName, tuple[1] ]].collectEntries() + } + + // check data field + assert tuple[1] instanceof Map : + "Error in module '${key_}' id '${tuple[0]}': second element of tuple in channel should be a Map\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" + + // rename keys of data field in tuple + if (workflowArgs.renameKeys) { + assert workflowArgs.renameKeys instanceof Map : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class: Map. Found: renameKeys.getClass() is ${workflowArgs.renameKeys.getClass()}" + assert tuple[1] instanceof Map : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" + + // TODO: allow renameKeys to be a function? + workflowArgs.renameKeys.each { newKey, oldKey -> + assert newKey instanceof CharSequence : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class of newKey: String. Found: newKey.getClass() is ${newKey.getClass()}" + assert oldKey instanceof CharSequence : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class of oldKey: String. Found: oldKey.getClass() is ${oldKey.getClass()}" + assert tuple[1].containsKey(oldKey) : + "Error renaming data keys in module '${key}' id '${tuple[0]}'.\n" + + " Key '$oldKey' is missing in the data map. tuple[1].keySet() is '${tuple[1].keySet()}'" + tuple[1].put(newKey, tuple[1][oldKey]) + } + tuple[1].keySet().removeAll(workflowArgs.renameKeys.collect{ newKey, oldKey -> oldKey }) + } + tuple + } + + + def chRun = null + def chPassthrough = null + if (workflowArgs.runIf) { + def runIfBranch = chModified.branch{ tup -> + run: workflowArgs.runIf(tup[0], tup[1]) + passthrough: true + } + chRun = runIfBranch.run + chPassthrough = runIfBranch.passthrough + } else { + chRun = chModified + chPassthrough = Channel.empty() + } + + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + + def chArgs = workflowArgs.fromState ? + chRunFiltered | map{ + def new_data = workflowArgs.fromState(it.take(2)) + [it[0], new_data] + } : + chRunFiltered | map {tup -> tup.take(2)} + + // fill in defaults + def chArgsWithDefaults = chArgs + | map { tuple -> + def id_ = tuple[0] + def data_ = tuple[1] + + // TODO: could move fromState to here + + // fetch default params from functionality + def defaultArgs = meta.config.allArguments + .findAll { it.containsKey("default") } + .collectEntries { [ it.plainName, it.default ] } + + // fetch overrides in params + def paramArgs = meta.config.allArguments + .findAll { par -> + def argKey = key_ + "__" + par.plainName + params.containsKey(argKey) + } + .collectEntries { [ it.plainName, params[key_ + "__" + it.plainName] ] } + + // fetch overrides in data + def dataArgs = meta.config.allArguments + .findAll { data_.containsKey(it.plainName) } + .collectEntries { [ it.plainName, data_[it.plainName] ] } + + // combine params + def combinedArgs = defaultArgs + paramArgs + workflowArgs.args + dataArgs + + // remove arguments with explicit null values + combinedArgs + .removeAll{_, val -> val == null || val == "viash_no_value" || val == "force_null"} + + combinedArgs = _processInputValues(combinedArgs, meta.config, id_, key_) + + [id_, combinedArgs] + tuple.drop(2) + } + + // TODO: move some of the _meta.join_id wrangling to the safeJoin() function. + def chInitialOutputMulti = chArgsWithDefaults + | _debug(workflowArgs, "processed") + // run workflow + | innerWorkflowFactory(workflowArgs) + def chInitialOutputList = chInitialOutputMulti instanceof List ? chInitialOutputMulti : [chInitialOutputMulti] + assert chInitialOutputList.size() > 0: "should have emitted at least one output channel" + // Add a channel ID to the events, which designates the channel the event was emitted from as a running number + // This number is used to sort the events later when the events are gathered from across the channels. + def chInitialOutputListWithIndexedEvents = chInitialOutputList.withIndex().collect{channel, channelIndex -> + def newChannel = channel + | map {tuple -> + assert tuple instanceof List : + "Error in module '${key_}': element in output channel should be a tuple [id, data, ...otherargs...]\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: List. Found: tuple.getClass() is ${tuple.getClass()}" + + def newEvent = [channelIndex] + tuple + return newEvent + } + return newChannel + } + // Put the events into 1 channel, cover case where there is only one channel is emitted + def chInitialOutput = chInitialOutputList.size() > 1 ? \ + chInitialOutputListWithIndexedEvents[0].mix(*chInitialOutputListWithIndexedEvents.tail()) : \ + chInitialOutputListWithIndexedEvents[0] + def chInitialOutputProcessed = chInitialOutput + | map { tuple -> + def channelId = tuple[0] + def id_ = tuple[1] + def output_ = tuple[2] + + // see if output map contains metadata + def meta_ = + output_ instanceof Map && output_.containsKey("_meta") ? + output_["_meta"] : + [:] + def join_id = meta_.join_id ?: id_ + + // remove metadata + output_ = output_.findAll{k, v -> k != "_meta"} + + // check value types + output_ = _checkValidOutputArgument(output_, meta.config, id_, key_) + + [join_id, channelId, id_, output_] + } + // | view{"chInitialOutput: ${it.take(3)}"} + + // join the output [prev_id, channel_id, new_id, output] with the previous state [prev_id, state, ...] + def chPublishWithPreviousState = safeJoin(chInitialOutputProcessed, chRunFiltered, key_) + // input tuple format: [join_id, channel_id, id, output, prev_state, ...] + // output tuple format: [join_id, channel_id, id, new_state, ...] + | map{ tup -> + def new_state = workflowArgs.toState(tup.drop(2).take(3)) + tup.take(3) + [new_state] + tup.drop(5) + } + if (workflowArgs.auto.publish == "state") { + def chPublishFiles = chPublishWithPreviousState + // input tuple format: [join_id, channel_id, id, new_state, ...] + // output tuple format: [join_id, channel_id, id, new_state] + | map{ tup -> + tup.take(4) + } + + safeJoin(chPublishFiles, chArgsWithDefaults, key_) + // input tuple format: [join_id, channel_id, id, new_state, orig_state, ...] + // output tuple format: [id, new_state, orig_state] + | map { tup -> + tup.drop(2).take(3) + } + | publishFilesByConfig(key: key_, config: meta.config) + } + // Join the state from the events that were emitted from different channels + def chJoined = chInitialOutputProcessed + | map {tuple -> + def join_id = tuple[0] + def channel_id = tuple[1] + def id = tuple[2] + def other = tuple.drop(3) + // Below, groupTuple is used to join the events. To make sure resuming a workflow + // keeps working, the output state must be deterministic. This means the state needs to be + // sorted with groupTuple's has a 'sort' argument. This argument can be set to 'hash', + // but hashing the state when it is large can be problematic in terms of performance. + // Therefore, a custom comparator function is provided. We add the channel ID to the + // states so that we can use the channel ID to sort the items. + def stateWithChannelID = [[channel_id] * other.size(), other].transpose() + // A comparator that is provided to groupTuple's 'sort' argument is applied + // to all elements of the event tuple (that is not the 'id'). The comparator + // closure that is used below expects the input to be List. So the join_id and + // channel_id must also be wrapped in a list. + [[join_id], [channel_id], id] + stateWithChannelID + } + | groupTuple(by: 2, sort: {a, b -> a[0] <=> b[0]}, size: chInitialOutputList.size(), remainder: true) + | map {join_ids, _, id, statesWithChannelID -> + // Remove the channel IDs from the states + def states = statesWithChannelID.collect{it[1]} + def newJoinId = join_ids.flatten().unique{a, b -> a <=> b} + assert newJoinId.size() == 1: "Multiple events were emitted for '$id'." + def newJoinIdUnique = newJoinId[0] + + // Merge the states from the different channels + def newState = states.inject([:]){ old_state, state_to_add -> + return old_state + state_to_add.collectEntries{k, v -> + if (!multipleArgs.contains(k)) { + // if the key is not a multiple argument, we expect only one value + if (old_state.containsKey(k)) { + assert old_state[k] == v : "ID $id: multiple entries for argument $k were emitted." + } + [k, v] + } else { + // if the key is a multiple argument, append the different values into one list + def prevValue = old_state.getOrDefault(k, []) + def prevValueAsList = prevValue instanceof List ? prevValue : [prevValue] + [k, prevValueAsList + v] + } + } + } + + _checkAllRequiredOuputsPresent(newState, meta.config, id, key_) + + // simplify output if need be + if (workflowArgs.auto.simplifyOutput && newState.size() == 1) { + newState = newState.values()[0] + } + + return [newJoinIdUnique, id, newState] + } + + // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] + def chNewState = safeJoin(chJoined, chRunFiltered, key_) + // input tuple format: [join_id, id, output, prev_state, ...] + // output tuple format: [join_id, id, new_state, ...] + | map{ tup -> + def new_state = workflowArgs.toState(tup.drop(1).take(3)) + tup.take(2) + [new_state] + tup.drop(4) + } + + if (workflowArgs.auto.publish == "state") { + def chPublishStates = chNewState + // input tuple format: [join_id, id, new_state, ...] + // output tuple format: [join_id, id, new_state] + | map{ tup -> + tup.take(3) + } + + safeJoin(chPublishStates, chArgsWithDefaults, key_) + // input tuple format: [join_id, id, new_state, orig_state, ...] + // output tuple format: [id, new_state, orig_state] + | map { tup -> + tup.drop(1).take(3) + } + | publishStatesByConfig(key: key_, config: meta.config) + } + chReturn = chNewState + | map { tup -> + // input tuple format: [join_id, id, new_state, ...] + // output tuple format: [id, new_state, ...] + tup.drop(1) + } + | _debug(workflowArgs, "output") + | concat(chPassthrough) + + emit: chReturn + } + + def wf = workflowInstance.cloneWithName(key_) + + // add factory function + wf.metaClass.run = { runArgs -> + workflowFactory(runArgs, workflowArgs, meta) + } + // add config to module for later introspection + wf.metaClass.config = meta.config + + return wf +} + +nextflow.enable.dsl=2 + +// START COMPONENT-SPECIFIC CODE + +// create meta object +meta = [ + "resources_dir": moduleDir.toRealPath().normalize(), + "config": processConfig(readJsonBlob('''{ + "name" : "concat_text", + "version" : "v0.2.0", + "authors" : [ + { + "name" : "Toni Verbeiren", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "github" : "tverbeiren", + "linkedin" : "verbeiren" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist and CEO" + } + ] + } + }, + { + "name" : "Dries Schaumont", + "roles" : [ + "reviewer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], + "argument_groups" : [ + { + "name" : "Input arguments", + "arguments" : [ + { + "type" : "file", + "name" : "--input", + "description" : "A list of (gzipped) text files.", + "example" : [ + "input?.txt.gz" + ], + "must_exist" : true, + "create_parent" : true, + "required" : true, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + } + ] + }, + { + "name" : "Output arguments", + "arguments" : [ + { + "type" : "boolean_true", + "name" : "--gzip_output", + "description" : "Should the output be zipped?", + "direction" : "input" + }, + { + "type" : "file", + "name" : "--output", + "description" : "File to write the output to, optionally gzipped.", + "example" : [ + "output.txt" + ], + "must_exist" : true, + "create_parent" : true, + "required" : false, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" + } + ] + } + ], + "resources" : [ + { + "type" : "bash_script", + "path" : "script.sh", + "is_executable" : true + } + ], + "summary" : "Concatenate a number of text files", + "description" : "Concatenate a number of text files, handle gzipped text files gracefully and\noptionally gzip the output text file.\n\nThis component is useful for concatening fastq files from different lanes, for instance.\n", + "test_resources" : [ + { + "type" : "bash_script", + "path" : "test.sh", + "is_executable" : true + } + ], + "info" : { + "improvements" : "This component could be improved in 2 ways:\n 1. Allow for a mix of zipped and plain input files\n 2. Allow to specify a compression algorithm for the output\n" + }, + "status" : "enabled", + "scope" : { + "image" : "public", + "target" : "public" + }, + "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" : "alpine:latest", + "target_registry" : "images.viash-hub.com", + "target_tag" : "v0.2.0", + "namespace_separator" : "/", + "setup" : [ + { + "type" : "apk", + "packages" : [ + "bash", + "procps", + "file" + ] + } + ] + }, + { + "type" : "native", + "id" : "native" + } + ], + "build_info" : { + "config" : "/workdir/root/repo/src/concat_text/config.vsh.yaml", + "runner" : "nextflow", + "engine" : "docker|native", + "output" : "target/nextflow/concat_text", + "viash_version" : "0.9.4", + "git_commit" : "1c1b0a4a1aff891ab678072b0ba915ac3ac71610", + "git_remote" : "https://github.com/viash-hub/craftbox", + "git_tag" : "v0.1.0-8-g1c1b0a4" + }, + "package_config" : { + "name" : "craftbox", + "version" : "v0.2.0", + "summary" : "A collection of custom-tailored scripts and applied utilities built with Viash.\n", + "description" : "`craftbox` is a curated collection of custom scripts and utilities designed to tackle context-specific tasks.\n\nEmphasizing the Viash principles, `craftbox` components aim for **reusability**, **reproducibility**, and adherence to **best practices**. Key features generally include:\n\n* **Standalone & Nextflow Ready:** Components are built to run directly via the command line or be smoothly integrated into Nextflow workflows.\n* **Custom Implementations:** Contains scripts and tools developed for particular tasks that may not be found in broader collections.\n* **High Quality Standards (promoted by Viash):**\n * Clear documentation for components and their parameters.\n * Full exposure of underlying script/tool arguments for fine-grained control.\n * Containerized (Docker) to ensure dependency management and a consistent, reproducible runtime environment.\n * Unit tested where applicable to ensure components function as expected.\n", + "viash_version" : "0.9.4", + "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 := 'v0.2.0'" + ], + "keywords" : [ + "scripts", + "custom", + "implementations", + "utilities" + ], + "license" : "MIT", + "organization" : "vsh", + "links" : { + "repository" : "https://github.com/viash-hub/craftbox", + "issue_tracker" : "https://github.com/viash-hub/craftbox/issues" + } + } +}''')) +] + +// resolve dependencies dependencies (if any) + + +// inner workflow +// inner workflow hook +def innerWorkflowFactory(args) { + def rawScript = '''set -e +tempscript=".viash_script.sh" +cat > "$tempscript" << VIASHMAIN +## VIASH START +# The following code has been auto-generated by Viash. +$( if [ ! -z ${VIASH_PAR_INPUT+x} ]; then echo "${VIASH_PAR_INPUT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_input='&'#" ; else echo "# par_input="; fi ) +$( if [ ! -z ${VIASH_PAR_GZIP_OUTPUT+x} ]; then echo "${VIASH_PAR_GZIP_OUTPUT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_gzip_output='&'#" ; else echo "# par_gzip_output="; fi ) +$( if [ ! -z ${VIASH_PAR_OUTPUT+x} ]; then echo "${VIASH_PAR_OUTPUT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_output='&'#" ; else echo "# par_output="; fi ) +$( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "${VIASH_META_NAME}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_name='&'#" ; else echo "# meta_name="; fi ) +$( if [ ! -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then echo "${VIASH_META_FUNCTIONALITY_NAME}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_functionality_name='&'#" ; else echo "# meta_functionality_name="; fi ) +$( if [ ! -z ${VIASH_META_RESOURCES_DIR+x} ]; then echo "${VIASH_META_RESOURCES_DIR}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_resources_dir='&'#" ; else echo "# meta_resources_dir="; fi ) +$( if [ ! -z ${VIASH_META_EXECUTABLE+x} ]; then echo "${VIASH_META_EXECUTABLE}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_executable='&'#" ; else echo "# meta_executable="; fi ) +$( if [ ! -z ${VIASH_META_CONFIG+x} ]; then echo "${VIASH_META_CONFIG}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_config='&'#" ; else echo "# meta_config="; fi ) +$( if [ ! -z ${VIASH_META_TEMP_DIR+x} ]; then echo "${VIASH_META_TEMP_DIR}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_temp_dir='&'#" ; else echo "# meta_temp_dir="; fi ) +$( if [ ! -z ${VIASH_META_CPUS+x} ]; then echo "${VIASH_META_CPUS}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_cpus='&'#" ; else echo "# meta_cpus="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_B+x} ]; then echo "${VIASH_META_MEMORY_B}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_b='&'#" ; else echo "# meta_memory_b="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_KB+x} ]; then echo "${VIASH_META_MEMORY_KB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_kb='&'#" ; else echo "# meta_memory_kb="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_MB+x} ]; then echo "${VIASH_META_MEMORY_MB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_mb='&'#" ; else echo "# meta_memory_mb="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_GB+x} ]; then echo "${VIASH_META_MEMORY_GB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_gb='&'#" ; else echo "# meta_memory_gb="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_TB+x} ]; then echo "${VIASH_META_MEMORY_TB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_tb='&'#" ; else echo "# meta_memory_tb="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_PB+x} ]; then echo "${VIASH_META_MEMORY_PB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_pb='&'#" ; else echo "# meta_memory_pb="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_KIB+x} ]; then echo "${VIASH_META_MEMORY_KIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_kib='&'#" ; else echo "# meta_memory_kib="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_MIB+x} ]; then echo "${VIASH_META_MEMORY_MIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_mib='&'#" ; else echo "# meta_memory_mib="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_GIB+x} ]; then echo "${VIASH_META_MEMORY_GIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_gib='&'#" ; else echo "# meta_memory_gib="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_TIB+x} ]; then echo "${VIASH_META_MEMORY_TIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_tib='&'#" ; else echo "# meta_memory_tib="; fi ) +$( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo "${VIASH_META_MEMORY_PIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_pib='&'#" ; else echo "# meta_memory_pib="; fi ) + +## VIASH END +#!/usr/bin/env bash + +set -euo pipefail + +TMPDIR=\\$(mktemp -d "\\$meta_temp_dir/concat_text-XXXXXX") +function clean_up { + [[ -d "\\$TMPDIR" ]] && rm -r "\\$TMPDIR" +} +trap clean_up EXIT + +par_input="\\$(echo "\\$par_input" | tr ';' ' ')" + +echo -n ">> Check if input is gzipped... " +set +eo pipefail +file \\$par_input | grep -q 'gzip' +is_zipped="\\$?" +set -euo pipefail +[[ "\\$is_zipped" == "0" ]] && echo "yes" || echo "no" + +if [[ "\\$is_zipped" == "0" ]]; then + echo ">> zcat gzipped files" + zcat \\$par_input > \\$TMPDIR/contents +else + echo ">> cat plain files" + cat \\$par_input > \\$TMPDIR/contents +fi + +if [ "\\$par_gzip_output" == true ]; then + echo ">> Zip output file" + gzip \\$TMPDIR/contents + mv \\$TMPDIR/contents.gz \\$par_output +else + mv \\$TMPDIR/contents \\$par_output +fi +VIASHMAIN +bash "$tempscript" +''' + + return vdsl3WorkflowFactory(args, meta, rawScript) +} + + + +/** + * Generate a workflow for VDSL3 modules. + * + * This function is called by the workflowFactory() function. + * + * Input channel: [id, input_map] + * Output channel: [id, output_map] + * + * Internally, this workflow will convert the input channel + * to a format which the Nextflow module will be able to handle. + */ +def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { + def key = args["key"] + def processObj = null + + workflow processWf { + take: input_ + main: + + if (processObj == null) { + processObj = _vdsl3ProcessFactory(args, meta, rawScript) + } + + output_ = input_ + | map { tuple -> + def id = tuple[0] + def data_ = tuple[1] + + if (workflow.stubRun) { + // add id if missing + data_ = [id: 'stub'] + data_ + } + + // process input files separately + def inputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + .collect { par -> + def val = data_.containsKey(par.plainName) ? data_[par.plainName] : [] + def inputFiles = [] + if (val == null) { + inputFiles = [] + } else if (val instanceof List) { + inputFiles = val + } else if (val instanceof Path) { + inputFiles = [ val ] + } else { + inputFiles = [] + } + if (!workflow.stubRun) { + // throw error when an input file doesn't exist + inputFiles.each{ file -> + assert file.exists() : + "Error in module '${key}' id '${id}' argument '${par.plainName}'.\n" + + " Required input file does not exist.\n" + + " Path: '$file'.\n" + + " Expected input file to exist" + } + } + inputFiles + } + + // remove input files + def argsExclInputFiles = meta.config.allArguments + .findAll { (it.type != "file" || it.direction != "input") && data_.containsKey(it.plainName) } + .collectEntries { par -> + def parName = par.plainName + def val = data_[parName] + if (par.multiple && val instanceof Collection) { + val = val.join(par.multiple_sep) + } + if (par.direction == "output" && par.type == "file") { + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) + } + [parName, val] + } + + [ id ] + inputPaths + [ argsExclInputFiles, meta.resources_dir ] + } + | processObj + | map { output -> + def outputFiles = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .indexed() + .collectEntries{ index, par -> + def out = output[index + 1] + // strip dummy '.exitcode' file from output (see nextflow-io/nextflow#2678) + if (!out instanceof List || out.size() <= 1) { + if (par.multiple) { + out = [] + } else { + assert !par.required : + "Error in module '${key}' id '${output[0]}' argument '${par.plainName}'.\n" + + " Required output file is missing" + out = null + } + } else if (out.size() == 2 && !par.multiple) { + out = out[1] + } else { + out = out.drop(1) + } + [ par.plainName, out ] + } + + // drop null outputs + outputFiles.removeAll{it.value == null} + + [ output[0], outputFiles ] + } + emit: output_ + } + + return processWf +} + +// depends on: session? +def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { + // autodetect process key + def wfKey = workflowArgs["key"] + def procKeyPrefix = "${wfKey}_process" + def scriptMeta = nextflow.script.ScriptMeta.current() + def existing = scriptMeta.getProcessNames().findAll{it.startsWith(procKeyPrefix)} + def numbers = existing.collect{it.replace(procKeyPrefix, "0").toInteger()} + def newNumber = (numbers + [-1]).max() + 1 + + def procKey = newNumber == 0 ? procKeyPrefix : "$procKeyPrefix$newNumber" + + if (newNumber > 0) { + log.warn "Key for module '${wfKey}' is duplicated.\n", + "If you run a component multiple times in the same workflow,\n" + + "it's recommended you set a unique key for every call,\n" + + "for example: ${wfKey}.run(key: \"foo\")." + } + + // subset directives and convert to list of tuples + def drctv = workflowArgs.directives + + // TODO: unit test the two commands below + // convert publish array into tags + def valueToStr = { val -> + // ignore closures + if (val instanceof CharSequence) { + if (!val.matches('^[{].*[}]$')) { + '"' + val + '"' + } else { + val + } + } else if (val instanceof List) { + "[" + val.collect{valueToStr(it)}.join(", ") + "]" + } else if (val instanceof Map) { + "[" + val.collect{k, v -> k + ": " + valueToStr(v)}.join(", ") + "]" + } else { + val.inspect() + } + } + + // multiple entries allowed: label, publishdir + def drctvStrs = drctv.collect { key, value -> + if (key in ["label", "publishDir"]) { + value.collect{ val -> + if (val instanceof Map) { + "\n$key " + val.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") + } else if (val == null) { + "" + } else { + "\n$key " + valueToStr(val) + } + }.join() + } else if (value instanceof Map) { + "\n$key " + value.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") + } else { + "\n$key " + valueToStr(value) + } + }.join() + + def inputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + .collect { ', path(viash_par_' + it.plainName + ', stageAs: "_viash_par/' + it.plainName + '_?/*")' } + .join() + + def outputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .collect { par -> + // insert dummy into every output (see nextflow-io/nextflow#2678) + if (!par.multiple) { + ', path{[".exitcode", args.' + par.plainName + ']}' + } else { + ', path{[".exitcode"] + args.' + par.plainName + '}' + } + } + .join() + + // TODO: move this functionality somewhere else? + if (workflowArgs.auto.transcript) { + outputPaths = outputPaths + ', path{[".exitcode", ".command*"]}' + } else { + outputPaths = outputPaths + ', path{[".exitcode"]}' + } + + // create dirs for output files (based on BashWrapper.createParentFiles) + def createParentStr = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" && it.create_parent } + .collect { par -> + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" + } + .join("\n") + + // construct inputFileExports + def inputFileExports = meta.config.allArguments + .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } + .collect { par -> + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" + } + + // NOTE: if using docker, use /tmp instead of tmpDir! + def tmpDir = java.nio.file.Paths.get( + System.getenv('NXF_TEMP') ?: + System.getenv('VIASH_TEMP') ?: + System.getenv('VIASH_TMPDIR') ?: + System.getenv('VIASH_TEMPDIR') ?: + System.getenv('VIASH_TMP') ?: + System.getenv('TEMP') ?: + System.getenv('TMPDIR') ?: + System.getenv('TEMPDIR') ?: + System.getenv('TMP') ?: + '/tmp' + ).toAbsolutePath() + + // construct stub + def stub = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .collect { par -> + "\${ args.containsKey(\"${par.plainName}\") ? \"touch2 \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"].replace(\"_*\", \"_0\") : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + } + .join("\n") + + // escape script + def escapedScript = rawScript.replace('\\', '\\\\').replace('$', '\\$').replace('"""', '\\"\\"\\"') + + // publishdir assert + def assertStr = (workflowArgs.auto.publish == true) || workflowArgs.auto.transcript ? + """\nassert task.publishDir.size() > 0: "if auto.publish is true, params.publish_dir needs to be defined.\\n Example: --publish_dir './output/'" """ : + "" + + // generate process string + def procStr = + """nextflow.enable.dsl=2 + | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } + |process $procKey {$drctvStrs + |input: + | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") + |output: + | tuple val("\$id")$outputPaths, optional: true + |stub: + |\"\"\" + |touch2() { mkdir -p "\\\$(dirname "\\\$1")" && touch "\\\$1" ; } + |$stub + |\"\"\" + |script:$assertStr + |def parInject = args + | .findAll{key, value -> value != null} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} + | .join("\\n") + |\"\"\" + |# meta exports + |export VIASH_META_RESOURCES_DIR="\${resourcesDir}" + |export VIASH_META_TEMP_DIR="${['docker', 'podman', 'charliecloud'].any{ it == workflow.containerEngine } ? '/tmp' : tmpDir}" + |export VIASH_META_NAME="${meta.config.name}" + |# export VIASH_META_EXECUTABLE="\\\$VIASH_META_RESOURCES_DIR/\\\$VIASH_META_NAME" + |export VIASH_META_CONFIG="\\\$VIASH_META_RESOURCES_DIR/.config.vsh.yaml" + |\${task.cpus ? "export VIASH_META_CPUS=\$task.cpus" : "" } + |\${task.memory?.bytes != null ? "export VIASH_META_MEMORY_B=\$task.memory.bytes" : "" } + |if [ ! -z \\\${VIASH_META_MEMORY_B+x} ]; then + | export VIASH_META_MEMORY_KB=\\\$(( (\\\$VIASH_META_MEMORY_B+999) / 1000 )) + | export VIASH_META_MEMORY_MB=\\\$(( (\\\$VIASH_META_MEMORY_KB+999) / 1000 )) + | export VIASH_META_MEMORY_GB=\\\$(( (\\\$VIASH_META_MEMORY_MB+999) / 1000 )) + | export VIASH_META_MEMORY_TB=\\\$(( (\\\$VIASH_META_MEMORY_GB+999) / 1000 )) + | export VIASH_META_MEMORY_PB=\\\$(( (\\\$VIASH_META_MEMORY_TB+999) / 1000 )) + | export VIASH_META_MEMORY_KIB=\\\$(( (\\\$VIASH_META_MEMORY_B+1023) / 1024 )) + | export VIASH_META_MEMORY_MIB=\\\$(( (\\\$VIASH_META_MEMORY_KIB+1023) / 1024 )) + | export VIASH_META_MEMORY_GIB=\\\$(( (\\\$VIASH_META_MEMORY_MIB+1023) / 1024 )) + | export VIASH_META_MEMORY_TIB=\\\$(( (\\\$VIASH_META_MEMORY_GIB+1023) / 1024 )) + | export VIASH_META_MEMORY_PIB=\\\$(( (\\\$VIASH_META_MEMORY_TIB+1023) / 1024 )) + |fi + | + |# meta synonyms + |export VIASH_TEMP="\\\$VIASH_META_TEMP_DIR" + |export TEMP_DIR="\\\$VIASH_META_TEMP_DIR" + | + |# create output dirs if need be + |function mkdir_parent { + | for file in "\\\$@"; do + | mkdir -p "\\\$(dirname "\\\$file")" + | done + |} + |$createParentStr + | + |# argument exports${inputFileExports.join()} + |\$parInject + | + |# process script + |${escapedScript} + |\"\"\" + |} + |""".stripMargin() + + // TODO: print on debug + // if (workflowArgs.debug == true) { + // println("######################\n$procStr\n######################") + // } + + // write process to temp file + def tempFile = java.nio.file.Files.createTempFile("viash-process-${procKey}-", ".nf") + addShutdownHook { java.nio.file.Files.deleteIfExists(tempFile) } + tempFile.text = procStr + + // create process from temp file + def binding = new nextflow.script.ScriptBinding([:]) + def session = nextflow.Nextflow.getSession() + def parser = _getScriptLoader(session) + .setModule(true) + .setBinding(binding) + def moduleScript = parser.runScript(tempFile) + .getScript() + + // register module in meta + def module = new nextflow.script.IncludeDef.Module(name: procKey) + scriptMeta.addModule(moduleScript, module.name, module.alias) + + // retrieve and return process from meta + return scriptMeta.getProcess(procKey) +} + +// use Reflection to get a ScriptParser / ScriptLoader +// <25.02.0-edge: new nextflow.script.ScriptParser(session) +// >=25.02.0-edge: nextflow.script.ScriptLoaderFactory.create(session) +def _getScriptLoader(nextflow.Session session) { + // try using the old method + try { + Class scriptParserClass = Class.forName('nextflow.script.ScriptParser') + return scriptParserClass.getDeclaredConstructor(nextflow.Session).newInstance(session) + } catch (ClassNotFoundException e) { + // else try with the new method + try { + Class scriptLoaderFactoryClass = Class.forName('nextflow.script.ScriptLoaderFactory') + def createMethod = scriptLoaderFactoryClass.getDeclaredMethod('create', nextflow.Session) + return createMethod.invoke(null, session) // null because create is static + } catch (ClassNotFoundException | NoSuchMethodException | IllegalAccessException | java.lang.reflect.InvocationTargetException e2) { + // Handle the case where neither class is found + throw new Exception("Neither nextflow.script.ScriptParser nor nextflow.script.ScriptLoaderFactory could be found. Is this a compatible Nextflow version?", e2) + } + } +} + +// defaults +meta["defaults"] = [ + // key to be used to trace the process and determine output names + key: null, + + // fixed arguments to be passed to script + args: [:], + + // default directives + directives: readJsonBlob('''{ + "container" : { + "registry" : "images.viash-hub.com", + "image" : "vsh/craftbox/concat_text", + "tag" : "v0.2.0" + }, + "tag" : "$id" +}'''), + + // auto settings + auto: readJsonBlob('''{ + "simplifyInput" : true, + "simplifyOutput" : false, + "transcript" : false, + "publish" : false +}'''), + + // Apply a map over the incoming tuple + // Example: `{ tup -> [ tup[0], [input: tup[1].output] ] + tup.drop(2) }` + map: null, + + // Apply a map over the ID element of a tuple (i.e. the first element) + // Example: `{ id -> id + "_foo" }` + mapId: null, + + // Apply a map over the data element of a tuple (i.e. the second element) + // Example: `{ data -> [ input: data.output ] }` + mapData: null, + + // Apply a map over the passthrough elements of a tuple (i.e. the tuple excl. the first two elements) + // Example: `{ pt -> pt.drop(1) }` + mapPassthrough: null, + + // Filter the channel + // Example: `{ tup -> tup[0] == "foo" }` + filter: null, + + // Choose whether or not to run the component on the tuple if the condition is true. + // Otherwise, the tuple will be passed through. + // Example: `{ tup -> tup[0] != "skip_this" }` + runIf: null, + + // Rename keys in the data field of the tuple (i.e. the second element) + // Will likely be deprecated in favour of `fromState`. + // Example: `[ "new_key": "old_key" ]` + renameKeys: null, + + // Fetch data from the state and pass it to the module without altering the current state. + // + // `fromState` should be `null`, `List[String]`, `Map[String, String]` or a function. + // + // - If it is `null`, the state will be passed to the module as is. + // - If it is a `List[String]`, the data will be the values of the state at the given keys. + // - If it is a `Map[String, String]`, the data will be the values of the state at the given keys, with the keys renamed according to the map. + // - If it is a function, the tuple (`[id, state]`) in the channel will be passed to the function, and the result will be used as the data. + // + // Example: `{ id, state -> [input: state.fastq_file] }` + // Default: `null` + fromState: null, + + // Determine how the state should be updated after the module has been run. + // + // `toState` should be `null`, `List[String]`, `Map[String, String]` or a function. + // + // - If it is `null`, the state will be replaced with the output of the module. + // - If it is a `List[String]`, the state will be updated with the values of the data at the given keys. + // - If it is a `Map[String, String]`, the state will be updated with the values of the data at the given keys, with the keys renamed according to the map. + // - If it is a function, a tuple (`[id, output, state]`) will be passed to the function, and the result will be used as the new state. + // + // Example: `{ id, output, state -> state + [counts: state.output] }` + // Default: `{ id, output, state -> output }` + toState: null, + + // Whether or not to print debug messages + // Default: `false` + debug: false +] + +// initialise default workflow +meta["workflow"] = workflowFactory([key: meta.config.name], meta.defaults, meta) + +// add workflow to environment +nextflow.script.ScriptMeta.current().addDefinition(meta.workflow) + +// anonymous workflow for running this module as a standalone +workflow { + // add id argument if it's not already in the config + // TODO: deep copy + def newConfig = deepClone(meta.config) + def newParams = deepClone(params) + + def argsContainsId = newConfig.allArguments.any{it.plainName == "id"} + if (!argsContainsId) { + def idArg = [ + 'name': '--id', + 'required': false, + 'type': 'string', + 'description': 'A unique id for every entry.', + 'multiple': false + ] + newConfig.arguments.add(0, idArg) + newConfig = processConfig(newConfig) + } + if (!newParams.containsKey("id")) { + newParams.id = "run" + } + + helpMessage(newConfig) + + channelFromParams(newParams, newConfig) + // make sure id is not in the state if id is not in the args + | map {id, state -> + if (!argsContainsId) { + [id, state.findAll{k, v -> k != "id"}] + } else { + [id, state] + } + } + | meta.workflow.run( + auto: [ publish: "state" ] + ) +} + +// END COMPONENT-SPECIFIC CODE diff --git a/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow.config b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow.config new file mode 100644 index 00000000..b4f5e7a2 --- /dev/null +++ b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow.config @@ -0,0 +1,126 @@ +manifest { + name = 'concat_text' + mainScript = 'main.nf' + nextflowVersion = '!>=20.12.1-edge' + version = 'v0.2.0' + description = 'Concatenate a number of text files, handle gzipped text files gracefully and\noptionally gzip the output text file.\n\nThis component is useful for concatening fastq files from different lanes, for instance.\n' + author = 'Toni Verbeiren, Dries Schaumont' +} + +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 } +} + + diff --git a/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow_schema.json b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow_schema.json new file mode 100644 index 00000000..2767afbd --- /dev/null +++ b/target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/nextflow_schema.json @@ -0,0 +1,106 @@ +{ +"$schema": "http://json-schema.org/draft-07/schema", +"title": "concat_text", +"description": "Concatenate a number of text files, handle gzipped text files gracefully and\noptionally gzip the output text file.\n\nThis component is useful for concatening fastq files from different lanes, for instance.\n", +"type": "object", +"definitions": { + + + + "input arguments" : { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + + + "input": { + "type": + "string", + "description": "Type: List of `file`, required, example: `input?.txt.gz`, multiple_sep: `\";\"`. A list of (gzipped) text files", + "help_text": "Type: List of `file`, required, example: `input?.txt.gz`, multiple_sep: `\";\"`. A list of (gzipped) text files." + + } + + +} +}, + + + "output arguments" : { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + + + "gzip_output": { + "type": + "boolean", + "description": "Type: `boolean_true`, default: `false`. Should the output be zipped?", + "help_text": "Type: `boolean_true`, default: `false`. Should the output be zipped?" + , + "default":false + } + + + , + "output": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.output.txt`, example: `output.txt`. File to write the output to, optionally gzipped", + "help_text": "Type: `file`, default: `$id.$key.output.txt`, example: `output.txt`. File to write the output to, optionally gzipped." + , + "default":"$id.$key.output.txt" + } + + +} +}, + + + "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/nextflow input-output arguments" + } +] +} diff --git a/target/executable/eset/create_eset/.config.vsh.yaml b/target/executable/eset/create_eset/.config.vsh.yaml index cb322a25..79622ffd 100644 --- a/target/executable/eset/create_eset/.config.vsh.yaml +++ b/target/executable/eset/create_eset/.config.vsh.yaml @@ -203,9 +203,9 @@ build_info: output: "target/executable/eset/create_eset" executable: "target/executable/eset/create_eset/create_eset" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_eset/create_eset b/target/executable/eset/create_eset/create_eset index a9ebc9df..817175ec 100755 --- a/target/executable/eset/create_eset/create_eset +++ b/target/executable/eset/create_eset/create_eset @@ -456,9 +456,9 @@ RUN Rscript -e 'options(warn = 2); if (!requireNamespace("remotes", quietly = TR LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_eset" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/eset/create_fdata/.config.vsh.yaml b/target/executable/eset/create_fdata/.config.vsh.yaml index b982fdd6..3cd02bfc 100644 --- a/target/executable/eset/create_fdata/.config.vsh.yaml +++ b/target/executable/eset/create_fdata/.config.vsh.yaml @@ -180,9 +180,9 @@ build_info: output: "target/executable/eset/create_fdata" executable: "target/executable/eset/create_fdata/create_fdata" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_fdata/create_fdata b/target/executable/eset/create_fdata/create_fdata index 4af7b541..a1b83bcb 100755 --- a/target/executable/eset/create_fdata/create_fdata +++ b/target/executable/eset/create_fdata/create_fdata @@ -458,9 +458,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_fdata" -LABEL org.opencontainers.image.created="2025-05-16T09:12:20Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/eset/create_pdata/.config.vsh.yaml b/target/executable/eset/create_pdata/.config.vsh.yaml index 570c4ce4..b7e18b8c 100644 --- a/target/executable/eset/create_pdata/.config.vsh.yaml +++ b/target/executable/eset/create_pdata/.config.vsh.yaml @@ -194,9 +194,9 @@ build_info: output: "target/executable/eset/create_pdata" executable: "target/executable/eset/create_pdata/create_pdata" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_pdata/create_pdata b/target/executable/eset/create_pdata/create_pdata index eb01db10..1706def0 100755 --- a/target/executable/eset/create_pdata/create_pdata +++ b/target/executable/eset/create_pdata/create_pdata @@ -458,9 +458,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_pdata" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml b/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml index 9f05dcbc..d9b644cf 100644 --- a/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml +++ b/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml @@ -152,9 +152,9 @@ build_info: output: "target/executable/integration_test_components/htrnaseq/check_eset" executable: "target/executable/integration_test_components/htrnaseq/check_eset/check_eset" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/integration_test_components/htrnaseq/check_eset/check_eset b/target/executable/integration_test_components/htrnaseq/check_eset/check_eset index 2abaa873..6610aac5 100755 --- a/target/executable/integration_test_components/htrnaseq/check_eset/check_eset +++ b/target/executable/integration_test_components/htrnaseq/check_eset/check_eset @@ -455,9 +455,9 @@ RUN Rscript -e 'options(warn = 2); if (!requireNamespace("remotes", quietly = TR LABEL org.opencontainers.image.authors="Dries Schaumont" LABEL org.opencontainers.image.description="Companion container for running component integration_test_components/htrnaseq check_eset" -LABEL org.opencontainers.image.created="2025-05-16T09:12:18Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml index 0c2adecd..3be2a101 100644 --- a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml +++ b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml @@ -161,9 +161,9 @@ build_info: output: "target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output" executable: "target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output index eec4cd55..e05c0f3f 100755 --- a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output +++ b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output @@ -457,9 +457,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont" LABEL org.opencontainers.image.description="Companion container for running component integration_test_components/well_demultiplexing check_cutadapt_output" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/io/publish_fastqs/.config.vsh.yaml b/target/executable/io/publish_fastqs/.config.vsh.yaml index b300cfa8..ec70388c 100644 --- a/target/executable/io/publish_fastqs/.config.vsh.yaml +++ b/target/executable/io/publish_fastqs/.config.vsh.yaml @@ -136,9 +136,9 @@ build_info: output: "target/executable/io/publish_fastqs" executable: "target/executable/io/publish_fastqs/publish_fastqs" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/io/publish_fastqs/publish_fastqs b/target/executable/io/publish_fastqs/publish_fastqs index 297372cb..3e5c65a4 100755 --- a/target/executable/io/publish_fastqs/publish_fastqs +++ b/target/executable/io/publish_fastqs/publish_fastqs @@ -450,9 +450,9 @@ RUN apt-get update && \ rm -rf /var/lib/apt/lists/* LABEL org.opencontainers.image.description="Companion container for running component io publish_fastqs" -LABEL org.opencontainers.image.created="2025-05-16T09:12:18Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/io/publish_results/.config.vsh.yaml b/target/executable/io/publish_results/.config.vsh.yaml index 36d036d9..108dd3b2 100644 --- a/target/executable/io/publish_results/.config.vsh.yaml +++ b/target/executable/io/publish_results/.config.vsh.yaml @@ -199,9 +199,9 @@ build_info: output: "target/executable/io/publish_results" executable: "target/executable/io/publish_results/publish_results" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/io/publish_results/publish_results b/target/executable/io/publish_results/publish_results index d32d9b2d..a3b3c32a 100755 --- a/target/executable/io/publish_results/publish_results +++ b/target/executable/io/publish_results/publish_results @@ -450,9 +450,9 @@ RUN apt-get update && \ rm -rf /var/lib/apt/lists/* LABEL org.opencontainers.image.description="Companion container for running component io publish_results" -LABEL org.opencontainers.image.created="2025-05-16T09:12:18Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/parallel_map/.config.vsh.yaml b/target/executable/parallel_map/.config.vsh.yaml index ed334102..5a32caef 100644 --- a/target/executable/parallel_map/.config.vsh.yaml +++ b/target/executable/parallel_map/.config.vsh.yaml @@ -282,9 +282,9 @@ build_info: output: "target/executable/parallel_map" executable: "target/executable/parallel_map/parallel_map" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/parallel_map/parallel_map b/target/executable/parallel_map/parallel_map index 92673b80..dbb17571 100755 --- a/target/executable/parallel_map/parallel_map +++ b/target/executable/parallel_map/parallel_map @@ -461,9 +461,9 @@ ENV STAR_BINARY=STAR COPY STAR /usr/local/bin/$STAR_BINARY LABEL org.opencontainers.image.authors="Dries Schaumont, Toni Verbeiren" LABEL org.opencontainers.image.description="Companion container for running component parallel_map" -LABEL org.opencontainers.image.created="2025-05-16T09:12:17Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:23Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/report/create_report/.config.vsh.yaml b/target/executable/report/create_report/.config.vsh.yaml index 59b2a8f8..7e0172e0 100644 --- a/target/executable/report/create_report/.config.vsh.yaml +++ b/target/executable/report/create_report/.config.vsh.yaml @@ -212,9 +212,9 @@ build_info: output: "target/executable/report/create_report" executable: "target/executable/report/create_report/create_report" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/report/create_report/create_report b/target/executable/report/create_report/create_report index f224a57e..c7dfbf58 100755 --- a/target/executable/report/create_report/create_report +++ b/target/executable/report/create_report/create_report @@ -465,9 +465,9 @@ RUN Rscript -e 'options(warn = 2); if (!requireNamespace("remotes", quietly = TR LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component report create_report" -LABEL org.opencontainers.image.created="2025-05-16T09:12:17Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/stats/combine_star_logs/.config.vsh.yaml b/target/executable/stats/combine_star_logs/.config.vsh.yaml index 2d7f2f17..7410f68f 100644 --- a/target/executable/stats/combine_star_logs/.config.vsh.yaml +++ b/target/executable/stats/combine_star_logs/.config.vsh.yaml @@ -201,9 +201,9 @@ build_info: output: "target/executable/stats/combine_star_logs" executable: "target/executable/stats/combine_star_logs/combine_star_logs" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/combine_star_logs/combine_star_logs b/target/executable/stats/combine_star_logs/combine_star_logs index fa3f7378..1183277f 100755 --- a/target/executable/stats/combine_star_logs/combine_star_logs +++ b/target/executable/stats/combine_star_logs/combine_star_logs @@ -457,9 +457,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont" LABEL org.opencontainers.image.description="Companion container for running component stats combine_star_logs" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/stats/generate_pool_statistics/.config.vsh.yaml b/target/executable/stats/generate_pool_statistics/.config.vsh.yaml index bdf62ec9..c829301c 100644 --- a/target/executable/stats/generate_pool_statistics/.config.vsh.yaml +++ b/target/executable/stats/generate_pool_statistics/.config.vsh.yaml @@ -185,9 +185,9 @@ build_info: output: "target/executable/stats/generate_pool_statistics" executable: "target/executable/stats/generate_pool_statistics/generate_pool_statistics" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/generate_pool_statistics/generate_pool_statistics b/target/executable/stats/generate_pool_statistics/generate_pool_statistics index 4df642d0..04010c54 100755 --- a/target/executable/stats/generate_pool_statistics/generate_pool_statistics +++ b/target/executable/stats/generate_pool_statistics/generate_pool_statistics @@ -458,9 +458,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component stats generate_pool_statistics" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:20Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/stats/generate_well_statistics/.config.vsh.yaml b/target/executable/stats/generate_well_statistics/.config.vsh.yaml index f00931c0..88f17a42 100644 --- a/target/executable/stats/generate_well_statistics/.config.vsh.yaml +++ b/target/executable/stats/generate_well_statistics/.config.vsh.yaml @@ -267,9 +267,9 @@ build_info: output: "target/executable/stats/generate_well_statistics" executable: "target/executable/stats/generate_well_statistics/generate_well_statistics" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/generate_well_statistics/generate_well_statistics b/target/executable/stats/generate_well_statistics/generate_well_statistics index 3e421534..7fcc2344 100755 --- a/target/executable/stats/generate_well_statistics/generate_well_statistics +++ b/target/executable/stats/generate_well_statistics/generate_well_statistics @@ -461,9 +461,9 @@ RUN pip install --upgrade pip && \ LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component stats generate_well_statistics" -LABEL org.opencontainers.image.created="2025-05-16T09:12:19Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/utils/save_params/.config.vsh.yaml b/target/executable/utils/save_params/.config.vsh.yaml index 1e027dbe..92f4a96e 100644 --- a/target/executable/utils/save_params/.config.vsh.yaml +++ b/target/executable/utils/save_params/.config.vsh.yaml @@ -148,9 +148,9 @@ build_info: output: "target/executable/utils/save_params" executable: "target/executable/utils/save_params/save_params" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/utils/save_params/save_params b/target/executable/utils/save_params/save_params index b63f123b..bb78fb01 100755 --- a/target/executable/utils/save_params/save_params +++ b/target/executable/utils/save_params/save_params @@ -453,9 +453,9 @@ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pyyaml" LABEL org.opencontainers.image.description="Companion container for running component utils save_params" -LABEL org.opencontainers.image.created="2025-05-16T09:12:18Z" +LABEL org.opencontainers.image.created="2025-07-25T08:01:21Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" +LABEL org.opencontainers.image.revision="a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/nextflow/eset/create_eset/.config.vsh.yaml b/target/nextflow/eset/create_eset/.config.vsh.yaml index 64fdeca4..385b6b7b 100644 --- a/target/nextflow/eset/create_eset/.config.vsh.yaml +++ b/target/nextflow/eset/create_eset/.config.vsh.yaml @@ -203,9 +203,9 @@ build_info: output: "target/nextflow/eset/create_eset" executable: "target/nextflow/eset/create_eset/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_eset/main.nf b/target/nextflow/eset/create_eset/main.nf index bb6e894e..63b039b0 100644 --- a/target/nextflow/eset/create_eset/main.nf +++ b/target/nextflow/eset/create_eset/main.nf @@ -3304,9 +3304,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_eset", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/eset/create_eset/nextflow_schema.json b/target/nextflow/eset/create_eset/nextflow_schema.json index 0dc57228..c0bc8910 100644 --- a/target/nextflow/eset/create_eset/nextflow_schema.json +++ b/target/nextflow/eset/create_eset/nextflow_schema.json @@ -1,111 +1,71 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "create_eset", -"description": "No description", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "pDataFile": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "fDataFile": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "mappingDir": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "poolName": { - "type": - "string", - "description": "Type: `string`, required. ", - "help_text": "Type: `string`, required. " - - } - - - , - "output": { - "type": - "string", - "description": "Type: `file`, required, default: `eset.$id.rds`. ", - "help_text": "Type: `file`, required, default: `eset.$id.rds`. " - , - "default":"eset.$id.rds" - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "create_eset", + "description": "No description", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "pDataFile": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "fDataFile": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "mappingDir": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "poolName": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "output": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"eset.$id.rds\"`, direction: `output`. ", + "default": "eset.$id.rds" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/eset/create_fdata/.config.vsh.yaml b/target/nextflow/eset/create_fdata/.config.vsh.yaml index 1c1b9dd0..06305fcd 100644 --- a/target/nextflow/eset/create_fdata/.config.vsh.yaml +++ b/target/nextflow/eset/create_fdata/.config.vsh.yaml @@ -180,9 +180,9 @@ build_info: output: "target/nextflow/eset/create_fdata" executable: "target/nextflow/eset/create_fdata/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_fdata/main.nf b/target/nextflow/eset/create_fdata/main.nf index 841cdee8..2bc101b1 100644 --- a/target/nextflow/eset/create_fdata/main.nf +++ b/target/nextflow/eset/create_fdata/main.nf @@ -3274,9 +3274,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_fdata", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/eset/create_fdata/nextflow_schema.json b/target/nextflow/eset/create_fdata/nextflow_schema.json index 69cc44b1..ccc97ab7 100644 --- a/target/nextflow/eset/create_fdata/nextflow_schema.json +++ b/target/nextflow/eset/create_fdata/nextflow_schema.json @@ -1,81 +1,49 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "create_fdata", -"description": "Create a fdata file\n", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "gtf": { - "type": - "string", - "description": "Type: `file`, required. Genome annotation file in GTF format", - "help_text": "Type: `file`, required. Genome annotation file in GTF format." - - } - - - , - "output": { - "type": - "string", - "description": "Type: `file`, default: `fData.$id.txt`. Tab-delimited text file containing information about the \u0027gene\u0027 or \u0027transcript\u0027\nentries from the input GTF file", - "help_text": "Type: `file`, default: `fData.$id.txt`. Tab-delimited text file containing information about the \u0027gene\u0027 or \u0027transcript\u0027\nentries from the input GTF file. The \u0027transcript\u0027 entries are used in case the source\nof the GTF was \u0027refGene\u0027 or \u0027ncbiRefSeq\u0027. \n" - , - "default":"fData.$id.txt" - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "create_fdata", + "description": "Create a fdata file\n", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "gtf": { + "type": "string", + "format": "path", + "exists": true, + "description": "Genome annotation file in GTF format.", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "output": { + "type": "string", + "format": "path", + "description": "Tab-delimited text file containing information about the 'gene' or 'transcript'\nentries from the input GTF file", + "help_text": "Type: `file`, multiple: `False`, default: `\"fData.$id.txt\"`, direction: `output`. ", + "default": "fData.$id.txt" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/eset/create_pdata/.config.vsh.yaml b/target/nextflow/eset/create_pdata/.config.vsh.yaml index 86fa69fb..f30a83e2 100644 --- a/target/nextflow/eset/create_pdata/.config.vsh.yaml +++ b/target/nextflow/eset/create_pdata/.config.vsh.yaml @@ -194,9 +194,9 @@ build_info: output: "target/nextflow/eset/create_pdata" executable: "target/nextflow/eset/create_pdata/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_pdata/main.nf b/target/nextflow/eset/create_pdata/main.nf index 821ba3c7..be00974e 100644 --- a/target/nextflow/eset/create_pdata/main.nf +++ b/target/nextflow/eset/create_pdata/main.nf @@ -3288,9 +3288,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_pdata", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/eset/create_pdata/nextflow_schema.json b/target/nextflow/eset/create_pdata/nextflow_schema.json index 85da40c1..e28629e6 100644 --- a/target/nextflow/eset/create_pdata/nextflow_schema.json +++ b/target/nextflow/eset/create_pdata/nextflow_schema.json @@ -1,91 +1,56 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "create_pdata", -"description": "Create a pdata file by combining the mapping statistics \n", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "star_stats_file": { - "type": - "string", - "description": "Type: `file`, required. Tab-delimited text file containing statistics (per column) that were generated\nfrom the STAR log files (Log", - "help_text": "Type: `file`, required. Tab-delimited text file containing statistics (per column) that were generated\nfrom the STAR log files (Log.final.out, Summary.csv, ReadsPerGene.out.tab).\nEach entry (row) in the file describes the values for one well (barcode).\n" - - } - - - , - "nrReadsNrGenesPerChromPool": { - "type": - "string", - "description": "Type: `file`, required. Pivot table in tsv format of the combined nrReadsNrGenesPerChrom files from STAR", - "help_text": "Type: `file`, required. Pivot table in tsv format of the combined nrReadsNrGenesPerChrom files from STAR. \nDescribes per chromosome (as columns) the number of reads, as well as the total number \nof reads per cell barcode and the percentage of nuclear, ERCC and mitochondrial\nreads.\n" - - } - - - , - "output": { - "type": - "string", - "description": "Type: `file`, default: `pData.$id.txt`. ", - "help_text": "Type: `file`, default: `pData.$id.txt`. " - , - "default":"pData.$id.txt" - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "create_pdata", + "description": "Create a pdata file by combining the mapping statistics \n", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "star_stats_file": { + "type": "string", + "format": "path", + "exists": true, + "description": "Tab-delimited text file containing statistics (per column) that were generated\nfrom the STAR log files (Log.final.out, Summary.csv, ReadsPerGene.out.tab).\nEach entry (row) in the file describes the values for one well (barcode).\n", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "nrReadsNrGenesPerChromPool": { + "type": "string", + "format": "path", + "exists": true, + "description": "Pivot table in tsv format of the combined nrReadsNrGenesPerChrom files from STAR", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "output": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"pData.$id.txt\"`, direction: `output`. ", + "default": "pData.$id.txt" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml b/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml index eff5be6d..6597002c 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml @@ -152,9 +152,9 @@ build_info: output: "target/nextflow/integration_test_components/htrnaseq/check_eset" executable: "target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf b/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf index 3e45b5db..424526db 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf @@ -3228,9 +3228,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/integration_test_components/htrnaseq/check_eset", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_schema.json b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_schema.json index 419acacf..976505a1 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_schema.json +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_schema.json @@ -1,80 +1,52 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "check_eset", -"description": "This component test the ExpressionSet object as output by the main pipeline.", -"type": "object", -"definitions": { - - - - "inputs" : { - "title": "Inputs", - "type": "object", - "description": "No description", - "properties": { - - - "eset": { - "type": - "string", - "description": "Type: `file`, required, example: `eset.rds`. Path to an ExpressionSet object", - "help_text": "Type: `file`, required, example: `eset.rds`. Path to an ExpressionSet object." - - } - - - , - "star_output": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/inputs" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "check_eset", + "description": "This component test the ExpressionSet object as output by the main pipeline.", + "type": "object", + "$defs": { + "inputs": { + "title": "Inputs", + "type": "object", + "description": "No description", + "properties": { + "eset": { + "type": "string", + "format": "path", + "exists": true, + "description": "Path to an ExpressionSet object.", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"eset.rds\"`. " + }, + "star_output": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "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": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/inputs" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml index 639e8680..a16f1fef 100644 --- a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml +++ b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml @@ -161,9 +161,9 @@ build_info: output: "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output" executable: "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf index 9c1f4222..a98b83de 100644 --- a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf +++ b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf @@ -3239,9 +3239,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/nextflow_schema.json b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/nextflow_schema.json index 09576187..80233fb5 100644 --- a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/nextflow_schema.json +++ b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/nextflow_schema.json @@ -1,90 +1,63 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "check_cutadapt_output", -"description": "This component test the cutadapt output from the well_demultiplex subworkflow.", -"type": "object", -"definitions": { - - - - "inputs" : { - "title": "Inputs", - "type": "object", - "description": "No description", - "properties": { - - - "fastq_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Path to the forward reads to test", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Path to the forward reads to test." - - } - - - , - "fastq_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Path to the reverse reads to test", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Path to the reverse reads to test." - - } - - - , - "ids": { - "type": - "string", - "description": "Type: List of `string`, required, multiple_sep: `\";\"`. Well IDs for the corresponding fastq input", - "help_text": "Type: List of `string`, required, multiple_sep: `\";\"`. Well IDs for the corresponding fastq input" - - } - - -} -}, - - - "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" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "check_cutadapt_output", + "description": "This component test the cutadapt output from the well_demultiplex subworkflow.", + "type": "object", + "$defs": { + "inputs": { + "title": "Inputs", + "type": "object", + "description": "No description", + "properties": { + "fastq_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Path to the forward reads to test.", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "fastq_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Path to the reverse reads to test.", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "ids": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Well IDs for the corresponding fastq input", + "help_text": "Type: `string`, multiple: `True`, required. " + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/inputs" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/io/publish_fastqs/.config.vsh.yaml b/target/nextflow/io/publish_fastqs/.config.vsh.yaml index 7f56e3a2..09ab700e 100644 --- a/target/nextflow/io/publish_fastqs/.config.vsh.yaml +++ b/target/nextflow/io/publish_fastqs/.config.vsh.yaml @@ -136,9 +136,9 @@ build_info: output: "target/nextflow/io/publish_fastqs" executable: "target/nextflow/io/publish_fastqs/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/io/publish_fastqs/main.nf b/target/nextflow/io/publish_fastqs/main.nf index c4695dda..58ab3dd9 100644 --- a/target/nextflow/io/publish_fastqs/main.nf +++ b/target/nextflow/io/publish_fastqs/main.nf @@ -3202,9 +3202,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/io/publish_fastqs", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/io/publish_fastqs/nextflow_schema.json b/target/nextflow/io/publish_fastqs/nextflow_schema.json index f341fc18..0150c949 100644 --- a/target/nextflow/io/publish_fastqs/nextflow_schema.json +++ b/target/nextflow/io/publish_fastqs/nextflow_schema.json @@ -1,95 +1,62 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "publish_fastqs", -"description": "Publish the fastq files per well", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Directory to write fastq data to", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Directory to write fastq data to" - - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "output": { - "type": - "string", - "description": "Type: `file`, default: `$id`. ", - "help_text": "Type: `file`, default: `$id`. " - , - "default":"$id" - } - - -} -}, - - - "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" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "publish_fastqs", + "description": "Publish the fastq files per well", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Directory to write fastq data to", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "output": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"$id\"`, direction: `output`. ", + "default": "$id" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "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": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/io/publish_results/.config.vsh.yaml b/target/nextflow/io/publish_results/.config.vsh.yaml index 5371cf68..1cf718ca 100644 --- a/target/nextflow/io/publish_results/.config.vsh.yaml +++ b/target/nextflow/io/publish_results/.config.vsh.yaml @@ -199,9 +199,9 @@ build_info: output: "target/nextflow/io/publish_results" executable: "target/nextflow/io/publish_results/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/io/publish_results/main.nf b/target/nextflow/io/publish_results/main.nf index 41fcaa9e..cdeb91c1 100644 --- a/target/nextflow/io/publish_results/main.nf +++ b/target/nextflow/io/publish_results/main.nf @@ -3272,9 +3272,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/io/publish_results", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/io/publish_results/nextflow_schema.json b/target/nextflow/io/publish_results/nextflow_schema.json index 77234e37..b438683b 100644 --- a/target/nextflow/io/publish_results/nextflow_schema.json +++ b/target/nextflow/io/publish_results/nextflow_schema.json @@ -1,165 +1,126 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "publish_results", -"description": "Publish the results", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "star_output": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Output from mapping with STAR", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Output from mapping with STAR" - - } - - - , - "nrReadsNrGenesPerChrom": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "star_qc_metrics": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "eset": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "f_data": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "p_data": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "html_report": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "run_params": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "output": { - "type": - "string", - "description": "Type: `file`, default: `$id`. ", - "help_text": "Type: `file`, default: `$id`. " - , - "default":"$id" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/input arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "publish_results", + "description": "Publish the results", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "star_output": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Output from mapping with STAR", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "nrReadsNrGenesPerChrom": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "star_qc_metrics": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "eset": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "f_data": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "p_data": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "html_report": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "run_params": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "output": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"$id\"`, direction: `output`. ", + "default": "$id" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/parallel_map/.config.vsh.yaml b/target/nextflow/parallel_map/.config.vsh.yaml index fa967d9a..ab1a3215 100644 --- a/target/nextflow/parallel_map/.config.vsh.yaml +++ b/target/nextflow/parallel_map/.config.vsh.yaml @@ -282,9 +282,9 @@ build_info: output: "target/nextflow/parallel_map" executable: "target/nextflow/parallel_map/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/parallel_map/main.nf b/target/nextflow/parallel_map/main.nf index 7f28f9ed..e463f695 100644 --- a/target/nextflow/parallel_map/main.nf +++ b/target/nextflow/parallel_map/main.nf @@ -3374,9 +3374,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/parallel_map", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/parallel_map/nextflow_schema.json b/target/nextflow/parallel_map/nextflow_schema.json index ce9ea034..702bf13a 100644 --- a/target/nextflow/parallel_map/nextflow_schema.json +++ b/target/nextflow/parallel_map/nextflow_schema.json @@ -1,196 +1,135 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "parallel_map", -"description": "Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Input FASTQ files for the forward reads", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Input FASTQ files for the forward reads. All FASTQ file names must start with the prefix \u0027{well_id}_R1\u0027, where\n\u0027well_id\u0027 can be found as the sequence identifier in the barcodes FASTA file (see \u0027barcodesFasta\u0027 argument).\nFor each FASTQ file, a matching FASTQ file for the reverse reads must be provided to the \u0027input_r2\u0027 argument,\nmeaning that their \u0027well_id\u0027 prefix must match. The number of items provided for \u0027input_r1\u0027 must be equal\nto the number of items for \u0027input_r2\u0027.\n" - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Input FASTQ files for the reverse reads", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Input FASTQ files for the reverse reads. All FASTQ file names must start with the prefix \u0027{well_id}_R2\u0027, where\n\u0027well_id\u0027 can be found as the sequence identifier in the barcodes FASTA file (see \u0027barcodesFasta\u0027 argument).\nFor each FASTQ file, a matching FASTQ file for the reverse reads must be provided to the \u0027input_r1\u0027 argument,\nmeaning that their \u0027well_id\u0027 prefix must match. The number of items provided for \u0027input_r1\u0027 must be equal\nto the number of items for \u0027input_r2\u0027.\n" - - } - - - , - "genomeDir": { - "type": - "string", - "description": "Type: `file`, required. Reference genome to match to", - "help_text": "Type: `file`, required. Reference genome to match to. Can be generated from genomic FASTA sequences and a genome annotation\nby using STAR with \u0027--runMode genomeGenerate\u0027.\n" - - } - - - , - "barcodesFasta": { - "type": - "string", - "description": "Type: `file`, required. FASTA file where each entry specifies a unique barcode sequence present at the start of the forward input reads\n(input_r1)", - "help_text": "Type: `file`, required. FASTA file where each entry specifies a unique barcode sequence present at the start of the forward input reads\n(input_r1). The IDs of each barcode (the start of the FASTA headers up until the first whitespace character) must\nmatch with the start of one input FASTQ pair.\n" - - } - - -} -}, - - - "barcode arguments" : { - "title": "Barcode arguments", - "type": "object", - "description": "No description", - "properties": { - - - "umiLength": { - "type": - "integer", - "description": "Type: `integer`, required. Length of the Unique Molecular Identifiers (UMI)", - "help_text": "Type: `integer`, required. Length of the Unique Molecular Identifiers (UMI). The UMI are expected to be located after the barcodes in the\nforwards reads.\n" - - } - - - , - "limitBAMsortRAM": { - "type": - "string", - "description": "Type: `string`, default: `10000000000`. ", - "help_text": "Type: `string`, default: `10000000000`. " - , - "default":"10000000000" - } - - -} -}, - - - "runtime arguments" : { - "title": "Runtime arguments", - "type": "object", - "description": "No description", - "properties": { - - - "runThreadN": { - "type": - "integer", - "description": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution", - "help_text": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution." - , - "default":1 - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "output": { - "type": - "string", - "description": "Type: List of `file`, required, default: `./*`, multiple_sep: `\";\"`. A list of output folders which are the result of using STAR to map each input FASTQ pair STAR to the reference genome", - "help_text": "Type: List of `file`, required, default: `./*`, multiple_sep: `\";\"`. A list of output folders which are the result of using STAR to map each input FASTQ pair STAR to the reference genome.\nThe order of the items DO NOT match with the order of the entries in the barcodes FASTA file or the input FASTQ pairs. \n" - , - "default":"./*" - } - - - , - "joblog": { - "type": - "string", - "description": "Type: `file`, default: `execution_log.txt`. Where to store the log file listing all the jobs", - "help_text": "Type: `file`, default: `execution_log.txt`. Where to store the log file listing all the jobs." - , - "default":"execution_log.txt" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/input arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "parallel_map", + "description": "Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Input FASTQ files for the forward reads", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "input_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Input FASTQ files for the reverse reads", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "genomeDir": { + "type": "string", + "format": "path", + "exists": true, + "description": "Reference genome to match to", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "barcodesFasta": { + "type": "string", + "format": "path", + "exists": true, + "description": "FASTA file where each entry specifies a unique barcode sequence present at the start of the forward input reads\n(input_r1)", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/barcode arguments" + "barcode arguments": { + "title": "Barcode arguments", + "type": "object", + "description": "No description", + "properties": { + "umiLength": { + "type": "integer", + "description": "Length of the Unique Molecular Identifiers (UMI)", + "help_text": "Type: `integer`, multiple: `False`, required. " + }, + "limitBAMsortRAM": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`, default: `\"10000000000\"`. ", + "default": "10000000000" + } + } }, - - { - "$ref": "#/definitions/runtime arguments" + "runtime arguments": { + "title": "Runtime arguments", + "type": "object", + "description": "No description", + "properties": { + "runThreadN": { + "type": "integer", + "description": "Number of threads to use for a single STAR execution.", + "help_text": "Type: `integer`, multiple: `False`, default: `1`. ", + "default": 1 + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "output": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "A list of output folders which are the result of using STAR to map each input FASTQ pair STAR to the reference genome.\nThe order of the items DO NOT match with the order of the entries in the barcodes FASTA file or the input FASTQ pairs", + "help_text": "Type: `file`, multiple: `True`, required, default: `[\"./*\"]`, direction: `output`. ", + "default": [ + "./*" + ] + }, + "joblog": { + "type": "string", + "format": "path", + "description": "Where to store the log file listing all the jobs.", + "help_text": "Type: `file`, multiple: `False`, default: `\"execution_log.txt\"`, direction: `output`. ", + "default": "execution_log.txt" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/barcode arguments" + }, + { + "$ref": "#/$defs/runtime arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/report/create_report/.config.vsh.yaml b/target/nextflow/report/create_report/.config.vsh.yaml index b1309a84..49693b08 100644 --- a/target/nextflow/report/create_report/.config.vsh.yaml +++ b/target/nextflow/report/create_report/.config.vsh.yaml @@ -212,9 +212,9 @@ build_info: output: "target/nextflow/report/create_report" executable: "target/nextflow/report/create_report/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/report/create_report/main.nf b/target/nextflow/report/create_report/main.nf index 565ba2d3..91255d9f 100644 --- a/target/nextflow/report/create_report/main.nf +++ b/target/nextflow/report/create_report/main.nf @@ -3318,9 +3318,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/report/create_report", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/report/create_report/nextflow_schema.json b/target/nextflow/report/create_report/nextflow_schema.json index 54f4d99c..5362bf8e 100644 --- a/target/nextflow/report/create_report/nextflow_schema.json +++ b/target/nextflow/report/create_report/nextflow_schema.json @@ -1,81 +1,52 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "create_report", -"description": "Create a basic QC report in HTML format based on a number of esets.\n", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "eset": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "output_report": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.output_report.html`, example: `report.html`. ", - "help_text": "Type: `file`, required, default: `$id.$key.output_report.html`, example: `report.html`. " - , - "default":"$id.$key.output_report.html" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "create_report", + "description": "Create a basic QC report in HTML format based on a number of esets.\n", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "eset": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "output_report": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"$id.$key.output_report.html\"`, direction: `output`, example: `\"report.html\"`. ", + "default": "$id.$key.output_report.html" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "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": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/stats/combine_star_logs/.config.vsh.yaml b/target/nextflow/stats/combine_star_logs/.config.vsh.yaml index 3bd1b09a..8906ec80 100644 --- a/target/nextflow/stats/combine_star_logs/.config.vsh.yaml +++ b/target/nextflow/stats/combine_star_logs/.config.vsh.yaml @@ -201,9 +201,9 @@ build_info: output: "target/nextflow/stats/combine_star_logs" executable: "target/nextflow/stats/combine_star_logs/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/combine_star_logs/main.nf b/target/nextflow/stats/combine_star_logs/main.nf index 2da8c8f2..80bf659b 100644 --- a/target/nextflow/stats/combine_star_logs/main.nf +++ b/target/nextflow/stats/combine_star_logs/main.nf @@ -3290,9 +3290,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/combine_star_logs", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/stats/combine_star_logs/nextflow_schema.json b/target/nextflow/stats/combine_star_logs/nextflow_schema.json index d8ae39a9..a65b913d 100644 --- a/target/nextflow/stats/combine_star_logs/nextflow_schema.json +++ b/target/nextflow/stats/combine_star_logs/nextflow_schema.json @@ -1,111 +1,80 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "combine_star_logs", -"description": "No description", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "barcodes": { - "type": - "string", - "description": "Type: List of `string`, required, multiple_sep: `\";\"`. Barcodes responding to the respective log files", - "help_text": "Type: List of `string`, required, multiple_sep: `\";\"`. Barcodes responding to the respective log files.\n" - - } - - - , - "star_logs": { - "type": - "string", - "description": "Type: List of `file`, required, example: `Log.final.out`, multiple_sep: `\";\"`. Paths to the STAR log files (most frequently called Log", - "help_text": "Type: List of `file`, required, example: `Log.final.out`, multiple_sep: `\";\"`. Paths to the STAR log files (most frequently called Log.final.out)\n" - - } - - - , - "gene_summary_logs": { - "type": - "string", - "description": "Type: List of `file`, required, example: `Summary.txt`, multiple_sep: `\";\"`. Paths to the Summary", - "help_text": "Type: List of `file`, required, example: `Summary.txt`, multiple_sep: `\";\"`. Paths to the Summary.csv files from the STAR Solo output. Can be found in\nthe \u0027Solo.out/Gene\u0027 folder relative to the root of the STAR output directory. \n" - - } - - - , - "reads_per_gene_logs": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Paths to the \u0027ReadsPerGene", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Paths to the \u0027ReadsPerGene.out.tab\u0027 files as output by STAR.\n" - - } - - - , - "output": { - "type": - "string", - "description": "Type: `file`, default: `starLogs.txt`. Tab-delimited file describing for each barcode (as the rows), the metrics (as columns)\ngathered from the different input files", - "help_text": "Type: `file`, default: `starLogs.txt`. Tab-delimited file describing for each barcode (as the rows), the metrics (as columns)\ngathered from the different input files. \n" - , - "default":"starLogs.txt" - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "combine_star_logs", + "description": "No description", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "barcodes": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Barcodes responding to the respective log files.\n", + "help_text": "Type: `string`, multiple: `True`, required. " + }, + "star_logs": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Paths to the STAR log files (most frequently called Log.final.out)\n", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`, example: `[\"Log.final.out\"]`. " + }, + "gene_summary_logs": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Paths to the Summary.csv files from the STAR Solo output", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`, example: `[\"Summary.txt\"]`. " + }, + "reads_per_gene_logs": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Paths to the 'ReadsPerGene.out.tab' files as output by STAR.\n", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "output": { + "type": "string", + "format": "path", + "description": "Tab-delimited file describing for each barcode (as the rows), the metrics (as columns)\ngathered from the different input files", + "help_text": "Type: `file`, multiple: `False`, default: `\"starLogs.txt\"`, direction: `output`. ", + "default": "starLogs.txt" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml b/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml index 3d07d2f5..01c528bb 100644 --- a/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml +++ b/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml @@ -185,9 +185,9 @@ build_info: output: "target/nextflow/stats/generate_pool_statistics" executable: "target/nextflow/stats/generate_pool_statistics/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/generate_pool_statistics/main.nf b/target/nextflow/stats/generate_pool_statistics/main.nf index 7a46cbe1..cba1bc00 100644 --- a/target/nextflow/stats/generate_pool_statistics/main.nf +++ b/target/nextflow/stats/generate_pool_statistics/main.nf @@ -3274,9 +3274,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/generate_pool_statistics", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json b/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json index 1f0ea034..e69de29b 100644 --- a/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json +++ b/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json @@ -1,82 +0,0 @@ -{ -"$schema": "http://json-schema.org/draft-07/schema", -"title": "generate_pool_statistics", -"description": "No description", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "nrReadsNrGenesPerChrom": { - "type": - "string", - "description": "Type: List of `file`, default: `processedBamFile_well1.tsv;processedBamfile_well2.tsv`, multiple_sep: `\";\"`. Path to an output file that contains a ", - "help_text": "Type: List of `file`, default: `processedBamFile_well1.tsv;processedBamfile_well2.tsv`, multiple_sep: `\";\"`. Path to an output file that contains a .tsv formatted table describing\nper chromosome the number of reads that were mapped to that chromosome (NumberOfReads\ncolumn) and the number of genes on that chromosome that had at least one\nread mapped to it (NumberOfGenes).\n" - , - "default":"processedBamFile_well1.tsv;processedBamfile_well2.tsv" - } - - - , - "nrReadsNrGenesPerChromPool": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChromPool.txt`, example: `nrReadsNrGenesPerChrom.txt`. Pivot table in tsv format of the combined input nrReadsNrGenesPerChrom files", - "help_text": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChromPool.txt`, example: `nrReadsNrGenesPerChrom.txt`. Pivot table in tsv format of the combined input nrReadsNrGenesPerChrom files. Describes\nper chromosome (as columns) the number of reads, as well as the total number \nof reads per cell barcode and the percentage of nuclear, ERCC and mitochondrial\nreads.\n" - , - "default":"$id.$key.nrReadsNrGenesPerChromPool.txt" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/arguments" - }, - - { - "$ref": "#/definitions/nextflow input-output arguments" - } -] -} diff --git a/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml b/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml index 03098e11..bcbbeca8 100644 --- a/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml +++ b/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml @@ -267,9 +267,9 @@ build_info: output: "target/nextflow/stats/generate_well_statistics" executable: "target/nextflow/stats/generate_well_statistics/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/generate_well_statistics/main.nf b/target/nextflow/stats/generate_well_statistics/main.nf index 93f5d214..d693be56 100644 --- a/target/nextflow/stats/generate_well_statistics/main.nf +++ b/target/nextflow/stats/generate_well_statistics/main.nf @@ -3369,9 +3369,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/generate_well_statistics", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/stats/generate_well_statistics/nextflow_schema.json b/target/nextflow/stats/generate_well_statistics/nextflow_schema.json index a432968c..3df2dae3 100644 --- a/target/nextflow/stats/generate_well_statistics/nextflow_schema.json +++ b/target/nextflow/stats/generate_well_statistics/nextflow_schema.json @@ -1,145 +1,85 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "generate_well_statistics", -"description": "Generate summary statistics from BAM files generated by STAR solo.", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input": { - "type": - "string", - "description": "Type: `file`, example: `input.bam`. The ", - "help_text": "Type: `file`, example: `input.bam`. The .bam file as returned by the mapping tool STAR." - - } - - - , - "barcode": { - "type": - "string", - "description": "Type: `string`, required. The barcode for the well that is being processed", - "help_text": "Type: `string`, required. The barcode for the well that is being processed. Is only used to add a metadata\ncolumn to all output files.\n" - - } - - - , - "well_id": { - "type": - "string", - "description": "Type: `string`, required. ID of this well", - "help_text": "Type: `string`, required. ID of this well. Only used to add a metadata column to the output files.\n" - - } - - - , - "processedBAMFile": { - "type": - "string", - "description": "Type: `file`, default: `processedBamFile.txt`. Path to a ", - "help_text": "Type: `file`, default: `processedBamFile.txt`. Path to a .tsv file listing, per read in the BAM file,\nthe value for the \"CB\", \"UX\", \"GX\" and \"GN\" tag, together with the\nchromsome to which the read was mapped to.\n" - , - "default":"processedBamFile.txt" - } - - - , - "nrReadsNrGenesPerChrom": { - "type": - "string", - "description": "Type: `file`, default: `nrReadsNrGenesPerChrom.txt`. Path to an output file that contains a ", - "help_text": "Type: `file`, default: `nrReadsNrGenesPerChrom.txt`. Path to an output file that contains a .tsv formatted table describing\nper chromosome the number of reads that were mapped to that chromosome (NumberOfReads\ncolumn) and the number of genes on that chromosome that had at least one\nread mapped to it (NumberOfGenes).\n" - , - "default":"nrReadsNrGenesPerChrom.txt" - } - - - , - "nrReadsNrUMIsPerCB": { - "type": - "string", - "description": "Type: `file`, default: `nrReadsNrUMIsPerCB.txt`. Path to an output file that contains a ", - "help_text": "Type: `file`, default: `nrReadsNrUMIsPerCB.txt`. Path to an output file that contains a .tsv formatted table describing\nper barcode the number of UMI\u0027s (nrUMIs) and the total number of reads (NumberOfReads).\n" - , - "default":"nrReadsNrUMIsPerCB.txt" - } - - - , - "umiFreqTop": { - "type": - "string", - "description": "Type: `file`, default: `umiFreqTop100.txt`. Path to an output file that contains a ", - "help_text": "Type: `file`, default: `umiFreqTop100.txt`. Path to an output file that contains a .tsv formatted table describing\nper UMI (column UB) the frequency at which they occur in the reads (column\nN). Only the top 100 UMIs are included.\n" - , - "default":"umiFreqTop100.txt" - } - - - , - "threads": { - "type": - "integer", - "description": "Type: `integer`, default: `1`. Number of threads to use for decompressing BAM files", - "help_text": "Type: `integer`, default: `1`. Number of threads to use for decompressing BAM files.\n" - , - "default":1 - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "generate_well_statistics", + "description": "Generate summary statistics from BAM files generated by STAR solo.", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "input": { + "type": "string", + "format": "path", + "description": "The .bam file as returned by the mapping tool STAR.", + "help_text": "Type: `file`, multiple: `False`, direction: `input`, example: `\"input.bam\"`. " + }, + "barcode": { + "type": "string", + "description": "The barcode for the well that is being processed", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "well_id": { + "type": "string", + "description": "ID of this well", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "processedBAMFile": { + "type": "string", + "format": "path", + "description": "Path to a .tsv file listing, per read in the BAM file,\nthe value for the \"CB\", \"UX\", \"GX\" and \"GN\" tag, together with the\nchromsome to which the read was mapped to.\n", + "help_text": "Type: `file`, multiple: `False`, default: `\"processedBamFile.txt\"`, direction: `output`. ", + "default": "processedBamFile.txt" + }, + "nrReadsNrGenesPerChrom": { + "type": "string", + "format": "path", + "description": "Path to an output file that contains a .tsv formatted table describing\nper chromosome the number of reads that were mapped to that chromosome (NumberOfReads\ncolumn) and the number of genes on that chromosome that had at least one\nread mapped to it (NumberOfGenes).\n", + "help_text": "Type: `file`, multiple: `False`, default: `\"nrReadsNrGenesPerChrom.txt\"`, direction: `output`. ", + "default": "nrReadsNrGenesPerChrom.txt" + }, + "nrReadsNrUMIsPerCB": { + "type": "string", + "format": "path", + "description": "Path to an output file that contains a .tsv formatted table describing\nper barcode the number of UMI's (nrUMIs) and the total number of reads (NumberOfReads).\n", + "help_text": "Type: `file`, multiple: `False`, default: `\"nrReadsNrUMIsPerCB.txt\"`, direction: `output`. ", + "default": "nrReadsNrUMIsPerCB.txt" + }, + "umiFreqTop": { + "type": "string", + "format": "path", + "description": "Path to an output file that contains a .tsv formatted table describing\nper UMI (column UB) the frequency at which they occur in the reads (column\nN)", + "help_text": "Type: `file`, multiple: `False`, default: `\"umiFreqTop100.txt\"`, direction: `output`. ", + "default": "umiFreqTop100.txt" + }, + "threads": { + "type": "integer", + "description": "Number of threads to use for decompressing BAM files.\n", + "help_text": "Type: `integer`, multiple: `False`, default: `1`. ", + "default": 1 + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/utils/concatRuns/.config.vsh.yaml b/target/nextflow/utils/concatRuns/.config.vsh.yaml index 47744573..247dfdf6 100644 --- a/target/nextflow/utils/concatRuns/.config.vsh.yaml +++ b/target/nextflow/utils/concatRuns/.config.vsh.yaml @@ -157,9 +157,9 @@ build_info: output: "target/nextflow/utils/concatRuns" executable: "target/nextflow/utils/concatRuns/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" dependencies: - "target/dependencies/vsh/vsh/craftbox/v0.1.0/nextflow/concat_text" package_config: diff --git a/target/nextflow/utils/concatRuns/main.nf b/target/nextflow/utils/concatRuns/main.nf index 86d6c99c..2ae9fc71 100644 --- a/target/nextflow/utils/concatRuns/main.nf +++ b/target/nextflow/utils/concatRuns/main.nf @@ -3224,9 +3224,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/utils/concatRuns", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/utils/concatRuns/nextflow_schema.json b/target/nextflow/utils/concatRuns/nextflow_schema.json index e39d0478..9fb8392c 100644 --- a/target/nextflow/utils/concatRuns/nextflow_schema.json +++ b/target/nextflow/utils/concatRuns/nextflow_schema.json @@ -1,112 +1,80 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "concatRuns", -"description": "Concatenate well FASTQ files from different runs in order to increase sequencing depth.\n", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "sample_id": { - "type": - "string", - "description": "Type: `string`, required. ", - "help_text": "Type: `string`, required. " - - } - - - , - "output_r1": { - "type": - "string", - "description": "Type: List of `file`, default: `$id.$key.output_r1_*`, multiple_sep: `\";\"`. Path to read 1 fastq/fasta file", - "help_text": "Type: List of `file`, default: `$id.$key.output_r1_*`, multiple_sep: `\";\"`. Path to read 1 fastq/fasta file" - , - "default":"$id.$key.output_r1_*" - } - - - , - "output_r2": { - "type": - "string", - "description": "Type: List of `file`, default: `$id.$key.output_r2_*`, multiple_sep: `\";\"`. Path to read 2 fastq/fasta file", - "help_text": "Type: List of `file`, default: `$id.$key.output_r2_*`, multiple_sep: `\";\"`. Path to read 2 fastq/fasta file" - , - "default":"$id.$key.output_r2_*" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "concatRuns", + "description": "Concatenate well FASTQ files from different runs in order to increase sequencing depth.\n", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "input_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "input_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "sample_id": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "output_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "Path to read 1 fastq/fasta file", + "help_text": "Type: `file`, multiple: `True`, default: `\"$id.$key.output_r1_*\"`, direction: `output`. ", + "default": "$id.$key.output_r1_*" + }, + "output_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "Path to read 2 fastq/fasta file", + "help_text": "Type: `file`, multiple: `True`, default: `\"$id.$key.output_r2_*\"`, direction: `output`. ", + "default": "$id.$key.output_r2_*" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "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": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/utils/listInputDir/.config.vsh.yaml b/target/nextflow/utils/listInputDir/.config.vsh.yaml index 13484c1f..149f7935 100644 --- a/target/nextflow/utils/listInputDir/.config.vsh.yaml +++ b/target/nextflow/utils/listInputDir/.config.vsh.yaml @@ -168,9 +168,9 @@ build_info: output: "target/nextflow/utils/listInputDir" executable: "target/nextflow/utils/listInputDir/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/utils/listInputDir/main.nf b/target/nextflow/utils/listInputDir/main.nf index 9415227e..c3478d66 100644 --- a/target/nextflow/utils/listInputDir/main.nf +++ b/target/nextflow/utils/listInputDir/main.nf @@ -3234,9 +3234,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/utils/listInputDir", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/utils/listInputDir/nextflow_schema.json b/target/nextflow/utils/listInputDir/nextflow_schema.json index ee2f29c9..370a5200 100644 --- a/target/nextflow/utils/listInputDir/nextflow_schema.json +++ b/target/nextflow/utils/listInputDir/nextflow_schema.json @@ -1,133 +1,82 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "listInputDir", -"description": "List the contents of a directory and parse contained fastq files", -"type": "object", -"definitions": { - - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input": { - "type": - "string", - "description": "Type: `file`, required, example: `fastq_dir`. Path to the directory containing fastq files", - "help_text": "Type: `file`, required, example: `fastq_dir`. Path to the directory containing fastq files" - - } - - - , - "ignore": { - "type": - "string", - "description": "Type: List of `string`, default: `Undetermined`, multiple_sep: `\";\"`. Pool names to ignore", - "help_text": "Type: List of `string`, default: `Undetermined`, multiple_sep: `\";\"`. Pool names to ignore." - , - "default":"Undetermined" - } - - - , - "r1_output": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.r1_output`. Path to read 1 fastq/fasta file", - "help_text": "Type: `file`, default: `$id.$key.r1_output`. Path to read 1 fastq/fasta file" - , - "default":"$id.$key.r1_output" - } - - - , - "r2_output": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.r2_output`. Path to read 2 fastq/fasta file", - "help_text": "Type: `file`, default: `$id.$key.r2_output`. Path to read 2 fastq/fasta file" - , - "default":"$id.$key.r2_output" - } - - - , - "lane": { - "type": - "string", - "description": "Type: `string`. Lane nr", - "help_text": "Type: `string`. Lane nr" - - } - - - , - "sample": { - "type": - "string", - "description": "Type: `string`. Sample nr", - "help_text": "Type: `string`. Sample nr" - - } - - - , - "sample_id": { - "type": - "string", - "description": "Type: `string`. Sample name", - "help_text": "Type: `string`. Sample name" - - } - - -} -}, - - - "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/arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "listInputDir", + "description": "List the contents of a directory and parse contained fastq files", + "type": "object", + "$defs": { + "arguments": { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + "input": { + "type": "string", + "format": "path", + "exists": true, + "description": "Path to the directory containing fastq files", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"fastq_dir\"`. " + }, + "ignore": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Pool names to ignore.", + "help_text": "Type: `string`, multiple: `True`, default: `[\"Undetermined\"]`. ", + "default": [ + "Undetermined" + ] + }, + "r1_output": { + "type": "string", + "format": "path", + "description": "Path to read 1 fastq/fasta file", + "help_text": "Type: `file`, multiple: `False`, default: `\"$id.$key.r1_output\"`, direction: `output`. ", + "default": "$id.$key.r1_output" + }, + "r2_output": { + "type": "string", + "format": "path", + "description": "Path to read 2 fastq/fasta file", + "help_text": "Type: `file`, multiple: `False`, default: `\"$id.$key.r2_output\"`, direction: `output`. ", + "default": "$id.$key.r2_output" + }, + "lane": { + "type": "string", + "description": "Lane nr", + "help_text": "Type: `string`, multiple: `False`. " + }, + "sample": { + "type": "string", + "description": "Sample nr", + "help_text": "Type: `string`, multiple: `False`. " + }, + "sample_id": { + "type": "string", + "description": "Sample name", + "help_text": "Type: `string`, multiple: `False`. " + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/utils/save_params/.config.vsh.yaml b/target/nextflow/utils/save_params/.config.vsh.yaml index c61c9402..ba8e1fe7 100644 --- a/target/nextflow/utils/save_params/.config.vsh.yaml +++ b/target/nextflow/utils/save_params/.config.vsh.yaml @@ -148,9 +148,9 @@ build_info: output: "target/nextflow/utils/save_params" executable: "target/nextflow/utils/save_params/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/utils/save_params/main.nf b/target/nextflow/utils/save_params/main.nf index 2c95cff6..f95a5967 100644 --- a/target/nextflow/utils/save_params/main.nf +++ b/target/nextflow/utils/save_params/main.nf @@ -3218,9 +3218,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/utils/save_params", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/utils/save_params/nextflow_schema.json b/target/nextflow/utils/save_params/nextflow_schema.json index 5e2be192..d6f579fc 100644 --- a/target/nextflow/utils/save_params/nextflow_schema.json +++ b/target/nextflow/utils/save_params/nextflow_schema.json @@ -1,105 +1,62 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "save_params", -"description": "Save parameters to a YAML file\n", -"type": "object", -"definitions": { - - - - "inputs" : { - "title": "Inputs", - "type": "object", - "description": "No description", - "properties": { - - - "id": { - "type": - "string", - "description": "Type: `string`, required. The id of the job\n", - "help_text": "Type: `string`, required. The id of the job\n" - - } - - - , - "params_yaml": { - "type": - "string", - "description": "Type: `string`, required. base64 encoded yaml containing the state\n", - "help_text": "Type: `string`, required. base64 encoded yaml containing the state\n" - - } - - -} -}, - - - "outputs" : { - "title": "Outputs", - "type": "object", - "description": "No description", - "properties": { - - - "output": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.output.yaml`, example: `output.yaml`. The output YAML file\n", - "help_text": "Type: `file`, required, default: `$id.$key.output.yaml`, example: `output.yaml`. The output YAML file\n" - , - "default":"$id.$key.output.yaml" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/inputs" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "save_params", + "description": "Save parameters to a YAML file\n", + "type": "object", + "$defs": { + "inputs": { + "title": "Inputs", + "type": "object", + "description": "No description", + "properties": { + "id": { + "type": "string", + "description": "The id of the job\n", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "params_yaml": { + "type": "string", + "description": "base64 encoded yaml containing the state\n", + "help_text": "Type: `string`, multiple: `False`, required. " + } + } }, - - { - "$ref": "#/definitions/outputs" + "outputs": { + "title": "Outputs", + "type": "object", + "description": "No description", + "properties": { + "output": { + "type": "string", + "format": "path", + "description": "The output YAML file\n", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"$id.$key.output.yaml\"`, direction: `output`, example: `\"output.yaml\"`. ", + "default": "$id.$key.output.yaml" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/inputs" + }, + { + "$ref": "#/$defs/outputs" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/workflows/htrnaseq/.config.vsh.yaml b/target/nextflow/workflows/htrnaseq/.config.vsh.yaml index 87ceda5c..fda415c1 100644 --- a/target/nextflow/workflows/htrnaseq/.config.vsh.yaml +++ b/target/nextflow/workflows/htrnaseq/.config.vsh.yaml @@ -262,7 +262,7 @@ repositories: - type: "vsh" name: "bb" repo: "biobox" - tag: "v0.1.0" + tag: "v0.3.1" license: "MIT" links: repository: "https://github.com/viash-hub/htrnaseq" @@ -342,9 +342,9 @@ build_info: output: "target/nextflow/workflows/htrnaseq" executable: "target/nextflow/workflows/htrnaseq/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" dependencies: - "target/nextflow/stats/combine_star_logs" - "target/nextflow/stats/generate_pool_statistics" diff --git a/target/nextflow/workflows/htrnaseq/main.nf b/target/nextflow/workflows/htrnaseq/main.nf index 04abb588..3a537fa5 100644 --- a/target/nextflow/workflows/htrnaseq/main.nf +++ b/target/nextflow/workflows/htrnaseq/main.nf @@ -3384,7 +3384,7 @@ meta = [ "type" : "vsh", "name" : "bb", "repo" : "biobox", - "tag" : "v0.1.0" + "tag" : "v0.3.1" } ], "license" : "MIT", @@ -3479,9 +3479,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/htrnaseq", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/workflows/htrnaseq/nextflow_schema.json b/target/nextflow/workflows/htrnaseq/nextflow_schema.json index 952bd8d3..9fabc233 100644 --- a/target/nextflow/workflows/htrnaseq/nextflow_schema.json +++ b/target/nextflow/workflows/htrnaseq/nextflow_schema.json @@ -1,244 +1,170 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "htrnaseq", -"description": "No description", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Forward reads in FASTQ format", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Forward reads in FASTQ format. Multiple files corresponding to different lanes can be provided which will\nbe demultiplexed separately before joining the results for each individual well.\n" - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Reverse reads in FASTQ format", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Reverse reads in FASTQ format. Multiple files corresponding to different lanes can be provided which will\nbe demultiplexed separately before joining the results for each individual well.\n" - - } - - - , - "barcodesFasta": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "umi_length": { - "type": - "integer", - "description": "Type: `integer`, default: `10`. Length of the UMI sequences\n", - "help_text": "Type: `integer`, default: `10`. Length of the UMI sequences\n" - , - "default":10 - } - - - , - "genomeDir": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "annotation": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "sample_id": { - "type": - "string", - "description": "Type: `string`. Sample ID for the provided input files", - "help_text": "Type: `string`. Sample ID for the provided input files. If not provided, the value of --id\nwill be used. Input files will allways be demultiplexed separately,\nbut the FASTQs for wells with matching sample IDs will be concatenated before mapping.\n" - - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "fastq_output": { - "type": - "string", - "description": "Type: List of `file`, required, default: `fastq/*`, multiple_sep: `\";\"`. Directory containing output fastq files", - "help_text": "Type: List of `file`, required, default: `fastq/*`, multiple_sep: `\";\"`. Directory containing output fastq files" - , - "default":"fastq/*" - } - - - , - "star_output": { - "type": - "string", - "description": "Type: List of `file`, required, default: `star.$id/*`, multiple_sep: `\";\"`. Output from mapping with STAR", - "help_text": "Type: List of `file`, required, default: `star.$id/*`, multiple_sep: `\";\"`. Output from mapping with STAR" - , - "default":"star.$id/*" - } - - - , - "nrReadsNrGenesPerChrom": { - "type": - "string", - "description": "Type: `file`, required, default: `nrReadsNrGenesPerChrom.$id.txt`. ", - "help_text": "Type: `file`, required, default: `nrReadsNrGenesPerChrom.$id.txt`. " - , - "default":"nrReadsNrGenesPerChrom.$id.txt" - } - - - , - "star_qc_metrics": { - "type": - "string", - "description": "Type: `file`, required, default: `starLogs.$id.txt`. ", - "help_text": "Type: `file`, required, default: `starLogs.$id.txt`. " - , - "default":"starLogs.$id.txt" - } - - - , - "eset": { - "type": - "string", - "description": "Type: `file`, required, default: `eset.$id.rds`. ", - "help_text": "Type: `file`, required, default: `eset.$id.rds`. " - , - "default":"eset.$id.rds" - } - - - , - "f_data": { - "type": - "string", - "description": "Type: `file`, required, default: `fData.$id.tsv`. ", - "help_text": "Type: `file`, required, default: `fData.$id.tsv`. " - , - "default":"fData.$id.tsv" - } - - - , - "p_data": { - "type": - "string", - "description": "Type: `file`, required, default: `pData.$id.tsv`. ", - "help_text": "Type: `file`, required, default: `pData.$id.tsv`. " - , - "default":"pData.$id.tsv" - } - - - , - "html_report": { - "type": - "string", - "description": "Type: `file`, required, default: `report.$id.html`. ", - "help_text": "Type: `file`, required, default: `report.$id.html`. " - , - "default":"report.$id.html" - } - - - , - "run_params": { - "type": - "string", - "description": "Type: `file`, default: `params.$id.yaml`. ", - "help_text": "Type: `file`, default: `params.$id.yaml`. " - , - "default":"params.$id.yaml" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/input arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "htrnaseq", + "description": "No description", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Forward reads in FASTQ format", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "input_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Reverse reads in FASTQ format", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "barcodesFasta": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "umi_length": { + "type": "integer", + "description": "Length of the UMI sequences\n", + "help_text": "Type: `integer`, multiple: `False`, default: `10`. ", + "default": 10 + }, + "genomeDir": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "annotation": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "sample_id": { + "type": "string", + "description": "Sample ID for the provided input files", + "help_text": "Type: `string`, multiple: `False`. " + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "fastq_output": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "Directory containing output fastq files", + "help_text": "Type: `file`, multiple: `True`, required, default: `[\"fastq/*\"]`, direction: `output`. ", + "default": [ + "fastq/*" + ] + }, + "star_output": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "Output from mapping with STAR", + "help_text": "Type: `file`, multiple: `True`, required, default: `[\"star.$id/*\"]`, direction: `output`. ", + "default": [ + "star.$id/*" + ] + }, + "nrReadsNrGenesPerChrom": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"nrReadsNrGenesPerChrom.$id.txt\"`, direction: `output`. ", + "default": "nrReadsNrGenesPerChrom.$id.txt" + }, + "star_qc_metrics": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"starLogs.$id.txt\"`, direction: `output`. ", + "default": "starLogs.$id.txt" + }, + "eset": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"eset.$id.rds\"`, direction: `output`. ", + "default": "eset.$id.rds" + }, + "f_data": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"fData.$id.tsv\"`, direction: `output`. ", + "default": "fData.$id.tsv" + }, + "p_data": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"pData.$id.tsv\"`, direction: `output`. ", + "default": "pData.$id.tsv" + }, + "html_report": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"report.$id.html\"`, direction: `output`. ", + "default": "report.$id.html" + }, + "run_params": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"params.$id.yaml\"`, direction: `output`. ", + "default": "params.$id.yaml" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/workflows/runner/.config.vsh.yaml b/target/nextflow/workflows/runner/.config.vsh.yaml index 179fc898..9a8cfd2e 100644 --- a/target/nextflow/workflows/runner/.config.vsh.yaml +++ b/target/nextflow/workflows/runner/.config.vsh.yaml @@ -235,9 +235,9 @@ build_info: output: "target/nextflow/workflows/runner" executable: "target/nextflow/workflows/runner/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" dependencies: - "target/nextflow/utils/listInputDir" - "target/nextflow/workflows/htrnaseq" diff --git a/target/nextflow/workflows/runner/main.nf b/target/nextflow/workflows/runner/main.nf index f2719a96..6d3250c7 100644 --- a/target/nextflow/workflows/runner/main.nf +++ b/target/nextflow/workflows/runner/main.nf @@ -3331,9 +3331,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/runner", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/workflows/runner/nextflow_schema.json b/target/nextflow/workflows/runner/nextflow_schema.json index 4cb26e92..3e32c922 100644 --- a/target/nextflow/workflows/runner/nextflow_schema.json +++ b/target/nextflow/workflows/runner/nextflow_schema.json @@ -1,236 +1,148 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "runner", -"description": "Runner for HT RNA-seq pipeline", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input": { - "type": - "string", - "description": "Type: `file`, required. Base directory of the form `s3:/\u003cbucket\u003e/Sequencing/\u003cSequencer\u003e/\u003cRunID\u003e/\u003cdemultiplex_dir\u003e`", - "help_text": "Type: `file`, required. Base directory of the form `s3:/\u003cbucket\u003e/Sequencing/\u003cSequencer\u003e/\u003cRunID\u003e/\u003cdemultiplex_dir\u003e`" - - } - - - , - "barcodesFasta": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "genomeDir": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "annotation": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - - , - "ignore": { - "type": - "string", - "description": "Type: List of `string`, default: `Undetermined`, multiple_sep: `\";\"`. Pool names to ignore", - "help_text": "Type: List of `string`, default: `Undetermined`, multiple_sep: `\";\"`. Pool names to ignore." - , - "default":"Undetermined" - } - - - , - "umi_length": { - "type": - "integer", - "description": "Type: `integer`, default: `10`. Length of the UMI sequences\n", - "help_text": "Type: `integer`, default: `10`. Length of the UMI sequences\n" - , - "default":10 - } - - - , - "run_params": { - "type": - "string", - "description": "Type: `file`, default: `params.yaml`. ", - "help_text": "Type: `file`, default: `params.yaml`. " - , - "default":"params.yaml" - } - - -} -}, - - - "metadata arguments" : { - "title": "Metadata arguments", - "type": "object", - "description": "No description", - "properties": { - - - "id": { - "type": - "string", - "description": "Type: `string`. Unique identifier for the run", - "help_text": "Type: `string`. Unique identifier for the run" - - } - - - , - "project_id": { - "type": - "string", - "description": "Type: `string`, required. Project ID", - "help_text": "Type: `string`, required. Project ID" - - } - - - , - "experiment_id": { - "type": - "string", - "description": "Type: `string`, required. Experiment ID", - "help_text": "Type: `string`, required. Experiment ID" - - } - - -} -}, - - - "annotation flags" : { - "title": "Annotation flags", - "type": "object", - "description": "No description", - "properties": { - - - "plain_output": { - "type": - "boolean", - "description": "Type: `boolean_true`, default: `false`. Flag to indicate that the output should be stored directly under $publish_dir rather than\nunder a subdirectory structure runID/\u003cdate_time\u003e_demultiplex_\u003cversion\u003e/", - "help_text": "Type: `boolean_true`, default: `false`. Flag to indicate that the output should be stored directly under $publish_dir rather than\nunder a subdirectory structure runID/\u003cdate_time\u003e_demultiplex_\u003cversion\u003e/.\n" - , - "default":false - } - - -} -}, - - - "publish arguments" : { - "title": "Publish arguments", - "type": "object", - "description": "No description", - "properties": { - - - "fastq_publish_dir": { - "type": - "string", - "description": "Type: `string`, required. ", - "help_text": "Type: `string`, required. " - - } - - - , - "results_publish_dir": { - "type": - "string", - "description": "Type: `string`, required. ", - "help_text": "Type: `string`, required. " - - } - - -} -}, - - - "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" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "runner", + "description": "Runner for HT RNA-seq pipeline", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input": { + "type": "string", + "format": "path", + "exists": true, + "description": "Base directory of the form `s3://Sequencing///`", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "barcodesFasta": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "genomeDir": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "annotation": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + }, + "ignore": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Pool names to ignore.", + "help_text": "Type: `string`, multiple: `True`, default: `[\"Undetermined\"]`. ", + "default": [ + "Undetermined" + ] + }, + "umi_length": { + "type": "integer", + "description": "Length of the UMI sequences\n", + "help_text": "Type: `integer`, multiple: `False`, default: `10`. ", + "default": 10 + }, + "run_params": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"params.yaml\"`, direction: `output`. ", + "default": "params.yaml" + } + } }, - - { - "$ref": "#/definitions/metadata arguments" + "metadata arguments": { + "title": "Metadata arguments", + "type": "object", + "description": "No description", + "properties": { + "id": { + "type": "string", + "description": "Unique identifier for the run", + "help_text": "Type: `string`, multiple: `False`. " + }, + "project_id": { + "type": "string", + "description": "Project ID", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "experiment_id": { + "type": "string", + "description": "Experiment ID", + "help_text": "Type: `string`, multiple: `False`, required. " + } + } }, - - { - "$ref": "#/definitions/annotation flags" + "annotation flags": { + "title": "Annotation flags", + "type": "object", + "description": "No description", + "properties": { + "plain_output": { + "type": "boolean", + "description": "Flag to indicate that the output should be stored directly under $publish_dir rather than\nunder a subdirectory structure runID/_demultiplex_/.\n", + "help_text": "Type: `boolean_true`, multiple: `False`, default: `false`. ", + "default": false + } + } }, - - { - "$ref": "#/definitions/publish arguments" + "publish arguments": { + "title": "Publish arguments", + "type": "object", + "description": "No description", + "properties": { + "fastq_publish_dir": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`, required. " + }, + "results_publish_dir": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`, required. " + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/metadata arguments" + }, + { + "$ref": "#/$defs/annotation flags" + }, + { + "$ref": "#/$defs/publish arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml b/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml index 320f4fb1..6cbdb133 100644 --- a/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml +++ b/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml @@ -120,21 +120,21 @@ dependencies: repository: type: "vsh" repo: "biobox" - tag: "v0.3.0" + tag: "v0.3.1" - name: "concat_text" repository: type: "vsh" repo: "craftbox" - tag: "v0.1.0" + tag: "v0.2.0" repositories: - type: "vsh" name: "bb" repo: "biobox" - tag: "v0.3.0" + tag: "v0.3.1" - type: "vsh" name: "cb" repo: "craftbox" - tag: "v0.1.0" + tag: "v0.2.0" license: "MIT" links: repository: "https://github.com/viash-hub/htrnaseq" @@ -214,12 +214,12 @@ build_info: output: "target/nextflow/workflows/well_demultiplex" executable: "target/nextflow/workflows/well_demultiplex/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" dependencies: - - "target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt" - - "target/dependencies/vsh/vsh/craftbox/v0.1.0/nextflow/concat_text" + - "target/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt" + - "target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/workflows/well_demultiplex/main.nf b/target/nextflow/workflows/well_demultiplex/main.nf index e1fded11..b73d78dd 100644 --- a/target/nextflow/workflows/well_demultiplex/main.nf +++ b/target/nextflow/workflows/well_demultiplex/main.nf @@ -3196,7 +3196,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "biobox", - "tag" : "v0.3.0" + "tag" : "v0.3.1" } }, { @@ -3204,7 +3204,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "craftbox", - "tag" : "v0.1.0" + "tag" : "v0.2.0" } } ], @@ -3213,13 +3213,13 @@ meta = [ "type" : "vsh", "name" : "bb", "repo" : "biobox", - "tag" : "v0.3.0" + "tag" : "v0.3.1" }, { "type" : "vsh", "name" : "cb", "repo" : "craftbox", - "tag" : "v0.1.0" + "tag" : "v0.2.0" } ], "license" : "MIT", @@ -3314,9 +3314,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/well_demultiplex", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", @@ -3362,8 +3362,8 @@ meta = [ // resolve dependencies dependencies (if any) meta["root_dir"] = getRootDir() -include { cutadapt } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt/main.nf" -include { concat_text } from "${meta.root_dir}/dependencies/vsh/vsh/craftbox/v0.1.0/nextflow/concat_text/main.nf" +include { cutadapt } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.3.1/nextflow/cutadapt/main.nf" +include { concat_text } from "${meta.root_dir}/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/concat_text/main.nf" // inner workflow // user-provided Nextflow code diff --git a/target/nextflow/workflows/well_demultiplex/nextflow_schema.json b/target/nextflow/workflows/well_demultiplex/nextflow_schema.json index 9b7209ac..b703bedc 100644 --- a/target/nextflow/workflows/well_demultiplex/nextflow_schema.json +++ b/target/nextflow/workflows/well_demultiplex/nextflow_schema.json @@ -1,126 +1,96 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "well_demultiplex", -"description": "Demultiplexing on well level", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Forward reads in FASTQ format", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Forward reads in FASTQ format. Multiple files can be provided which will\nbe demultiplexed separately before joining the results for each individual well.\n" - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. Reverse reads in FASTQ format", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. Reverse reads in FASTQ format. Multiple files can be provided which will\nbe demultiplexed separately before joining the results for each individual well.\n" - - } - - - , - "barcodesFasta": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "output_r1": { - "type": - "string", - "description": "Type: List of `file`, required, default: `fastq/*_R1_001.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", - "help_text": "Type: List of `file`, required, default: `fastq/*_R1_001.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" - , - "default":"fastq/*_R1_001.fastq" - } - - - , - "output_r2": { - "type": - "string", - "description": "Type: List of `file`, required, default: `fastq/*_R2_001.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", - "help_text": "Type: List of `file`, required, default: `fastq/*_R2_001.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" - , - "default":"fastq/*_R2_001.fastq" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/input arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "well_demultiplex", + "description": "Demultiplexing on well level", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Forward reads in FASTQ format", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "input_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "Reverse reads in FASTQ format", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "barcodesFasta": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "output_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "List of demultiplexed fastq files", + "help_text": "Type: `file`, multiple: `True`, required, default: `[\"fastq/*_R1_001.fastq\"]`, direction: `output`. ", + "default": [ + "fastq/*_R1_001.fastq" + ] + }, + "output_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "description": "List of demultiplexed fastq files", + "help_text": "Type: `file`, multiple: `True`, required, default: `[\"fastq/*_R2_001.fastq\"]`, direction: `output`. ", + "default": [ + "fastq/*_R2_001.fastq" + ] + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] } diff --git a/target/nextflow/workflows/well_metadata/.config.vsh.yaml b/target/nextflow/workflows/well_metadata/.config.vsh.yaml index 8da06607..392cb457 100644 --- a/target/nextflow/workflows/well_metadata/.config.vsh.yaml +++ b/target/nextflow/workflows/well_metadata/.config.vsh.yaml @@ -212,9 +212,9 @@ build_info: output: "target/nextflow/workflows/well_metadata" executable: "target/nextflow/workflows/well_metadata/main.nf" viash_version: "0.9.4" - git_commit: "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80" + git_commit: "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957" git_remote: "https://github.com/viash-hub/htrnaseq" - git_tag: "v0.7.2-5-g7e47ecc" + git_tag: "v0.7.2-6-ga3b7ae3" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/workflows/well_metadata/main.nf b/target/nextflow/workflows/well_metadata/main.nf index 18ba6f6e..9b4213c0 100644 --- a/target/nextflow/workflows/well_metadata/main.nf +++ b/target/nextflow/workflows/well_metadata/main.nf @@ -3294,9 +3294,9 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/well_metadata", "viash_version" : "0.9.4", - "git_commit" : "7e47ecc5dbf74e3bd5c35783f78bb948f6616d80", + "git_commit" : "a3b7ae3f31ff5eeee305a2cca1ce09ebe1cd8957", "git_remote" : "https://github.com/viash-hub/htrnaseq", - "git_tag" : "v0.7.2-5-g7e47ecc" + "git_tag" : "v0.7.2-6-ga3b7ae3" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/workflows/well_metadata/nextflow_schema.json b/target/nextflow/workflows/well_metadata/nextflow_schema.json index 5418332f..b15de895 100644 --- a/target/nextflow/workflows/well_metadata/nextflow_schema.json +++ b/target/nextflow/workflows/well_metadata/nextflow_schema.json @@ -1,187 +1,123 @@ { -"$schema": "http://json-schema.org/draft-07/schema", -"title": "well_metadata", -"description": "No description", -"type": "object", -"definitions": { - - - - "input arguments" : { - "title": "Input arguments", - "type": "object", - "description": "No description", - "properties": { - - - "input_r1": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. List of FASTQ files for the forward reads, 1 per well", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. List of FASTQ files for the forward reads, 1 per well.\n" - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. List of FASTQ files for the forward reads, 1 per well", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. List of FASTQ files for the forward reads, 1 per well.\n" - - } - - - , - "star_mapping": { - "type": - "string", - "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", - "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " - - } - - - , - "barcodesFasta": { - "type": - "string", - "description": "Type: `file`, required. ", - "help_text": "Type: `file`, required. " - - } - - -} -}, - - - "output arguments" : { - "title": "Output arguments", - "type": "object", - "description": "No description", - "properties": { - - - "output_r1": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.output_r1`. Output fastq file", - "help_text": "Type: `file`, required, default: `$id.$key.output_r1`. Output fastq file." - , - "default":"$id.$key.output_r1" - } - - - , - "output_r2": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.output_r2`. Output fastq file", - "help_text": "Type: `file`, required, default: `$id.$key.output_r2`. Output fastq file." - , - "default":"$id.$key.output_r2" - } - - - , - "pool": { - "type": - "string", - "description": "Type: `string`. The original pool / sample name", - "help_text": "Type: `string`. The original pool / sample name" - - } - - - , - "well_id": { - "type": - "string", - "description": "Type: `string`. ", - "help_text": "Type: `string`. " - - } - - - , - "barcode": { - "type": - "string", - "description": "Type: `string`. ", - "help_text": "Type: `string`. " - - } - - - , - "n_wells": { - "type": - "integer", - "description": "Type: `integer`. The number of wells in the pool is well is a part of", - "help_text": "Type: `integer`. The number of wells in the pool is well is a part of." - - } - - - , - "well_star_mapping": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.well_star_mapping`. ", - "help_text": "Type: `file`, default: `$id.$key.well_star_mapping`. " - , - "default":"$id.$key.well_star_mapping" - } - - -} -}, - - - "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": [ - - { - "$ref": "#/definitions/input arguments" + "$schema": "https://json-schema.org/draft/2020-12/schema", + "title": "well_metadata", + "description": "No description", + "type": "object", + "$defs": { + "input arguments": { + "title": "Input arguments", + "type": "object", + "description": "No description", + "properties": { + "input_r1": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "List of FASTQ files for the forward reads, 1 per well.\n", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "input_r2": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "List of FASTQ files for the forward reads, 1 per well.\n", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "star_mapping": { + "type": "array", + "items": { + "type": "string" + }, + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `True`, required, direction: `input`. " + }, + "barcodesFasta": { + "type": "string", + "format": "path", + "exists": true, + "description": "", + "help_text": "Type: `file`, multiple: `False`, required, direction: `input`. " + } + } }, - - { - "$ref": "#/definitions/output arguments" + "output arguments": { + "title": "Output arguments", + "type": "object", + "description": "No description", + "properties": { + "output_r1": { + "type": "string", + "format": "path", + "description": "Output fastq file.", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"$id.$key.output_r1\"`, direction: `output`. ", + "default": "$id.$key.output_r1" + }, + "output_r2": { + "type": "string", + "format": "path", + "description": "Output fastq file.", + "help_text": "Type: `file`, multiple: `False`, required, default: `\"$id.$key.output_r2\"`, direction: `output`. ", + "default": "$id.$key.output_r2" + }, + "pool": { + "type": "string", + "description": "The original pool / sample name", + "help_text": "Type: `string`, multiple: `False`. " + }, + "well_id": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`. " + }, + "barcode": { + "type": "string", + "description": "", + "help_text": "Type: `string`, multiple: `False`. " + }, + "n_wells": { + "type": "integer", + "description": "The number of wells in the pool is well is a part of.", + "help_text": "Type: `integer`, multiple: `False`. " + }, + "well_star_mapping": { + "type": "string", + "format": "path", + "description": "", + "help_text": "Type: `file`, multiple: `False`, default: `\"$id.$key.well_star_mapping\"`, direction: `output`. ", + "default": "$id.$key.well_star_mapping" + } + } }, - - { - "$ref": "#/definitions/nextflow input-output arguments" + "nextflow input-output arguments": { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + "publish_dir": { + "type": "string", + "description": "Path to an output directory.", + "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. " + } + } } -] + }, + "allOf": [ + { + "$ref": "#/$defs/input arguments" + }, + { + "$ref": "#/$defs/output arguments" + }, + { + "$ref": "#/$defs/nextflow input-output arguments" + } + ] }