Build branch fix-integration-tests with version fix-integration-tests (da62b4ff)

Build pipeline: vsh-ci-dev-gckj5

Source commit: da62b4ffe3

Source message: Add labels to qc_test component

target/executable/dataflow/split_modalities/.config.vsh.yaml

@@ -0,0 +1,259 @@
+name: "split_modalities"
+namespace: "dataflow"
+version: "fix-integration-tests"
+authors:
+- name: "Dries Schaumont"
+  roles:
+  - "maintainer"
+  info:
+    role: "Core Team Member"
+    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"
+- name: "Robrecht Cannoodt"
+  roles:
+  - "contributor"
+  info:
+    role: "Core Team Member"
+    links:
+      email: "robrecht@data-intuitive.com"
+      github: "rcannood"
+      orcid: "0000-0003-3641-729X"
+      linkedin: "robrechtcannoodt"
+    organizations:
+    - name: "Data Intuitive"
+      href: "https://www.data-intuitive.com"
+      role: "Data Science Engineer"
+    - name: "Open Problems"
+      href: "https://openproblems.bio"
+      role: "Core Member"
+argument_groups:
+- name: "Arguments"
+  arguments:
+  - type: "file"
+    name: "--input"
+    alternatives:
+    - "-i"
+    description: "Path to a single .h5mu file."
+    info: null
+    default:
+    - "sample_path"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--output"
+    alternatives:
+    - "-o"
+    description: "Output directory containing multiple h5mu files."
+    info: null
+    example:
+    - "/path/to/output"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "output"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--output_compression"
+    description: "The compression format to be used on the output h5mu object."
+    info: null
+    example:
+    - "gzip"
+    required: false
+    choices:
+    - "gzip"
+    - "lzf"
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--output_types"
+    description: "A csv containing the base filename and modality type per output\
+      \ file."
+    info: null
+    example:
+    - "types.csv"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "output"
+    multiple: false
+    multiple_sep: ";"
+resources:
+- type: "python_script"
+  path: "script.py"
+  is_executable: true
+- type: "file"
+  path: "setup_logger.py"
+- type: "file"
+  path: "nextflow_labels.config"
+  dest: "nextflow_labels.config"
+description: "Split the modalities from a single .h5mu multimodal sample into seperate\
+  \ .h5mu files. \n"
+test_resources:
+- type: "python_script"
+  path: "test.py"
+  is_executable: true
+- type: "file"
+  path: "openpipelinetestutils"
+  dest: "openpipelinetestutils"
+info: null
+status: "enabled"
+links:
+  repository: "https://github.com/openpipelines-bio/openpipeline"
+  docker_registry: "ghcr.io"
+runners:
+- type: "executable"
+  id: "executable"
+  docker_setup_strategy: "ifneedbepullelsecachedbuild"
+- type: "nextflow"
+  id: "nextflow"
+  directives:
+    label:
+    - "singlecpu"
+    - "lowmem"
+    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"
+    script:
+    - "includeConfig(\"nextflow_labels.config\")"
+  debug: false
+  container: "docker"
+engines:
+- type: "docker"
+  id: "docker"
+  image: "python:3.12-slim"
+  target_registry: "images.viash-hub.com"
+  target_tag: "fix-integration-tests"
+  namespace_separator: "/"
+  setup:
+  - type: "apt"
+    packages:
+    - "procps"
+    interactive: false
+  - type: "python"
+    user: false
+    packages:
+    - "anndata==0.10.8"
+    - "mudata~=0.2.4"
+    - "pandas!=2.1.2"
+    - "numpy<2.0.0"
+    upgrade: true
+  test_setup:
+  - type: "docker"
+    copy:
+    - "openpipelinetestutils /opt/openpipelinetestutils"
+  - type: "python"
+    user: false
+    packages:
+    - "/opt/openpipelinetestutils"
+    upgrade: true
+  - type: "python"
+    user: false
+    packages:
+    - "viashpy==0.8.0"
+    upgrade: true
+  entrypoint: []
+  cmd: null
+- type: "native"
+  id: "native"
+build_info:
+  config: "src/dataflow/split_modalities/config.vsh.yaml"
+  runner: "executable"
+  engine: "docker|native"
+  output: "target/executable/dataflow/split_modalities"
+  executable: "target/executable/dataflow/split_modalities/split_modalities"
+  viash_version: "0.9.0"
+  git_commit: "da62b4ffe30b6ef36fcb7ef5944f29d45d1138ff"
+  git_remote: "https://x-access-token:ghs_WgbTvvspBKMSQ5BPucz45vMfHrxqK54Vys9e@github.com/openpipelines-bio/openpipeline"
+  git_tag: "0.2.0-1939-gda62b4ff"
+package_config:
+  name: "openpipeline"
+  version: "fix-integration-tests"
+  info:
+    test_resources:
+    - type: "s3"
+      path: "s3://openpipelines-data"
+      dest: "resources_test"
+  viash_version: "0.9.0"
+  source: "src"
+  target: "target"
+  config_mods:
+  - ".test_resources += {path: '/src/base/openpipelinetestutils', dest: 'openpipelinetestutils'}\n\
+    .resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n\
+    .runners[.type == 'nextflow'].directives.tag := '$id'\n.runners[.type == 'nextflow'].config.script\
+    \ := 'includeConfig(\"nextflow_labels.config\")'\n"
+  - ".engines += { type: \"native\" }"
+  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
+  - ".engines[.type == 'docker'].target_tag := 'fix-integration-tests'"
+  organization: "vsh"
+  links:
+    repository: "https://github.com/openpipelines-bio/openpipeline"
+    docker_registry: "ghcr.io"
+    homepage: "https://openpipelines.bio"
+    documentation: "https://openpipelines.bio/fundamentals"
+    issue_tracker: "https://github.com/openpipelines-bio/openpipeline/issues"

target/executable/dataflow/split_modalities/nextflow_labels.config

@@ -0,0 +1,42 @@
+process {
+  // Default resources for components that hardly do any processing
+  memory = { 2.GB * task.attempt }
+  cpus = 1
+
+  // Retry for exit codes that have something to do with memory issues
+  errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
+  maxRetries = 3
+  maxMemory = null
+
+  // Resource labels
+  withLabel: singlecpu { cpus = 1 }
+  withLabel: lowcpu { cpus = 4 }
+  withLabel: midcpu { cpus = 10 }
+  withLabel: highcpu { cpus = 20 }
+  
+  withLabel: lowmem { memory = { get_memory( 4.GB * task.attempt ) } }
+  withLabel: midmem { memory = { get_memory( 25.GB * task.attempt ) } }
+  withLabel: highmem { memory = { get_memory( 50.GB * task.attempt ) } }
+  withLabel: veryhighmem { memory = { get_memory( 75.GB * task.attempt ) } }
+}
+
+def get_memory(to_compare) {
+  if (!process.containsKey("maxMemory") || !process.maxMemory) {
+    return to_compare
+  }
+
+  try {
+    if (process.containsKey("maxRetries") && process.maxRetries && task.attempt == (process.maxRetries as int)) {
+      return process.maxMemory
+    }
+    else if (to_compare.compareTo(process.maxMemory as nextflow.util.MemoryUnit) == 1) {
+      return max_memory as nextflow.util.MemoryUnit
+    }
+    else {
+      return to_compare
+    }  
+  } catch (all) {
+        println "Error processing memory resources. Please check that process.maxMemory '${process.maxMemory}' and process.maxRetries '${process.maxRetries}' are valid!"
+        System.exit(1)
+  }
+}

target/executable/dataflow/split_modalities/setup_logger.py

@@ -0,0 +1,12 @@
+def setup_logger():
+    import logging
+    from sys import stdout
+
+    logger = logging.getLogger()
+    logger.setLevel(logging.INFO)
+    console_handler = logging.StreamHandler(stdout)
+    logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
+    console_handler.setFormatter(logFormatter)
+    logger.addHandler(console_handler)
+
+    return logger