#!/usr/bin/env bash

# cellxgene_census v4.0.4
# 
# 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:
#  * Matthias Beyens (maintainer, author)
#  * Dries De Maeyer (author)
#  * Robrecht Cannoodt (author)
#  * Kai Waldrant (contributor)

set -e

if [ -z "$VIASH_TEMP" ]; then
  VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMPDIR}
  VIASH_TEMP=${VIASH_TEMP:-$VIASH_TEMPDIR}
  VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMP}
  VIASH_TEMP=${VIASH_TEMP:-$TMPDIR}
  VIASH_TEMP=${VIASH_TEMP:-$TMP}
  VIASH_TEMP=${VIASH_TEMP:-$TEMPDIR}
  VIASH_TEMP=${VIASH_TEMP:-$TEMP}
  VIASH_TEMP=${VIASH_TEMP:-/tmp}
fi

# define helper functions
# ViashQuote: put quotes around non flag values
# $1     : unquoted string
# return : possibly quoted string
# examples:
#   ViashQuote --foo      # returns --foo
#   ViashQuote bar        # returns 'bar'
#   Viashquote --foo=bar  # returns --foo='bar'
function ViashQuote {
  if [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+=.+$ ]]; then
    echo "$1" | sed "s#=\(.*\)#='\1'#"
  elif [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+$ ]]; then
    echo "$1"
  else
    echo "'$1'"
  fi
}
# ViashRemoveFlags: Remove leading flag
# $1     : string with a possible leading flag
# return : string without possible leading flag
# examples:
#   ViashRemoveFlags --foo=bar  # returns bar
function ViashRemoveFlags {
  echo "$1" | sed 's/^--*[a-zA-Z0-9_\-]*=//'
}
# ViashSourceDir: return the path of a bash file, following symlinks
# usage   : ViashSourceDir ${BASH_SOURCE[0]}
# $1      : Should always be set to ${BASH_SOURCE[0]}
# returns : The absolute path of the bash file
function ViashSourceDir {
  local source="$1"
  while [ -h "$source" ]; do
    local dir="$( cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd )"
    source="$(readlink "$source")"
    [[ $source != /* ]] && source="$dir/$source"
  done
  cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd
}
# ViashFindTargetDir: return the path of the '.build.yaml' file, following symlinks
# usage   : ViashFindTargetDir 'ScriptPath'
# $1      : The location from where to start the upward search
# returns : The absolute path of the '.build.yaml' file
function ViashFindTargetDir {
  local source="$1"
  while [[ "$source" != "" && ! -e "$source/.build.yaml" ]]; do
    source=${source%/*}
  done
  echo $source
}
# see https://en.wikipedia.org/wiki/Syslog#Severity_level
VIASH_LOGCODE_EMERGENCY=0
VIASH_LOGCODE_ALERT=1
VIASH_LOGCODE_CRITICAL=2
VIASH_LOGCODE_ERROR=3
VIASH_LOGCODE_WARNING=4
VIASH_LOGCODE_NOTICE=5
VIASH_LOGCODE_INFO=6
VIASH_LOGCODE_DEBUG=7
VIASH_VERBOSITY=$VIASH_LOGCODE_NOTICE

# ViashLog: Log events depending on the verbosity level
# usage: ViashLog 1 alert Oh no something went wrong!
# $1: required verbosity level
# $2: display tag
# $3+: messages to display
# stdout: Your input, prepended by '[$2] '.
function ViashLog {
  local required_level="$1"
  local display_tag="$2"
  shift 2
  if [ $VIASH_VERBOSITY -ge $required_level ]; then
    >&2 echo "[$display_tag]" "$@"
  fi
}

# ViashEmergency: log events when the system is unstable
# usage: ViashEmergency Oh no something went wrong.
# stdout: Your input, prepended by '[emergency] '.
function ViashEmergency {
  ViashLog $VIASH_LOGCODE_EMERGENCY emergency "$@"
}

# ViashAlert: log events when actions must be taken immediately (e.g. corrupted system database)
# usage: ViashAlert Oh no something went wrong.
# stdout: Your input, prepended by '[alert] '.
function ViashAlert {
  ViashLog $VIASH_LOGCODE_ALERT alert "$@"
}

# ViashCritical: log events when a critical condition occurs
# usage: ViashCritical Oh no something went wrong.
# stdout: Your input, prepended by '[critical] '.
function ViashCritical {
  ViashLog $VIASH_LOGCODE_CRITICAL critical "$@"
}

# ViashError: log events when an error condition occurs
# usage: ViashError Oh no something went wrong.
# stdout: Your input, prepended by '[error] '.
function ViashError {
  ViashLog $VIASH_LOGCODE_ERROR error "$@"
}

# ViashWarning: log potentially abnormal events
# usage: ViashWarning Something may have gone wrong.
# stdout: Your input, prepended by '[warning] '.
function ViashWarning {
  ViashLog $VIASH_LOGCODE_WARNING warning "$@"
}

# ViashNotice: log significant but normal events
# usage: ViashNotice This just happened.
# stdout: Your input, prepended by '[notice] '.
function ViashNotice {
  ViashLog $VIASH_LOGCODE_NOTICE notice "$@"
}

# ViashInfo: log normal events
# usage: ViashInfo This just happened.
# stdout: Your input, prepended by '[info] '.
function ViashInfo {
  ViashLog $VIASH_LOGCODE_INFO info "$@"
}

# ViashDebug: log all events, for debugging purposes
# usage: ViashDebug This just happened.
# stdout: Your input, prepended by '[debug] '.
function ViashDebug {
  ViashLog $VIASH_LOGCODE_DEBUG debug "$@"
}

# find source folder of this component
VIASH_META_RESOURCES_DIR=`ViashSourceDir ${BASH_SOURCE[0]}`

# find the root of the built components & dependencies
VIASH_TARGET_DIR=`ViashFindTargetDir $VIASH_META_RESOURCES_DIR`

# define meta fields
VIASH_META_NAME="cellxgene_census"
VIASH_META_FUNCTIONALITY_NAME="cellxgene_census"
VIASH_META_EXECUTABLE="$VIASH_META_RESOURCES_DIR/$VIASH_META_NAME"
VIASH_META_CONFIG="$VIASH_META_RESOURCES_DIR/.config.vsh.yaml"
VIASH_META_TEMP_DIR="$VIASH_TEMP"



# initialise variables
VIASH_MODE='run'
VIASH_ENGINE_ID='docker'

######## Helper functions for setting up Docker images for viash ########
# expects: ViashDockerBuild

# ViashDockerInstallationCheck: check whether Docker is installed correctly
#
# examples:
#   ViashDockerInstallationCheck
function ViashDockerInstallationCheck {
  ViashDebug "Checking whether Docker is installed"
  if [ ! command -v docker &> /dev/null ]; then
    ViashCritical "Docker doesn't seem to be installed. See 'https://docs.docker.com/get-docker/' for instructions."
    exit 1
  fi

  ViashDebug "Checking whether the Docker daemon is running"
  local save=$-; set +e
  local docker_version=$(docker version --format '{{.Client.APIVersion}}' 2> /dev/null)
  local out=$?
  [[ $save =~ e ]] && set -e
  if [ $out -ne 0 ]; then
    ViashCritical "Docker daemon does not seem to be running. Try one of the following:"
    ViashCritical "- Try running 'dockerd' in the command line"
    ViashCritical "- See https://docs.docker.com/config/daemon/"
    exit 1
  fi
}

# ViashDockerRemoteTagCheck: check whether a Docker image is available 
# on a remote. Assumes `docker login` has been performed, if relevant.
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# exit code $?        : whether or not the image was found
# examples:
#   ViashDockerRemoteTagCheck python:latest
#   echo $?                                     # returns '0'
#   ViashDockerRemoteTagCheck sdaizudceahifu
#   echo $?                                     # returns '1'
function ViashDockerRemoteTagCheck {
  docker manifest inspect $1 > /dev/null 2> /dev/null
}

# ViashDockerLocalTagCheck: check whether a Docker image is available locally
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# exit code $?        : whether or not the image was found
# examples:
#   docker pull python:latest
#   ViashDockerLocalTagCheck python:latest
#   echo $?                                     # returns '0'
#   ViashDockerLocalTagCheck sdaizudceahifu
#   echo $?                                     # returns '1'
function ViashDockerLocalTagCheck {
  [ -n "$(docker images -q $1)" ]
}

# ViashDockerPull: pull a Docker image
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# exit code $?        : whether or not the image was found
# examples:
#   ViashDockerPull python:latest
#   echo $?                                     # returns '0'
#   ViashDockerPull sdaizudceahifu
#   echo $?                                     # returns '1'
function ViashDockerPull {
  ViashNotice "Checking if Docker image is available at '$1'"
  if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then
    docker pull $1 && return 0 || return 1
  else
    local save=$-; set +e
    docker pull $1 2> /dev/null > /dev/null
    local out=$?
    [[ $save =~ e ]] && set -e
    if [ $out -ne 0 ]; then
      ViashWarning "Could not pull from '$1'. Docker image doesn't exist or is not accessible."
    fi
    return $out
  fi
}

# ViashDockerPush: push a Docker image
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# exit code $?        : whether or not the image was found
# examples:
#   ViashDockerPush python:latest
#   echo $?                                     # returns '0'
#   ViashDockerPush sdaizudceahifu
#   echo $?                                     # returns '1'
function ViashDockerPush {
  ViashNotice "Pushing image to '$1'"
  local save=$-; set +e
  local out
  if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then
    docker push $1
    out=$?
  else
    docker push $1 2> /dev/null > /dev/null
    out=$?
  fi
  [[ $save =~ e ]] && set -e
  if [ $out -eq 0 ]; then
    ViashNotice "Container '$1' push succeeded."
  else
    ViashError "Container '$1' push errored. You might not be logged in or have the necessary permissions."
  fi
  return $out
}

# ViashDockerPullElseBuild: pull a Docker image, else build it
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# ViashDockerBuild    : a Bash function which builds a docker image, takes image identifier as argument.
# examples:
#   ViashDockerPullElseBuild mynewcomponent
function ViashDockerPullElseBuild {
  local save=$-; set +e
  ViashDockerPull $1
  local out=$?
  [[ $save =~ e ]] && set -e
  if [ $out -ne 0 ]; then
    ViashDockerBuild $@
  fi
}

# ViashDockerSetup: create a Docker image, according to specified docker setup strategy
#
# $1          : image identifier with format `[registry/]image[:tag]`
# $2          : docker setup strategy, see DockerSetupStrategy.scala
# examples:
#   ViashDockerSetup mynewcomponent alwaysbuild
function ViashDockerSetup {
  local image_id="$1"
  local setup_strategy="$2"
  if [ "$setup_strategy" == "alwaysbuild" -o "$setup_strategy" == "build" -o "$setup_strategy" == "b" ]; then
    ViashDockerBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id")
  elif [ "$setup_strategy" == "alwayspull" -o "$setup_strategy" == "pull" -o "$setup_strategy" == "p" ]; then
    ViashDockerPull $image_id
  elif [ "$setup_strategy" == "alwayspullelsebuild" -o "$setup_strategy" == "pullelsebuild" ]; then
    ViashDockerPullElseBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id")
  elif [ "$setup_strategy" == "alwayspullelsecachedbuild" -o "$setup_strategy" == "pullelsecachedbuild" ]; then
    ViashDockerPullElseBuild $image_id $(ViashDockerBuildArgs "$engine_id")
  elif [ "$setup_strategy" == "alwayscachedbuild" -o "$setup_strategy" == "cachedbuild" -o "$setup_strategy" == "cb" ]; then
    ViashDockerBuild $image_id $(ViashDockerBuildArgs "$engine_id")
  elif [[ "$setup_strategy" =~ ^ifneedbe ]]; then
    local save=$-; set +e
    ViashDockerLocalTagCheck $image_id
    local outCheck=$?
    [[ $save =~ e ]] && set -e
    if [ $outCheck -eq 0 ]; then
      ViashInfo "Image $image_id already exists"
    elif [ "$setup_strategy" == "ifneedbebuild" ]; then
      ViashDockerBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id")
    elif [ "$setup_strategy" == "ifneedbecachedbuild" ]; then
      ViashDockerBuild $image_id $(ViashDockerBuildArgs "$engine_id")
    elif [ "$setup_strategy" == "ifneedbepull" ]; then
      ViashDockerPull $image_id
    elif [ "$setup_strategy" == "ifneedbepullelsebuild" ]; then
      ViashDockerPullElseBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id")
    elif [ "$setup_strategy" == "ifneedbepullelsecachedbuild" ]; then
      ViashDockerPullElseBuild $image_id $(ViashDockerBuildArgs "$engine_id")
    else
      ViashError "Unrecognised Docker strategy: $setup_strategy"
      exit 1
    fi
  elif [ "$setup_strategy" == "push" -o "$setup_strategy" == "forcepush" -o "$setup_strategy" == "alwayspush" ]; then
    ViashDockerPush "$image_id"
  elif [ "$setup_strategy" == "pushifnotpresent" -o "$setup_strategy" == "gentlepush" -o "$setup_strategy" == "maybepush" ]; then
    local save=$-; set +e
    ViashDockerRemoteTagCheck $image_id
    local outCheck=$?
    [[ $save =~ e ]] && set -e
    if [ $outCheck -eq 0 ]; then
      ViashNotice "Container '$image_id' exists, doing nothing."
    else
      ViashNotice "Container '$image_id' does not yet exist."
      ViashDockerPush "$image_id"
    fi
  elif [ "$setup_strategy" == "donothing" -o "$setup_strategy" == "meh" ]; then
    ViashNotice "Skipping setup."
  else
    ViashError "Unrecognised Docker strategy: $setup_strategy"
    exit 1
  fi
}

# ViashDockerCheckCommands: Check whether a docker container has the required commands
#
# $1                  : image identifier with format `[registry/]image[:tag]`
# $@                  : commands to verify being present
# examples:
#   ViashDockerCheckCommands bash:4.0 bash ps foo
function ViashDockerCheckCommands {
  local image_id="$1"
  shift 1
  local commands="$@"
  local save=$-; set +e
  local missing # mark 'missing' as local in advance, otherwise the exit code of the command will be missing and always be '0'
  missing=$(docker run --rm --entrypoint=sh "$image_id" -c "for command in $commands; do command -v \$command >/dev/null 2>&1; if [ \$? -ne 0 ]; then echo \$command; exit 1; fi; done")
  local outCheck=$?
  [[ $save =~ e ]] && set -e
  if [ $outCheck -ne 0 ]; then
  	ViashError "Docker container '$image_id' does not contain command '$missing'."
  	exit 1
  fi
}

# ViashDockerBuild: build a docker image
# $1                               : image identifier with format `[registry/]image[:tag]`
# $...                             : additional arguments to pass to docker build
# $VIASH_META_TEMP_DIR             : temporary directory to store dockerfile & optional resources in
# $VIASH_META_NAME                 : name of the component
# $VIASH_META_RESOURCES_DIR        : directory containing the resources
# $VIASH_VERBOSITY                 : verbosity level
# exit code $?                     : whether or not the image was built successfully
function ViashDockerBuild {
  local image_id="$1"
  shift 1

  # create temporary directory to store dockerfile & optional resources in
  local tmpdir=$(mktemp -d "$VIASH_META_TEMP_DIR/dockerbuild-$VIASH_META_NAME-XXXXXX")
  local dockerfile="$tmpdir/Dockerfile"
  function clean_up {
    rm -rf "$tmpdir"
  }
  trap clean_up EXIT

  # store dockerfile and resources
  ViashDockerfile "$VIASH_ENGINE_ID" > "$dockerfile"

  # generate the build command
  local docker_build_cmd="docker build -t '$image_id' $@ '$VIASH_META_RESOURCES_DIR' -f '$dockerfile'"

  # build the container
  ViashNotice "Building container '$image_id' with Dockerfile"
  ViashInfo "$docker_build_cmd"
  local save=$-; set +e
  if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then
    eval $docker_build_cmd
  else
    eval $docker_build_cmd &> "$tmpdir/docker_build.log"
  fi

  # check exit code
  local out=$?
  [[ $save =~ e ]] && set -e
  if [ $out -ne 0 ]; then
    ViashError "Error occurred while building container '$image_id'"
    if [ $VIASH_VERBOSITY -lt $VIASH_LOGCODE_INFO ]; then
      ViashError "Transcript: --------------------------------"
      cat "$tmpdir/docker_build.log"
      ViashError "End of transcript --------------------------"
    fi
    exit 1
  fi
}

######## End of helper functions for setting up Docker images for viash ########

# ViashDockerFile: print the dockerfile to stdout
# $1    : engine identifier
# return : dockerfile required to run this component
# examples:
#   ViashDockerFile
function ViashDockerfile {
  local engine_id="$1"

  if [[ "$engine_id" == "docker" ]]; then
    cat << 'VIASHDOCKER'
FROM python:3.11
ENTRYPOINT []
RUN pip install --upgrade pip && \
  pip install --upgrade --no-cache-dir "anndata~=0.12.7" "awkward" "mudata~=0.3.2" "scanpy~=1.11.4" "cellxgene-census" && \
  python -c 'exec("try:\n  import zarr; from importlib.metadata import version\nexcept ModuleNotFoundError:\n  exit(0)\nelse:  assert int(version(\"zarr\").partition(\".\")[0]) > 2")'

LABEL org.opencontainers.image.authors="Matthias Beyens, Dries De Maeyer, Robrecht Cannoodt, Kai Waldrant"
LABEL org.opencontainers.image.description="Companion container for running component query cellxgene_census"
LABEL org.opencontainers.image.created="2026-03-17T13:31:48Z"
LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline"
LABEL org.opencontainers.image.revision="fb7dc76676aa63d06ae1421bbdd6312ad4f67312"
LABEL org.opencontainers.image.version="v4.0.4"

VIASHDOCKER
  fi
}

# ViashDockerBuildArgs: return the arguments to pass to docker build
# $1    : engine identifier
# return : arguments to pass to docker build
function ViashDockerBuildArgs {
  local engine_id="$1"

  if [[ "$engine_id" == "docker" ]]; then
    echo ""
  fi
}

# ViashAbsolutePath: generate absolute path from relative path
# borrowed from https://stackoverflow.com/a/21951256
# $1     : relative filename
# return : absolute path
# examples:
#   ViashAbsolutePath some_file.txt   # returns /path/to/some_file.txt
#   ViashAbsolutePath /foo/bar/..     # returns /foo
function ViashAbsolutePath {
  local thePath
  local parr
  local outp
  local len
  if [[ ! "$1" =~ ^/ ]]; then
    thePath="$PWD/$1"
  else
    thePath="$1"
  fi
  echo "$thePath" | (
    IFS=/
    read -a parr
    declare -a outp
    for i in "${parr[@]}"; do
      case "$i" in
      ''|.) continue ;;
      ..)
        len=${#outp[@]}
        if ((len==0)); then
          continue
        else
          unset outp[$((len-1))]
        fi
        ;;
      *)
        len=${#outp[@]}
        outp[$len]="$i"
      ;;
      esac
    done
    echo /"${outp[*]}"
  )
}
# ViashDockerAutodetectMount: auto configuring docker mounts from parameters
# $1                             : The parameter value
# returns                        : New parameter
# $VIASH_DIRECTORY_MOUNTS        : Added another parameter to be passed to docker
# $VIASH_DOCKER_AUTOMOUNT_PREFIX : The prefix to be used for the automounts
# examples:
#   ViashDockerAutodetectMount /path/to/bar      # returns '/viash_automount/path/to/bar'
#   ViashDockerAutodetectMountArg /path/to/bar   # returns '--volume="/path/to:/viash_automount/path/to"'
function ViashDockerAutodetectMount {
  local abs_path=$(ViashAbsolutePath "$1")
  local mount_source
  local base_name
  if [ -d "$abs_path" ]; then
    mount_source="$abs_path"
    base_name=""
  else
    mount_source=`dirname "$abs_path"`
    base_name=`basename "$abs_path"`
  fi
  local mount_target="$VIASH_DOCKER_AUTOMOUNT_PREFIX$mount_source"
  if [ -z "$base_name" ]; then
    echo "$mount_target"
  else
    echo "$mount_target/$base_name"
  fi
}
function ViashDockerAutodetectMountArg {
  local abs_path=$(ViashAbsolutePath "$1")
  local mount_source
  local base_name
  if [ -d "$abs_path" ]; then
    mount_source="$abs_path"
    base_name=""
  else
    mount_source=`dirname "$abs_path"`
    base_name=`basename "$abs_path"`
  fi
  local mount_target="$VIASH_DOCKER_AUTOMOUNT_PREFIX$mount_source"
  ViashDebug "ViashDockerAutodetectMountArg $1 -> $mount_source -> $mount_target"
  echo "--volume=\"$mount_source:$mount_target\""
}
function ViashDockerStripAutomount {
  local abs_path=$(ViashAbsolutePath "$1")
  echo "${abs_path#$VIASH_DOCKER_AUTOMOUNT_PREFIX}"
}
# initialise variables
VIASH_DIRECTORY_MOUNTS=()

# configure default docker automount prefix if it is unset
if [ -z "${VIASH_DOCKER_AUTOMOUNT_PREFIX+x}" ]; then
  VIASH_DOCKER_AUTOMOUNT_PREFIX="/viash_automount"
fi

# initialise docker variables
VIASH_DOCKER_RUN_ARGS=(-i --rm)


# ViashHelp: Display helpful explanation about this executable
function ViashHelp {
  echo "cellxgene_census v4.0.4"
  echo ""
  echo "Query cells from a CellxGene Census or custom TileDBSoma object."
  echo "Aside from fetching the cells' RNA counts (\`.X\`), cell metadata"
  echo "(\`.obs\`) and gene metadata (\`.var\`), this component also fetches"
  echo "the dataset metadata and joins it into the cell metadata."
  echo ""
  echo "Input database:"
  echo "    Open CellxGene Census by version or URI."
  echo ""
  echo "    --input_uri"
  echo "        type: string"
  echo "        example: s3://bucket/path"
  echo "        If specified, a URI containing the Census SOMA objects. If specified,"
  echo "        will take precedence over the \`--census_version\` argument."
  echo ""
  echo "    --census_version"
  echo "        type: string"
  echo "        example: stable"
  echo "        Which release of CellxGene census to use. Possible values are \"latest\","
  echo "        \"stable\", or the date of one of the releases (e.g. \"2023-07-25\"). For"
  echo "        more information, check the documentation on [Census data"
  echo "       "
  echo "releases](https://chanzuckerberg.github.io/cellxgene-census/cellxgene_census_docsite_data_release_info.html)."
  echo ""
  echo "    --add_dataset_metadata"
  echo "        type: boolean_true"
  echo "        If true, the experiment metadata will be added to the cell metadata."
  echo "        More specifically: \`collection_id\`, \`collection_name\`, \`collection_doi\`,"
  echo "        \`dataset_title\`."
  echo ""
  echo "Cell query:"
  echo "    Arguments related to the query."
  echo ""
  echo "    --species"
  echo "        type: string, required parameter"
  echo "        example: homo_sapiens"
  echo "        The organism to query, usually one of \`Homo sapiens\` or \`Mus musculus\`."
  echo ""
  echo "    --obs_value_filter"
  echo "        type: string, required parameter"
  echo "        example: is_primary_data == True and cell_type_ontology_term_id in"
  echo "['CL:0000136', 'CL:1000311', 'CL:0002616'] and suspension_type == 'cell'"
  echo "        Filter for selecting the \`obs\` metadata (i.e. cells). Value is a filter"
  echo "        query written in the SOMA \`value_filter\` syntax."
  echo ""
  echo "Filter cells by grouping:"
  echo "    Filter groups with fewer than X number of cells."
  echo ""
  echo "    --cell_filter_grouping"
  echo "        type: string, multiple values allowed"
  echo "        example: dataset_id;tissue;assay;disease;cell_type"
  echo "        A subset of 'obs' columns by which to group the cells for filtering."
  echo "        Only groups surpassing or equal to the \`--cell_filter_minimum_count\`"
  echo "        threshold will be retained. Take care not to introduce a selection"
  echo "        bias against cells with more fine-grained ontology annotations."
  echo ""
  echo "    --cell_filter_minimum_count"
  echo "        type: integer"
  echo "        example: 100"
  echo "        A minimum number of cells per group to retain. If"
  echo "        \`--cell_filter_grouping\`"
  echo "        is defined, this parameter should also be provided and vice versa."
  echo ""
  echo "Count filtering:"
  echo "    Arguments related to filtering cells and genes by counts."
  echo ""
  echo "    --cell_filter_min_genes"
  echo "        type: integer"
  echo "        default: 50"
  echo "        Remove cells with less than this number of genes."
  echo ""
  echo "    --cell_filter_min_counts"
  echo "        type: integer"
  echo "        default: 0"
  echo "        Remove cells with less than this number of counts."
  echo ""
  echo "    --gene_filter_min_cells"
  echo "        type: integer"
  echo "        default: 5"
  echo "        Remove genes expressed in less than this number of cells."
  echo ""
  echo "    --gene_filter_min_counts"
  echo "        type: integer"
  echo "        default: 0"
  echo "        Remove genes with less than this number of counts."
  echo ""
  echo "Outputs:"
  echo "    Output arguments."
  echo ""
  echo "    --output"
  echo "        type: file, required parameter, output, file must exist"
  echo "        example: output.h5mu"
  echo "        Output h5mu file."
  echo ""
  echo "    --output_modality"
  echo "        type: string"
  echo "        default: rna"
  echo "        Which modality to store the output in."
  echo ""
  echo "    --output_layer_counts"
  echo "        type: string"
  echo "        Which layer to store the raw counts in. If not provided, the .X layer"
  echo "        will be used."
  echo ""
  echo "    --output_compression"
  echo "        type: string"
  echo "        example: gzip"
  echo "        choices: [ gzip, lzf ]"
  echo "        Compression format to use for the output AnnData and/or Mudata objects."
  echo "        By default no compression is applied."
  echo ""
  echo "Viash built in Computational Requirements:"
  echo "    ---cpus=INT"
  echo "        Number of CPUs to use"
  echo "    ---memory=STRING"
  echo "        Amount of memory to use. Examples: 4GB, 3MiB."
  echo ""
  echo "Viash built in Docker:"
  echo "    ---setup=STRATEGY"
  echo "        Setup the docker container. Options are: alwaysbuild, alwayscachedbuild, ifneedbebuild, ifneedbecachedbuild, alwayspull, alwayspullelsebuild, alwayspullelsecachedbuild, ifneedbepull, ifneedbepullelsebuild, ifneedbepullelsecachedbuild, push, pushifnotpresent, donothing."
  echo "        Default: ifneedbepullelsecachedbuild"
  echo "    ---dockerfile"
  echo "        Print the dockerfile to stdout."
  echo "    ---docker_run_args=ARG"
  echo "        Provide runtime arguments to Docker. See the documentation on \`docker run\` for more information."
  echo "    ---docker_image_id"
  echo "        Print the docker image id to stdout."
  echo "    ---debug"
  echo "        Enter the docker container for debugging purposes."
  echo ""
  echo "Viash built in Engines:"
  echo "    ---engine=ENGINE_ID"
  echo "        Specify the engine to use. Options are: docker, native."
  echo "        Default: docker"
}

# initialise array
VIASH_POSITIONAL_ARGS=''

while [[ $# -gt 0 ]]; do
    case "$1" in
        -h|--help)
            ViashHelp
            exit
            ;;
        ---v|---verbose)
            let "VIASH_VERBOSITY=VIASH_VERBOSITY+1"
            shift 1
            ;;
        ---verbosity)
            VIASH_VERBOSITY="$2"
            shift 2
            ;;
        ---verbosity=*)
            VIASH_VERBOSITY="$(ViashRemoveFlags "$1")"
            shift 1
            ;;
        --version)
            echo "cellxgene_census v4.0.4"
            exit
            ;;
        --input_uri)
            [ -n "$VIASH_PAR_INPUT_URI" ] && ViashError Bad arguments for option \'--input_uri\': \'$VIASH_PAR_INPUT_URI\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_INPUT_URI="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --input_uri. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --input_uri=*)
            [ -n "$VIASH_PAR_INPUT_URI" ] && ViashError Bad arguments for option \'--input_uri=*\': \'$VIASH_PAR_INPUT_URI\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_INPUT_URI=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --census_version)
            [ -n "$VIASH_PAR_CENSUS_VERSION" ] && ViashError Bad arguments for option \'--census_version\': \'$VIASH_PAR_CENSUS_VERSION\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CENSUS_VERSION="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --census_version. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --census_version=*)
            [ -n "$VIASH_PAR_CENSUS_VERSION" ] && ViashError Bad arguments for option \'--census_version=*\': \'$VIASH_PAR_CENSUS_VERSION\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CENSUS_VERSION=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --add_dataset_metadata)
            [ -n "$VIASH_PAR_ADD_DATASET_METADATA" ] && ViashError Bad arguments for option \'--add_dataset_metadata\': \'$VIASH_PAR_ADD_DATASET_METADATA\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_ADD_DATASET_METADATA=true
            shift 1
            ;;
        --species)
            [ -n "$VIASH_PAR_SPECIES" ] && ViashError Bad arguments for option \'--species\': \'$VIASH_PAR_SPECIES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_SPECIES="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --species. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --species=*)
            [ -n "$VIASH_PAR_SPECIES" ] && ViashError Bad arguments for option \'--species=*\': \'$VIASH_PAR_SPECIES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_SPECIES=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --obs_value_filter)
            [ -n "$VIASH_PAR_OBS_VALUE_FILTER" ] && ViashError Bad arguments for option \'--obs_value_filter\': \'$VIASH_PAR_OBS_VALUE_FILTER\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OBS_VALUE_FILTER="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_value_filter. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --obs_value_filter=*)
            [ -n "$VIASH_PAR_OBS_VALUE_FILTER" ] && ViashError Bad arguments for option \'--obs_value_filter=*\': \'$VIASH_PAR_OBS_VALUE_FILTER\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OBS_VALUE_FILTER=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --cell_filter_grouping)
            if [ -z "$VIASH_PAR_CELL_FILTER_GROUPING" ]; then
              VIASH_PAR_CELL_FILTER_GROUPING="$2"
            else
              VIASH_PAR_CELL_FILTER_GROUPING="$VIASH_PAR_CELL_FILTER_GROUPING;""$2"
            fi
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --cell_filter_grouping. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --cell_filter_grouping=*)
            if [ -z "$VIASH_PAR_CELL_FILTER_GROUPING" ]; then
              VIASH_PAR_CELL_FILTER_GROUPING=$(ViashRemoveFlags "$1")
            else
              VIASH_PAR_CELL_FILTER_GROUPING="$VIASH_PAR_CELL_FILTER_GROUPING;"$(ViashRemoveFlags "$1")
            fi
            shift 1
            ;;
        --cell_filter_minimum_count)
            [ -n "$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT" ] && ViashError Bad arguments for option \'--cell_filter_minimum_count\': \'$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MINIMUM_COUNT="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --cell_filter_minimum_count. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --cell_filter_minimum_count=*)
            [ -n "$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT" ] && ViashError Bad arguments for option \'--cell_filter_minimum_count=*\': \'$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MINIMUM_COUNT=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --cell_filter_min_genes)
            [ -n "$VIASH_PAR_CELL_FILTER_MIN_GENES" ] && ViashError Bad arguments for option \'--cell_filter_min_genes\': \'$VIASH_PAR_CELL_FILTER_MIN_GENES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MIN_GENES="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --cell_filter_min_genes. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --cell_filter_min_genes=*)
            [ -n "$VIASH_PAR_CELL_FILTER_MIN_GENES" ] && ViashError Bad arguments for option \'--cell_filter_min_genes=*\': \'$VIASH_PAR_CELL_FILTER_MIN_GENES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MIN_GENES=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --cell_filter_min_counts)
            [ -n "$VIASH_PAR_CELL_FILTER_MIN_COUNTS" ] && ViashError Bad arguments for option \'--cell_filter_min_counts\': \'$VIASH_PAR_CELL_FILTER_MIN_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MIN_COUNTS="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --cell_filter_min_counts. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --cell_filter_min_counts=*)
            [ -n "$VIASH_PAR_CELL_FILTER_MIN_COUNTS" ] && ViashError Bad arguments for option \'--cell_filter_min_counts=*\': \'$VIASH_PAR_CELL_FILTER_MIN_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_CELL_FILTER_MIN_COUNTS=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --gene_filter_min_cells)
            [ -n "$VIASH_PAR_GENE_FILTER_MIN_CELLS" ] && ViashError Bad arguments for option \'--gene_filter_min_cells\': \'$VIASH_PAR_GENE_FILTER_MIN_CELLS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_GENE_FILTER_MIN_CELLS="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --gene_filter_min_cells. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --gene_filter_min_cells=*)
            [ -n "$VIASH_PAR_GENE_FILTER_MIN_CELLS" ] && ViashError Bad arguments for option \'--gene_filter_min_cells=*\': \'$VIASH_PAR_GENE_FILTER_MIN_CELLS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_GENE_FILTER_MIN_CELLS=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --gene_filter_min_counts)
            [ -n "$VIASH_PAR_GENE_FILTER_MIN_COUNTS" ] && ViashError Bad arguments for option \'--gene_filter_min_counts\': \'$VIASH_PAR_GENE_FILTER_MIN_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_GENE_FILTER_MIN_COUNTS="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --gene_filter_min_counts. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --gene_filter_min_counts=*)
            [ -n "$VIASH_PAR_GENE_FILTER_MIN_COUNTS" ] && ViashError Bad arguments for option \'--gene_filter_min_counts=*\': \'$VIASH_PAR_GENE_FILTER_MIN_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_GENE_FILTER_MIN_COUNTS=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --output)
            [ -n "$VIASH_PAR_OUTPUT" ] && ViashError Bad arguments for option \'--output\': \'$VIASH_PAR_OUTPUT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --output. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --output=*)
            [ -n "$VIASH_PAR_OUTPUT" ] && ViashError Bad arguments for option \'--output=*\': \'$VIASH_PAR_OUTPUT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --output_modality)
            [ -n "$VIASH_PAR_OUTPUT_MODALITY" ] && ViashError Bad arguments for option \'--output_modality\': \'$VIASH_PAR_OUTPUT_MODALITY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_MODALITY="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --output_modality. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --output_modality=*)
            [ -n "$VIASH_PAR_OUTPUT_MODALITY" ] && ViashError Bad arguments for option \'--output_modality=*\': \'$VIASH_PAR_OUTPUT_MODALITY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_MODALITY=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --output_layer_counts)
            [ -n "$VIASH_PAR_OUTPUT_LAYER_COUNTS" ] && ViashError Bad arguments for option \'--output_layer_counts\': \'$VIASH_PAR_OUTPUT_LAYER_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_LAYER_COUNTS="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --output_layer_counts. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --output_layer_counts=*)
            [ -n "$VIASH_PAR_OUTPUT_LAYER_COUNTS" ] && ViashError Bad arguments for option \'--output_layer_counts=*\': \'$VIASH_PAR_OUTPUT_LAYER_COUNTS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_LAYER_COUNTS=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        --output_compression)
            [ -n "$VIASH_PAR_OUTPUT_COMPRESSION" ] && ViashError Bad arguments for option \'--output_compression\': \'$VIASH_PAR_OUTPUT_COMPRESSION\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_COMPRESSION="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to --output_compression. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        --output_compression=*)
            [ -n "$VIASH_PAR_OUTPUT_COMPRESSION" ] && ViashError Bad arguments for option \'--output_compression=*\': \'$VIASH_PAR_OUTPUT_COMPRESSION\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_PAR_OUTPUT_COMPRESSION=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        ---engine)
            VIASH_ENGINE_ID="$2"
            shift 2
            ;;
        ---engine=*)
            VIASH_ENGINE_ID="$(ViashRemoveFlags "$1")"
            shift 1
            ;;
        ---setup)
            VIASH_MODE='setup'
            VIASH_SETUP_STRATEGY="$2"
            shift 2
            ;;
        ---setup=*)
            VIASH_MODE='setup'
            VIASH_SETUP_STRATEGY="$(ViashRemoveFlags "$1")"
            shift 1
            ;;
        ---dockerfile)
            VIASH_MODE='dockerfile'
            shift 1
            ;;
        ---docker_run_args)
            VIASH_DOCKER_RUN_ARGS+=("$2")
            shift 2
            ;;
        ---docker_run_args=*)
            VIASH_DOCKER_RUN_ARGS+=("$(ViashRemoveFlags "$1")")
            shift 1
            ;;
        ---docker_image_id)
            VIASH_MODE='docker_image_id'
            shift 1
            ;;
        ---debug)
            VIASH_MODE='debug'
            shift 1
            ;;
        ---cpus)
            [ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_META_CPUS="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to ---cpus. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        ---cpus=*)
            [ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus=*\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_META_CPUS=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        ---memory)
            [ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_META_MEMORY="$2"
            [ $# -lt 2 ] && ViashError Not enough arguments passed to ---memory. Use "--help" to get more information on the parameters. && exit 1
            shift 2
            ;;
        ---memory=*)
            [ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory=*\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
            VIASH_META_MEMORY=$(ViashRemoveFlags "$1")
            shift 1
            ;;
        *)  # positional arg or unknown option
            # since the positional args will be eval'd, can we always quote, instead of using ViashQuote
            VIASH_POSITIONAL_ARGS="$VIASH_POSITIONAL_ARGS '$1'"
            [[ $1 == -* ]] && ViashWarning $1 looks like a parameter but is not a defined parameter and will instead be treated as a positional argument. Use "--help" to get more information on the parameters.
            shift # past argument
            ;;
    esac
done

# parse positional parameters
eval set -- $VIASH_POSITIONAL_ARGS


if   [ "$VIASH_ENGINE_ID" == "native" ]  ; then
  VIASH_ENGINE_TYPE='native'
elif   [ "$VIASH_ENGINE_ID" == "docker" ]  ; then
  VIASH_ENGINE_TYPE='docker'
else
  ViashError "Engine '$VIASH_ENGINE_ID' is not recognized. Options are: docker, native."
  exit 1
fi

if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  # check if docker is installed properly
  ViashDockerInstallationCheck

  # determine docker image id
  if [[ "$VIASH_ENGINE_ID" == 'docker' ]]; then
    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline/query/cellxgene_census:v4.0.4'
  fi

  # print dockerfile
  if [ "$VIASH_MODE" == "dockerfile" ]; then
    ViashDockerfile "$VIASH_ENGINE_ID"
    exit 0

  elif [ "$VIASH_MODE" == "docker_image_id" ]; then
    echo "$VIASH_DOCKER_IMAGE_ID"
    exit 0
  
  # enter docker container
  elif [[ "$VIASH_MODE" == "debug" ]]; then
    VIASH_CMD="docker run --entrypoint=bash ${VIASH_DOCKER_RUN_ARGS[@]} -v '$(pwd)':/pwd --workdir /pwd -t $VIASH_DOCKER_IMAGE_ID"
    ViashNotice "+ $VIASH_CMD"
    eval $VIASH_CMD
    exit 

  # build docker image
  elif [ "$VIASH_MODE" == "setup" ]; then
    ViashDockerSetup "$VIASH_DOCKER_IMAGE_ID" "$VIASH_SETUP_STRATEGY"
    ViashDockerCheckCommands "$VIASH_DOCKER_IMAGE_ID" 'bash'
    exit 0
  fi

  # check if docker image exists
  ViashDockerSetup "$VIASH_DOCKER_IMAGE_ID" ifneedbepullelsecachedbuild
  ViashDockerCheckCommands "$VIASH_DOCKER_IMAGE_ID" 'bash'
fi

# setting computational defaults

# helper function for parsing memory strings
function ViashMemoryAsBytes {
  local memory=`echo "$1" | tr '[:upper:]' '[:lower:]' | tr -d '[:space:]'`
  local memory_regex='^([0-9]+)([kmgtp]i?b?|b)$'
  if [[ $memory =~ $memory_regex ]]; then
    local number=${memory/[^0-9]*/}
    local symbol=${memory/*[0-9]/}
    
    case $symbol in
      b)      memory_b=$number ;;
      kb|k)   memory_b=$(( $number * 1000 )) ;;
      mb|m)   memory_b=$(( $number * 1000 * 1000 )) ;;
      gb|g)   memory_b=$(( $number * 1000 * 1000 * 1000 )) ;;
      tb|t)   memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 )) ;;
      pb|p)   memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 * 1000 )) ;;
      kib|ki)   memory_b=$(( $number * 1024 )) ;;
      mib|mi)   memory_b=$(( $number * 1024 * 1024 )) ;;
      gib|gi)   memory_b=$(( $number * 1024 * 1024 * 1024 )) ;;
      tib|ti)   memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 )) ;;
      pib|pi)   memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 * 1024 )) ;;
    esac
    echo "$memory_b"
  fi
}
# compute memory in different units
if [ ! -z ${VIASH_META_MEMORY+x} ]; then
  VIASH_META_MEMORY_B=`ViashMemoryAsBytes $VIASH_META_MEMORY`
  # do not define other variables if memory_b is an empty string
  if [ ! -z "$VIASH_META_MEMORY_B" ]; then
    VIASH_META_MEMORY_KB=$(( ($VIASH_META_MEMORY_B+999) / 1000 ))
    VIASH_META_MEMORY_MB=$(( ($VIASH_META_MEMORY_KB+999) / 1000 ))
    VIASH_META_MEMORY_GB=$(( ($VIASH_META_MEMORY_MB+999) / 1000 ))
    VIASH_META_MEMORY_TB=$(( ($VIASH_META_MEMORY_GB+999) / 1000 ))
    VIASH_META_MEMORY_PB=$(( ($VIASH_META_MEMORY_TB+999) / 1000 ))
    VIASH_META_MEMORY_KIB=$(( ($VIASH_META_MEMORY_B+1023) / 1024 ))
    VIASH_META_MEMORY_MIB=$(( ($VIASH_META_MEMORY_KIB+1023) / 1024 ))
    VIASH_META_MEMORY_GIB=$(( ($VIASH_META_MEMORY_MIB+1023) / 1024 ))
    VIASH_META_MEMORY_TIB=$(( ($VIASH_META_MEMORY_GIB+1023) / 1024 ))
    VIASH_META_MEMORY_PIB=$(( ($VIASH_META_MEMORY_TIB+1023) / 1024 ))
  else
    # unset memory if string is empty
    unset $VIASH_META_MEMORY_B
  fi
fi
# unset nproc if string is empty
if [ -z "$VIASH_META_CPUS" ]; then
  unset $VIASH_META_CPUS
fi


# check whether required parameters exist
if [ -z ${VIASH_PAR_SPECIES+x} ]; then
  ViashError '--species' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_PAR_OBS_VALUE_FILTER+x} ]; then
  ViashError '--obs_value_filter' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_PAR_OUTPUT+x} ]; then
  ViashError '--output' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_NAME+x} ]; then
  ViashError 'name' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then
  ViashError 'functionality_name' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_RESOURCES_DIR+x} ]; then
  ViashError 'resources_dir' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_EXECUTABLE+x} ]; then
  ViashError 'executable' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_CONFIG+x} ]; then
  ViashError 'config' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi
if [ -z ${VIASH_META_TEMP_DIR+x} ]; then
  ViashError 'temp_dir' is a required argument. Use "--help" to get more information on the parameters.
  exit 1
fi

# filling in defaults
if [ -z ${VIASH_PAR_ADD_DATASET_METADATA+x} ]; then
  VIASH_PAR_ADD_DATASET_METADATA="false"
fi
if [ -z ${VIASH_PAR_CELL_FILTER_MIN_GENES+x} ]; then
  VIASH_PAR_CELL_FILTER_MIN_GENES="50"
fi
if [ -z ${VIASH_PAR_CELL_FILTER_MIN_COUNTS+x} ]; then
  VIASH_PAR_CELL_FILTER_MIN_COUNTS="0"
fi
if [ -z ${VIASH_PAR_GENE_FILTER_MIN_CELLS+x} ]; then
  VIASH_PAR_GENE_FILTER_MIN_CELLS="5"
fi
if [ -z ${VIASH_PAR_GENE_FILTER_MIN_COUNTS+x} ]; then
  VIASH_PAR_GENE_FILTER_MIN_COUNTS="0"
fi
if [ -z ${VIASH_PAR_OUTPUT_MODALITY+x} ]; then
  VIASH_PAR_OUTPUT_MODALITY="rna"
fi

# check whether parameters values are of the right type
if [[ -n "$VIASH_PAR_ADD_DATASET_METADATA" ]]; then
  if ! [[ "$VIASH_PAR_ADD_DATASET_METADATA" =~ ^(true|True|TRUE|false|False|FALSE|yes|Yes|YES|no|No|NO)$ ]]; then
    ViashError '--add_dataset_metadata' has to be a boolean_true. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT" ]]; then
  if ! [[ "$VIASH_PAR_CELL_FILTER_MINIMUM_COUNT" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError '--cell_filter_minimum_count' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_PAR_CELL_FILTER_MIN_GENES" ]]; then
  if ! [[ "$VIASH_PAR_CELL_FILTER_MIN_GENES" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError '--cell_filter_min_genes' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_PAR_CELL_FILTER_MIN_COUNTS" ]]; then
  if ! [[ "$VIASH_PAR_CELL_FILTER_MIN_COUNTS" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError '--cell_filter_min_counts' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_PAR_GENE_FILTER_MIN_CELLS" ]]; then
  if ! [[ "$VIASH_PAR_GENE_FILTER_MIN_CELLS" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError '--gene_filter_min_cells' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_PAR_GENE_FILTER_MIN_COUNTS" ]]; then
  if ! [[ "$VIASH_PAR_GENE_FILTER_MIN_COUNTS" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError '--gene_filter_min_counts' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_CPUS" ]]; then
  if ! [[ "$VIASH_META_CPUS" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'cpus' has to be an integer. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_B" ]]; then
  if ! [[ "$VIASH_META_MEMORY_B" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_b' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_KB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_KB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_kb' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_MB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_MB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_mb' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_GB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_GB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_gb' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_TB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_TB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_tb' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_PB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_PB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_pb' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_KIB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_KIB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_kib' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_MIB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_MIB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_mib' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_GIB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_GIB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_gib' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_TIB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_TIB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_tib' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi
if [[ -n "$VIASH_META_MEMORY_PIB" ]]; then
  if ! [[ "$VIASH_META_MEMORY_PIB" =~ ^[-+]?[0-9]+$ ]]; then
    ViashError 'memory_pib' has to be a long. Use "--help" to get more information on the parameters.
    exit 1
  fi
fi

# check whether value is belongs to a set of choices
if [ ! -z "$VIASH_PAR_OUTPUT_COMPRESSION" ]; then
  VIASH_PAR_OUTPUT_COMPRESSION_CHOICES=("gzip;lzf")
  IFS=';'
  set -f
  if ! [[ ";${VIASH_PAR_OUTPUT_COMPRESSION_CHOICES[*]};" =~ ";$VIASH_PAR_OUTPUT_COMPRESSION;" ]]; then
    ViashError '--output_compression' specified value of \'$VIASH_PAR_OUTPUT_COMPRESSION\' is not in the list of allowed values. Use "--help" to get more information on the parameters.
    exit 1
  fi
  set +f
  unset IFS
fi

# create parent directories of output files, if so desired
if [ ! -z "$VIASH_PAR_OUTPUT" ] && [ ! -d "$(dirname "$VIASH_PAR_OUTPUT")" ]; then
  mkdir -p "$(dirname "$VIASH_PAR_OUTPUT")"
fi

if  [ "$VIASH_ENGINE_ID" == "native" ]  ; then
  if [ "$VIASH_MODE" == "run" ]; then
    VIASH_CMD="bash"
  else
    ViashError "Engine '$VIASH_ENGINE_ID' does not support mode '$VIASH_MODE'."
    exit 1
  fi
fi

if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  # detect volumes from file arguments
  VIASH_CHOWN_VARS=()
if [ ! -z "$VIASH_PAR_OUTPUT" ]; then
  VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_PAR_OUTPUT")" )
  VIASH_PAR_OUTPUT=$(ViashDockerAutodetectMount "$VIASH_PAR_OUTPUT")
  VIASH_CHOWN_VARS+=( "$VIASH_PAR_OUTPUT" )
fi
if [ ! -z "$VIASH_META_RESOURCES_DIR" ]; then
  VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_RESOURCES_DIR")" )
  VIASH_META_RESOURCES_DIR=$(ViashDockerAutodetectMount "$VIASH_META_RESOURCES_DIR")
fi
if [ ! -z "$VIASH_META_EXECUTABLE" ]; then
  VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_EXECUTABLE")" )
  VIASH_META_EXECUTABLE=$(ViashDockerAutodetectMount "$VIASH_META_EXECUTABLE")
fi
if [ ! -z "$VIASH_META_CONFIG" ]; then
  VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_CONFIG")" )
  VIASH_META_CONFIG=$(ViashDockerAutodetectMount "$VIASH_META_CONFIG")
fi
if [ ! -z "$VIASH_META_TEMP_DIR" ]; then
  VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_TEMP_DIR")" )
  VIASH_META_TEMP_DIR=$(ViashDockerAutodetectMount "$VIASH_META_TEMP_DIR")
fi
  
  # get unique mounts
  VIASH_UNIQUE_MOUNTS=($(for val in "${VIASH_DIRECTORY_MOUNTS[@]}"; do echo "$val"; done | sort -u))
fi

if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  # change file ownership
  function ViashPerformChown {
    if (( ${#VIASH_CHOWN_VARS[@]} )); then
      set +e
      VIASH_CMD="docker run --entrypoint=bash --rm ${VIASH_UNIQUE_MOUNTS[@]} $VIASH_DOCKER_IMAGE_ID -c 'chown $(id -u):$(id -g) --silent --recursive ${VIASH_CHOWN_VARS[@]}'"
      ViashDebug "+ $VIASH_CMD"
      eval $VIASH_CMD
      set -e
    fi
  }
  trap ViashPerformChown EXIT
fi

if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  # helper function for filling in extra docker args
  if [ ! -z "$VIASH_META_MEMORY_B" ]; then
    VIASH_DOCKER_RUN_ARGS+=("--memory=${VIASH_META_MEMORY_B}")
  fi
  if [ ! -z "$VIASH_META_CPUS" ]; then
    VIASH_DOCKER_RUN_ARGS+=("--cpus=${VIASH_META_CPUS}")
  fi
fi

if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  VIASH_CMD="docker run --entrypoint=bash ${VIASH_DOCKER_RUN_ARGS[@]} ${VIASH_UNIQUE_MOUNTS[@]} $VIASH_DOCKER_IMAGE_ID"
fi


# set dependency paths


ViashDebug "Running command: $(echo $VIASH_CMD)"
cat << VIASHEOF | eval $VIASH_CMD
set -e
tempscript=\$(mktemp "$VIASH_META_TEMP_DIR/viash-run-cellxgene_census-XXXXXX").py
function clean_up {
  rm "\$tempscript"
}
function interrupt {
  echo -e "\nCTRL-C Pressed..."
  exit 1
}
trap clean_up EXIT
trap interrupt INT SIGINT
cat > "\$tempscript" << 'VIASHMAIN'
import sys
import cellxgene_census
import scanpy as sc
import mudata as mu

## VIASH START
# The following code has been auto-generated by Viash.
par = {
  'input_uri': $( if [ ! -z ${VIASH_PAR_INPUT_URI+x} ]; then echo "r'${VIASH_PAR_INPUT_URI//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'census_version': $( if [ ! -z ${VIASH_PAR_CENSUS_VERSION+x} ]; then echo "r'${VIASH_PAR_CENSUS_VERSION//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'add_dataset_metadata': $( if [ ! -z ${VIASH_PAR_ADD_DATASET_METADATA+x} ]; then echo "r'${VIASH_PAR_ADD_DATASET_METADATA//\'/\'\"\'\"r\'}'.lower() == 'true'"; else echo None; fi ),
  'species': $( if [ ! -z ${VIASH_PAR_SPECIES+x} ]; then echo "r'${VIASH_PAR_SPECIES//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'obs_value_filter': $( if [ ! -z ${VIASH_PAR_OBS_VALUE_FILTER+x} ]; then echo "r'${VIASH_PAR_OBS_VALUE_FILTER//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'cell_filter_grouping': $( if [ ! -z ${VIASH_PAR_CELL_FILTER_GROUPING+x} ]; then echo "r'${VIASH_PAR_CELL_FILTER_GROUPING//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi ),
  'cell_filter_minimum_count': $( if [ ! -z ${VIASH_PAR_CELL_FILTER_MINIMUM_COUNT+x} ]; then echo "int(r'${VIASH_PAR_CELL_FILTER_MINIMUM_COUNT//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'cell_filter_min_genes': $( if [ ! -z ${VIASH_PAR_CELL_FILTER_MIN_GENES+x} ]; then echo "int(r'${VIASH_PAR_CELL_FILTER_MIN_GENES//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'cell_filter_min_counts': $( if [ ! -z ${VIASH_PAR_CELL_FILTER_MIN_COUNTS+x} ]; then echo "int(r'${VIASH_PAR_CELL_FILTER_MIN_COUNTS//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'gene_filter_min_cells': $( if [ ! -z ${VIASH_PAR_GENE_FILTER_MIN_CELLS+x} ]; then echo "int(r'${VIASH_PAR_GENE_FILTER_MIN_CELLS//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'gene_filter_min_counts': $( if [ ! -z ${VIASH_PAR_GENE_FILTER_MIN_COUNTS+x} ]; then echo "int(r'${VIASH_PAR_GENE_FILTER_MIN_COUNTS//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'output': $( if [ ! -z ${VIASH_PAR_OUTPUT+x} ]; then echo "r'${VIASH_PAR_OUTPUT//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'output_modality': $( if [ ! -z ${VIASH_PAR_OUTPUT_MODALITY+x} ]; then echo "r'${VIASH_PAR_OUTPUT_MODALITY//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'output_layer_counts': $( if [ ! -z ${VIASH_PAR_OUTPUT_LAYER_COUNTS+x} ]; then echo "r'${VIASH_PAR_OUTPUT_LAYER_COUNTS//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'output_compression': $( if [ ! -z ${VIASH_PAR_OUTPUT_COMPRESSION+x} ]; then echo "r'${VIASH_PAR_OUTPUT_COMPRESSION//\'/\'\"\'\"r\'}'"; else echo None; fi )
}
meta = {
  'name': $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "r'${VIASH_META_NAME//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'functionality_name': $( if [ ! -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then echo "r'${VIASH_META_FUNCTIONALITY_NAME//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'resources_dir': $( if [ ! -z ${VIASH_META_RESOURCES_DIR+x} ]; then echo "r'${VIASH_META_RESOURCES_DIR//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'executable': $( if [ ! -z ${VIASH_META_EXECUTABLE+x} ]; then echo "r'${VIASH_META_EXECUTABLE//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'config': $( if [ ! -z ${VIASH_META_CONFIG+x} ]; then echo "r'${VIASH_META_CONFIG//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'temp_dir': $( if [ ! -z ${VIASH_META_TEMP_DIR+x} ]; then echo "r'${VIASH_META_TEMP_DIR//\'/\'\"\'\"r\'}'"; else echo None; fi ),
  'cpus': $( if [ ! -z ${VIASH_META_CPUS+x} ]; then echo "int(r'${VIASH_META_CPUS//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_b': $( if [ ! -z ${VIASH_META_MEMORY_B+x} ]; then echo "int(r'${VIASH_META_MEMORY_B//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_kb': $( if [ ! -z ${VIASH_META_MEMORY_KB+x} ]; then echo "int(r'${VIASH_META_MEMORY_KB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_mb': $( if [ ! -z ${VIASH_META_MEMORY_MB+x} ]; then echo "int(r'${VIASH_META_MEMORY_MB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_gb': $( if [ ! -z ${VIASH_META_MEMORY_GB+x} ]; then echo "int(r'${VIASH_META_MEMORY_GB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_tb': $( if [ ! -z ${VIASH_META_MEMORY_TB+x} ]; then echo "int(r'${VIASH_META_MEMORY_TB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_pb': $( if [ ! -z ${VIASH_META_MEMORY_PB+x} ]; then echo "int(r'${VIASH_META_MEMORY_PB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_kib': $( if [ ! -z ${VIASH_META_MEMORY_KIB+x} ]; then echo "int(r'${VIASH_META_MEMORY_KIB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_mib': $( if [ ! -z ${VIASH_META_MEMORY_MIB+x} ]; then echo "int(r'${VIASH_META_MEMORY_MIB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_gib': $( if [ ! -z ${VIASH_META_MEMORY_GIB+x} ]; then echo "int(r'${VIASH_META_MEMORY_GIB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_tib': $( if [ ! -z ${VIASH_META_MEMORY_TIB+x} ]; then echo "int(r'${VIASH_META_MEMORY_TIB//\'/\'\"\'\"r\'}')"; else echo None; fi ),
  'memory_pib': $( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo "int(r'${VIASH_META_MEMORY_PIB//\'/\'\"\'\"r\'}')"; else echo None; fi )
}
dep = {
  
}

## VIASH END

sys.path.append(meta["resources_dir"])


from setup_logger import setup_logger

logger = setup_logger()


def connect_census(uri, census_version):
    """
    Connect to CellxGene Census or user-provided TileDBSoma object
    """
    ver = census_version or "stable"
    logger.info(
        "Connecting to CellxGene Census at %s",
        f"'{uri}'" if uri else f"version '{ver}'",
    )
    return cellxgene_census.open_soma(uri=uri, census_version=ver)


def get_anndata(census_connection, par):
    logger.info(
        "Getting gene expression data based on \`%s\` query.", par["obs_value_filter"]
    )
    return cellxgene_census.get_anndata(
        census=census_connection,
        obs_value_filter=par["obs_value_filter"],
        organism=par["species"],
    )


def add_cellcensus_metadata_obs(census_connection, adata):
    logger.info("Adding additional metadata to gene expression data.")
    census_datasets = (
        census_connection["census_info"]["datasets"].read().concat().to_pandas()
    )

    adata.obs.dataset_id = adata.obs.dataset_id.astype("category")

    dataset_info = (
        census_datasets[
            census_datasets.dataset_id.isin(adata.obs.dataset_id.cat.categories)
        ][
            [
                "collection_id",
                "collection_name",
                "collection_doi",
                "dataset_id",
                "dataset_title",
            ]
        ]
        .reset_index(drop=True)
        .astype("category")
    )

    adata.obs = adata.obs.merge(dataset_info, on="dataset_id", how="left")


def filter_min_cells_per_group(adata, par):
    n_cells_before, _ = adata.shape
    cell_count = adata.obs.groupby(par["cell_filter_grouping"])[
        "soma_joinid"
    ].transform("count")
    adata = adata[cell_count >= par["cell_filter_minimum_count"]]
    n_cells_after, _ = adata.shape
    logger.info(
        "Removed %s cells based on %s cell_filter_minimum_count of %s cell_filter_grouping."
        % (
            (n_cells_before - n_cells_after),
            par["cell_filter_minimum_count"],
            par["cell_filter_grouping"],
        )
    )
    return adata


def filter_by_counts(adata, par):
    logger.info("Remove cells with few counts and genes with few counts.")
    n_cells_before, n_genes_before = adata.shape
    # remove cells with few counts and genes with few counts
    scanpy_proc = {
        par["cell_filter_min_counts"]: (sc.pp.filter_cells, "min_counts"),
        par["cell_filter_min_genes"]: (sc.pp.filter_cells, "min_genes"),
        par["gene_filter_min_counts"]: (sc.pp.filter_genes, "min_counts"),
        par["gene_filter_min_cells"]: (sc.pp.filter_genes, "min_cells"),
    }
    for threshold, (func, arg) in scanpy_proc.items():
        if threshold:
            func(adata, **{arg: threshold})
    n_cells_after, n_genes_after = adata.shape
    logger.info(
        "Removed %s cells and %s genes.",
        (n_cells_before - n_cells_after),
        (n_genes_before - n_genes_after),
    )


def move_x_to_layers(adata, layer_name):
    logger.info(f"Move .X to .layers['{layer_name}']")
    adata.layers[layer_name] = adata.X
    adata.X = None


def print_unique(adata, column):
    unique_values = adata.obs[column].unique().astype(str)
    formatted = "', '".join(unique_values[:50])
    if len(unique_values) > 50:
        formatted += ", ..."
    logger.info(f"Unique {column}: ['{formatted}']")


def print_summary(adata):
    logger.info(f"Resulting dataset: {adata}")

    logger.info("Summary of dataset:")
    for field in adata.obs.columns:
        print_unique(adata, field)


def write_anndata(adata, par):
    logger.info("Writing MuData object to '%s'", par["output"])

    mdata = mu.MuData({par["output_modality"]: adata})

    mdata.write_h5mu(par["output"], compression=par["output_compression"])


def main(par, meta):
    # check arguments
    if (par["cell_filter_grouping"] is None) != (
        par["cell_filter_minimum_count"] is None
    ):
        raise NotImplementedError(
            "You need to specify either both or none of the following parameters: cell_filter_grouping, cell_filter_minimum_count"
        )

    with connect_census(
        uri=par["input_uri"], census_version=par["census_version"]
    ) as conn:
        adata = get_anndata(conn, par)

        if par["add_dataset_metadata"]:
            add_cellcensus_metadata_obs(conn, adata)

    print(f"AnnData: {adata}", flush=True)

    if par["cell_filter_grouping"] is not None:
        adata = filter_min_cells_per_group(adata, par)

    # remove cells with few counts and genes with few counts
    filter_by_counts(adata, par)

    # logger.log(f"Filtered AnnData: {adata}")
    print(f"Filtered AnnData: {adata}", flush=True)

    # use feature_id as var_names
    adata.var_names = adata.var["feature_id"]

    # move .X to .layers["counts"]
    if par["output_layer_counts"]:
        move_x_to_layers(adata, par["output_layer_counts"])

    # print summary
    print_summary(adata)

    # write output to file
    write_anndata(adata, par)


if __name__ == "__main__":
    main(par, meta)
VIASHMAIN
python -B "\$tempscript" &
wait "\$!"

VIASHEOF


if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
  # strip viash automount from file paths
  
  if [ ! -z "$VIASH_PAR_OUTPUT" ]; then
    VIASH_PAR_OUTPUT=$(ViashDockerStripAutomount "$VIASH_PAR_OUTPUT")
  fi
  if [ ! -z "$VIASH_META_RESOURCES_DIR" ]; then
    VIASH_META_RESOURCES_DIR=$(ViashDockerStripAutomount "$VIASH_META_RESOURCES_DIR")
  fi
  if [ ! -z "$VIASH_META_EXECUTABLE" ]; then
    VIASH_META_EXECUTABLE=$(ViashDockerStripAutomount "$VIASH_META_EXECUTABLE")
  fi
  if [ ! -z "$VIASH_META_CONFIG" ]; then
    VIASH_META_CONFIG=$(ViashDockerStripAutomount "$VIASH_META_CONFIG")
  fi
  if [ ! -z "$VIASH_META_TEMP_DIR" ]; then
    VIASH_META_TEMP_DIR=$(ViashDockerStripAutomount "$VIASH_META_TEMP_DIR")
  fi
fi


# check whether required files exist
if [ ! -z "$VIASH_PAR_OUTPUT" ] && [ ! -e "$VIASH_PAR_OUTPUT" ]; then
  ViashError "Output file '$VIASH_PAR_OUTPUT' does not exist."
  exit 1
fi


exit 0
