description: A schema for validation of samplesheet.csv for taxprofiler pipeline.
imports:
  - https://schema.databio.org/pep/2.1.0.yaml
properties:
  samples:
    type: array
    items:
      type: object
      properties:
        sample:
          type: string
          description: "Sample identifier."
          pattern: "^\\S*$"
        run_accession:
          type: string
          description: "Run accession number."
        instrument_platform:
          type: string
          description: "Name of the platform that sequenced the samples."
          enum:
            [
              "ABI_SOLID",
              "BGISEQ",
              "CAPILLARY",
              "COMPLETE_GENOMICS",
              "DNBSEQ",
              "HELICOS",
              "ILLUMINA",
              "ION_TORRENT",
              "LS454",
              "OXFORD_NANOPORE",
              "PACBIO_SMRT",
            ]
        fastq1:
          type: ["string", "null"]
          description: "Optional FASTQ file for read 1 of paired-end sequenced libraries."
          pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
        fastq2:
          type: ["string", "null"]
          description: "Optional FASTQ file for read 2 of paired-end sequenced libraries."
          pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
        fasta:
          type: ["string", "null"]
          description: "Optional FASTA file."
          pattern: "^[\\S]+.(fa\\.gz|fasta\\.gz)$"
      required:
        - sample
        - run_accession
        - instrument_platform
      files:
        - fastq1
        - fastq2
        - fasta
required:
  - samples