shell:
    """
    abricate --threads {threads} --nopath --db {params.dbname} --minid {params.minid} --mincov {params.mincov} {input.contigs} > {output.report} 2> {log}
    abricate --version | perl -p -e 's/abricate (.+)/--analysis_software_version $1/' > {output.metadata}
    abricate --list | grep {params.dbname} | perl -p -e 's/.+?\t.+?\t.+?\t(.+)/--reference_database_version $1/' >> {output.metadata}
    """

shell:
    """
    hamronize abricate $(paste - - < {input.metadata}) {input.report} > {output}
    """

shell:
    """
    amrfinder -n {input.contigs} -o {output.report} -d {params.db}/latest >{log} 2>&1
    rm -rf {params.output_tmp_dir}
    amrfinder --version | perl -p -e 's/(.+)/--analysis_software_version $1/' > {output.metadata}
    cat {input.dbversion} | perl -p -e 's/(.+)/--reference_database_version $1/' >> {output.metadata} 
    """

shell:
    """
    mkdir -p {params.db_dir}
    wget -O {output.megares_db} http://megares.meglab.org/download/megares_v2.00/megares_full_database_v2.00.fasta
    wget -O {output.megares_annot} http://megares.meglab.org/download/megares_v2.00/megares_full_annotations_v2.00.csv
    cd {params.db_dir}
    bwa index megares_full_database_v2.00.fasta
    """

shell:
   """
   mkdir -p {params.output_prefix_tmp}
   trimmomatic PE {input.read1} {input.read2} {params.output_prefix_tmp}/{wildcards.sample}_r1_pe_trimmed.fq {params.output_prefix_tmp}/{wildcards.sample}_r1_se_trimmed.fq {params.output_prefix_tmp}/{wildcards.sample}_r2_pe_trimmed.fq {params.output_prefix_tmp}/{wildcards.sample}_r2_se_trimmed.fq SLIDINGWINDOW:4:15 LEADING:3 TRAILING:3 MINLEN:36 >{log} 2>&1 
   bwa mem {input.megares_db} {params.output_prefix_tmp}/{wildcards.sample}_r1_pe_trimmed.fq {params.output_prefix_tmp}/{wildcards.sample}_r2_pe_trimmed.fq 2>> {log} | samtools sort -n -O sam > {params.output_prefix_tmp}/{wildcards.sample}.sam 2>>{log}
   {input.resistome_tool} -ref_fp {input.megares_db} -annot_fp {input.megares_annot} -sam_fp {params.output_prefix_tmp}/{wildcards.sample}.sam -gene_fp {output.amr_gene} -group_fp {output.amr_group} -class_fp {output.amr_class} -mech_fp {output.amr_mech} -t 80  >>{log} 2>&1
   {input.rarefaction_tool} -ref_fp {input.megares_db} -annot_fp {input.megares_annot} -sam_fp {params.output_prefix_tmp}/{wildcards.sample}.sam -gene_fp {output.amr_gene}_rare -group_fp {output.amr_group}_rare -class_fp {output.amr_class}_rare -mech_fp {output.amr_mech}_rare -min 5 -max 100 -skip 5 -samples 1 -t 80 >>{log} 2>&1
   {input.snp_tool} -amr_fp {input.megares_db} -sampe {params.output_prefix_tmp}/{wildcards.sample}.sam -out_fp {output.amr_snps} >>{log} 2>&1
   #rm -rf {params.output_prefix_tmp}

   echo "--analysis_software_version {params.resistome_analyzer_version}" > {output.metadata}
   echo "--reference_database_version v2.00" >> {output.metadata}
   """

shell:
    """
    ariba getref card {params.db_dir}/ariba_card > {log}
    ariba prepareref -f {params.db_dir}/ariba_card.fa -m {params.db_dir}/ariba_card.tsv {output.db} >> {log}
    date +"{params.dateformat}" > {output.dbversion}
    """

shell:
    """
    hamronize deeparg --input_file_name {input.read1} $(paste - - < {input.metadata}) {input.report} > {output}
    """

    shell:
        """
	    rm -rf {params.db_dir}/groot_clustered
        groot get -d {params.db_source} -o {params.db_dir}/groot_clustered 
        groot index -p {threads} -m {params.db_dir}/groot_clustered/{params.db_source}.90 -i {output.db} -w {params.read_length} --log {log}
        """

shell:
   """
   zcat {input.read1} {input.read2} | seqkit seq --min-len {params.min_read_length} --max-len {params.max_read_length} | groot align -g {params.graph_dir} -p {threads} -i {input.db_index} --log {log} | groot report --log {log} > {output.report}
   groot version | perl -p -e 's/(.+)/--analysis_software_version $1/' > {output.metadata}
   """

shell:
    """
    # proper database is downloaded like this but is 20G and downloads
    # from the DTU FTP very slowly, so not going to support this feature
    # for now and just use a single type klebsiella genome for now
    #pushd {params.db_dir}
    #git clone https://bitbucket.org/genomicepidemiology/kmerfinder_db.git
    #cd kmerfinder_db
    #export KmerFinder_DB=$(pwd)
    #bash INSTALL.sh $KmerFinder_DB bacteria latest
    curl https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/240/185/GCF_000240185.1_ASM24018v2/GCF_000240185.1_ASM24018v2_genomic.fna.gz | gunzip > {params.db_dir}/klebsiella_type_genome.fasta 
    kma index -i {params.db_dir}/klebsiella_type_genome.fasta -o {params.species_db} -Sparse ATG

    curl https://bitbucket.org/genomicepidemiology/resfinder_db/get/{params.db_version}.zip --output {params.db_dir}.zip
    mkdir -p {params.db_dir}/resfinder
    unzip -j -d {params.db_dir}/resfinder {params.db_dir}.zip
    cat {params.db_dir}/resfinder/*.fsa > {params.db_dir}/resfinder.fsa
    kma index -i {params.db_dir}/resfinder.fsa -o {params.kma_resfinder_db}
    """

shell:
    """
    cd {params.binary_dir}
    git clone https://bitbucket.org/genomicepidemiology/pointfinder.git --recursive

    # tidy up shebang
    sed -i "s|env python3$|env python|" pointfinder/PointFinder.py
    chmod +x pointfinder/PointFinder.py
    """

shell:
    """
    python {input.pointfinder_script} -i {input.contigs} -p {input.pointfinder_db} -s {params.species} -m blastn -m_p $(which blastn) -o results/{wildcards.sample}/pointfinder > {log} 2>&1
    cp {params.output_dir}/*_blastn_results.tsv {output.report}
    rm -rf {params.output_tmp_dir}
    """

shell:
   """
   prodigal -p meta -i {input.contigs} -a {params.output_prefix}/protein_seqs.faa > {log} 2>&1
   hmmsearch --cpu {threads} --tblout {output.report} {input.resfams_hmms} {params.output_prefix}/protein_seqs.faa  >>{log} 2>&1
   hmmsearch -h | grep "# HMMER " | perl -p -e 's/# HMMER (.+) \(.+/--analysis_software_version hmmsearch_v$1/' >> {output.metadata}
   cat {input.dbversion} | perl -p -e 's/(.+)/--reference_database_version $1/' >> {output.metadata} 
   """

shell:
   """
   rgi card_annotation --input {input.card_db_bwt} > {log} 2>&1 
   rgi load --card_json {input.card_db_bwt} --card_annotation card_database_v*.fasta >> {log} 2>&1
   rm card_database_v*.fasta
   rgi bwt --read_one {input.read1} --read_two {input.read2} --output_file {params.output_prefix} --aligner bwa --threads {threads} >>{log} 2>&1

   echo "--analysis_software_version $(rgi main --version)" > {output.metadata}
   echo "--reference_database_version $(rgi database --version)" >> {output.metadata}
   """

shell:
   """
   sraX -i {input.genome_dir} -t 4 -db {params.dbtype} -o {params.outdir} > {log} 2>&1
   mv {params.result_output_dir}/* {params.outdir}
   sraX --version | grep version | perl -p -e 's/.+version: (.+)/--analysis_software_version $1/' > {output.metadata}
   date +"{params.dateformat}" | perl -p -e 's/(.+)/--reference_database_version $1/' >> {output.metadata}
   """

shell:
   """
   srst2 --threads {threads} --gene_db {params.gene_db} --forward {params.for_suffix} --reverse {params.rev_suffix} --input_pe {input.read1} {input.read2} --min_depth {params.min_depth} --output {params.output_prefix} > {log} 2>&1
   srst2 --version 2>&1 | perl -p -e 's/srst2 (.+)/--analysis_software_version $1/' > {output.metadata}
   cat {input.dbversion} | perl -p -e 's/(.+)/--reference_database_version $1/' >> {output.metadata} 
   """