_bedtools

#compdef bedtools annotateBed bamToBed bamToFastq bed12ToBed6 bedpeToBam bedToBam closestBed complementBed coverageBed fisher flankBed genomeCoverageBed fastaFromBed bedToIgv intersectBed mergeBed maskFastaFromBed

# all aliases should also be in the compdef line above
local -A aliases
aliases[annotateBed]="annotate"
aliases[bamToBed]="bamtobed"
aliases[bamToFastq]="bamtofastq"
aliases[bed12ToBed6]="bed12tobed6"
aliases[bedpeToBam]="bedpetobam"
aliases[bedToBam]="bedtobam"
aliases[closestBed]="closest"
aliases[complementBed]="complement"
aliases[coverageBed]="coverage"
aliases[fisher]="fisher"
aliases[flankBed]="flank"
aliases[genomeCoverageBed]="genomecov"
aliases[fastaFromBed]="getfasta"
aliases[bedToIgv]="igv"
aliases[intersectBed]="intersect"
aliases[mergeBed]="merge"
aliases[maskFastaFromBed]="maskfasta"

_bedtools-annotate() {
	local ret=1
	local -a args
	if [[ $service == bedtools ]]; then
		args+=('1:command:')
	fi
	args+=(
		'-names[A list of names (one / file) to describe each file in -i]: :'
		'(-both)-counts[Report the count of features in each file that overlap -i]'
		'(-counts)-both[Report the counts followed by the % coverage]'
		'(-S)-s[Require same strandedness]'
		'(-s)-S[Require different strandedness]'
		'(-names -counts -both -s -S)-i[intervals]:file:_files -g \*.\(bed\|gff\|vcf\)'
	)
	if (( words[(I)-i] )); then
		args+=('(-)-files[input files]:*:file:_files')
	fi
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-bamtobed() {
	integer ret=1
	local -a args
	if [[ $service == bedtools ]]; then
		args+=('1:command:')
	fi
	args+=(
		'(-split)-bed12[Write "blocked" BED format (aka "BED12")]'
		'(-tag)-bedpe[Write BEDPE format]'		
		'-cigar[Add the CIGAR string to the BED entry as a 7th column]'
		'-color[An R,G,B string for the color used with BED12 format]:color string:'
		'-ed[Use BAM edit distance (NM tag) for BED score]'
		'-i[Reads]:bam file:_files -g \*.bam'
		'-split[Report "split" BAM alignments as separate BED entries]'
		'(-split)-splitD[Split alignments based on N and D CIGAR operators]'
		'-tag[Use other NUMERIC BAM alignment tag for BED score]'
	)
	if (( words[(I)-bedpe] )); then
		args+=('-mate1[always report mate one as the first BEDPE "block"]')
	fi
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-bamtofastq() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[Reads]:bam file:_files -g \*.bam'
		'-fq[Output FASTQ]:fastq file:_files -g \*.\(fq\|fastq\)'
		'-fq2[FASTQ for second end]:fastq file:_files -g \*.\(fq\|fastq\)'
		'-tags[Create FASTQ based on the mate info]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-bed12tobed6() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[Reads]:bam file:_files'
		'-n[Force the score to be the (1-based) block number]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-bedpetobam() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-g[genome]:str:'
		'-mapq[Set the mapping quality for the BAM records]:int:'
		'-ubam[Wrinte uncompressed BAM output]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-bedtobam() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-g[genome]:str:'
		'-bed12[The BED file is in BED12 format]'
		'-mapq[Set the mapping quality for the BAM records]:int:'
		'-ubam[Wrinte uncompressed BAM output]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-closest() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-a[features to search for]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-b[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'(-D)-d[report closest feature distance as extra column]'
		'(-d)-D[report closest feature distance, with negative values for upstream]:orientation:((
			ref\:Report\ distance\ with\ respect\ to\ the\ reference\ genome
			a\:Report\ distance\ with\ respect\ to\ A
			b\:Report\ distance\ with\ respect\ to\ B
		))'
		'-io[Ignore features in B that overlap A]'
		'-iu[Ignore features in B that are upstream of features in A]'
		'-id[Ignore features in B that are downstream of features in A]'
		'-fu[Choose first from features in B that are upstream of features in A]'
		'-fd[Choose first from features in B that are downstream of features in A]'
		'-t[How ties for closest feature are handled]:strategy:((
			all\:Report\ all\ ties
			first\:Report\ the\ first\ tie\ that\ occurred\ in\ the\ B\ file
			last\:Report\ the\ last\ tie\ that\ occurred\ in\ the\ B\ file
		))'
		'-mdb[How multiple databases are resolved]:strategy:((
			each\:Report\ closest\ records\ for\ each\ database
			all\:Report\ closest\ records\ among\ all\ databases
		))'
		'-k[Report the k closest hits]:int:'
		'-N[Require that the query and the closest hit have different names]'
		'(-S)-s[Require same strandedness]'
		'(-s)-S[Require different strandedness]'
		'-f[Minimum overlap required as a fraction of A]:float:'
		'-F[Minimum overlap required as a fraction of B]:float:'
		'(-e)-r[Require that the fraction overlap be reciprocal for A AND B]'
		'(-r)-e[Require that the minimum fraction be satisfied for A OR B]'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-g[Genome file to enforce consistent chromosome sort order]:file:_files'
		'-nonamecheck[do not throw an error if the file has different naming conventions]'
		'(-names -filenames -sortout)-names[When using multiple databases, provide an alias for each that will appear instead of a fileId when also printing the DB record]'
		'(-names -filenames -sortout)-filenames[When using multiple databases, show each complete filename instead of a fileId when also printing the DB record.]'
		'(-names -filenames -sortout)-sortout[When using multiple databases, sort the output DB hits for each record]'
		'-bed[If using BAM input, write output as BED]'
		'-header[Print the header from the A file prior to results]'
		'(-iobuf)-nobuf[Disable buffered output]'
		'(-nobuf)-iobuf[Specify amount of memory to use for input buffer]:size:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-cluster() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-s[Force strandedness]'
		'-d[Maximum merging distance]:int:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-complement() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-g[genome]:file:_files'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-coverage() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-hist[report histogram]'
		'-a[features to search for]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-b[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-counts[Only report the count of overlaps]'
		'-mean[Report the mean depth of all positions in each A feature]'
		'-d[report closest feature distance as extra column]'
		'(-S)-s[Require same strandedness]'
		'(-s)-S[Require different strandedness]'
		'-f[Minimum overlap required as a fraction of A]:float:'
		'-F[Minimum overlap required as a fraction of B]:float:'
		'(-e)-r[Require that the fraction overlap be reciprocal for A AND B]'
		'(-r)-e[Require that the minimum fraction be satisfied for A OR B]'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-g[Genome file to enforce consistent chromosome sort order]:file:_files'
		'-nonamecheck[do not throw an error if the file has different naming conventions]'
		'(-names -filenames -sortout)-names[When using multiple databases, provide an alias for each that will appear instead of a fileId when also printing the DB record]'
		'(-names -filenames -sortout)-filenames[When using multiple databases, show each complete filename instead of a fileId when also printing the DB record.]'
		'(-names -filenames -sortout)-sortout[When using multiple databases, sort the output DB hits for each record]'
		'-bed[If using BAM input, write output as BED]'
		'-header[Print the header from the A file prior to results]'
		'(-iobuf)-nobuf[Disable buffered output]'
		'(-nobuf)-iobuf[Specify amount of memory to use for input buffer]:size:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-expand() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[Input file]:file:_files'
		'-c[Specify the column (1-based) that should be summarized]:int:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-fisher() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-a[features to search for]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-b[feature records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-m[Merge overlapping intervals]'
		'(-S)-s[Require same strandedness]'
		'(-s)-S[Require different strandedness]'
		'-f[Minimum overlap required as a fraction of A]:float:'
		'-F[Minimum overlap required as a fraction of B]:float:'
		'(-e)-r[Require that the fraction overlap be reciprocal for A AND B]'
		'(-r)-e[Require that the minimum fraction be satisfied for A OR B]'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-g[Genome file to enforce consistent chromosome sort order]:file:_files'
		'-nonamecheck[do not throw an error if the file has different naming conventions]'
		'-bed[If using BAM input, write output as BED]'
		'-header[Print the header from the A file prior to results]'
		'(-iobuf)-nobuf[Disable buffered output]'
		'(-nobuf)-iobuf[Specify amount of memory to use for input buffer]:size:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-flank() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[features records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-header[Print the header from the A file prior to results]'
		'-b[Create flanking interval(s) using -b base pairs in each direction]:int:'
		'(-b)-l[Number of base pairs that a flank should start from original start]:int:'
		'(-b)-r[Number of base pairs that a flank should end from original end]:int:'
		'(-b)-s[Define -l and -r based on strand]'
		'(-b)-pct[Define -l and -r as a fraction of the features length]'
		'-g[genome]:file:_files'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-genomecov() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[features records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-g[genome]:file:_files'
		'-ibam[The input file is in BAM format]:file:_files -g \*.bam'
		'(-max -dz)-d[Report the depth at each genome position (with one-based coordinates)]'
		'(-max -d)-dz[Report the depth at each genome position (with zero-based coordinates)]'
		'(-dz -d)-max[Combine all positions with a depth >= max into a single bin]'
		'(-bga)-bg[Report depth in BedGraph format]'
		'(-bg)-bga[Report depth in BedGraph format including zero-coverage regions]'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-strand[Calculate coverage of intervals from a specific strand]:string:(\- \+)'
		'(-3)-5[Calculate coverage of 5" positions]'
		'(-5)-3[Calculate coverage of 3" positions]'
		'-scale[Scale the coverage by a constant factor]:float:'
		'-trackline[Adds a UCSC/Genome-Browser track line definition in the first line of the output]'
		'-trackopts[Writes additional track line definition parameters in the first line]:text:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-getfasta() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-bed[features records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-fi[input fasta file]:file:_files'
		'-fo[ouput file]:file:_files'
		'-name[Use the name field for the FASTA header]:string:'
		'-name\+[Use the name field and coordinates for the FASTA header]:string:'
		'-tab[Write output in TAB delimited format]'
		'-s[Force strandedness]'
		'-fullHeader[Use full fasta header]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-igv() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[input file]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-path[The full path to which the IGV snapshots should be written]:directory:_files -/'
		'-sess[The full path to an existing IGV session file to be loaded prior to taking snapshots]:file:_files'
		'-sort[The type of BAM sorting you would like to apply to each image]:sorting:(base position strand quality sample readGroup)'
		'-clps[Collapse the aligned reads prior to taking a snapshot]'
		'-name[Use the "name" field (column 4) for each image filename]'
		'-slop[Number of flanking base pairs on the left and right of the image]:int:'
		'-img[The type of image to be created]:type:(png eps svg)'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-intersect() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-a[input file]:file:_files -g \*.\(bed\|gff\|vcf\|bam\)'
		'-b[input file]:file:_files -g \*.\(bed\|gff\|vcf\|bam\)'
		'-wa[Write the original entry in A for each overlap]'
		'-wb[Write the original entry in B for each overlap]'
		'-loj[Perform a "left outer join"]'
		'-wo[Write the original A and B entries plus the number of base pairs of overlap between the two features (only A features with overlap are reported)]'
		'-wao[Write the original A and B entries plus the number of base pairs of overlap between the two features (features w/o overlap are also reported)]'
		'-u[Write the original A entry _once_ if _any_ overlaps found in B]'
		'-c[For each entry in A, report the number of overlaps with B]'
		'-v[Only report those entries in A that have _no overlaps_ with B]'
		'-ubam[Write uncompressed BAM output (default writes compressed BAM)]'
		'-s[Require same strandedness]'
		'-S[Require different strandedness]'
		'-f[Minimum overlap required as a fraction of A]:float:'
		'-F[Minimum overlap required as a fraction of B]:float:'
		'-r[Require that the fraction overlap be reciprocal for A AND B]'
		'-e[Require that the minimum fraction be satisfied for A OR B]'
		'-split[Treat "split" BAM or BED12 entries as distinct BED intervals]'
		'-g[Provide a genome file to enforce consistent chromosome sort order across input files (only applies when used with -sorted option)]:file:_files'
		'-nonamecheck[For sorted data, do not throw an error if the file has different naming conventions for the same chromosome]'
		'-sorted[Use the "chromsweep" algorithm for sorted (-k1,1 -k2,2n) input]'
		'-names[When using multiple databases, provide an alias for each that will appear instead of a fileId when also printing the DB record]'
		'-filenames[When using multiple databases, show each complete filename instead of a fileId when also printing the DB record]'
		'-sortout[When using multiple databases, sort the output DB hits for each record]'
		'-bed[If using BAM input, write output as BED]'
		'-header[Print the header from the A file prior to results]'
		'-nobuf[Disable buffered output]'
		'-iobuf[Specify amount of memory to use for input buffer]:int:'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-maskfasta() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-bed[features records]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-fi[input fasta file]:file:_files'
		'-fo[ouput file]:file:_files'
		'-soft[Mask with lower-case bases, instead of masking with Ns]'
		'-mc[Replace masking character]:str:'
		'-fullHeader[Use full fasta header]'
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-makewindows() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-g[genome file]:file:_files'
		'-b[BED file]:file:_files -g \*.bed'
		'-w[window size]:int:'
		'-s[step size]:int:'
		'-n[number of windows]:int:'
		'-reverse[reverse numbering]'
		"-i[ID naming]:str:((
			src\:use\ the\ source\ interval\'s\ name
			winnum\:use\ the\ window\ number\ as\ the\ ID
			srcwinnum\:use\ the\ source\ interval\'s\ name\ with\ the\ window\ number
		))"
	)
	_arguments $args[@] && ret=0
	return ret
}

_bedtools-merge() {
	integer ret=1
	local -a args
	args+=(
		"$extra_arg"
		'-i[input file]:file:_files -g \*.\(bed\|gff\|vcf\)'
		'-s[Force strandedness]'
		'-S[Force merge for one specific strand only]'
		'-d[Maximum distance between features allowed for features to be merged]:int:'
		'-c[Specify columns from the B file to map onto intervals in A (default: 5, multiple columns can be specified in a comma-delimited list)]:int:'
		'-o[Specify the operation that should be applied to -c (default: sum, multiple columns can be specified in a comma-delimited list)]:str:((
			sum
			min
			max
			absmin
			absmax
			mean
			median
			mode
			antimode
			stdev
			sstdev
			collapse\:print\ a\ delimited\ list\ \(duplicates\ allowed\)
			distinct\:print\ a\ delimited\ list\ \(NO\ duplicates\ allowed\)
			distinct_sort_num\:as\ distinct\,\ sorted\ numerically\,\ ascending
			distinct_sort_num_desc\:as\ distinct\,\ sorted\ numerically\,\ desscending
			distinct_only\:delimited\ list\ of\ only\ unique\ values
			count
			count_distinct\:a\ count\ of\ the\ unique\ values\ in\ the\ column
			first\:just\ the\ first\ value\ in\ the\ column
			last\:just\ the\ last\ value\ in\ the\ column
		))'
		'-delim[Specify a custom delimiter for the collapse operations (default: ",")]:str:'
		'-prec[Sets the decimal precision for output (default: 5)]:int:'
		'-bed[If using BAM input, write output as BED]'
		'-header[Print the header from the A file prior to results]'
		'-nobuf[Disable buffered output]'
		'-iobuf[Specify amount of memory to use for input buffer]:int:'
	)
	_arguments $args[@] && ret=0
	return ret
}

# More to come

_bedtools-subcommand() {
	local ret=1

	local subcmd=_bedtools-$1
	if ! _call_function ret $subcmd; then
		_message "unknown subcomand: $subcmd"
		_arguments '*:file:_files'
	fi
	return ret
}

_bedtools-main() {
	local ret=1
	if (( CURRENT == 2)); then
		local -a args
		args+=(
			'1:command:((
				annotate\:Annotate\ coverage\ of\ features\ from\ multiple\ files
				bamtobed\:Convert\ BAM\ alignments\ to\ BED\ and\ other\ formats
				bamtofastq\:Convert\ BAM\ records\ to\ FASTQ\ records
				bed12tobed6\:Breaks\ BED12\ intervals\ into\ discrete\ BED6\ intervals
				bedpetobam\:Convert\ BEDPE\ intervals\ to\ BAM\ records
				bedtobam\:Convert\ intervals\ to\ BAM\ records
				closest\:Find\ the\ closest,\ potentially\ non-overlapping\ interval
				cluster\:Cluster\ \(but\ do\ not\ merge\)\ overlapping\/nearby\ intervals
				complement\:Extract\ intervals\ not\ represented\ by\ an\ interval\ file
				coverage\:Compute\ the\ coverage\ over\ defined\ intervals
				expand\:Replicate\ lines\ based\ on\ lists\ of\ values\ in\ columns
				fisher\:Calculate\ Fisher\ statistic\ b/w\ two\ feature\ files
				flank\:Create\ new\ intervals\ from\ the\ flanks\ of\ existing\ intervals
				genomecov\:Compute\ the\ coverage\ over\ an\ entire\ genome
				getfasta\:Use\ intervals\ to\ extract\ sequences\ from\ a\ FASTA\ file
				groupby\:Group\ by\ common\ cols.\ and\ summarize\ other\ cols
				igv\:Create\ an\ IGV\ snapshot\ batch\ script
				intersect\:Find\ overlapping\ intervals\ in\ various\ ways
				jaccard\:Calculate\ the\ Jaccard\ statistic\ b/w\ two\ sets\ of\ intervals
				links\:Create\ a\ HTML\ page\ of\ links\ to\ UCSC\ locations
				makewindows\:Make\ interval\ windows\ across\ a\ genome
				map\:Apply\ a\ function\ to\ a\ column\ for\ each\ overlapping\ interval
				maskfasta\:Use\ intervals\ to\ mask\ sequences\ from\ a\ FASTA\ file
				merge\:Combine\ overlapping/nearby\ intervals\ into\ a\ single\ interval
				multicov\:Counts\ coverage\ from\ multiple\ BAMs\ at\ specific\ intervals
				multiinter\:Identifies\ common\ intervals\ among\ multiple\ interval\ files
				nuc\:Profile\ the\ nucleotide\ content\ of\ intervals\ in\ a\ FASTA\ file
				overlap\:Computes\ the\ amount\ of\ overlap\ from\ two\ intervals
				pairtobed\:Find\ pairs\ that\ overlap\ intervals\ in\ various\ ways
				pairtopair\:Find\ pairs\ that\ overlap\ other\ pairs\ in\ various\ ways
				random\:Generate\ random\ intervals\ in\ a\ genome
				reldist\:Calculate\ the\ distribution\ of\ relative\ distances\ b/w\ two\ files
				sample\:Sample\ random\ records\ from\ file\ using\ reservoir\ sampling
				shift\:Adjust\ the\ position\ of\ intervals
				shuffle\:Randomly\ redistrubute\ intervals\ in\ a\ genome
				slop\:Adjust\ the\ size\ of\ intervals
				sort\:Order\ the\ intervals\ in\ a\ file
				spacing\:Report\ the\ gap\ lengths\ between\ intervals\ in\ a\ file
				split\:Split\ a\ file\ into\ multiple\ files\ with\ equal\ records\ or\ base\ pairs
				subtract\:Remove\ intervals\ based\ on\ overlaps\ b/w\ two\ files
				tag\:Tag\ BAM\ alignments\ based\ on\ overlaps\ with\ interval\ files
				unionbedg\:Combines\ coverage\ intervals\ from\ multiple\ BEDGRAPH\ files
				window\:Find\ overlapping\ intervals\ within\ a\ window\ around\ an\ interval
			))'
			'(- *)--help[Print help menu]'
			'(- *)--version[What version of bedtools are you using?]'
			'(- *)--contact[Feature requests, bugs, mailing lists, etc]'
		)
		_arguments $args[@] && ret=0
	else
		_bedtools-subcommand $words[2] && ret=0
	fi
	return ret
}

extra_arg=""
if [[ $service == bedtools ]]; then
	extra_arg='1:command:'
	_bedtools-main
else
	_bedtools-subcommand $aliases[$service]
fi