cmd

type Chain2Result struct {
	NAnchors int // The number of substrings

	AlignedFraction float64

	MatchedBases  int     // The number of matched bases.
	AlignedBasesQ int     // The number of aligned bases in Query sequence
	AlignedBasesT int     // The number of aligned bases in Subject sequence
	PIdent        float64 // percentage of identity
	AlignedLength int     // Aligned length, might be longer than AlignedBasesQ or AlignedBasesT
	Gaps          int     // The number of gaps

	QBegin, QEnd int // Query begin/end position (0-based)
	TBegin, TEnd int // Target begin/end position (0-based)

	MaxExtLen int // max extend length

	// for output
	CIGAR     []byte // cigar string
	QSeq      []byte // query seq
	TSeq      []byte // target seq
	Alignment []byte // alignment text

	// statistic
	Score    int
	BitScore int
	Evalue   float64
	// contains filtered or unexported fields
}

type Chain3Result struct {
	NAnchors int // The number of substrings

	AlignedFraction float64

	MatchedBases  int     // The number of matched bases.
	AlignedBasesQ int     // The number of aligned bases in Query sequence
	AlignedBasesT int     // The number of aligned bases in Subject sequence
	PIdent        float64 // percentage of identity
	AlignedLength int     // Aligned length, might be longer than AlignedBasesQ or AlignedBasesT
	Gaps          int     // The number of gaps

	QBegin, QEnd int // Query begin/end position (0-based)
	TBegin, TEnd int // Target begin/end position (0-based)
}

type Chainer struct {
	// contains filtered or unexported fields
}

type Chainer2 struct {
	// contains filtered or unexported fields
}

type Chainer3 struct {
	// contains filtered or unexported fields
}

type Chaining2Options struct {
	MaxGap      int
	MinScore    int // minimum score of a chain
	MinAlignLen int
	MinIdentity float64
	MaxDistance int
	BandCount   int // only check i in range of  i − A < j < i
	BandBase    int // only check i where i.Qstart+i.Len + A < j.Qstart
}

type Chaining3Options struct {
	MaxGap      int
	MinScore    int // minimum score of a chain
	MinAlignLen int
	MinIdentity float64
	MaxDistance int
	BandCount   int // only check i in range of  i − A < j < i
	BandBase    int // only check i where i.Qstart+i.Len + A < j.Qstart
}

type ChainingOptions struct {
	MaxGap      float64
	MinLen      uint8
	MinScore    float64
	MaxDistance float64
}

type Index struct {

	// k-mer-value searchers
	Searchers         []*kv.Searcher
	InMemorySearchers []*kv.InMemorySearcher

	BatchGenomeIndex2GenomeID map[uint64][]byte

	Taxonomy *taxdump.Taxonomy
	// contains filtered or unexported fields
}

type IndexBuildingOptions struct {
	// general
	NumCPUs      int
	Verbose      bool // show log
	Log2File     bool // log file
	Force        bool // force overwrite existed index
	MaxOpenFiles int  // maximum opened files, used in merging indexes
	MergeThreads int  // Maximum Concurrent Merge Jobs

	MinSeqLen int // minimum sequence length, should be >= k

	// skipping extremely large genome
	MaxGenomeSize int    // Maximum genome size. Extremely large genomes (non-isolate assemblies) will be skipped
	BigGenomeFile string // Out file of skipped files with genomes

	// LexicHash
	MaskFile string // file of custom masks

	K        int   // k-mer size
	Masks    int   // number of masks
	RandSeed int64 // random seed

	// filling sketching deserts
	DisableDesertFilling   bool   // disable desert filling (just for analysis index)
	DesertMaxLen           uint32 // maxi length of sketching deserts
	DesertExpectedSeedDist int    // expected distance between seeds
	DesertSeedPosRange     int    // the upstream and down stream region for adding a seeds

	// generate mask from the top N biggest genomes
	TopN      int // Select the the top N largest genomes for generating masks
	PrefixExt int // Extension length of prefixes

	Chunks     int // the number of chunks for storing k-mer data
	Partitions int // the number of partitions for indexing k-mer data

	GenomeBatchSize int // the maximum number of genomes of a batch

	ReRefName    *regexp.Regexp   // for extracting genome id from the file name
	ReSeqExclude []*regexp.Regexp // for excluding sequences according to name pattern

	ContigInterval int // the length of N's between contigs

	SaveSeedPositions bool

	Debug bool
}

type IndexInfo struct {
	MainVersion      uint8 `toml:"main-version" comment:"Index format"`
	MinorVersion     uint8 `toml:"minor-version"`
	K                uint8 `toml:"max-K" comment:"LexicHash"`
	Masks            int   `toml:"masks"`
	RandSeed         int64 `toml:"rand-seed"`
	MaxDesert        int   `toml:"max-seed-dist" comment:"Seed distance"`
	SeedDistInDesert int   `toml:"seed-dist-in-desert"`
	Chunks           int   `toml:"chunks" comment:"Seeds (k-mer-value data) files"`
	Partitions       int   `toml:"index-partitions"`
	InputGenomes     int   `toml:"input-genomes" comment:"Input genomes"`
	InputBases       int64 `toml:"input-bases" comment:"Input bases"`
	Genomes          int   `` /* 239-byte string literal not displayed */
	GenomeBatchSize  int   `toml:"genome-batch-size"`
	GenomeBatches    int   `toml:"genome-batches"`
	ContigInterval   int   `toml:"contig-interval"`
}

type IndexSearchingOptions struct {
	// general
	NumCPUs      int
	Verbose      bool // show log
	Log2File     bool // log file
	MaxOpenFiles int  // maximum opened files, used in merging indexes

	InMemorySearch bool  // load the seed/kv data into memory
	MinPrefix      uint8 // minimum prefix length, e.g., 15
	// MaxMismatch     int   // maximum mismatch, e.g., 3
	MinSinglePrefix uint8 // minimum prefix length of the single seed, e.g., 20
	// MinMatchedBases uint8 // the total matched bases
	TopN int // keep the topN scores, e.g, 10

	// seeds chaining
	MaxGap      float64 // e.g., 5000
	MaxDistance float64 // e.g., 20k

	// alignment
	ExtendLength  int // the length of extra sequence on the flanking of seeds.
	ExtendLength2 int // the length of extra sequence on the flanking of pseudo-alignment region.

	// alignment filtering
	MinQueryAlignedFractionInAGenome float64 // minimum query aligned fraction in the target genome
	MaxEvalue                        float64

	// Output
	OutputSeq bool

	// debug
	Debug bool

	// filter results by taxid
	TaxdumpDir              string
	Genome2TaxIdFile        string
	TaxIds                  []uint32
	NegativeTaxIds          []uint32
	KeepGenomesWithoutTaxId bool
}

type Options struct {
	NumCPUs int
	Verbose bool

	LogFile  string
	Log2File bool

	Compress         bool
	CompressionLevel int
}

type Query struct {
	// contains filtered or unexported fields
}

type SearchResult struct {
	Subs *[]*SubstrPair // matched substring pairs (query,target)

	BatchGenomeIndex uint64 // just for finding genome chunks of the same genome

	GenomeBatch int
	GenomeIndex int
	// ID          []byte
	GenomeSize int

	Score  float64 //  score for soring
	Chains *[]*[]int32

	// more about the alignment detail
	SimilarityDetails *[]*SimilarityDetail // sequence comparing
	AlignedFraction   float64              // query coverage per genome
}

type SearchResultOfAGenome struct {
	Hits    int
	Query   string
	Qlen    string
	Sgenome string
	QcovGnm string

	Score float64 // float64(BitScore) * PIdent

	Records []*SearchResultOfASequence
	// contains filtered or unexported fields
}

type SearchResultOfASequence struct {
	Sseqid   string
	Cls      string // should be smaller than int
	Hsp      string // should be smaller than int
	QcovHSP  string
	AlenHSP  string
	Pident   string
	Gaps     string
	Qstart   string
	Qend     string
	Sstart   string
	Send     string
	Sstr     string
	Slen     string
	Evalue   string
	Bitscore string

	Extra string
}

type SearchResultReader struct {
	// contains filtered or unexported fields
}

type SearchResultsHeap struct {
	// contains filtered or unexported fields
}

type SeqComparator struct {
	// contains filtered or unexported fields
}

type SeqComparatorOptions struct {
	// indexing
	K         uint8
	MinPrefix uint8

	// chaining
	Chaining2Options

	// seq similarity
	MinAlignedFraction float64 // minimum query aligned fraction in a HSP

	MinIdentity float64
}

type SeqComparatorResult struct {
	AlignedBases int // The number of aligned bases.

	AlignedFraction float64 // query (original query) coverage per HSP

	MatchedBases int
	PIdent       float64

	QueryLen int // length of the original query, used to compute/update AlignedFraction

	QBegin int
	QEnd   int
	TBegin int
	TEnd   int

	TSeq []byte // target seq

	Chains *[]*Chain2Result
}

type SimilarityDetail struct {
	// QBegin int
	// QEnd   int
	// TBegin int
	// TEnd   int
	RC bool

	SimilarityScore float64
	Similarity      *SeqComparatorResult
	// Chain           *[]int
	NSeeds int

	// sequence details
	SeqLen int
	SeqID  []byte // seqid of the region
}

type SubstrPair struct {
	QBegin int32 // start position of the substring (0-based) in query
	TBegin int32 // start position of the substring (0-based) in reference

	Len uint8 // prefix length

	TRC bool // is the substring from the reference seq on the negative strand.
	QRC bool // is the substring from the query seq on the negative strand.

}

type Uint64Slice []uint64