cmd

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

	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
	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 Chaining2Options struct {
	MaxGap      int
	MinScore    int // minimum score of a chain
	MinAlignLen int
	MinIdentity float64
	MaxDistance int
	Band        int // only check i in range of  i − A < j < i
}

type ChainingOptions struct {
	MaxGap      float64
	MinScore    float64
	MaxDistance float64
}

type File2GSize struct {
	Size int
	File string

} // An IntHeap is a min-heap of ints.

type File2GSizes []File2GSize

type Index struct {

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

	// 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

	// generate mask randomly
	Prefix int // length of prefix for checking low-complexity and choosing k-mers to fill deserts

	// filling sketching deserts
	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
}

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"`
	Chunks          int   `toml:"chunks" comment:"Seeds (k-mer-value data) files"`
	Partitions      int   `toml:"index-partitions"`
	Genomes         int   `toml:"genomes" comment:"Genome data"`
	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

	// seed searching
	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
	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.
	// seq similarity
	MinQueryAlignedFractionInAGenome float64 // minimum query aligned fraction in the target genome

	// Output
	OutputSeq bool
}

type Kmer2Locs [][2]uint64

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 {
	GenomeBatch int
	GenomeIndex int
	ID          []byte
	GenomeSize  int

	Subs *[]*SubstrPair // matched substring pairs (query,target)

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

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

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
	Mismatch uint8 // number of mismatches

	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