bamprovider

type BAMProvider struct {
	// Path of the *.bam file. Must be nonempty.
	Path string
	// Index is the pathname of *.bam.bai file. If "", Path + ".bai"
	Index string
	// contains filtered or unexported fields
}

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

type BoundedPairIteratorOpts struct {
	DuplicateShardCrossers bool
	MaxPairSpan            int
	TargetParallelism      int
}

type FileInfo struct {
	// ModTime is the last-modified time of the file. For PAM, it represents the
	// modtime of the *.index file of the first shard in the directory.
	ModTime time.Time
	// Size is the size of the file, in bytes.  For PAM, it represents the size of
	// the *.index file of the first shard in the directory.
	Size int64
}

type FileType int

type GenerateShardsOpts struct {
	// Strategy defines sharding strategy.
	Strategy ShardingStrategy

	Padding int
	// IncludeUnmapped causes GenerateShards() to produce shards for the
	// unmapped && mate-unmapped reads.
	IncludeUnmapped bool

	// SplitUnmappedCoords allows GenerateShards() to split unmapped
	// reads into multiple shards. Setting this flag true will cause shard
	// size to be more even, but the caller must be able to handle split
	// unmapped reads.
	SplitUnmappedCoords bool

	// SplitMappedCoords allows GenerateShards() to split mapped reads of
	// the same <refid, alignment position> into multiple shards. Setting
	// this flag true will cause shard size to be more even, but the caller
	// must be able to handle split reads.
	SplitMappedCoords bool

	// AlwaysSplitMappedAndUnmappedCoords causes GenerateShard always to split
	// shards at the boundary of mapped and unmapped reads.
	AlwaysSplitMappedAndUnmappedCoords bool

	// BytesPerShard is the target shard size, in bytes. This is consulted only in
	// ByteBased sharding strategy.
	BytesPerShard int64

	// NumShards is the target shard count. It is consulted by the ByteBased sharding
	// strategy, and is ignored if BytesPerShard is set.
	NumShards int

	// MinBasesPerShard defines the nimimum number of bases in each shard. This is
	// consulted only in ByteBased sharding strategy.
	MinBasesPerShard int
}

type Iterator interface {
	// Scan returns where there are any records remaining in the iterator,
	// and if so, advances the iterator to the next record. If the iterator
	// reaches the end of its range, Scan() returns false.  If an error
	// occurs, Scan() returns false and the error can be retrieved by
	// calling Error().
	//
	// Scan and Record always yield records in the ascending coordinate
	// (refid,position) order.
	//
	// REQUIRES: Close has not been called.
	Scan() bool

	// Record returns the current record in the iterator. This must be
	// called only after a call to Scan() returns true.
	//
	// REQUIRES: Close has not been called.
	Record() *sam.Record

	// Err returns the error encoutered during iteration, or nil if no error
	// occurred.  An io.EOF error will be translated to nil.
	Err() error

	// Close must be called exactly once. It returns the value of Err().
	Close() error
}

type MissingMateError struct {
	Message string
}

type PAMProvider struct {
	// Path prefix. Must be nonempty.
	Path string
	// Opts is passed to pam.NewReader.
	Opts pam.ReadOpts
	// contains filtered or unexported fields
}

type Pair = gbam.Pair

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

type Provider interface {
	// FileInfo returns metadata of the underlying file(s).
	//
	// TODO(saito) consider merging GetHeader into FileInfo.
	FileInfo() (FileInfo, error)

	// GetHeader returns the header for the provided BAM data.  The callee
	// must not modify the returned header object.
	//
	// REQUIRES: Close has not been called.
	GetHeader() (*sam.Header, error)

	// GenerateShards prepares for parallel reading of genomic data.
	//
	// The Shards split the BAM data from the given provider into
	// contiguous, non-overlapping genomic intervals. A SAM record is
	// associated with a shard if its alignment start position is within the
	// given padding distance of the shard. This means reads near shard
	// boundaries may be associated with more than one shard.
	//
	// Use NewIterator to read records in a shard.
	//
	// REQUIRES: Close has not been called.
	GenerateShards(opts GenerateShardsOpts) ([]gbam.Shard, error)

	// GetFileShards describes how records are split into files. For BAM, this
	// function just returns a UniversalShard since all records are in one
	// file. For PAM, this function returns one entry per fileshard.
	//
	// REQUIRES: Close has not been called.
	GetFileShards() ([]gbam.Shard, error)

	// NewIterator returns an iterator over record contained in the shard.  The
	// "shard" parameter is usually produced by GenerateShards, but the caller may
	// also manually construct it.
	//
	// REQUIRES: Close has not been called.
	NewIterator(shard gbam.Shard) Iterator

	// Close must be called exactly once. It returns any error encountered
	// by the provider, or any iterator created by the provider.
	//
	// REQUIRES: All the iterators created by NewIterator have been closed.
	Close() error
}

type ProviderOpts struct {
	// Index specifies the name of the BAM inde file. This field is meaningful
	// only for BAM files. If Index=="", it defaults to path + ".bai".
	Index string

	// DropFields causes the listed fields not to be filled in sam.Record. This
	// option is recognized only by the PAM reader.
	DropFields []gbam.FieldType
}

type ShardingStrategy int