sstable

type AbbreviatedKey = base.AbbreviatedKey

type BlockHandle struct {
	Offset, Length uint64
}

type BlockHandleWithProperties struct {
	BlockHandle
	Props []byte
}

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

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

type BlockPropertyCollector interface {
	// Name returns the name of the block property collector.
	Name() string
	// Add is called with each new entry added to a data block in the sstable.
	// The callee can assume that these are in sorted order.
	Add(key InternalKey, value []byte) error
	// FinishDataBlock is called when all the entries have been added to a
	// data block. Subsequent Add calls will be for the next data block. It
	// returns the property value for the finished block.
	FinishDataBlock(buf []byte) ([]byte, error)
	// AddPrevDataBlockToIndexBlock adds the entry corresponding to the
	// previous FinishDataBlock to the current index block.
	AddPrevDataBlockToIndexBlock()
	// FinishIndexBlock is called when an index block, containing all the
	// key-value pairs since the last FinishIndexBlock, will no longer see new
	// entries. It returns the property value for the index block.
	FinishIndexBlock(buf []byte) ([]byte, error)
	// FinishTable is called when the sstable is finished, and returns the
	// property value for the sstable.
	FinishTable(buf []byte) ([]byte, error)
}

type BlockPropertyFilter = base.BlockPropertyFilter

type ChecksumType byte

type Compare = base.Compare

type Comparer = base.Comparer

type Comparers map[string]*Comparer

type Compression int

type DataBlockIntervalCollector interface {
	// Add is called with each new entry added to a data block in the sstable.
	// The callee can assume that these are in sorted order.
	Add(key InternalKey, value []byte) error
	// FinishDataBlock is called when all the entries have been added to a
	// data block. Subsequent Add calls will be for the next data block. It
	// returns the [lower, upper) for the finished block.
	FinishDataBlock() (lower uint64, upper uint64, err error)
}

type Equal = base.Equal

type FileReopenOpt struct {
	FS       vfs.FS
	Filename string
}

type FilterMetrics struct {
	// The number of hits for the filter policy. This is the
	// number of times the filter policy was successfully used to avoid access
	// of a data block.
	Hits int64
	// The number of misses for the filter policy. This is the number of times
	// the filter policy was checked but was unable to filter an access of a data
	// block.
	Misses int64
}

type FilterPolicy = base.FilterPolicy

type FilterType = base.FilterType

type FilterWriter = base.FilterWriter

type InternalKey = base.InternalKey

type InternalKeyKind = base.InternalKeyKind

type Iterator interface {
	base.InternalIterator

	SetCloseHook(fn func(i Iterator) error)
}

type Layout struct {
	Data       []BlockHandleWithProperties
	Index      []BlockHandle
	TopIndex   BlockHandle
	Filter     BlockHandle
	RangeDel   BlockHandle
	RangeKey   BlockHandle
	Properties BlockHandle
	MetaIndex  BlockHandle
	Footer     BlockHandle
}

type Merger = base.Merger

type Mergers map[string]*Merger

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

type Properties struct {
	// ID of column family for this SST file, corresponding to the CF identified
	// by column_family_name.
	ColumnFamilyID uint64 `prop:"rocksdb.column.family.id"`
	// Name of the column family with which this SST file is associated. Empty if
	// the column family is unknown.
	ColumnFamilyName string `prop:"rocksdb.column.family.name"`
	// The name of the comparer used in this table.
	ComparerName string `prop:"rocksdb.comparator"`
	// The compression algorithm used to compress blocks.
	CompressionName string `prop:"rocksdb.compression"`
	// The compression options used to compress blocks.
	CompressionOptions string `prop:"rocksdb.compression_options"`
	// The time when the SST file was created. Since SST files are immutable,
	// this is equivalent to last modified time.
	CreationTime uint64 `prop:"rocksdb.creation.time"`
	// The total size of all data blocks.
	DataSize uint64 `prop:"rocksdb.data.size"`
	// The external sstable version format. Version 2 is the one RocksDB has been
	// using since 5.13. RocksDB only uses the global sequence number for an
	// sstable if this property has been set.
	ExternalFormatVersion uint32 `prop:"rocksdb.external_sst_file.version"`
	// Actual SST file creation time. 0 means unknown.
	FileCreationTime uint64 `prop:"rocksdb.file.creation.time"`
	// The name of the filter policy used in this table. Empty if no filter
	// policy is used.
	FilterPolicyName string `prop:"rocksdb.filter.policy"`
	// The size of filter block.
	FilterSize uint64 `prop:"rocksdb.filter.size"`
	// If 0, key is variable length. Otherwise number of bytes for each key.
	FixedKeyLen uint64 `prop:"rocksdb.fixed.key.length"`
	// Format version, reserved for backward compatibility.
	FormatVersion uint64 `prop:"rocksdb.format.version"`
	// The global sequence number to use for all entries in the table. Present if
	// the table was created externally and ingested whole.
	GlobalSeqNum uint64 `prop:"rocksdb.external_sst_file.global_seqno"`
	// Whether the index key is user key or an internal key.
	IndexKeyIsUserKey uint64 `prop:"rocksdb.index.key.is.user.key"`
	// Total number of index partitions if kTwoLevelIndexSearch is used.
	IndexPartitions uint64 `prop:"rocksdb.index.partitions"`
	// The size of index block.
	IndexSize uint64 `prop:"rocksdb.index.size"`
	// The index type. TODO(peter): add a more detailed description.
	IndexType uint32 `prop:"rocksdb.block.based.table.index.type"`
	// Whether delta encoding is used to encode the index values.
	IndexValueIsDeltaEncoded uint64 `prop:"rocksdb.index.value.is.delta.encoded"`
	// The name of the merger used in this table. Empty if no merger is used.
	MergerName string `prop:"rocksdb.merge.operator"`
	// The number of blocks in this table.
	NumDataBlocks uint64 `prop:"rocksdb.num.data.blocks"`
	// The number of deletion entries in this table, including both point and
	// range deletions.
	NumDeletions uint64 `prop:"rocksdb.deleted.keys"`
	// The number of entries in this table.
	NumEntries uint64 `prop:"rocksdb.num.entries"`
	// The number of merge operands in the table.
	NumMergeOperands uint64 `prop:"rocksdb.merge.operands"`
	// The number of range deletions in this table.
	NumRangeDeletions uint64 `prop:"rocksdb.num.range-deletions"`
	// The number of RANGEKEYDELs in this table.
	NumRangeKeyDels uint64 `prop:"pebble.num.range-key-dels"`
	// The number of RANGEKEYSETs in this table.
	NumRangeKeySets uint64 `prop:"pebble.num.range-key-sets"`
	// The number of RANGEKEYUNSETs in this table.
	NumRangeKeyUnsets uint64 `prop:"pebble.num.range-key-unsets"`
	// Timestamp of the earliest key. 0 if unknown.
	OldestKeyTime uint64 `prop:"rocksdb.oldest.key.time"`
	// The name of the prefix extractor used in this table. Empty if no prefix
	// extractor is used.
	PrefixExtractorName string `prop:"rocksdb.prefix.extractor.name"`
	// If filtering is enabled, was the filter created on the key prefix.
	PrefixFiltering bool `prop:"rocksdb.block.based.table.prefix.filtering"`
	// A comma separated list of names of the property collectors used in this
	// table.
	PropertyCollectorNames string `prop:"rocksdb.property.collectors"`
	// Total raw key size.
	RawKeySize uint64 `prop:"rocksdb.raw.key.size"`
	// Total raw rangekey key size.
	RawRangeKeyKeySize uint64 `prop:"pebble.raw.range-key.key.size"`
	// Total raw rangekey value size.
	RawRangeKeyValueSize uint64 `prop:"pebble.raw.range-key.value.size"`
	// Total raw value size.
	RawValueSize uint64 `prop:"rocksdb.raw.value.size"`
	// Size of the top-level index if kTwoLevelIndexSearch is used.
	TopLevelIndexSize uint64 `prop:"rocksdb.top-level.index.size"`
	// User collected properties.
	UserProperties map[string]string
	// If filtering is enabled, was the filter created on the whole key.
	WholeKeyFiltering bool `prop:"rocksdb.block.based.table.whole.key.filtering"`

	// Loaded set indicating which fields have been loaded from disk. Indexed by
	// the field's byte offset within the struct
	// (reflect.StructField.Offset). Only set if the properties have been loaded
	// from a file. Only exported for testing purposes.
	Loaded map[uintptr]struct{}
}

type ReadableFile interface {
	io.ReaderAt
	io.Closer
	Stat() (os.FileInfo, error)
}

type Reader struct {
	Compare   Compare
	FormatKey base.FormatKey
	Split     Split

	Properties Properties
	// contains filtered or unexported fields
}

type ReaderOption interface {
	// contains filtered or unexported methods
}

type ReaderOptions struct {
	// Cache is used to cache uncompressed blocks from sstables.
	//
	// The default cache size is a zero-size cache.
	Cache *cache.Cache

	// Comparer defines a total ordering over the space of []byte keys: a 'less
	// than' relationship. The same comparison algorithm must be used for reads
	// and writes over the lifetime of the DB.
	//
	// The default value uses the same ordering as bytes.Compare.
	Comparer *Comparer

	// Filters is a map from filter policy name to filter policy. It is used for
	// debugging tools which may be used on multiple databases configured with
	// different filter policies. It is not necessary to populate this filters
	// map during normal usage of a DB.
	Filters map[string]FilterPolicy

	// Merger defines the associative merge operation to use for merging values
	// written with {Batch,DB}.Merge. The MergerName is checked for consistency
	// with the value stored in the sstable when it was written.
	MergerName string
}

type Separator = base.Separator

type Split = base.Split

type Successor = base.Successor

type SuffixReplaceableBlockCollector interface {
	// UpdateKeySuffixes is called when a block is updated to change the suffix of
	// all keys in the block, and is passed the old value for that prop, if any,
	// for that block as well as the old and new suffix.
	UpdateKeySuffixes(oldProp []byte, oldSuffix, newSuffix []byte) error
}

type SuffixReplaceableTableCollector interface {
	// UpdateKeySuffixes is called when a table is updated to change the suffix of
	// all keys in the table, and is passed the old value for that prop, if any,
	// for that table as well as the old and new suffix.
	UpdateKeySuffixes(oldProps map[string]string, oldSuffix, newSuffix []byte) error
}

type TableFormat uint32

type TablePropertyCollector interface {
	// Add is called with each new entry added to the sstable. While the sstable
	// is itself sorted by key, do not assume that the entries are added in any
	// order. In particular, the ordering of point entries and range tombstones
	// is unspecified.
	Add(key InternalKey, value []byte) error

	// Finish is called when all entries have been added to the sstable. The
	// collected properties (if any) should be added to the specified map. Note
	// that in case of an error during sstable construction, Finish may not be
	// called.
	Finish(userProps map[string]string) error

	// The name of the property collector.
	Name() string
}

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

type WriterMetadata struct {
	Size          uint64
	SmallestPoint InternalKey
	// LargestPoint, LargestRangeKey, LargestRangeDel should not be accessed
	// before Writer.Close is called, because they may only be set on
	// Writer.Close.
	LargestPoint     InternalKey
	SmallestRangeDel InternalKey
	LargestRangeDel  InternalKey
	SmallestRangeKey InternalKey
	LargestRangeKey  InternalKey
	HasPointKeys     bool
	HasRangeDelKeys  bool
	HasRangeKeys     bool
	SmallestSeqNum   uint64
	LargestSeqNum    uint64
	Properties       Properties
}

type WriterOption interface {
	// contains filtered or unexported methods
}

type WriterOptions struct {
	// BlockRestartInterval is the number of keys between restart points
	// for delta encoding of keys.
	//
	// The default value is 16.
	BlockRestartInterval int

	// BlockSize is the target uncompressed size in bytes of each table block.
	//
	// The default value is 4096.
	BlockSize int

	// BlockSizeThreshold finishes a block if the block size is larger than the
	// specified percentage of the target block size and adding the next entry
	// would cause the block to be larger than the target block size.
	//
	// The default value is 90
	BlockSizeThreshold int

	// Cache is used to cache uncompressed blocks from sstables.
	//
	// The default is a nil cache.
	Cache *cache.Cache

	// Comparer defines a total ordering over the space of []byte keys: a 'less
	// than' relationship. The same comparison algorithm must be used for reads
	// and writes over the lifetime of the DB.
	//
	// The default value uses the same ordering as bytes.Compare.
	Comparer *Comparer

	// Compression defines the per-block compression to use.
	//
	// The default value (DefaultCompression) uses snappy compression.
	Compression Compression

	// FilterPolicy defines a filter algorithm (such as a Bloom filter) that can
	// reduce disk reads for Get calls.
	//
	// One such implementation is bloom.FilterPolicy(10) from the pebble/bloom
	// package.
	//
	// The default value means to use no filter.
	FilterPolicy FilterPolicy

	// FilterType defines whether an existing filter policy is applied at a
	// block-level or table-level. Block-level filters use less memory to create,
	// but are slower to access as a check for the key in the index must first be
	// performed to locate the filter block. A table-level filter will require
	// memory proportional to the number of keys in an sstable to create, but
	// avoids the index lookup when determining if a key is present. Table-level
	// filters should be preferred except under constrained memory situations.
	FilterType FilterType

	// IndexBlockSize is the target uncompressed size in bytes of each index
	// block. When the index block size is larger than this target, two-level
	// indexes are automatically enabled. Setting this option to a large value
	// (such as math.MaxInt32) disables the automatic creation of two-level
	// indexes.
	//
	// The default value is the value of BlockSize.
	IndexBlockSize int

	// Merger defines the associative merge operation to use for merging values
	// written with {Batch,DB}.Merge. The MergerName is checked for consistency
	// with the value stored in the sstable when it was written.
	MergerName string

	// TableFormat specifies the format version for writing sstables. The default
	// is TableFormatRocksDBv2 which creates RocksDB compatible sstables. Use
	// TableFormatLevelDB to create LevelDB compatible sstable which can be used
	// by a wider range of tools and libraries.
	TableFormat TableFormat

	// TablePropertyCollectors is a list of TablePropertyCollector creation
	// functions. A new TablePropertyCollector is created for each sstable built
	// and lives for the lifetime of the table.
	TablePropertyCollectors []func() TablePropertyCollector

	// BlockPropertyCollectors is a list of BlockPropertyCollector creation
	// functions. A new BlockPropertyCollector is created for each sstable
	// built and lives for the lifetime of writing that table.
	BlockPropertyCollectors []func() BlockPropertyCollector

	// Checksum specifies which checksum to use.
	Checksum ChecksumType

	// Parallelism is used to indicate that the sstable Writer is allowed to
	// compress data blocks and write datablocks to disk in parallel with the
	// Writer client goroutine.
	Parallelism bool
}