table

type ArrowSchemaVisitor[T any] interface {
	Schema(*arrow.Schema, T) T
	Struct(*arrow.StructType, []T) T
	Field(arrow.Field, T) T
	List(arrow.ListLikeType, T) T
	Map(mt *arrow.MapType, keyResult T, valueResult T) T
	Primitive(arrow.DataType) T
}

type BlobMetadata struct {
	Type           BlobType          `json:"type"`
	SnapshotID     int64             `json:"snapshot-id"`
	SequenceNumber int64             `json:"sequence-number"`
	Fields         []int32           `json:"fields"`
	Properties     map[string]string `json:"properties"`
}

type BlobType string

type CatalogIO interface {
	LoadTable(context.Context, Identifier) (*Table, error)
	CommitTable(context.Context, Identifier, []Requirement, []Update) (Metadata, string, error)
}

type ExpireSnapshotsOpt func(*expireSnapshotsCfg)

type FSysF func(ctx context.Context) (io.IO, error)

type FileScanTask struct {
	File          iceberg.DataFile
	DeleteFiles   []iceberg.DataFile
	Start, Length int64
}

type Identifier = []string

type LocationProvider interface {
	NewDataLocation(dataFileName string) string
	NewTableMetadataFileLocation(newVersion int) (string, error)
	NewMetadataLocation(metadataFileName string) string
}

type Metadata interface {
	// Version indicates the version of this metadata, 1 for V1, 2 for V2, etc.
	Version() int
	// TableUUID returns a UUID that identifies the table, generated when the
	// table is created. Implementations must throw an exception if a table's
	// UUID does not match the expected UUID after refreshing metadata.
	TableUUID() uuid.UUID
	// Location is the table's base location. This is used by writers to determine
	// where to store data files, manifest files, and table metadata files.
	Location() string
	// LastUpdatedMillis is the timestamp in milliseconds from the unix epoch when
	// the table was last updated. Each table metadata file should update this
	// field just before writing.
	LastUpdatedMillis() int64
	// LastColumnID returns the highest assigned column ID for the table.
	// This is used to ensure fields are always assigned an unused ID when
	// evolving schemas.
	LastColumnID() int
	// Schemas returns the list of schemas, stored as objects with their
	// schema-id.
	Schemas() []*iceberg.Schema
	// CurrentSchema returns the table's current schema.
	CurrentSchema() *iceberg.Schema
	// PartitionSpecs returns the list of all partition specs in the table.
	PartitionSpecs() []iceberg.PartitionSpec
	// PartitionSpec returns the current partition spec that the table is using.
	PartitionSpec() iceberg.PartitionSpec
	// DefaultPartitionSpec is the ID of the current spec that writers should
	// use by default.
	DefaultPartitionSpec() int
	// LastPartitionSpecID is the highest assigned partition field ID across
	// all partition specs for the table. This is used to ensure partition
	// fields are always assigned an unused ID when evolving specs.
	LastPartitionSpecID() *int
	// Snapshots returns the list of valid snapshots. Valid snapshots are
	// snapshots for which all data files exist in the file system. A data
	// file must not be deleted from the file system until the last snapshot
	// in which it was listed is garbage collected.
	Snapshots() []Snapshot
	// SnapshotByID find and return a specific snapshot by its ID. Returns
	// nil if the ID is not found in the list of snapshots.
	SnapshotByID(int64) *Snapshot
	// SnapshotByName searches the list of snapshots for a snapshot with a given
	// ref name. Returns nil if there's no ref with this name for a snapshot.
	SnapshotByName(name string) *Snapshot
	// CurrentSnapshot returns the table's current snapshot.
	CurrentSnapshot() *Snapshot
	// Ref returns the snapshot ref for the main branch.
	Ref() SnapshotRef
	// Refs returns a list of snapshot name/reference pairs.
	Refs() iter.Seq2[string, SnapshotRef]
	// SnapshotLogs returns the list of snapshot logs for the table.
	SnapshotLogs() iter.Seq[SnapshotLogEntry]
	// SortOrder returns the table's current sort order, ie: the one with the
	// ID that matches the default-sort-order-id.
	SortOrder() SortOrder
	// SortOrders returns the list of sort orders in the table.
	SortOrders() []SortOrder
	// DefaultSortOrder returns the ID of the current sort order that writers
	// should use by default.
	DefaultSortOrder() int
	// Properties is a string to string map of table properties. This is used
	// to control settings that affect reading and writing and is not intended
	// to be used for arbitrary metadata. For example, commit.retry.num-retries
	// is used to control the number of commit retries.
	Properties() iceberg.Properties
	// PreviousFiles returns the list of metadata log entries for the table.
	PreviousFiles() iter.Seq[MetadataLogEntry]
	Equals(Metadata) bool

	NameMapping() iceberg.NameMapping

	LastSequenceNumber() int64
	// Statistics returns an optional list of table statistics.
	// Table statistics files are valid Puffin files.
	// StatisticsFile are informational. A reader can choose to ignore statistics information.
	// StatisticsFile support is not required to read the table correctly.
	// A table can contain many statistics files associated with different table snapshots.
	Statistics() iter.Seq[StatisticsFile]
	// PartitionStatistics returns an optional list of partition statistics files.
	// Partition statistics are not required for reading or planning
	// and readers may ignore them. Each table snapshot may be associated
	// with at most one partition statistics file. A writer can optionally
	// write the partition statistics file during each write operation,
	// or it can also be computed on demand.
	PartitionStatistics() iter.Seq[PartitionStatisticsFile]
}

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

type MetadataLogEntry struct {
	MetadataFile string `json:"metadata-file"`
	TimestampMs  int64  `json:"timestamp-ms"`
}

type NullOrder string

type Operation string

type OrphanCleanupOption func(*orphanCleanupConfig)

type OrphanCleanupResult struct {
	OrphanFileLocations []string
	DeletedFiles        []string
	TotalSizeBytes      int64
}

type PartitionStatisticsFile struct {
	SnapshotID      int64  `json:"snapshot-id"`
	StatisticsPath  string `json:"statistics-path"`
	FileSizeInBytes int64  `json:"file-size-in-bytes"`
}

type PrefixMismatchMode int

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

type RefType string

type Requirement interface {
	// Validate checks that the current table metadata satisfies the requirement.
	Validate(Metadata) error
	GetType() string
}

type Requirements []Requirement

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

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

type ScanOption func(*Scan)

type Snapshot struct {
	SnapshotID       int64    `json:"snapshot-id"`
	ParentSnapshotID *int64   `json:"parent-snapshot-id,omitempty"`
	SequenceNumber   int64    `json:"sequence-number"`
	TimestampMs      int64    `json:"timestamp-ms"`
	ManifestList     string   `json:"manifest-list,omitempty"`
	Summary          *Summary `json:"summary,omitempty"`
	SchemaID         *int     `json:"schema-id,omitempty"`
}

type SnapshotLogEntry struct {
	SnapshotID  int64 `json:"snapshot-id"`
	TimestampMs int64 `json:"timestamp-ms"`
}

type SnapshotRef struct {
	SnapshotID         int64   `json:"snapshot-id"`
	SnapshotRefType    RefType `json:"type"`
	MinSnapshotsToKeep *int    `json:"min-snapshots-to-keep,omitempty"`
	MaxSnapshotAgeMs   *int64  `json:"max-snapshot-age-ms,omitempty"`
	MaxRefAgeMs        *int64  `json:"max-ref-age-ms,omitempty"`
}

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

type SortDirection string

type SortField struct {
	// SourceID is the source column id from the table's schema
	SourceID int `json:"source-id"`
	// Transform is the tranformation used to produce values to be
	// sorted on from the source column.
	Transform iceberg.Transform `json:"transform"`
	// Direction is an enum indicating ascending or descending direction.
	Direction SortDirection `json:"direction"`
	// NullOrder describes the order of null values when sorting
	// should be only either nulls-first or nulls-last enum values.
	NullOrder NullOrder `json:"null-order"`
}

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

type StagedTable struct {
	*Table
}

type StatisticsFile struct {
	SnapshotID            int64          `json:"snapshot-id"`
	StatisticsPath        string         `json:"statistics-path"`
	FileSizeInBytes       int64          `json:"file-size-in-bytes"`
	FileFooterSizeInBytes int64          `json:"file-footer-size-in-bytes"`
	KeyMetadata           *string        `json:"key-metadata,omitempty"`
	BlobMetadata          []BlobMetadata `json:"blob-metadata"`
}

type Summary struct {
	Operation  Operation
	Properties iceberg.Properties
}

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

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

type Update interface {
	// Action returns the name of the action that the update represents.
	Action() string
	// Apply applies the update to the given metadata builder.
	Apply(*MetadataBuilder) error
	// PostCommit is called after successful commit of the update
	PostCommit(context.Context, *Table, *Table) error
}

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

type Updates []Update

type WriteTask struct {
	Uuid        uuid.UUID
	ID          int
	Schema      *iceberg.Schema
	Batches     []arrow.RecordBatch
	SortOrderID int
}