Artifact [a53c552510]

Artifact a53c552510b6790a95716c8689239921af6dc690271212b32f19ac9a7c662829:

• File internal/content/cone_reference_facts.go — part of check-in [e5bdac3d33] at 2026-10-22 22:18:31 on branch feat/horizon-cones — feat(content): an origin classification memo extended by appends

  An origin re-reads its store for every horizon request: the reference facts behind the path classification and the trees of the whole held set. draft-fossil-horizon-00 §6.2 asks it to keep the classification keyed by cone digest and store prefix, extend it by the artifacts appended since, and recompute in full only when an arrival carries a name a held P, B or S card cited while it was absent.

  Memo keeps the store's cone-independent references (the reference facts, the check-in graph and the dangling P/B/S names) at a prefix, and per cone digest and per horizon the classification over them. A view extends each by the appended and filled rids: the loader's decisions for those rids alone, classification of the facts' new tails, and the tree walk of the check-ins K gained. Anything other than an append or an uncited fill (a cited arrival, a deleted or phantomized row, a first tree) reads the store in full. Views are copy-on-write and reach the memo only when published, so a rolled-back request leaves nothing behind. (user: [email protected], size: 6216) [annotate] [blame] [check-ins using] [more...]

package content

import (
	"context"
	"maps"

	"github.com/danmestas/go-libfossil/db"
	"github.com/danmestas/go-libfossil/internal/cone"
	"github.com/danmestas/go-libfossil/internal/deck"
	libfossil "github.com/danmestas/go-libfossil/internal/fsltype"
)

// ConeReferenceFacts holds immutable reference facts for one database
// snapshot, without a cone key. The owner must validate that snapshot before
// using these facts against a database that may have changed.
//
// Loading names every artifact in the store, but reads raw bytes only where
// the crosslink tables cannot answer: never a file version the crosslinker
// found to be no artifact, and a check-in only when its link is incomplete
// or its tree is not reproduced by mlink (see answerable). It serves whole-store
// work (a pull's inventory, compaction, verification, crosslink), never a
// clone round. Retained decks are classification projections, not complete
// artifacts suitable for marshaling.
type ConeReferenceFacts struct {
	names      map[libfossil.FslID]string
	held       map[string]libfossil.FslID // Read and hash-verified.
	nodes      map[libfossil.FslID]*deck.Deck
	byUUID     map[string]*deck.Deck
	records    []coneReferenceRecord
	roots      []*deck.Deck
	unreadable []string
	// spine and files are linked check-ins' facts, from the tables: the
	// check-ins and their references, and their trees' (name, file) pairs.
	spine []string
	files []deck.FileCard
}

type coneReferenceRecord struct {
	uuid string
	deck *deck.Deck
}

func LoadConeReferenceFacts(ctx context.Context, q db.Querier) (*ConeReferenceFacts, error) {
	// Discovery is guarded before allocation. Counting only check-ins/trees
	// does not bound wiki, forum, cluster or file storage. Oversized
	// snapshots fail rather than allocate first and discover their budget
	// after parsing.
	facts, _, err := loadConeReferenceFactsBounded(ctx, q, defaultReferenceLimits.refs, true)
	return facts, err
}

// referenceLimits bounds one classification: its raw reference reads, and
// under a content horizon the tree walk of the held set, which is charged
// per check-in in that set rather than per artifact in the store.
type referenceLimits struct {
	refs           ReferenceBudget
	treePerCheckin int64
	treeMax        int64
}

// ExpandedBytes also pays for the delta chains a raw read must expand: a
// check-in whose parent never arrived is read raw, and in the Fossil SCM
// repository one such manifest sits 1,594 deltas from its full base, about
// 120 MiB of expansion. Bases are released as the chain advances, so this
// bounds work rather than memory. The tree budget scales with the held set
// so that a horizon's cost follows the history it keeps.
var defaultReferenceLimits = referenceLimits{
	refs: ReferenceBudget{
		Artifacts: coneReferenceNodes, StoredBytes: 64 << 20,
		InflatedBytes: 128 << 20, ExpandedBytes: 512 << 20, Cards: 1 << 20,
	},
	treePerCheckin: 1 << 20, treeMax: 4 << 30,
}

// Classify creates request-local membership; neither the facts nor previous
// classifications are changed. Maps of raw identities and decks are read-only.
func (facts *ConeReferenceFacts) Classify(
	ctx context.Context, c *cone.Cone,
) (*ConeReferences, error) {
	if facts == nil || ctx == nil {
		panic("content.ConeReferenceFacts.Classify: nil facts or context")
	}
	p := facts.references(nil)
	if err := ctx.Err(); err != nil {
		return nil, err
	}
	if c == nil {
		return p, nil
	}
	if _, err := facts.classifyFrom(ctx, c, p, factsMark{}); err != nil {
		return nil, err
	}
	return p, nil
}

// references is a classification over facts: from's membership copied,
// so the copy can grow without changing from, or empty when from is nil.
func (facts *ConeReferenceFacts) references(from *ConeReferences) *ConeReferences {
	p := &ConeReferences{
		names: facts.names, held: facts.held, nodes: facts.nodes,
		outside: map[string]bool{}, inside: map[string]bool{},
		required: map[string]bool{}, tree: map[string]bool{},
	}
	if from != nil {
		p.outside, p.inside = maps.Clone(from.outside), maps.Clone(from.inside)
		p.required, p.tree = maps.Clone(from.required), maps.Clone(from.tree)
	}
	return p
}

// factsMark is how far into each of a ConeReferenceFacts' append-only lists
// a classification has read, and the tree nodes its walk has visited.
type factsMark struct {
	records, roots, unreadable, spine, files int
	visited                                  int
}

// mark is the end of every list facts holds.
func (facts *ConeReferenceFacts) mark() factsMark {
	return factsMark{records: len(facts.records), roots: len(facts.roots), unreadable: len(facts.unreadable),
		spine: len(facts.spine), files: len(facts.files)}
}

// classifyFrom adds to p what the facts past from say of c, and returns the
// mark it read through. Every set it adds to is a union over the lists, so
// classifying a list's tail into the classification of its head is
// classifying the whole list.
func (facts *ConeReferenceFacts) classifyFrom(
	ctx context.Context, c *cone.Cone, p *ConeReferences, from factsMark,
) (factsMark, error) {
	if c == nil {
		panic("content.ConeReferenceFacts.classifyFrom: nil cone")
	}
	for _, uuid := range facts.unreadable[from.unreadable:] {
		p.required[uuid] = true
	}
	for _, uuid := range facts.spine[from.spine:] {
		p.required[uuid] = true
	}
	for _, f := range facts.files[from.files:] {
		if c.Covers(f.Name) {
			p.inside[f.UUID] = true
		} else {
			p.outside[f.UUID] = true
		}
	}
	for _, record := range facts.records[from.records:] {
		if err := ctx.Err(); err != nil {
			return factsMark{}, err
		}
		d := record.deck
		if d.Type != deck.Submanifest {
			p.required[record.uuid] = true
		}
		for _, f := range d.F {
			if f.UUID == "" {
				continue
			}
			if c.Covers(f.Name) {
				p.inside[f.UUID] = true
			} else {
				p.outside[f.UUID] = true
			}
		}
		p.structural(d)
	}
	w := coneReferenceWalk{ctx: ctx, cone: c, refs: p, nodes: facts.byUUID, path: map[string]bool{},
		visited: from.visited}
	for _, root := range facts.roots[from.roots:] {
		if err := w.walk(root.S, "", 1, true); err != nil {
			return factsMark{}, err
		}
	}
	through := facts.mark()
	through.visited = w.visited
	return through, nil
}