mesh-controller/internal/builder/reuse.go

package builder

import (
	"context"
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"net/http"
	"os"
	"sort"
	"strconv"
	"strings"
	"time"

	"github.com/novox/mesh-controller/internal/artifacts"
	"github.com/novox/mesh-controller/internal/catalogue"
)

// One build per change (novox/hq ADR 0350).
//
// **The merge check builds what the merge would move** (§1): every artifact of every module the delivery plan
// moves, from the merged tree it checks, into the artifact store's scratch namespace — never a module's own —
// kept under a **reuse key**: the source fingerprint as the build takes it (the module's tree, its contexts' trees,
// its bases and toolchains by digest; issue 280) with the builder's own version and, for an upstream artifact, the
// image it copies. **The walk of a trunk commit takes that build** (§2): before building, it takes the reuse key
// of the trunk commit's tree the same way, and where a check build holds the same key it copies it by digest into
// the module's namespace and answers with that, building nothing. Otherwise it builds and says why (§3): no check
// built it, the key differs (naming the part), or the check build is gone; a copy that fails is said and built.
//
// **What the key names is what a fresh build could differ by.** The tree is every file the recipe and the
// compiler see; the contexts are the other repositories it reads, by tree; the bases and toolchains are what it
// stands on, by digest; the builder's version is how it is built. A build whose source does not pin it — one that
// resolves packages from the mesh's registry when it is built, or copies an upstream image named by tag — has no
// key, and is always built.

// Version is this builder's own version, as the reuse key takes it: the digest of the running executable, so any
// change to how it builds is a change of key (§1). Set once by the build seat's holder (SelfVersion); empty — no
// key, every build its own — when it cannot be said.
var Version string

// SelfVersion is the version the reuse key takes: the running executable's digest, or the version stamped at build
// when the executable cannot be read. Empty when neither says anything ("development" says nothing: every unstamped
// builder would read as one).
func SelfVersion(stamped string) string {
	if exe, err := os.Executable(); err == nil {
		if f, err := os.Open(exe); err == nil {
			defer f.Close()
			sum := sha256.New()
			if _, err := io.Copy(sum, f); err == nil {
				return "exe:sha256:" + hex.EncodeToString(sum.Sum(nil))
			}
		}
	}
	if stamped == "" || stamped == "development" {
		return ""
	}
	return stamped
}

// ScratchPrefix is the namespace a check builds into (novox/hq ADR 0239 §9, ADR 0350 §1): `scratch/<module>/<artifact>`.
// Registration refuses a reference into it; only the walk's copy, in the module's own namespace, is registered.
const ScratchPrefix = "scratch/"

// checksRepository holds one document per check that built: which builds it made, of which pull request, when.
// What the holder lets go of by (§5).
const checksRepository = ScratchPrefix + "checks"

// reuseTagPrefix names a check build's record under its module's scratch repository: `r1-<hex>`.
const reuseTagPrefix = "r1-"

// CheckBuildsKept is how long a check build is kept in the scratch namespace (§5).
const CheckBuildsKept = 7 * 24 * time.Hour

// The parts of a reuse key, as the walk names the one that differs (§3).
const (
	partModule   = "the module"
	partTree     = "the build source"
	partBases    = "a base image"
	partBuilder  = "the builder's version"
	partContext  = "a context"
	partTool     = "a toolchain"
	partUpstream = "an upstream image"
)

// reuseKey is a build's reuse key and the parts it was made from; Key empty, with why, when it has none.
type reuseKey struct {
	Key   string
	Parts map[string]string
	Why   string
}

// keyOf is the reuse key of what src says the build was made from, built by version (ADR 0350 §1).
func keyOf(src *sourceInputs, manifest catalogue.Manifest, version string) reuseKey {
	if src == nil || src.unpinned != "" || src.tree == "" {
		why := "its source does not pin the build"
		if src != nil && src.unpinned != "" {
			why = src.unpinned
		} else if src != nil && src.tree == "" {
			why = "its tree could not be named"
		}
		return reuseKey{Why: why}
	}
	if version == "" {
		return reuseKey{Why: "the builder's version cannot be said"}
	}
	parts := map[string]string{partModule: src.module, partTree: src.tree, partBuilder: version}
	var bases []string
	seen := map[string]bool{}
	for _, b := range src.bases {
		if d := referenceDigest(b); !seen[d] {
			seen[d] = true
			bases = append(bases, d)
		}
	}
	sort.Strings(bases)
	parts[partBases] = strings.Join(bases, " ")
	for a, t := range src.contexts {
		parts[partContext+" "+a] = t
	}
	for a, t := range src.toolchains {
		parts[partTool+" "+a] = t
	}
	// An upstream artifact is copied, not built: what it copies is in module.json, and so in the tree — but a tag
	// names whatever its registry says today, so only an image pinned by digest is the same image tomorrow.
	if manifest.Build != nil {
		for _, a := range manifest.Build.Artifacts {
			if a.Kind != catalogue.ArtifactUpstream {
				continue
			}
			if !strings.Contains(a.From, "@sha256:") {
				return reuseKey{Why: fmt.Sprintf("%s copies %s, named by tag, which can move", a.Name, a.From)}
			}
			parts[partUpstream+" "+a.Name] = a.From
		}
	}
	lines := make([]string, 0, len(parts))
	for k, v := range parts {
		lines = append(lines, k+"="+v)
	}
	sort.Strings(lines)
	sum := sha256.Sum256([]byte(strings.Join(lines, "\n")))
	return reuseKey{Key: "r1:" + hex.EncodeToString(sum[:]), Parts: parts}
}

// tagOf is the tag a key's record is kept under.
func tagOf(key string) string { return reuseTagPrefix + strings.TrimPrefix(key, "r1:") }

// differing names the parts of two keys that differ, in a fixed order: what the walk says when it builds (§3).
func differing(was, now map[string]string) []string {
	names := map[string]bool{}
	for k := range was {
		names[k] = true
	}
	for k := range now {
		names[k] = true
	}
	var out []string
	for k := range names {
		if was[k] != now[k] {
			out = append(out, k)
		}
	}
	sort.Strings(out)
	return out
}

// PullRef names a pull request.
type PullRef struct {
	Owner  string `json:"owner"`
	Repo   string `json:"repo"`
	Number int    `json:"number"`
}

func (p PullRef) String() string { return fmt.Sprintf("%s/%s#%d", p.Owner, p.Repo, p.Number) }

// slug is the pull request as a tag's first part: owner.repo.number, every other character a dash.
func (p PullRef) slug() string {
	clean := func(s string) string {
		return strings.Map(func(r rune) rune {
			if r >= 'a' && r <= 'z' || r >= 'A' && r <= 'Z' || r >= '0' && r <= '9' || r == '_' || r == '-' {
				return r
			}
			return '-'
		}, s)
	}
	return clean(p.Owner) + "." + clean(p.Repo) + "." + strconv.Itoa(p.Number)
}

// CheckBuild is one module a check built into the scratch namespace, kept under its reuse key (§1).
type CheckBuild struct {
	Key    string            `json:"key"`
	Module string            `json:"module"`
	Parts  map[string]string `json:"parts"`
	// Made are its artifacts, in the scratch namespace.
	Made []catalogue.Built `json:"made"`
	// Pull is the pull request checked, Head its head and Trunk the trunk commit it was merged into; Check the
	// check's ask; At when it was built.
	Pull  PullRef   `json:"pull"`
	Head  string    `json:"head,omitempty"`
	Trunk string    `json:"trunk,omitempty"`
	Check string    `json:"check"`
	At    time.Time `json:"at"`
}

// Said is the check build as the walk names it: "the check of owner/repo#n at head H (trunk T)".
func (c CheckBuild) Said() string {
	s := "the check of " + c.Pull.String()
	if c.Head != "" {
		s += " at head " + twelve(c.Head)
	}
	if c.Trunk != "" {
		s += " (merged into trunk " + twelve(c.Trunk) + ")"
	}
	return s
}

// checkIndex is one check's document under checksRepository: every build it made.
type checkIndex struct {
	Pull   PullRef      `json:"pull"`
	Check  string       `json:"check"`
	At     time.Time    `json:"at"`
	Builds []CheckBuild `json:"builds"`
}

// Scratch is where check builds are kept and taken from: the artifact store's scratch namespace (ADR 0350). The
// Registry is one; a test's is a map.
type Scratch interface {
	// Keep records a check's builds: each under its module and key, and the check's own document.
	Keep(ctx context.Context, pull PullRef, check string, at time.Time, builds []CheckBuild) error
	// Find is the check build kept under a module's key; false when none is.
	Find(ctx context.Context, module, key string) (CheckBuild, bool, error)
	// OfPulls are the check builds kept for those pull requests, newest first: what the walk names a differing
	// key from.
	OfPulls(ctx context.Context, pulls []PullRef) ([]CheckBuild, error)
	// Take copies one artifact of a check build by digest into the module's own namespace, and answers it there.
	Take(ctx context.Context, module string, made catalogue.Built) (catalogue.Built, error)
	// Forget lets go of every check build of a pull request, and Expire of every check older than the bound;
	// each answers how many checks it let go of.
	Forget(ctx context.Context, pull PullRef) (int, error)
	Expire(ctx context.Context, older time.Duration, now time.Time) (int, error)
	// Discard lets go of what builds a check could not keep made: nothing would ever find them.
	Discard(ctx context.Context, builds []CheckBuild) error
}

// scratchPublisher is a Publisher into the scratch namespace: what a check builds is never under a module's
// own name (ADR 0239 §9). A base the build stands on is copied where every build copies it.
type scratchPublisher struct{ to Publisher }

func (s scratchPublisher) PublishImage(ctx context.Context, localTag, repository string) (string, error) {
	return s.to.PublishImage(ctx, localTag, ScratchPrefix+repository)
}

func (s scratchPublisher) PublishArchive(ctx context.Context, repository string, body []byte, digest string) (string, error) {
	return s.to.PublishArchive(ctx, ScratchPrefix+repository, body, digest)
}

func (s scratchPublisher) MirrorImage(ctx context.Context, from, repository string) (string, error) {
	m, can := s.to.(Mirrorer)
	if !can {
		return "", errors.New("the artifact store here cannot copy an upstream image")
	}
	return m.MirrorImage(ctx, from, ScratchPrefix+repository)
}

func (s scratchPublisher) MirrorBase(ctx context.Context, from, repository, former string) (string, error) {
	if m, can := s.to.(BaseMirrorer); can {
		return m.MirrorBase(ctx, from, repository, former)
	}
	if m, can := s.to.(Mirrorer); can {
		return m.MirrorImage(ctx, from, repository)
	}
	return "", errors.New("the artifact store here cannot copy a base")
}

// The registry as the scratch namespace.

func (r Registry) store() artifacts.Store {
	return artifacts.Store{Address: r.Address, HTTP: r.client()}
}

const recordMedia = "application/vnd.novox.mesh.check-build.v1+json"

// Keep puts each build's record under its module's scratch repository, by key, and the check's document.
func (r Registry) Keep(ctx context.Context, pull PullRef, check string, at time.Time, builds []CheckBuild) error {
	store := r.store()
	for _, b := range builds {
		body, err := json.Marshal(b)
		if err != nil {
			return err
		}
		if _, err := store.PutTagged(ctx, ScratchPrefix+b.Module, tagOf(b.Key), recordMedia, body); err != nil {
			return fmt.Errorf("keeping %s's check build: %w", b.Module, err)
		}
	}
	body, err := json.Marshal(checkIndex{Pull: pull, Check: check, At: at, Builds: builds})
	if err != nil {
		return err
	}
	if _, err := store.PutTagged(ctx, checksRepository, pull.slug()+"."+check, recordMedia, body); err != nil {
		return fmt.Errorf("keeping which builds the check of %s made: %w", pull, err)
	}
	return nil
}

// Find reads the record kept under a module's key.
func (r Registry) Find(ctx context.Context, module, key string) (CheckBuild, bool, error) {
	body, _, err := r.store().GetTagged(ctx, ScratchPrefix+module, tagOf(key))
	if errors.Is(err, artifacts.ErrNoTag) {
		return CheckBuild{}, false, nil
	}
	if err != nil {
		return CheckBuild{}, false, err
	}
	var b CheckBuild
	if err := json.Unmarshal(body, &b); err != nil {
		return CheckBuild{}, false, fmt.Errorf("%s's check build under %s is not one: %w", module, tagOf(key), err)
	}
	if b.Key != key || b.Module != module {
		return CheckBuild{}, false, nil
	}
	return b, true, nil
}

// checks are the check documents kept, by tag; only those of the pull requests named when any are.
func (r Registry) checks(ctx context.Context, pulls []PullRef) (map[string]checkIndex, error) {
	store := r.store()
	tags, err := store.Tags(ctx, checksRepository)
	if err != nil {
		return nil, err
	}
	wanted := map[string]PullRef{}
	for _, p := range pulls {
		wanted[p.slug()+"."] = p
	}
	out := map[string]checkIndex{}
	for _, tag := range tags {
		if len(pulls) > 0 {
			match := false
			for prefix := range wanted {
				match = match || strings.HasPrefix(tag, prefix)
			}
			if !match {
				continue
			}
		}
		body, _, err := store.GetTagged(ctx, checksRepository, tag)
		if errors.Is(err, artifacts.ErrNoTag) {
			continue
		}
		if err != nil {
			return nil, err
		}
		var c checkIndex
		if err := json.Unmarshal(body, &c); err != nil {
			continue // not a document this wrote: left to nobody, said by nothing — it names no build
		}
		if len(pulls) > 0 {
			if p := wanted[c.Pull.slug()+"."]; p != c.Pull {
				continue // a slug two pull requests share: only the one named
			}
		}
		out[tag] = c
	}
	return out, nil
}

// OfPulls are the check builds of those pull requests, newest first.
func (r Registry) OfPulls(ctx context.Context, pulls []PullRef) ([]CheckBuild, error) {
	if len(pulls) == 0 {
		return nil, nil
	}
	checks, err := r.checks(ctx, pulls)
	if err != nil {
		return nil, err
	}
	var out []CheckBuild
	for _, c := range checks {
		out = append(out, c.Builds...)
	}
	sort.SliceStable(out, func(i, j int) bool { return out[i].At.After(out[j].At) })
	return out, nil
}

// Take copies one artifact of a check build into the module's namespace by digest: an image's manifests as they
// are, so the digest registered is the digest the check built; an archive's blob mounted across, and held.
func (r Registry) Take(ctx context.Context, module string, made catalogue.Built) (catalogue.Built, error) {
	repository := module + "/" + made.Name
	from := ScratchPrefix + repository
	if made.Digest != "" || strings.Contains(made.Reference, "/blobs/") {
		digest := made.Digest
		if digest == "" {
			_, digest, _ = strings.Cut(made.Reference, "/blobs/")
		}
		where := upstream{base: "http://" + r.Address, repository: from, reference: digest}
		if err := r.copyBlob(ctx, &source{client: r.client(), mountFrom: from}, where, digest, repository); err != nil {
			return catalogue.Built{}, err
		}
		size, err := r.blobSize(ctx, repository, digest)
		if err != nil {
			return catalogue.Built{}, err
		}
		if err := r.hold(ctx, repository, digest, int(size)); err != nil {
			return catalogue.Built{}, err
		}
		return catalogue.Built{Name: made.Name, Kind: made.Kind, Digest: digest, Launchers: made.Launchers,
			Reference: "http://" + r.Address + "/v2/" + repository + "/blobs/" + digest}, nil
	}
	_, digest, pinned := strings.Cut(made.Reference, "@")
	if !pinned || !strings.HasPrefix(digest, "sha256:") {
		return catalogue.Built{}, fmt.Errorf("%s's check build %s is not pinned by digest", module, made.Reference)
	}
	reference, err := r.MirrorBase(ctx, r.Address+"/"+from+"@"+digest, repository, from)
	if err != nil {
		return catalogue.Built{}, err
	}
	if !strings.HasSuffix(reference, "@"+digest) {
		return catalogue.Built{}, fmt.Errorf("%s's check build was copied as %s, not as %s", module, reference, digest)
	}
	return catalogue.Built{Name: made.Name, Kind: made.Kind, Reference: reference, Launchers: made.Launchers}, nil
}

// blobSize is the size the store says a blob has.
func (r Registry) blobSize(ctx context.Context, repository, digest string) (int64, error) {
	request, err := http.NewRequestWithContext(ctx, http.MethodHead, "http://"+r.Address+"/v2/"+repository+"/blobs/"+digest, nil)
	if err != nil {
		return 0, err
	}
	response, err := r.client().Do(request)
	if err != nil {
		return 0, err
	}
	response.Body.Close()
	if response.StatusCode != http.StatusOK || response.ContentLength < 0 {
		return 0, fmt.Errorf("%s/blobs/%s: %s", repository, digest, response.Status)
	}
	return response.ContentLength, nil
}

// Forget lets go of every check build of a pull request (§5): what each check built in the scratch namespace, the
// record under its key when it is still that check's, and the check's document.
func (r Registry) Forget(ctx context.Context, pull PullRef) (int, error) {
	all, err := r.checks(ctx, nil)
	if err != nil {
		return 0, err
	}
	mine := map[string]checkIndex{}
	for tag, c := range all {
		if c.Pull == pull {
			mine[tag] = c
		}
	}
	return r.letGo(ctx, mine, all)
}

// Expire lets go of every check older than the bound (§5).
func (r Registry) Expire(ctx context.Context, older time.Duration, now time.Time) (int, error) {
	checks, err := r.checks(ctx, nil)
	if err != nil {
		return 0, err
	}
	old := map[string]checkIndex{}
	for tag, c := range checks {
		if now.Sub(c.At) > older {
			old[tag] = c
		}
	}
	return r.letGo(ctx, old, checks)
}

// Discard lets go of builds no check document names.
func (r Registry) Discard(ctx context.Context, builds []CheckBuild) error {
	all, err := r.checks(ctx, nil)
	if err != nil {
		return err
	}
	_, err = r.letGo(ctx, map[string]checkIndex{"": {Builds: builds}}, all)
	return err
}

// letGo lets go of each check's builds, then its document; a check whose builds could not all be let go of keeps
// its document, so the next sweep asks again. **A build another check still names stays**: deletion is by digest,
// and two checks that built one digest in one repository — a check asked again, a dependent two pull requests move —
// share it; it goes with the last check that names it. all are every check kept, the ones going among them.
func (r Registry) letGo(ctx context.Context, checks, all map[string]checkIndex) (int, error) {
	store := r.store()
	stays := map[string]bool{}
	for tag, c := range all {
		if _, going := checks[tag]; going {
			continue
		}
		for _, b := range c.Builds {
			for _, m := range b.Made {
				stays[catalogue.Recorded(m.Reference)] = true
			}
		}
	}
	gone := 0
	var failed []string
	for tag, c := range checks {
		ok := true
		for _, b := range c.Builds {
			for _, m := range b.Made {
				reference := catalogue.Recorded(m.Reference)
				if path, kept := catalogue.InArtifactStore(reference); !kept || !strings.HasPrefix(path, ScratchPrefix) {
					continue // never anything outside the scratch namespace
				}
				if stays[reference] {
					continue // another check still names it
				}
				if err := store.LetGo(ctx, reference); err != nil && !errors.Is(err, artifacts.Gone) {
					ok = false
					failed = append(failed, fmt.Sprintf("%s: %v", m.Reference, err))
				}
			}
			// The record under the key, only while it is still this check's: a later check of the same key
			// replaced it, and that one is its own check's to let go of.
			if kept, found, err := r.Find(ctx, b.Module, b.Key); err == nil && found && kept.Check == c.Check {
				if err := store.DeleteTagged(ctx, ScratchPrefix+b.Module, tagOf(b.Key)); err != nil && !errors.Is(err, artifacts.Gone) {
					ok = false
					failed = append(failed, fmt.Sprintf("%s's record: %v", b.Module, err))
				}
			}
		}
		if !ok {
			continue
		}
		if tag == "" {
			gone++
			continue
		}
		if err := store.DeleteTagged(ctx, checksRepository, tag); err != nil && !errors.Is(err, artifacts.Gone) {
			failed = append(failed, fmt.Sprintf("%s: %v", tag, err))
			continue
		}
		gone++
	}
	if len(failed) > 0 {
		sort.Strings(failed)
		return gone, fmt.Errorf("not let go of: %s", strings.Join(failed, "; "))
	}
	return gone, nil
}

// Reused is what the walk took from a check instead of building (§2, §4).
type Reused struct {
	From CheckBuild
	// Made are the copies in the module's namespace: what is registered.
	Made []catalogue.Built
}

// Words is the walk's word for a module it took: "reused from <check build>", with each digest (§4).
func (r Reused) Words() string {
	var digests []string
	for _, m := range r.Made {
		d := m.Digest
		if d == "" {
			_, d, _ = strings.Cut(m.Reference, "@")
		}
		digests = append(digests, m.Name+" "+d)
	}
	return "reused from " + r.From.Said() + ": " + strings.Join(digests, ", ")
}

// NamedBuild is a build a check's verdict names (ADR 0350 §2): its module, key and each artifact's digest.
type NamedBuild struct {
	Pull    PullRef
	Check   string
	Module  string
	Key     string
	Digests map[string]string
}

// DigestOf is the digest a reference names: an image's after `@`, an archive's after `/blobs/`.
func DigestOf(reference string) string {
	if _, d, ok := strings.Cut(reference, "/blobs/"); ok {
		return d
	}
	if _, d, ok := strings.Cut(reference, "@"); ok {
		return d
	}
	return ""
}

// unnamed is why a record found under a key is not taken: no verdict of the walk's pull requests names that module,
// key and every one of its digests. Empty when one does.
func unnamed(named []NamedBuild, module, key string, found CheckBuild) string {
	for _, n := range named {
		if n.Module != module || n.Key != key || n.Check != found.Check || len(n.Digests) != len(found.Made) {
			continue
		}
		same := true
		for _, m := range found.Made {
			d := m.Digest
			if d == "" {
				d = DigestOf(m.Reference)
			}
			same = same && d != "" && n.Digests[m.Name] == d
		}
		if same {
			return ""
		}
	}
	return "a build is kept under this key, and no check verdict of the walk's pull requests names it with its " +
		"digests: not taken"
}