feat(admin): online dictionary update — upload archive, preview word diff, install & activate

Replace the dictionary hot-reload with an online update flow in the GM console (/_gm/dictionary): the operator uploads scrabble-dawg-vX.Y.Z.tar.gz, previews the per-variant words added/removed against the active dictionary, and confirms to install + activate it. Versions are immutable; in-progress games keep their pinned version while new games use the new one. - engine: DiffWords (enumerate both DAWGs, decode only the differences), OpenFinder, Registry.Finder, DictFiles; OpenWithVersions skips the .staging area. - dictadmin: hardened release-archive validation + extraction (path-traversal, symlink, oversize, entry-count rejection) and staging -> install (atomic rename). - game: active dictionary version persisted in the dictionary_state singleton (single source of truth, restored on boot), concurrency-safe accessor. - storage: BACKEND_DICT_DIR is a named volume seeded from the image (nonroot-owned), so uploaded versions persist across redeploys; the build's DICT_VERSION labels the seed and equals the resident tag (BACKEND_DICT_VERSION). - docs: ARCHITECTURE §5, FUNCTIONAL (+ru), backend README, TESTING, PRERELEASE. Tests: engine + dictadmin unit; integration upload->preview->install->activate-> restart->pin->immutability->CSRF.
2026-06-13 23:29:06 +02:00
parent 5ff07da025
commit 0f3671f42d
31 changed files with 1590 additions and 78 deletions
@@ -0,0 +1,134 @@
+package engine
+
+import (
+	"bytes"
+	"fmt"
+	"maps"
+	"path/filepath"
+	"sort"
+
+	dawg "github.com/iliadenisov/dafsa"
+)
+
+// WordDiff is the set difference between two dictionaries of one variant: the
+// words present only in the new dictionary (Added) and only in the old one
+// (Removed), decoded to characters and each sorted by the variant's alphabet
+// order. It drives the admin dictionary-update preview.
+type WordDiff struct {
+	Added   []string
+	Removed []string
+}
+
+// DictFiles returns a copy of the variant-to-committed-DAWG-filename map. It lets
+// callers outside the package (the dictionary-admin upload validation) check an
+// archive against the expected file set without sharing the engine's own map.
+func DictFiles() map[Variant]string {
+	out := make(map[Variant]string, len(dictFiles))
+	maps.Copy(out, dictFiles)
+	return out
+}
+
+// OpenFinder loads the committed DAWG of variant v from dir and returns its
+// finder. The caller owns the finder and must Close it. It backs enumeration of
+// a staged, not-yet-registered dictionary version.
+func OpenFinder(dir string, v Variant) (dawg.Finder, error) {
+	name, ok := dictFiles[v]
+	if !ok {
+		return nil, fmt.Errorf("%w: %d", ErrUnknownVariant, v)
+	}
+	path := filepath.Join(dir, name)
+	finder, err := dawg.Load(path)
+	if err != nil {
+		return nil, fmt.Errorf("engine: load %s dictionary from %s: %w", v, path, err)
+	}
+	return finder, nil
+}
+
+// Finder returns the loaded finder for the (variant, version) pair so its words
+// can be enumerated, or ErrUnknownVariant / ErrUnknownVersion when that
+// dictionary is not resident. The finder remains owned by the registry; callers
+// must not Close it.
+func (r *Registry) Finder(v Variant, version string) (dawg.Finder, error) {
+	r.mu.RLock()
+	defer r.mu.RUnlock()
+	versions, ok := r.entries[v]
+	if !ok {
+		return nil, fmt.Errorf("%w: %s", ErrUnknownVariant, v)
+	}
+	e, ok := versions[version]
+	if !ok {
+		return nil, fmt.Errorf("%w: %s/%s", ErrUnknownVersion, v, version)
+	}
+	return e.finder, nil
+}
+
+// DiffWords compares the old and new finders of variant v and returns the words
+// added and removed, decoded through v's alphabet. Both dictionaries are
+// enumerated as alphabet-index bytes and merged; only the differing words are
+// decoded, so a full-dictionary comparison does not materialise two large string
+// sets.
+func DiffWords(v Variant, old, updated dawg.Finder) (WordDiff, error) {
+	rs, ok := v.ruleset()
+	if !ok {
+		return WordDiff{}, fmt.Errorf("%w: %d", ErrUnknownVariant, v)
+	}
+	oldWords := collectWords(old)
+	newWords := collectWords(updated)
+
+	var diff WordDiff
+	i, j := 0, 0
+	for i < len(oldWords) && j < len(newWords) {
+		switch cmp := bytes.Compare(oldWords[i], newWords[j]); {
+		case cmp == 0:
+			i++
+			j++
+		case cmp < 0:
+			s, err := rs.Alphabet.Decode(oldWords[i])
+			if err != nil {
+				return WordDiff{}, fmt.Errorf("engine: decode %s removed word: %w", v, err)
+			}
+			diff.Removed = append(diff.Removed, s)
+			i++
+		default:
+			s, err := rs.Alphabet.Decode(newWords[j])
+			if err != nil {
+				return WordDiff{}, fmt.Errorf("engine: decode %s added word: %w", v, err)
+			}
+			diff.Added = append(diff.Added, s)
+			j++
+		}
+	}
+	for ; i < len(oldWords); i++ {
+		s, err := rs.Alphabet.Decode(oldWords[i])
+		if err != nil {
+			return WordDiff{}, fmt.Errorf("engine: decode %s removed word: %w", v, err)
+		}
+		diff.Removed = append(diff.Removed, s)
+	}
+	for ; j < len(newWords); j++ {
+		s, err := rs.Alphabet.Decode(newWords[j])
+		if err != nil {
+			return WordDiff{}, fmt.Errorf("engine: decode %s added word: %w", v, err)
+		}
+		diff.Added = append(diff.Added, s)
+	}
+	return diff, nil
+}
+
+// collectWords enumerates every complete word of f as a copy of its
+// alphabet-index bytes, sorted ascending. The dawg already enumerates in index
+// order; the explicit sort makes the merge in DiffWords robust to that being an
+// implementation detail.
+func collectWords(f dawg.Finder) [][]byte {
+	out := make([][]byte, 0, f.NumAdded())
+	f.EnumerateB(func(_ int, word []byte, final bool) dawg.EnumerationResult {
+		if final && len(word) > 0 {
+			cp := make([]byte, len(word))
+			copy(cp, word)
+			out = append(out, cp)
+		}
+		return dawg.Continue
+	})
+	sort.Slice(out, func(a, b int) bool { return bytes.Compare(out[a], out[b]) < 0 })
+	return out
+}
@@ -0,0 +1,134 @@
+package engine
+
+import (
+	"errors"
+	"testing"
+
+	"github.com/iliadenisov/alphabet"
+	dawg "github.com/iliadenisov/dafsa"
+)
+
+// buildFinderB builds an in-memory finder over idx from the given words, each
+// expressed as alphabet-index bytes. The words must be supplied in strictly
+// increasing alphabet-index order, as the builder requires.
+func buildFinderB(t *testing.T, idx alphabet.Indexer, words ...[]byte) dawg.Finder {
+	t.Helper()
+	b := dawg.New(idx)
+	for _, w := range words {
+		if err := b.AddB(w); err != nil {
+			t.Fatalf("addB %v: %v", w, err)
+		}
+	}
+	return b.Finish()
+}
+
+// mustDecode decodes index bytes through idx or fails the test.
+func mustDecode(t *testing.T, idx alphabet.Indexer, word []byte) string {
+	t.Helper()
+	s, err := idx.Decode(word)
+	if err != nil {
+		t.Fatalf("decode %v: %v", word, err)
+	}
+	return s
+}
+
+func equalStrings(a, b []string) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	for i := range a {
+		if a[i] != b[i] {
+			return false
+		}
+	}
+	return true
+}
+
+// TestDiffWords checks that DiffWords reports the words present only in the new
+// dictionary as added and those present only in the old one as removed, decoded
+// to characters through the variant's alphabet.
+func TestDiffWords(t *testing.T) {
+	rs, _ := VariantEnglish.ruleset()
+	idx := rs.Alphabet
+
+	old := buildFinderB(t, idx, []byte{0}, []byte{0, 1}, []byte{2})
+	defer func() { _ = old.Close() }()
+	updated := buildFinderB(t, idx, []byte{0}, []byte{2}, []byte{2, 3})
+	defer func() { _ = updated.Close() }()
+
+	diff, err := DiffWords(VariantEnglish, old, updated)
+	if err != nil {
+		t.Fatalf("DiffWords: %v", err)
+	}
+
+	wantAdded := []string{mustDecode(t, idx, []byte{2, 3})}
+	wantRemoved := []string{mustDecode(t, idx, []byte{0, 1})}
+	if !equalStrings(diff.Added, wantAdded) {
+		t.Errorf("added = %v, want %v", diff.Added, wantAdded)
+	}
+	if !equalStrings(diff.Removed, wantRemoved) {
+		t.Errorf("removed = %v, want %v", diff.Removed, wantRemoved)
+	}
+}
+
+// TestDiffWordsIdentical checks that comparing a dictionary with itself yields an
+// empty diff.
+func TestDiffWordsIdentical(t *testing.T) {
+	rs, _ := VariantEnglish.ruleset()
+	f := buildFinderB(t, rs.Alphabet, []byte{0}, []byte{1}, []byte{1, 2})
+	defer func() { _ = f.Close() }()
+
+	diff, err := DiffWords(VariantEnglish, f, f)
+	if err != nil {
+		t.Fatalf("DiffWords: %v", err)
+	}
+	if len(diff.Added) != 0 || len(diff.Removed) != 0 {
+		t.Errorf("diff = %+v, want empty", diff)
+	}
+}
+
+// TestDiffWordsUnknownVariant checks that an unrecognised variant is rejected.
+func TestDiffWordsUnknownVariant(t *testing.T) {
+	rs, _ := VariantEnglish.ruleset()
+	f := buildFinderB(t, rs.Alphabet, []byte{0})
+	defer func() { _ = f.Close() }()
+	if _, err := DiffWords(Variant(250), f, f); !errors.Is(err, ErrUnknownVariant) {
+		t.Errorf("err = %v, want ErrUnknownVariant", err)
+	}
+}
+
+// TestOpenFinder checks that OpenFinder loads a committed DAWG from a directory.
+func TestOpenFinder(t *testing.T) {
+	f, err := OpenFinder(testDictDir(), VariantEnglish)
+	if err != nil {
+		t.Fatalf("OpenFinder: %v", err)
+	}
+	defer func() { _ = f.Close() }()
+	if f.NumAdded() == 0 {
+		t.Error("english dictionary is empty")
+	}
+}
+
+// TestRegistryFinder checks that Finder returns the resident finder for a pair
+// and the right sentinel when the version is absent.
+func TestRegistryFinder(t *testing.T) {
+	if _, err := testReg.Finder(VariantEnglish, testVersion); err != nil {
+		t.Errorf("Finder(scrabble_en, %q): %v", testVersion, err)
+	}
+	if _, err := testReg.Finder(VariantEnglish, "absent"); !errors.Is(err, ErrUnknownVersion) {
+		t.Errorf("Finder absent version err = %v, want ErrUnknownVersion", err)
+	}
+}
+
+// TestDictFiles checks that DictFiles exposes the variant filename map as a copy
+// the caller cannot use to mutate the engine's own map.
+func TestDictFiles(t *testing.T) {
+	files := DictFiles()
+	if len(files) != len(Variants()) {
+		t.Fatalf("DictFiles has %d entries, want %d", len(files), len(Variants()))
+	}
+	files[VariantEnglish] = "tampered"
+	if again := DictFiles(); again[VariantEnglish] == "tampered" {
+		t.Error("DictFiles returned a shared map; mutating it changed the engine's map")
+	}
+}
@@ -5,6 +5,7 @@ import (
 	"os"
 	"path/filepath"
 	"sort"
+	"strings"
 	"sync"

 	dawg "github.com/iliadenisov/dafsa"
@@ -83,7 +84,9 @@ func OpenWithVersions(dir, bootVersion string) (*Registry, error) {
 		return nil, fmt.Errorf("engine: scan dictionary dir %s: %w", dir, err)
 	}
 	for _, e := range entries {
-		if !e.IsDir() || e.Name() == bootVersion {
+		// Skip non-directories, the boot version (already loaded as the flat dir)
+		// and dot-prefixed directories (the upload staging area, dir/.staging/).
+		if !e.IsDir() || e.Name() == bootVersion || strings.HasPrefix(e.Name(), ".") {
 			continue
 		}
 		if _, err := r.LoadAvailable(filepath.Join(dir, e.Name()), e.Name()); err != nil {
@@ -91,6 +91,27 @@ func TestOpenWithVersionsScansSubdirs(t *testing.T) {
 	}
 }

+// TestOpenWithVersionsSkipsDotDirs verifies the boot scan ignores dot-prefixed
+// subdirectories (the upload staging area), so a half-extracted archive there
+// never becomes a resident version.
+func TestOpenWithVersionsSkipsDotDirs(t *testing.T) {
+	dir := t.TempDir()
+	for _, v := range Variants() {
+		copyDawg(t, testDictDir(), dir, v)
+	}
+	copyDawg(t, testDictDir(), filepath.Join(dir, ".staging"), VariantEnglish)
+
+	reg, err := OpenWithVersions(dir, "v1")
+	if err != nil {
+		t.Fatalf("open with versions: %v", err)
+	}
+	defer func() { _ = reg.Close() }()
+
+	if got := reg.Versions(VariantEnglish); len(got) != 1 || got[0] != "v1" {
+		t.Errorf("scrabble_en versions = %v, want only [v1] (.staging skipped)", got)
+	}
+}
+
 // TestReloadRegistersNewVersion verifies Load adds a second version to a variant
 // already resident, moves the latest pointer and keeps the earlier version.
 func TestReloadRegistersNewVersion(t *testing.T) {