Reduce letter folds to a fixed point in gen_folds.py
CI / ci (push) Successful in 1m32s
CI / ci (pull_request) Successful in 1m33s

A fold result could itself be foldable: ǿ folded to ø and ǽ to æ, while
the canonically equivalent ø+U+0301 and æ+U+0301 reached o and ae.
Normalize writes a result without folding it again, so the generator now
folds every result letter by letter until it settles (and fails if it does
not), making the committed table fully reduced. TestLetterFoldsFullyReduced
pins that, and the canonical-equivalence tests now cover ǿ and ǽ through
Normalize, Similar and Deduper.IsDuplicate.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-05 09:07:02 -04:00
co-authored by Claude Opus 5.5
parent 7729488cde
commit d2d5e9c742
3 changed files with 48 additions and 9 deletions
+24 -1
View File
@@ -1,6 +1,9 @@
package harness
import "testing"
import (
"testing"
"unicode"
)
func TestNormalize(t *testing.T) {
tests := []struct {
@@ -48,6 +51,8 @@ func TestNormalizeCanonicalEquivalence(t *testing.T) {
{"Cơm Tấm", "Co\u031bm Ta\u0302\u0301m", "com tam"},
{"Ẓaʿtar Ȟash", "Z\u0323aʿtar H\u030cash", "zaʿtar hash"},
{"Smǫrrebrød", "Smo\u0328rrebrød", "smorrebrod"},
{"Smǿrrebrǿd", "Smø\u0301rrebrø\u0301d", "smorrebrod"}, // ǿ folds through ø
{"Ǽbleskiver", "Æ\u0301bleskiver", "aebleskiver"}, // ǽ folds through æ
}
for _, tt := range tests {
c, d := Normalize(tt.composed), Normalize(tt.decomposed)
@@ -58,6 +63,24 @@ func TestNormalizeCanonicalEquivalence(t *testing.T) {
if !Similar(tt.composed, tt.decomposed) {
t.Errorf("Similar(%q, %+q) = false, want true", tt.composed, tt.decomposed)
}
dedupe := NewDeduper(DedupeSources{Regulars: []string{tt.decomposed}})
if !dedupe.IsDuplicate(tt.composed) {
t.Errorf("IsDuplicate(%q) over %+q = false, want true", tt.composed, tt.decomposed)
}
}
}
// TestLetterFoldsFullyReduced checks that every fold result is final:
// Normalize writes a result without folding it again, so a result that
// still holds a foldable letter, a combining mark or an upper-case letter
// would split canonically equivalent spellings (ǿ -> ø instead of o).
func TestLetterFoldsFullyReduced(t *testing.T) {
for r, folded := range letterFolds {
for _, c := range folded {
if letterFolds[c] != "" || unicode.Is(unicode.Mn, c) || unicode.ToLower(c) != c {
t.Errorf("letterFolds[%U] = %q holds %U, which Normalize would change", r, folded, c)
}
}
}
}