Add fast path for two-character patterns in FuzzyMatchV2

For two ASCII characters, rows 0 and 1 of the score matrix collapse to
scalar running state, so Phase 2 and Phase 3 fuse into one pass with no
score arrays. withPos stores the two rows for the backtrace. Up to 1.4x
on two-char queries, the most common multi-char length.

Verify both fast paths against the general algorithm with exhaustive
(every short string over a class-complete alphabet) and fuzz tests,
runnable via the new make fuzz target.
This commit is contained in:
Junegunn Choi
2026-07-27 21:19:37 +09:00
parent 232722145e
commit f779e6a4df
5 changed files with 410 additions and 3 deletions
+72
View File
@@ -241,3 +241,75 @@ func TestResultPositionsWithReusedSlab(t *testing.T) {
}
}
}
// TestFuzzyMatchV2TwoEquivalence verifies that the two-character fast path
// produces the same Result and positions as the general algorithm across
// case sensitivity, direction, and withPos, using a reused slab to surface
// any stale-data reads in the backtrace.
func TestFuzzyMatchV2TwoEquivalence(t *testing.T) {
words := []string{"src", "main", "core", "config", "parser", "render", "server",
"client", "index", "handler", "util", "list", "cache", "reader"}
exts := []string{".go", ".rb", ".py", ".md", ".c", ".txt"}
// Deterministic corpus (LCG), plus adversarial short/repeated items
corpus := []util.Chars{}
seed := uint32(12345)
next := func(n int) int { seed = seed*1664525 + 1013904223; return int(seed>>8) % n }
for i := 0; i < 4000; i++ {
depth := 2 + next(4)
s := ""
for d := 0; d < depth; d++ {
if d > 0 {
s += "/"
}
s += words[next(len(words))]
if next(5) == 0 {
s += "_" + words[next(len(words))]
}
}
s += exts[next(len(exts))]
corpus = append(corpus, util.ToChars([]byte(s)))
}
for _, s := range []string{"", "a", "ab", "aa", "aXb", "a/b", "//", "..", "abcabc",
"AaBb", "x.y.z", "a_b_c", "CoreCore", " co"} {
corpus = append(corpus, util.ToChars([]byte(s)))
}
pats := []string{"co", "ab", "aa", "//", "..", "sr", "a/", "_c", "oo", "Ab",
"z.", "b.", "1a", "ll", "re", "er", "Co"}
slab := util.MakeSlab(100*1024, 2048)
for _, cs := range []bool{false, true} {
for _, fwd := range []bool{true, false} {
for _, wp := range []bool{false, true} {
for _, p := range pats {
pattern := []rune(p)
for j := range corpus {
disableTwo = true
rg, pg := FuzzyMatchV2(cs, false, fwd, &corpus[j], pattern, wp, slab)
disableTwo = false
rt, pt := FuzzyMatchV2(cs, false, fwd, &corpus[j], pattern, wp, slab)
if rg != rt {
t.Fatalf("Result cs=%v fwd=%v wp=%v pat=%q item=%q: general %v vs two %v",
cs, fwd, wp, p, corpus[j].ToString(), rg, rt)
}
if (pg == nil) != (pt == nil) || (pg != nil && !equalInts(*pg, *pt)) {
t.Fatalf("Pos cs=%v fwd=%v wp=%v pat=%q item=%q: general %v vs two %v",
cs, fwd, wp, p, corpus[j].ToString(), pg, pt)
}
}
}
}
}
}
}
func equalInts(a, b []int) bool {
if len(a) != len(b) {
return false
}
for i := range a {
if a[i] != b[i] {
return false
}
}
return true
}