8388a50c23
Resolves issues from the review of be326aa..119f5e4. Each fix has a
regression test attached and overclaimed findings (parserEngineRules
defensive copy, runTier dead-code branch, init-vars architecture)
were intentionally not touched after re-evaluation.
Goroutine leak mitigation
- previewMaxChars dropped from 256k to 64k runes. The splitter does
not accept a context.Context, so when previewTimeout fires the
worker keeps running. Bounding input size keeps worst-case CPU
per request well under a second on commodity hardware. Sized so
10 concurrent timeouts don't pile up faster than they finish.
- Frontend MAX_CHARS lowered to match.
- Comment in handler explains the trade-off and points at the
follow-up: real cancellation needs the splitter to take a ctx.
Performance
- ApproxTokenCountFromRuneLen variant lets the preview handler
reuse a single rune-count per chunk for stats + size + token
estimation. Eliminates the previous triple []rune allocation per
chunk in the response loop.
- computeChunkSizeStats now takes []int (pre-computed rune lens)
instead of []chunker.Chunk; sumSq computed in float64 to avoid
the int*int overflow at l > ~46k.
Correctness / UX
- Preview panel sends strategy / token_limit / languages
unconditionally, mirroring the buildSubmitData convention so the
preview faithfully reflects what would happen on save.
- Empty-text returns a friendly 400 ("paste a sample…") instead of
gin's cryptic 'Field validation failed on the required tag'.
Tests
- TestSplit_DelegatesToSplitWithDiagnostics renamed to
TestSplit_AndDiagnostics_AgreeOnChunks (the post-audit refactor
made the original name a misnomer; the test still asserts the
right invariant under the new name).
- New TestSplitWithDiagnostics_ProfileSetForAuto and
TestSplitWithDiagnostics_ProfileNilForExplicit lock in the
profile-reuse contract that the preview endpoint depends on.
- New chunker_debug_test.go covers computeChunkSizeStats edge
cases (empty / single / varying / no-variance underflow) plus
PreviewChunking httptest scenarios (auto path, legacy strategy,
empty-text rejection, oversize rejection, chunk truncation with
full-set stats).
Doc cleanup
- runTier comment updated; the "stubbed in this scaffold" line was
obsolete since the heading and heuristic splitters shipped.
https://claude.ai/code/session_01XADhx6mtu2ZYW3DE9Lun6k
99 lines
3.8 KiB
Go
99 lines
3.8 KiB
Go
package chunker
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestSplitWithDiagnostics_LegacyStrategy_ReportsLegacyTier(t *testing.T) {
|
|
// Splittable input so the validator accepts the legacy output cleanly.
|
|
text := strings.Repeat("Hello world.\n\nNext paragraph here.\n\n", 50)
|
|
cfg := SplitterConfig{ChunkSize: 200, ChunkOverlap: 20, Separators: []string{"\n\n", "\n"}, Strategy: StrategyLegacy}
|
|
chunks, diag := SplitWithDiagnostics(text, cfg)
|
|
if len(chunks) == 0 {
|
|
t.Fatal("expected chunks")
|
|
}
|
|
if diag.SelectedTier != TierLegacy {
|
|
t.Errorf("expected SelectedTier=legacy, got %s", diag.SelectedTier)
|
|
}
|
|
if len(diag.TierChain) != 1 || diag.TierChain[0] != TierLegacy {
|
|
t.Errorf("expected single-tier chain [legacy], got %v", diag.TierChain)
|
|
}
|
|
if len(diag.Rejected) != 0 {
|
|
t.Errorf("expected no rejections for splittable input, got %v", diag.Rejected)
|
|
}
|
|
}
|
|
|
|
func TestSplitWithDiagnostics_AutoOnHeadingDoc_PicksHeading(t *testing.T) {
|
|
doc := strings.Repeat("# Top\nintro paragraph here.\n\n## Section A\nbody A here.\n\n## Section B\nbody B here.\n\n## Section C\nbody C here.\n\n", 1)
|
|
cfg := SplitterConfig{ChunkSize: 300, ChunkOverlap: 30, Strategy: StrategyAuto}
|
|
_, diag := SplitWithDiagnostics(doc, cfg)
|
|
if len(diag.TierChain) == 0 {
|
|
t.Fatal("expected non-empty tier chain")
|
|
}
|
|
// Heading tier should be tried first for this doc.
|
|
if diag.TierChain[0] != TierHeading {
|
|
t.Errorf("expected heading tier first, got chain %v", diag.TierChain)
|
|
}
|
|
}
|
|
|
|
func TestSplitWithDiagnostics_EmptyText(t *testing.T) {
|
|
chunks, diag := SplitWithDiagnostics("", DefaultConfig())
|
|
if chunks != nil {
|
|
t.Errorf("expected nil chunks for empty text, got %v", chunks)
|
|
}
|
|
if diag == nil {
|
|
t.Fatal("diag must never be nil")
|
|
}
|
|
}
|
|
|
|
// TestSplit_AndDiagnostics_AgreeOnChunks ensures Split (no diagnostics)
|
|
// and SplitWithDiagnostics produce the same chunk set for a given input.
|
|
// They run independent loops as of the post-audit refactor — this test
|
|
// is the regression wall against them drifting.
|
|
func TestSplit_AndDiagnostics_AgreeOnChunks(t *testing.T) {
|
|
text := "para one.\n\npara two.\n\npara three."
|
|
cfg := SplitterConfig{ChunkSize: 100, ChunkOverlap: 10}
|
|
a := Split(text, cfg)
|
|
b, diag := SplitWithDiagnostics(text, cfg)
|
|
if len(a) != len(b) {
|
|
t.Fatalf("chunk count disagrees: Split=%d Diagnostics=%d", len(a), len(b))
|
|
}
|
|
for i := range a {
|
|
if a[i].Content != b[i].Content || a[i].Start != b[i].Start || a[i].End != b[i].End {
|
|
t.Errorf("chunk %d differs:\n Split: %+v\n Diag : %+v", i, a[i], b[i])
|
|
}
|
|
}
|
|
if diag == nil {
|
|
t.Error("diagnostics must not be nil")
|
|
}
|
|
}
|
|
|
|
// TestSplitWithDiagnostics_ProfileSetForAuto verifies that auto-strategy
|
|
// returns the DocProfile that drove tier selection — required by the
|
|
// preview endpoint to avoid double-profiling.
|
|
func TestSplitWithDiagnostics_ProfileSetForAuto(t *testing.T) {
|
|
doc := "# Top\nintro.\n\n## A\nbody A.\n\n## B\nbody B."
|
|
_, diag := SplitWithDiagnostics(doc, SplitterConfig{ChunkSize: 200, Strategy: StrategyAuto})
|
|
if diag.Profile == nil {
|
|
t.Fatal("auto strategy must populate diag.Profile")
|
|
}
|
|
if diag.Profile.MdHeadingTotal == 0 {
|
|
t.Errorf("profile should have detected headings, got %+v", diag.Profile)
|
|
}
|
|
}
|
|
|
|
// TestSplitWithDiagnostics_ProfileNilForExplicit verifies the inverse:
|
|
// explicit strategies bypass profiling and leave Profile nil so the
|
|
// preview handler knows to materialize one if it needs stats.
|
|
func TestSplitWithDiagnostics_ProfileNilForExplicit(t *testing.T) {
|
|
for _, strat := range []string{StrategyHeading, StrategyHeuristic, StrategyRecursive, StrategyLegacy} {
|
|
t.Run(strat, func(t *testing.T) {
|
|
_, diag := SplitWithDiagnostics("plain text", SplitterConfig{ChunkSize: 200, Strategy: strat})
|
|
if diag.Profile != nil {
|
|
t.Errorf("strategy %q should leave Profile nil, got %+v", strat, diag.Profile)
|
|
}
|
|
})
|
|
}
|
|
}
|