eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Construct universal modules with decoded options

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-17 06:30:56 +00:00
parent ce3a07512f
commit b949e9bbc0
22 changed files with 290 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
internal/modules/generic/chunk/units/chunker_test.go
View File

@@ -44,10 +44,18 @@ func TestModuleSpecAndRegister(t *testing.T) {
if slots := chunker.ReferenceSlots(); len(slots) != 0 {
t.Fatalf("ReferenceSlots() = %#v, want none", slots)
}
configured, err := registry.BuildWithRequest(Key, pipeline.BuildRequest{Options: map[string]any{"max_units": 1}})
if err != nil {
t.Fatalf("BuildWithRequest(%q) error = %v, want nil", Key, err)
}
result, err := configured.Chunk(context.Background(), contracts.ChunkRequest{Source: testSource(2)})
if err != nil || len(result.Chunks) != 2 {
t.Fatalf("constructed chunker result = %#v, %v; want two chunks", result, err)
}
}
func TestChunkUsesDefaultsForSingleChunk(t *testing.T) {
result, err := New().Chunk(context.Background(), contracts.ChunkRequest{Source: testSource(3), Options: nil})
result, err := newChunker(t, nil).Chunk(context.Background(), contracts.ChunkRequest{Source: testSource(3)})
if err != nil {
t.Fatalf("Chunk() error = %v, want nil", err)
}
@@ -74,10 +82,7 @@ func TestChunkUsesDefaultsForSingleChunk(t *testing.T) {
}
func TestChunkExactBoundaries(t *testing.T) {
result, err := New().Chunk(context.Background(), contracts.ChunkRequest{
Source: testSource(6),
Options: map[string]any{"max_units": 2},
})
result, err := newChunker(t, map[string]any{"max_units": 2}).Chunk(context.Background(), contracts.ChunkRequest{Source: testSource(6)})
if err != nil {
t.Fatalf("Chunk() error = %v, want nil", err)
}
@@ -93,10 +98,7 @@ func TestChunkExactBoundaries(t *testing.T) {
}
func TestChunkOverlap(t *testing.T) {
result, err := New().Chunk(context.Background(), contracts.ChunkRequest{
Source: testSource(7),
Options: map[string]any{"max_units": 3, "overlap_units": 1},
})
result, err := newChunker(t, map[string]any{"max_units": 3, "overlap_units": 1}).Chunk(context.Background(), contracts.ChunkRequest{Source: testSource(7)})
if err != nil {
t.Fatalf("Chunk() error = %v, want nil", err)
}
@@ -123,19 +125,17 @@ func TestChunkRejectsInvalidOptions(t *testing.T) {
{name: "overlap negative", options: map[string]any{"overlap_units": -1}, want: "non-negative"},
{name: "overlap too large", options: map[string]any{"max_units": 2, "overlap_units": 2}, want: "less than"},
{name: "json number", options: map[string]any{"max_units": json.Number("bad")}, want: "integer"},
{name: "unknown", options: map[string]any{"unexpected": true}, want: "unknown option"},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := New().Chunk(context.Background(), contracts.ChunkRequest{
Source: testSource(3),
Options: test.options,
})
_, err := DecodeOptions(test.options)
if err == nil {
t.Fatal("Chunk() error = nil, want error")
t.Fatal("DecodeOptions() error = nil, want error")
}
if !strings.Contains(err.Error(), "generic chunker") || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Chunk() error = %q, want module context and %q", err.Error(), test.want)
t.Fatalf("DecodeOptions() error = %q, want module context and %q", err.Error(), test.want)
}
})
}
@@ -145,7 +145,7 @@ func TestChunkRejectsEmptySource(t *testing.T) {
doc := testSource(1)
doc.Units = nil
_, err := New().Chunk(context.Background(), contracts.ChunkRequest{Source: doc})
_, err := newChunker(t, nil).Chunk(context.Background(), contracts.ChunkRequest{Source: doc})
if err == nil {
t.Fatal("Chunk() error = nil, want empty source error")
}
@@ -157,10 +157,7 @@ func TestChunkRejectsEmptySource(t *testing.T) {
func TestChunkDefensivelyCopiesUnits(t *testing.T) {
doc := testSource(2)
result, err := New().Chunk(context.Background(), contracts.ChunkRequest{
Source: doc,
Options: map[string]any{"max_units": 1},
})
result, err := newChunker(t, map[string]any{"max_units": 1}).Chunk(context.Background(), contracts.ChunkRequest{Source: doc})
if err != nil {
t.Fatalf("Chunk() error = %v, want nil", err)
}
@@ -183,6 +180,15 @@ func TestChunkDefensivelyCopiesUnits(t *testing.T) {
}
}
func newChunker(t *testing.T, rawOptions map[string]any) *Chunker {
t.Helper()
options, err := DecodeOptions(rawOptions)
if err != nil {
t.Fatalf("DecodeOptions() error = %v, want nil", err)
}
return New(options)
}
func testSource(count int) *source.SourceDocument {
units := make([]source.SourceUnit, 0, count)
for i := 1; i <= count; i++ {