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

Implement integer source units and chunk payloads

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-07 18:34:23 +00:00
parent 4f057b99ac
commit 9e3f8809b3
45 changed files with 618 additions and 451 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
internal/framework/contracts/contracts_test.go
View File

@@ -33,7 +33,7 @@ func TestFakeExtractorReturnsCandidateAndValidator(t *testing.T) {
Format: "text/plain",
Digest: "sha256:abc123",
Units: []source.SourceUnit{
{ID: "u1", Kind: "section", Text: "Source text."},
{ID: 1, Kind: "section", Text: "Source text."},
},
}
@@ -86,7 +86,7 @@ func TestFakeChunkerReturnsSourceChunks(t *testing.T) {
Format: "text/plain",
Digest: "sha256:abc123",
Units: []source.SourceUnit{
{ID: "u1", Kind: "section", Text: "Source text."},
{ID: 1, Kind: "section", Text: "Source text."},
},
}
chunker := fakeChunker{key: "generic-chunker"}
@@ -113,6 +113,12 @@ func TestFakeChunkerReturnsSourceChunks(t *testing.T) {
if chunk.Index != 0 {
t.Fatalf("SourceChunk.Index = %d, want 0", chunk.Index)
}
if chunk.StartUnitID != 1 || chunk.EndUnitID != 1 {
t.Fatalf("SourceChunk boundaries = %d-%d, want 1-1", chunk.StartUnitID, chunk.EndUnitID)
}
if chunk.MediaType != "application/json" || string(chunk.Content) != `{"units":[{"id":1,"kind":"section","text":"Source text."}]}` {
t.Fatalf("SourceChunk payload = %q %s, want JSON units", chunk.MediaType, chunk.Content)
}
if len(chunk.Units) != 1 {
t.Fatalf("len(SourceChunk.Units) = %d, want 1", len(chunk.Units))
}
@@ -125,7 +131,7 @@ func TestFakeChunkerReceivesLLMClient(t *testing.T) {
Format: "text/plain",
Digest: "sha256:abc123",
Units: []source.SourceUnit{
{ID: "u1", Kind: "section", Text: "Source text."},
{ID: 1, Kind: "section", Text: "Source text."},
},
}
client := fakeLLMClient{}
@@ -151,15 +157,19 @@ func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
Format: "text/plain",
Digest: "sha256:abc123",
Units: []source.SourceUnit{
{ID: "u1", Kind: "section", Text: "First source text."},
{ID: "u2", Kind: "section", Text: "Second source text."},
{ID: 1, Kind: "section", Text: "First source text."},
{ID: 2, Kind: "section", Text: "Second source text."},
},
}
chunk := SourceChunk{
ID: "source-1:chunk:1",
SourceID: doc.ID,
Index: 1,
Units: []source.SourceUnit{doc.Units[1]},
ID: "source-1:chunk:1",
SourceID: doc.ID,
Index: 1,
StartUnitID: 2,
EndUnitID: 2,
Content: []byte(`{"units":[{"id":2,"kind":"section","text":"Second source text."}]}`),
MediaType: "application/json",
Units: []source.SourceUnit{doc.Units[1]},
}
result, err := extractor.Extract(context.Background(), ExtractionRequest{
@@ -182,8 +192,8 @@ func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
t.Fatalf("len(SourceRefs) = %d, want 1", len(candidate.SourceRefs))
}
ref := candidate.SourceRefs[0]
if ref.StartUnitID != "u2" || ref.EndUnitID != "u2" {
t.Fatalf("SourceRef = %+v, want u2 range", ref)
if ref.StartUnitID != 2 || ref.EndUnitID != 2 {
t.Fatalf("SourceRef = %+v, want unit 2 range", ref)
}
}
@@ -365,7 +375,7 @@ func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
SourceID: "source-1",
Index: 0,
Units: []source.SourceUnit{
{ID: "u1", Kind: "section", Text: "Source text."},
{ID: 1, Kind: "section", Text: "Source text."},
},
}
merger := fakeMerger{key: "generic-merger"}
@@ -487,10 +497,14 @@ func (chunker fakeChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkRe
return ChunkResult{
Chunks: []SourceChunk{
{
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
Units: append([]source.SourceUnit(nil), req.Source.Units...),
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
StartUnitID: req.Source.Units[0].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[{"id":1,"kind":"section","text":"Source text."}]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
},
},
}, nil