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

40
internal/modules/input/seriatim/adapter_test.go
View File

@@ -41,8 +41,8 @@ func TestParseValidMinimalTranscript(t *testing.T) {
}
first := doc.Units[0]
if first.ID != "seg-001" {
t.Fatalf("first.ID = %q, want seg-001", first.ID)
if first.ID != 1 {
t.Fatalf("first.ID = %d, want 1", first.ID)
}
if first.Kind != UnitKind {
t.Fatalf("first.Kind = %q, want %q", first.Kind, UnitKind)
@@ -86,13 +86,13 @@ func TestParseAcceptsNumericSegmentIDs(t *testing.T) {
if len(doc.Units) != 2 {
t.Fatalf("len(doc.Units) = %d, want 2", len(doc.Units))
}
if doc.Units[0].ID != "1" || doc.Units[1].ID != "2" {
t.Fatalf("unit IDs = %#v, want numeric IDs normalized to strings", []string{doc.Units[0].ID, doc.Units[1].ID})
if doc.Units[0].ID != 1 || doc.Units[1].ID != 2 {
t.Fatalf("unit IDs = %#v, want numeric IDs", []int{doc.Units[0].ID, doc.Units[1].ID})
}
ref := source.SourceRef{
SourceID: doc.ID,
StartUnitID: "1",
EndUnitID: "2",
StartUnitID: 1,
EndUnitID: 2,
}
if err := source.ValidateRef(doc, ref); err != nil {
t.Fatalf("ValidateRef() error = %v, want nil", err)
@@ -115,7 +115,7 @@ func TestParseRequestSourceIDOverridesMetadataIDs(t *testing.T) {
}
func TestParseFallbackDocumentIDIsDeterministic(t *testing.T) {
raw := []byte(`{"metadata":{},"segments":[{"id":"s1","start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."}]}`)
raw := []byte(`{"metadata":{},"segments":[{"id":1,"start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."}]}`)
first, err := New().Parse(context.Background(), contracts.ParseRequest{Raw: raw})
if err != nil {
@@ -138,7 +138,7 @@ func TestParseFallbackDocumentIDIsDeterministic(t *testing.T) {
}
func TestParseUsesMetadataSourceIDWhenMetadataIDIsAbsent(t *testing.T) {
raw := []byte(`{"metadata":{"source_id":" source-from-metadata "},"segments":[{"id":"s1","start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."}]}`)
raw := []byte(`{"metadata":{"source_id":" source-from-metadata "},"segments":[{"id":1,"start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."}]}`)
doc, err := New().Parse(context.Background(), contracts.ParseRequest{Raw: raw})
if err != nil {
@@ -203,7 +203,7 @@ func TestParseRejectsInvalidInput(t *testing.T) {
{
name: "missing segment id",
raw: validJSONWithSegment(`"start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"id", "empty"},
wantErr: []string{"id", "positive"},
},
{
name: "invalid segment id type",
@@ -212,52 +212,52 @@ func TestParseRejectsInvalidInput(t *testing.T) {
},
{
name: "whitespace segment id",
raw: validJSONWithSegment(`"id":" s1 ","start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":" 1 ","start":0,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"id", "whitespace"},
},
{
name: "empty text",
raw: validJSONWithSegment(`"id":"s1","start":0,"end":1,"speaker":"Narrator","text":" "`),
raw: validJSONWithSegment(`"id":1,"start":0,"end":1,"speaker":"Narrator","text":" "`),
wantErr: []string{"text", "empty"},
},
{
name: "missing speaker",
raw: validJSONWithSegment(`"id":"s1","start":0,"end":1,"text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":0,"end":1,"text":"Synthetic text."`),
wantErr: []string{"speaker", "empty"},
},
{
name: "missing start",
raw: validJSONWithSegment(`"id":"s1","end":1,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"start", "empty"},
},
{
name: "missing end",
raw: validJSONWithSegment(`"id":"s1","start":0,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":0,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"end", "empty"},
},
{
name: "negative start",
raw: validJSONWithSegment(`"id":"s1","start":-1,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":-1,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"start", "negative"},
},
{
name: "non-numeric end",
raw: validJSONWithSegment(`"id":"s1","start":0,"end":"late","speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":0,"end":"late","speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"segment[0]", "end", "number"},
},
{
name: "non-finite timestamp",
raw: validJSONWithSegment(`"id":"s1","start":1e10000,"end":1e10000,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":1e10000,"end":1e10000,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"start", "valid number"},
},
{
name: "end before start",
raw: validJSONWithSegment(`"id":"s1","start":2,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":2,"end":1,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"end", "start"},
},
{
name: "end before start beyond float precision",
raw: validJSONWithSegment(`"id":"s1","start":9007199254740993,"end":9007199254740992,"speaker":"Narrator","text":"Synthetic text."`),
raw: validJSONWithSegment(`"id":1,"start":9007199254740993,"end":9007199254740992,"speaker":"Narrator","text":"Synthetic text."`),
wantErr: []string{"end", "start"},
},
}
@@ -284,7 +284,7 @@ func TestParseRejectsDuplicateSegmentIDs(t *testing.T) {
if err == nil {
t.Fatal("Parse() error = nil, want duplicate ID error")
}
if !strings.Contains(err.Error(), "duplicated") || !strings.Contains(err.Error(), "seg-001") {
if !strings.Contains(err.Error(), "duplicated") || !strings.Contains(err.Error(), "1") {
t.Fatalf("Parse() error = %q, want duplicate segment context", err.Error())
}
}