Bugfixes and documentation cleanup for v1.0 release.
All checks were successful
ci/woodpecker/tag/release Pipeline was successful

This commit is contained in:
2026-05-01 11:30:29 -05:00
parent c9e98e14b5
commit f20f06db12
17 changed files with 332 additions and 177 deletions

View File

@@ -21,11 +21,11 @@ func TestValidateMinimalTranscriptAcceptsValidTranscript(t *testing.T) {
}
}
func TestValidateDefaultTranscriptAcceptsValidTranscript(t *testing.T) {
transcript := validDefaultTranscript()
func TestValidateIntermediateTranscriptAcceptsValidTranscript(t *testing.T) {
transcript := validIntermediateTranscript()
if err := ValidateDefaultTranscript(transcript); err != nil {
t.Fatalf("validate default transcript: %v", err)
if err := ValidateIntermediateTranscript(transcript); err != nil {
t.Fatalf("validate intermediate transcript: %v", err)
}
}
@@ -34,7 +34,7 @@ func TestValidateMinimalJSONRejectsMissingRequiredField(t *testing.T) {
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "minimal"
"output_schema": "seriatim-minimal"
}
}`))
assertErrorContains(t, err, "segments")
@@ -45,7 +45,7 @@ func TestValidateMinimalJSONRejectsWrongFieldType(t *testing.T) {
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "minimal"
"output_schema": "seriatim-minimal"
},
"segments": [
{
@@ -68,7 +68,7 @@ func TestValidateMinimalJSONRejectsUnexpectedFields(t *testing.T) {
{
name: "top-level overlap groups",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "minimal"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-minimal"},
"segments": [],
"overlap_groups": []
}`,
@@ -76,28 +76,28 @@ func TestValidateMinimalJSONRejectsUnexpectedFields(t *testing.T) {
{
name: "segment source",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "minimal"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-minimal"},
"segments": [{"id": 1, "source": "input.json", "start": 1, "end": 2, "speaker": "Alice", "text": "hello"}]
}`,
},
{
name: "segment categories",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "minimal"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-minimal"},
"segments": [{"id": 1, "start": 1, "end": 2, "speaker": "Alice", "text": "hello", "categories": ["backchannel"]}]
}`,
},
{
name: "segment derived from",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "minimal"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-minimal"},
"segments": [{"id": 1, "start": 1, "end": 2, "speaker": "Alice", "text": "hello", "derived_from": ["input.json#0"]}]
}`,
},
{
name: "segment words",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "minimal"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-minimal"},
"segments": [{"id": 1, "start": 1, "end": 2, "speaker": "Alice", "text": "hello", "words": []}]
}`,
},
@@ -111,24 +111,24 @@ func TestValidateMinimalJSONRejectsUnexpectedFields(t *testing.T) {
}
}
func TestValidateDefaultJSONRejectsMissingRequiredField(t *testing.T) {
err := ValidateDefaultJSON([]byte(`{
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "default"
}
}`))
func TestValidateIntermediateJSONRejectsMissingRequiredField(t *testing.T) {
err := ValidateIntermediateJSON([]byte(`{
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "seriatim-intermediate"
}
}`))
assertErrorContains(t, err, "segments")
}
func TestValidateDefaultJSONRejectsWrongFieldType(t *testing.T) {
err := ValidateDefaultJSON([]byte(`{
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "default"
},
func TestValidateIntermediateJSONRejectsWrongFieldType(t *testing.T) {
err := ValidateIntermediateJSON([]byte(`{
"metadata": {
"application": "seriatim",
"version": "dev",
"output_schema": "seriatim-intermediate"
},
"segments": [
{
"id": "1",
@@ -142,7 +142,7 @@ func TestValidateDefaultJSONRejectsWrongFieldType(t *testing.T) {
assertErrorContains(t, err, "id")
}
func TestValidateDefaultJSONRejectsUnexpectedFields(t *testing.T) {
func TestValidateIntermediateJSONRejectsUnexpectedFields(t *testing.T) {
tests := []struct {
name string
json string
@@ -150,7 +150,7 @@ func TestValidateDefaultJSONRejectsUnexpectedFields(t *testing.T) {
{
name: "top-level overlap groups",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "default"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-intermediate"},
"segments": [],
"overlap_groups": []
}`,
@@ -158,21 +158,21 @@ func TestValidateDefaultJSONRejectsUnexpectedFields(t *testing.T) {
{
name: "segment source",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "default"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-intermediate"},
"segments": [{"id": 1, "source": "input.json", "start": 1, "end": 2, "speaker": "Alice", "text": "hello"}]
}`,
},
{
name: "segment derived from",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "default"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-intermediate"},
"segments": [{"id": 1, "start": 1, "end": 2, "speaker": "Alice", "text": "hello", "derived_from": ["input.json#0"]}]
}`,
},
{
name: "segment words",
json: `{
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "default"},
"metadata": {"application": "seriatim", "version": "dev", "output_schema": "seriatim-intermediate"},
"segments": [{"id": 1, "start": 1, "end": 2, "speaker": "Alice", "text": "hello", "words": []}]
}`,
},
@@ -180,7 +180,7 @@ func TestValidateDefaultJSONRejectsUnexpectedFields(t *testing.T) {
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
err := ValidateDefaultJSON([]byte(test.json))
err := ValidateIntermediateJSON([]byte(test.json))
assertErrorContains(t, err, "additional properties")
})
}
@@ -267,7 +267,7 @@ func TestValidateJSONRejectsUnexpectedInternalFields(t *testing.T) {
}
}
func TestValidateDefaultTranscriptRejectsMissingOrNonSequentialIDs(t *testing.T) {
func TestValidateIntermediateTranscriptRejectsMissingOrNonSequentialIDs(t *testing.T) {
tests := []struct {
name string
ids []int
@@ -280,10 +280,10 @@ func TestValidateDefaultTranscriptRejectsMissingOrNonSequentialIDs(t *testing.T)
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
transcript := validDefaultTranscript()
transcript := validIntermediateTranscript()
transcript.Segments = transcript.Segments[:0]
for index, id := range test.ids {
transcript.Segments = append(transcript.Segments, DefaultSegment{
transcript.Segments = append(transcript.Segments, IntermediateSegment{
ID: id,
Start: float64(index),
End: float64(index) + 1,
@@ -292,18 +292,18 @@ func TestValidateDefaultTranscriptRejectsMissingOrNonSequentialIDs(t *testing.T)
})
}
err := ValidateDefaultTranscript(transcript)
err := ValidateIntermediateTranscript(transcript)
assertErrorContains(t, err, test.want)
})
}
}
func TestValidateDefaultTranscriptRejectsInvalidTiming(t *testing.T) {
transcript := validDefaultTranscript()
func TestValidateIntermediateTranscriptRejectsInvalidTiming(t *testing.T) {
transcript := validIntermediateTranscript()
transcript.Segments[0].Start = 2
transcript.Segments[0].End = 1
err := ValidateDefaultTranscript(transcript)
err := ValidateIntermediateTranscript(transcript)
assertErrorContains(t, err, "segment 0 has end")
}
@@ -411,7 +411,7 @@ func validMinimalTranscript() MinimalTranscript {
Metadata: MinimalMetadata{
Application: "seriatim",
Version: "dev",
OutputSchema: "minimal",
OutputSchema: "seriatim-minimal",
},
Segments: []MinimalSegment{
{
@@ -425,14 +425,14 @@ func validMinimalTranscript() MinimalTranscript {
}
}
func validDefaultTranscript() DefaultTranscript {
return DefaultTranscript{
Metadata: DefaultMetadata{
func validIntermediateTranscript() IntermediateTranscript {
return IntermediateTranscript{
Metadata: IntermediateMetadata{
Application: "seriatim",
Version: "dev",
OutputSchema: "default",
OutputSchema: "seriatim-intermediate",
},
Segments: []DefaultSegment{
Segments: []IntermediateSegment{
{
ID: 1,
Start: 1,