Bugfixes and documentation cleanup for v1.0 release.
All checks were successful
ci/woodpecker/tag/release Pipeline was successful
All checks were successful
ci/woodpecker/tag/release Pipeline was successful
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"$id": "https://gitea.maximumdirect.net/eric/seriatim/schema/output.schema.json",
|
||||
"$id": "https://gitea.maximumdirect.net/eric/seriatim/schema/full-output.schema.json",
|
||||
"title": "seriatim full output transcript",
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"$id": "https://gitea.maximumdirect.net/eric/seriatim/schema/default-output.schema.json",
|
||||
"title": "seriatim default output transcript",
|
||||
"$id": "https://gitea.maximumdirect.net/eric/seriatim/schema/intermediate-output.schema.json",
|
||||
"title": "seriatim intermediate output transcript",
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"required": ["metadata", "segments"],
|
||||
@@ -13,7 +13,7 @@
|
||||
"properties": {
|
||||
"application": { "type": "string" },
|
||||
"version": { "type": "string" },
|
||||
"output_schema": { "type": "string", "const": "default" }
|
||||
"output_schema": { "type": "string", "const": "seriatim-intermediate" }
|
||||
}
|
||||
},
|
||||
"segments": {
|
||||
@@ -13,7 +13,7 @@
|
||||
"properties": {
|
||||
"application": { "type": "string" },
|
||||
"version": { "type": "string" },
|
||||
"output_schema": { "type": "string", "const": "minimal" }
|
||||
"output_schema": { "type": "string", "const": "seriatim-minimal" }
|
||||
}
|
||||
},
|
||||
"segments": {
|
||||
|
||||
@@ -14,9 +14,9 @@ import (
|
||||
var schemaFS embed.FS
|
||||
|
||||
const (
|
||||
outputSchemaPath = "output.schema.json"
|
||||
defaultOutputSchemaPath = "default-output.schema.json"
|
||||
minimalOutputSchemaPath = "minimal-output.schema.json"
|
||||
fullOutputSchemaPath = "full-output.schema.json"
|
||||
intermediateOutputSchemaPath = "intermediate-output.schema.json"
|
||||
minimalOutputSchemaPath = "minimal-output.schema.json"
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -32,10 +32,10 @@ type Transcript struct {
|
||||
OverlapGroups []OverlapGroup `json:"overlap_groups"`
|
||||
}
|
||||
|
||||
// DefaultTranscript is seriatim's default public JSON output contract.
|
||||
type DefaultTranscript struct {
|
||||
Metadata DefaultMetadata `json:"metadata"`
|
||||
Segments []DefaultSegment `json:"segments"`
|
||||
// IntermediateTranscript is seriatim's intermediate public JSON output contract.
|
||||
type IntermediateTranscript struct {
|
||||
Metadata IntermediateMetadata `json:"metadata"`
|
||||
Segments []IntermediateSegment `json:"segments"`
|
||||
}
|
||||
|
||||
// MinimalTranscript is seriatim's compact public JSON output contract.
|
||||
@@ -55,8 +55,8 @@ type Metadata struct {
|
||||
OutputModules []string `json:"output_modules"`
|
||||
}
|
||||
|
||||
// DefaultMetadata records default artifact identity.
|
||||
type DefaultMetadata struct {
|
||||
// IntermediateMetadata records intermediate artifact identity.
|
||||
type IntermediateMetadata struct {
|
||||
Application string `json:"application"`
|
||||
Version string `json:"version"`
|
||||
OutputSchema string `json:"output_schema"`
|
||||
@@ -84,9 +84,9 @@ type Segment struct {
|
||||
OverlapGroupID int `json:"overlap_group_id,omitempty"`
|
||||
}
|
||||
|
||||
// DefaultSegment is the compact public transcript segment shape with
|
||||
// IntermediateSegment is the compact public transcript segment shape with
|
||||
// categories.
|
||||
type DefaultSegment struct {
|
||||
type IntermediateSegment struct {
|
||||
ID int `json:"id"`
|
||||
Start float64 `json:"start"`
|
||||
End float64 `json:"end"`
|
||||
@@ -115,7 +115,7 @@ type OverlapGroup struct {
|
||||
Resolution string `json:"resolution"`
|
||||
}
|
||||
|
||||
// ValidateTranscript validates a typed transcript against the public JSON
|
||||
// ValidateTranscript validates a full transcript against the public JSON
|
||||
// schema and seriatim-specific semantic rules.
|
||||
func ValidateTranscript(transcript Transcript) error {
|
||||
if err := validateSemantics(transcript); err != nil {
|
||||
@@ -129,18 +129,18 @@ func ValidateTranscript(transcript Transcript) error {
|
||||
return ValidateJSON(data)
|
||||
}
|
||||
|
||||
// ValidateDefaultTranscript validates the default transcript against the
|
||||
// default JSON schema and seriatim-specific semantic rules.
|
||||
func ValidateDefaultTranscript(transcript DefaultTranscript) error {
|
||||
if err := validateDefaultSemantics(transcript); err != nil {
|
||||
// ValidateIntermediateTranscript validates the intermediate transcript against
|
||||
// the intermediate JSON schema and seriatim-specific semantic rules.
|
||||
func ValidateIntermediateTranscript(transcript IntermediateTranscript) error {
|
||||
if err := validateIntermediateSemantics(transcript); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
data, err := json.Marshal(transcript)
|
||||
if err != nil {
|
||||
return fmt.Errorf("marshal default transcript for schema validation: %w", err)
|
||||
return fmt.Errorf("marshal intermediate transcript for schema validation: %w", err)
|
||||
}
|
||||
return ValidateDefaultJSON(data)
|
||||
return ValidateIntermediateJSON(data)
|
||||
}
|
||||
|
||||
// ValidateMinimalTranscript validates a minimal transcript against the minimal
|
||||
@@ -159,13 +159,13 @@ func ValidateMinimalTranscript(transcript MinimalTranscript) error {
|
||||
|
||||
// ValidateJSON validates serialized output JSON against the public schema.
|
||||
func ValidateJSON(data []byte) error {
|
||||
return validateJSONWithSchema(data, outputSchemaPath)
|
||||
return validateJSONWithSchema(data, fullOutputSchemaPath)
|
||||
}
|
||||
|
||||
// ValidateDefaultJSON validates serialized default output JSON against the
|
||||
// default public schema.
|
||||
func ValidateDefaultJSON(data []byte) error {
|
||||
return validateJSONWithSchema(data, defaultOutputSchemaPath)
|
||||
// ValidateIntermediateJSON validates serialized intermediate output JSON
|
||||
// against the intermediate public schema.
|
||||
func ValidateIntermediateJSON(data []byte) error {
|
||||
return validateJSONWithSchema(data, intermediateOutputSchemaPath)
|
||||
}
|
||||
|
||||
// ValidateMinimalJSON validates serialized minimal output JSON against the
|
||||
@@ -245,7 +245,7 @@ func validateSemantics(transcript Transcript) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateDefaultSemantics(transcript DefaultTranscript) error {
|
||||
func validateIntermediateSemantics(transcript IntermediateTranscript) error {
|
||||
for index, segment := range transcript.Segments {
|
||||
wantID := index + 1
|
||||
if segment.ID != wantID {
|
||||
|
||||
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user