lyrics-transcriber 0.41.0__py3-none-any.whl → 0.42.0__py3-none-any.whl

lyrics_transcriber/frontend/src/types.ts

@@ -1,33 +1,36 @@
 export interface Word {
     id: string
     text: string
-    start_time: number
-    end_time: number
+    start_time: number | null
+    end_time: number | null
     confidence?: number
+    created_during_correction?: boolean
 }
 
 export interface LyricsSegment {
     id: string
     text: string
     words: Word[]
-    start_time: number
-    end_time: number
+    start_time: number | null
+    end_time: number | null
 }
 
 export interface WordCorrection {
-    id: string
+    id?: string
+    handler: string
     original_word: string
     corrected_word: string
-    segment_id: string
+    segment_id?: string
     word_id: string
+    corrected_word_id: string | null
     source: string
     confidence: number
     reason: string
     alternatives: Record<string, number>
     is_deletion: boolean
-    split_index?: number
-    split_total?: number
-    reference_positions?: Record<string, string>
+    split_index?: number | null
+    split_total?: number | null
+    reference_positions?: Record<string, number>
     length: number
 }
 
@@ -40,63 +43,70 @@ export interface PhraseScore {
 
 export interface AnchorSequence {
     id: string
-    words: string[]
-    text: string
-    length: number
-    word_ids: string[]
-    reference_word_ids: Record<string, string[]>
+    transcribed_word_ids: string[]
+    transcription_position: number
+    reference_positions: Record<string, number>
+    reference_word_ids: {
+        [source: string]: string[]
+    }
     confidence: number
     phrase_score: PhraseScore
     total_score: number
 }
 
-export interface AnchorReference {
-    text: string
-    word_ids: string[]
-    confidence: number
-}
-
 export interface GapSequence {
     id: string
-    text: string
-    words: string[]
-    word_ids: string[]
-    length: number
-    corrections: WordCorrection[]
-    preceding_anchor: AnchorReference | null
-    following_anchor: AnchorReference | null
-    reference_words: {
+    transcribed_word_ids: string[]
+    transcription_position: number
+    preceding_anchor_id: string | null
+    following_anchor_id: string | null
+    reference_word_ids: {
         [source: string]: string[]
     }
 }
 
-export interface LyricsData {
-    transcribed_text: string
-    corrected_text: string
-    original_segments: LyricsSegment[]
+export interface ReferenceSource {
+    segments: LyricsSegment[]
     metadata: {
-        anchor_sequences_count: number
-        gap_sequences_count: number
-        total_words: number
-        correction_ratio: number
+        source: string
+        track_name: string | null
+        artist_names: string | null
+        album_name: string | null
+        duration_ms: number | null
+        explicit: boolean | null
+        language: string | null
+        is_synced: boolean
+        lyrics_provider: string
+        lyrics_provider_id: string
+        provider_metadata: Record<string, unknown>
     }
-    anchor_sequences: AnchorSequence[]
-    gap_sequences: GapSequence[]
-    corrected_segments: LyricsSegment[]
-    corrections_made: number
-    confidence: number
+    source: string
+}
+
+export interface CorrectionStep {
+    handler_name: string
+    affected_word_ids: string[]
+    affected_segment_ids: string[]
     corrections: WordCorrection[]
-    reference_texts: Record<string, string>
+    segments_before: LyricsSegment[]
+    segments_after: LyricsSegment[]
+    created_word_ids: string[]
+    deleted_word_ids: string[]
+}
+
+export interface CorrectionHandler {
+    id: string
+    name: string
+    description: string
+    enabled: boolean
 }
 
 export interface CorrectionData {
-    transcribed_text: string
     original_segments: LyricsSegment[]
-    reference_texts: Record<string, string>
+    reference_lyrics: Record<string, ReferenceSource>
     anchor_sequences: AnchorSequence[]
     gap_sequences: GapSequence[]
-    resized_segments?: LyricsSegment[]
-    corrected_text: string
+    resized_segments: LyricsSegment[]
     corrections_made: number
     confidence: number
     corrections: WordCorrection[]
@@ -106,13 +116,24 @@ export interface CorrectionData {
         gap_sequences_count: number
         total_words: number
         correction_ratio: number
+        audio_filepath?: string
+        audio_hash?: string
+        available_handlers?: CorrectionHandler[]
+        enabled_handlers?: string[]
     }
+    correction_steps: CorrectionStep[]
+    word_id_map: Record<string, string>
+    segment_id_map: Record<string, string>
 }
 
 export interface HighlightInfo {
-    word_ids?: string[]
-    reference_word_ids?: Record<string, string[]>
-    type: 'single' | 'gap' | 'anchor'
+    type: 'single' | 'gap' | 'anchor' | 'correction'
+    sequence?: AnchorSequence | GapSequence
+    transcribed_words: Word[]
+    reference_words?: {
+        [source: string]: Word[]
+    }
+    correction?: WordCorrection
 }
 
 export type InteractionMode = 'highlight' | 'details' | 'edit'

lyrics_transcriber/frontend/src/validation.ts

@@ -0,0 +1,132 @@
+import { z } from 'zod'
+
+// Define schemas that match our TypeScript interfaces
+const WordSchema = z.object({
+    id: z.string(),
+    text: z.string(),
+    start_time: z.number().nullable(),
+    end_time: z.number().nullable(),
+    confidence: z.number().optional(),
+    created_during_correction: z.boolean().optional()
+})
+
+const LyricsSegmentSchema = z.object({
+    id: z.string(),
+    text: z.string(),
+    words: z.array(WordSchema),
+    start_time: z.number().nullable(),
+    end_time: z.number().nullable()
+})
+
+const WordCorrectionSchema = z.object({
+    id: z.string().optional(),
+    handler: z.string(),
+    original_word: z.string(),
+    corrected_word: z.string(),
+    segment_id: z.string().optional(),
+    word_id: z.string(),
+    corrected_word_id: z.string().nullable(),
+    source: z.string(),
+    confidence: z.number(),
+    reason: z.string(),
+    alternatives: z.record(z.number()),
+    is_deletion: z.boolean(),
+    split_index: z.number().nullable().optional(),
+    split_total: z.number().nullable().optional(),
+    reference_positions: z.record(z.number()).optional(),
+    length: z.number()
+})
+
+const ReferenceSourceSchema = z.object({
+    segments: z.array(LyricsSegmentSchema),
+    metadata: z.object({
+        source: z.string(),
+        track_name: z.string().nullable(),
+        artist_names: z.string().nullable(),
+        album_name: z.string().nullable(),
+        duration_ms: z.number().nullable(),
+        explicit: z.boolean().nullable(),
+        language: z.string().nullable(),
+        is_synced: z.boolean(),
+        lyrics_provider: z.string(),
+        lyrics_provider_id: z.string(),
+        provider_metadata: z.record(z.unknown())
+    }),
+    source: z.string()
+})
+
+const PhraseScoreSchema = z.object({
+    phrase_type: z.string(),
+    natural_break_score: z.number(),
+    length_score: z.number(),
+    total_score: z.number()
+})
+
+const AnchorSequenceSchema = z.object({
+    id: z.string(),
+    transcribed_word_ids: z.array(z.string()),
+    transcription_position: z.number(),
+    reference_positions: z.record(z.number()),
+    reference_word_ids: z.record(z.array(z.string())),
+    confidence: z.number(),
+    phrase_score: PhraseScoreSchema,
+    total_score: z.number()
+})
+
+const GapSequenceSchema = z.object({
+    id: z.string(),
+    transcribed_word_ids: z.array(z.string()),
+    transcription_position: z.number(),
+    preceding_anchor_id: z.string().nullable(),
+    following_anchor_id: z.string().nullable(),
+    reference_word_ids: z.record(z.array(z.string()))
+})
+
+const CorrectionStepSchema = z.object({
+    handler_name: z.string(),
+    affected_word_ids: z.array(z.string()),
+    affected_segment_ids: z.array(z.string()),
+    corrections: z.array(WordCorrectionSchema),
+    segments_before: z.array(LyricsSegmentSchema),
+    segments_after: z.array(LyricsSegmentSchema),
+    created_word_ids: z.array(z.string()),
+    deleted_word_ids: z.array(z.string())
+})
+
+// Add new schema for correction handlers
+const CorrectionHandlerSchema = z.object({
+    id: z.string(),
+    name: z.string(),
+    description: z.string(),
+    enabled: z.boolean()
+})
+
+// Update CorrectionDataSchema to include handler information
+const CorrectionDataSchema = z.object({
+    original_segments: z.array(LyricsSegmentSchema),
+    reference_lyrics: z.record(ReferenceSourceSchema),
+    anchor_sequences: z.array(AnchorSequenceSchema),
+    gap_sequences: z.array(GapSequenceSchema),
+    resized_segments: z.array(LyricsSegmentSchema),
+    corrections_made: z.number(),
+    confidence: z.number(),
+    corrections: z.array(WordCorrectionSchema),
+    corrected_segments: z.array(LyricsSegmentSchema),
+    metadata: z.object({
+        anchor_sequences_count: z.number(),
+        gap_sequences_count: z.number(),
+        total_words: z.number(),
+        correction_ratio: z.number(),
+        audio_filepath: z.string().optional(),
+        audio_hash: z.string().optional(),
+        available_handlers: z.array(CorrectionHandlerSchema).optional(),
+        enabled_handlers: z.array(z.string()).optional()
+    }),
+    correction_steps: z.array(CorrectionStepSchema),
+    word_id_map: z.record(z.string()),
+    segment_id_map: z.record(z.string())
+})
+
+export function validateCorrectionData(data: unknown) {
+    return CorrectionDataSchema.parse(data)
+} 

lyrics_transcriber/frontend/tsconfig.tsbuildinfo

@@ -1 +1 @@
-{"root":["./src/app.tsx","./src/api.ts","./src/main.tsx","./src/types.ts","./src/vite-env.d.ts","./src/components/audioplayer.tsx","./src/components/correctionmetrics.tsx","./src/components/detailsmodal.tsx","./src/components/editmodal.tsx","./src/components/fileupload.tsx","./src/components/lyricsanalyzer.tsx","./src/components/modeselector.tsx","./src/components/referenceview.tsx","./src/components/reviewchangesmodal.tsx","./src/components/segmentdetailsmodal.tsx","./src/components/timelineeditor.tsx","./src/components/transcriptionview.tsx","./src/components/wordeditcontrols.tsx","./src/components/shared/constants.ts","./src/components/shared/styles.ts","./src/components/shared/types.ts","./src/components/shared/components/highlightedtext.tsx","./src/components/shared/components/sourceselector.tsx","./src/components/shared/components/word.tsx","./src/components/shared/hooks/usewordclick.ts","./src/components/shared/utils/initializedatawithids.tsx","./src/components/shared/utils/referencelinecalculator.ts"],"version":"5.6.3"}
+{"root":["./src/app.tsx","./src/api.ts","./src/main.tsx","./src/types.ts","./src/validation.ts","./src/vite-env.d.ts","./src/components/audioplayer.tsx","./src/components/correctionmetrics.tsx","./src/components/detailsmodal.tsx","./src/components/editmodal.tsx","./src/components/fileupload.tsx","./src/components/header.tsx","./src/components/lyricsanalyzer.tsx","./src/components/modeselector.tsx","./src/components/previewvideosection.tsx","./src/components/referenceview.tsx","./src/components/reviewchangesmodal.tsx","./src/components/segmentdetailsmodal.tsx","./src/components/timelineeditor.tsx","./src/components/transcriptionview.tsx","./src/components/wordeditcontrols.tsx","./src/components/shared/constants.ts","./src/components/shared/styles.ts","./src/components/shared/types.ts","./src/components/shared/components/highlightedtext.tsx","./src/components/shared/components/sourceselector.tsx","./src/components/shared/components/word.tsx","./src/components/shared/hooks/usewordclick.ts","./src/components/shared/utils/keyboardhandlers.ts","./src/components/shared/utils/localstorage.ts","./src/components/shared/utils/referencelinecalculator.ts","./src/components/shared/utils/segmentoperations.ts","./src/components/shared/utils/wordutils.ts"],"version":"5.6.3"}