oomi-ai 0.2.49 → 0.3.0

package/lib/spokenMetadata.js

@@ -7,66 +7,66 @@ const ELLIPSIS_PLACEHOLDER = '__OOMI_ELLIPSIS__';
 function stripAvatarCommandTags(text) {
   return text.replace(/\[(anim|animation|face|expression|emotion|gesture|look|gaze):[^\]]+\]/gi, ' ');
 }
-
-function clampInteger(value, fallback, { min = 1, max = Number.MAX_SAFE_INTEGER } = {}) {
-  if (typeof value !== 'number' || !Number.isFinite(value)) return fallback;
-  const normalized = Math.floor(value);
-  if (normalized < min) return fallback;
-  if (normalized > max) return max;
-  return normalized;
-}
-
-const BOUNDED_LANGUAGE_TYPES = new Set([
-  'Auto',
-  'Chinese',
-  'English',
-  'German',
-  'Italian',
-  'Portuguese',
-  'Spanish',
-  'Japanese',
-  'Korean',
-  'French',
-  'Russian',
-]);
-
-const BOUNDED_PACE_VALUES = new Set(['very_slow', 'slow', 'medium', 'medium_fast', 'fast']);
-const BOUNDED_PITCH_VALUES = new Set(['low', 'slightly_low', 'neutral', 'slightly_high', 'high']);
-const BOUNDED_ENERGY_VALUES = new Set(['soft', 'calm', 'warm', 'bright', 'intense']);
-const BOUNDED_VOLUME_VALUES = new Set(['soft', 'normal', 'projected']);
-
-function inferSpokenLanguage(text) {
-  const normalized = trimString(text);
-  if (!normalized) return 'English';
-  return 'English';
-}
-
+
+function clampInteger(value, fallback, { min = 1, max = Number.MAX_SAFE_INTEGER } = {}) {
+  if (typeof value !== 'number' || !Number.isFinite(value)) return fallback;
+  const normalized = Math.floor(value);
+  if (normalized < min) return fallback;
+  if (normalized > max) return max;
+  return normalized;
+}
+
+const BOUNDED_LANGUAGE_TYPES = new Set([
+  'Auto',
+  'Chinese',
+  'English',
+  'German',
+  'Italian',
+  'Portuguese',
+  'Spanish',
+  'Japanese',
+  'Korean',
+  'French',
+  'Russian',
+]);
+
+const BOUNDED_PACE_VALUES = new Set(['very_slow', 'slow', 'medium', 'medium_fast', 'fast']);
+const BOUNDED_PITCH_VALUES = new Set(['low', 'slightly_low', 'neutral', 'slightly_high', 'high']);
+const BOUNDED_ENERGY_VALUES = new Set(['soft', 'calm', 'warm', 'bright', 'intense']);
+const BOUNDED_VOLUME_VALUES = new Set(['soft', 'normal', 'projected']);
+
+function inferSpokenLanguage(text) {
+  const normalized = trimString(text);
+  if (!normalized) return 'English';
+  return 'English';
+}
+
 function normalizeSpokenSegment(segment) {
   if (!segment || typeof segment !== 'object' || Array.isArray(segment)) return null;
 
   const text = normalizeSpeechText(trimString(segment.text));
   if (!text) return null;
-
-  const normalized = { text };
-  const pace = trimString(segment.pace);
-  const pitch = trimString(segment.pitch);
-  const energy = trimString(segment.energy);
-  const volume = trimString(segment.volume);
-  const pauseAfterMs = clampInteger(segment.pause_after_ms, 0, { min: 0, max: 1200 });
-
-  if (BOUNDED_PACE_VALUES.has(pace)) normalized.pace = pace;
-  if (BOUNDED_PITCH_VALUES.has(pitch)) normalized.pitch = pitch;
-  if (BOUNDED_ENERGY_VALUES.has(energy)) normalized.energy = energy;
-  if (BOUNDED_VOLUME_VALUES.has(volume)) normalized.volume = volume;
-  normalized.pause_after_ms = pauseAfterMs;
-
-  return normalized;
-}
-
-function stripEmoji(text) {
-  return text.replace(/[\uFE0E\uFE0F]/g, '').replace(/\p{Extended_Pictographic}|\p{Emoji_Presentation}/gu, '');
-}
-
+
+  const normalized = { text };
+  const pace = trimString(segment.pace);
+  const pitch = trimString(segment.pitch);
+  const energy = trimString(segment.energy);
+  const volume = trimString(segment.volume);
+  const pauseAfterMs = clampInteger(segment.pause_after_ms, 0, { min: 0, max: 1200 });
+
+  if (BOUNDED_PACE_VALUES.has(pace)) normalized.pace = pace;
+  if (BOUNDED_PITCH_VALUES.has(pitch)) normalized.pitch = pitch;
+  if (BOUNDED_ENERGY_VALUES.has(energy)) normalized.energy = energy;
+  if (BOUNDED_VOLUME_VALUES.has(volume)) normalized.volume = volume;
+  normalized.pause_after_ms = pauseAfterMs;
+
+  return normalized;
+}
+
+function stripEmoji(text) {
+  return text.replace(/[\uFE0E\uFE0F]/g, '').replace(/\p{Extended_Pictographic}|\p{Emoji_Presentation}/gu, '');
+}
+
 function normalizeSpeechText(text) {
   return stripEmoji(stripAvatarCommandTags(text))
     .replace(/\*\*(.*?)\*\*/g, '$1')
@@ -85,7 +85,7 @@ function normalizeSpeechText(text) {
     .replace(/\s+/g, ' ')
     .trim();
 }
-
+
 function splitSpeechSegments(text) {
   const normalized = normalizeSpeechText(text);
   if (!normalized) return [];
@@ -94,14 +94,14 @@ function splitSpeechSegments(text) {
     .split(/(?<=[.!?])\s+|\n+/)
     .map((segment) => segment.trim())
     .filter(Boolean);
-
-  const segments = [];
-  for (const segment of baseSegments) {
-    if (segment.length <= 96) {
-      segments.push(segment);
-      continue;
-    }
-
+
+  const segments = [];
+  for (const segment of baseSegments) {
+    if (segment.length <= 96) {
+      segments.push(segment);
+      continue;
+    }
+
     const clauseParts = segment
       .split(/(?<=[,;:])\s+/)
       .map((part) => part.trim())
@@ -113,15 +113,15 @@ function splitSpeechSegments(text) {
       }
       continue;
     }
-
-    segments.push(segment);
-  }
-
-  if (segments.length <= 5) return segments;
-
-  return [...segments.slice(0, 4), segments.slice(4).join(' ').trim()];
-}
-
+
+    segments.push(segment);
+  }
+
+  if (segments.length <= 5) return segments;
+
+  return [...segments.slice(0, 4), segments.slice(4).join(' ').trim()];
+}
+
 function inferSegmentStyle(segmentText, index, totalSegments) {
   const normalized = segmentText.toLowerCase();
   const greeting = /^(hey|hi|hello|yo)\b/.test(normalized);
@@ -151,9 +151,9 @@ function inferSegmentStyle(segmentText, index, totalSegments) {
       pause_after_ms: 0,
     };
   }
-
-  if (exclamatory) {
-    return {
+
+  if (exclamatory) {
+    return {
       pace: 'medium_fast',
       pitch: 'slightly_high',
       energy: 'bright',
@@ -178,75 +178,75 @@ function inferSegmentStyle(segmentText, index, totalSegments) {
     energy: 'warm',
     volume: 'normal',
     pause_after_ms: index < totalSegments - 1 ? 180 : 0,
-  };
-}
-
-function synthesizeSpokenSegments(text) {
-  const language = inferSpokenLanguage(text);
-  const rawSegments = splitSpeechSegments(text);
-  if (rawSegments.length === 0) return null;
-
-  const segments = rawSegments.map((segmentText, index) => ({
-    text: segmentText,
-    ...inferSegmentStyle(segmentText, index, rawSegments.length),
-  }));
-
-  return {
-    language,
-    segments,
-  };
-}
-
+  };
+}
+
+function synthesizeSpokenSegments(text) {
+  const language = inferSpokenLanguage(text);
+  const rawSegments = splitSpeechSegments(text);
+  if (rawSegments.length === 0) return null;
+
+  const segments = rawSegments.map((segmentText, index) => ({
+    text: segmentText,
+    ...inferSegmentStyle(segmentText, index, rawSegments.length),
+  }));
+
+  return {
+    language,
+    segments,
+  };
+}
+
 function normalizeSpokenMetadata(spoken) {
   if (!spoken || typeof spoken !== 'object' || Array.isArray(spoken)) return null;
 
   const text = normalizeSpeechText(trimString(spoken.text));
   if (!text) return null;
-
-  const normalized = { text };
-  const language = trimString(spoken.language);
-  if (BOUNDED_LANGUAGE_TYPES.has(language)) {
-    normalized.language = language;
-  }
-
-  const explicitSegments =
-    Array.isArray(spoken.segments)
-      ? spoken.segments.map((segment) => normalizeSpokenSegment(segment)).filter(Boolean)
-      : [];
-  if (explicitSegments.length > 0) {
-    normalized.segments = explicitSegments;
-  }
-
-  const instructions = trimString(spoken.instructions);
-  if (instructions) normalized.instructions = instructions;
-  if (spoken.style && typeof spoken.style === 'object' && !Array.isArray(spoken.style)) {
-    normalized.style = spoken.style;
-  }
-
-  const fallbackSegments = synthesizeSpokenSegments(text);
-  if (!normalized.language && fallbackSegments?.language) {
-    normalized.language = fallbackSegments.language;
-  }
-  if (!normalized.segments && fallbackSegments?.segments?.length) {
-    normalized.segments = fallbackSegments.segments;
-  }
-
-  return normalized;
-}
-
+
+  const normalized = { text };
+  const language = trimString(spoken.language);
+  if (BOUNDED_LANGUAGE_TYPES.has(language)) {
+    normalized.language = language;
+  }
+
+  const explicitSegments =
+    Array.isArray(spoken.segments)
+      ? spoken.segments.map((segment) => normalizeSpokenSegment(segment)).filter(Boolean)
+      : [];
+  if (explicitSegments.length > 0) {
+    normalized.segments = explicitSegments;
+  }
+
+  const instructions = trimString(spoken.instructions);
+  if (instructions) normalized.instructions = instructions;
+  if (spoken.style && typeof spoken.style === 'object' && !Array.isArray(spoken.style)) {
+    normalized.style = spoken.style;
+  }
+
+  const fallbackSegments = synthesizeSpokenSegments(text);
+  if (!normalized.language && fallbackSegments?.language) {
+    normalized.language = fallbackSegments.language;
+  }
+  if (!normalized.segments && fallbackSegments?.segments?.length) {
+    normalized.segments = fallbackSegments.segments;
+  }
+
+  return normalized;
+}
+
 function inferSpokenMetadataFromContent(content) {
   const text = normalizeSpeechText(trimString(content));
   if (!text) return null;
   const synthesized = synthesizeSpokenSegments(text);
-
-  const normalized = text.toLowerCase();
-  const upbeat =
-    /!/.test(text) ||
-    /\b(hell yeah|awesome|amazing|great|stoked|love|glad|perfect|nice|cool)\b/.test(normalized);
-  const gentle =
-    /\b(sorry|gentle|softly|careful|reassuring|calm|okay|it'?s okay|i know)\b/.test(normalized);
-  const curious = /\?/.test(text);
-
+
+  const normalized = text.toLowerCase();
+  const upbeat =
+    /!/.test(text) ||
+    /\b(hell yeah|awesome|amazing|great|stoked|love|glad|perfect|nice|cool)\b/.test(normalized);
+  const gentle =
+    /\b(sorry|gentle|softly|careful|reassuring|calm|okay|it'?s okay|i know)\b/.test(normalized);
+  const curious = /\?/.test(text);
+
   if (upbeat) {
     return normalizeSpokenMetadata({
       text,
@@ -285,7 +285,7 @@ function inferSpokenMetadataFromContent(content) {
     style: { emotion: 'neutral', energy: 'medium' },
   });
 }
-
+
 export {
   inferSpokenMetadataFromContent,
   normalizeSpokenMetadata,