Jyotisha/frontend/src/lib/public-thinking.ts

/**
 * Sanitize text that may appear on the public thinking channel.
 *
 * English-only process narration, tool ids and UUIDs stay off the client.
 * Chinese thinking fragments are allowed through a dedicated event type,
 * never through the spoken answer.
 *
 * Filtering is sentence-buffered: stream chunks are often one or two English
 * words, so a per-chunk "drop long Latin, keep the rest" pass turns a withheld
 * sentence into word salad. Wait for `。！？\\n` or `.!?`, then decide.
 */
const CJK_RE = /[\u4e00-\u9fff]/;
const PUBLIC_THINKING_UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}/gi;
const PUBLIC_THINKING_TOOL_RE = /run-jyotish(?:-consultation)?-?|rectification-[a-z0-9-]+/gi;
const SENTENCE_TERMINATOR_RE = /[。！？\n]|[.!?]/;

function stripIds(text: string): string {
  return text
    .replace(PUBLIC_THINKING_UUID_RE, "")
    .replace(PUBLIC_THINKING_TOOL_RE, "");
}

function sanitizeCompletedSentence(sentence: string): string | null {
  const cleaned = stripIds(sentence);
  if (!cleaned.trim()) return null;
  if (!CJK_RE.test(cleaned)) return null;
  const withoutEnglishWords = cleaned
    .replace(/[A-Za-z]{4,}/g, "")
    .replace(/[ \t]{2,}/g, " ");
  const trimmed = withoutEnglishWords.trim();
  if (!trimmed) return null;
  return trimmed.slice(0, 4_000);
}

function terminatorEnd(buffer: string): number {
  const match = SENTENCE_TERMINATOR_RE.exec(buffer);
  if (!match || match.index === undefined) return -1;
  return match.index + match[0].length;
}

export function createPublicThinkingSanitizer() {
  let buffer = "";

  function releaseCompleted(flush: boolean): string {
    let released = "";
    while (buffer) {
      const end = terminatorEnd(buffer);
      if (end >= 0) {
        const sentence = buffer.slice(0, end);
        buffer = buffer.slice(end);
        const cjk = sentence.search(CJK_RE);
        const cleaned = sanitizeCompletedSentence(cjk > 0 ? sentence.slice(cjk) : sentence);
        if (cleaned) released += cleaned;
        continue;
      }
      const cjk = buffer.search(CJK_RE);
      if (cjk > 0) {
        buffer = buffer.slice(cjk);
        continue;
      }
      break;
    }
    if (flush && buffer) {
      const leftover = buffer;
      buffer = "";
      const cleaned = sanitizeCompletedSentence(leftover);
      if (cleaned) released += cleaned;
    }
    return released;
  }

  return {
    push(chunk: string): string | null {
      if (!chunk) return null;
      buffer += chunk;
      const released = releaseCompleted(false);
      return released || null;
    },
    flush(): string | null {
      const released = releaseCompleted(true);
      return released || null;
    },
  };
}

export function sanitizePublicThinkingText(text: string): string | null {
  const sanitizer = createPublicThinkingSanitizer();
  const pushed = sanitizer.push(text) ?? "";
  const flushed = sanitizer.flush() ?? "";
  const combined = `${pushed}${flushed}`;
  return combined || null;
}