Lumotia/src/lib/utils/frontmatter.ts

// Transcript frontmatter + auto-tag derivation.
//
// A transcript's "frontmatter" is a flat object of metadata that can be
// exported as YAML for Obsidian or other Markdown consumers. Auto-tags are
// derived deterministically from existing fields (date, duration, source,
// text length) so they stay in sync without migration.
//
// Storage model:
//   - Source of truth is the existing transcript fields (id, title, date,
//     duration, source, text, segments).
//   - Manual tags live on `item.manualTags: string[]`.
//   - Auto-tags are never stored — derived on demand.

const DURATION_BUCKETS = [
  { max: 60, tag: "duration:short" },      // < 1 minute
  { max: 300, tag: "duration:medium" },    // < 5 minutes
  { max: 1800, tag: "duration:long" },     // < 30 minutes
  { max: Infinity, tag: "duration:very-long" },
];

const WORD_BUCKETS = [
  { max: 50, tag: "words:short" },
  { max: 300, tag: "words:medium" },
  { max: 1500, tag: "words:long" },
  { max: Infinity, tag: "words:very-long" },
];

function durationTag(seconds: number): string | null {
  if (!Number.isFinite(seconds) || seconds <= 0) return null;
  return DURATION_BUCKETS.find((b) => seconds < b.max)?.tag ?? null;
}

function wordCountTag(text: string): string | null {
  if (!text || typeof text !== "string") return null;
  const count = text.trim().split(/\s+/).filter(Boolean).length;
  return WORD_BUCKETS.find((b) => count < b.max)?.tag ?? null;
}

// Resolve time-of-day bucket from an ISO date or a legacy string like
// "19/04/2026, 11:37:23". Thresholds are fixed and local to the user's
// machine — hour 6-11 morning, 12-17 afternoon, 18-21 evening, else night.
function timeOfDayTag(dateStr: string): string | null {
  if (!dateStr) return null;
  let ts = Date.parse(dateStr);
  if (Number.isNaN(ts)) {
    // Try DD/MM/YYYY, HH:MM:SS (UK local format used by Kon history rows).
    const match = String(dateStr).match(
      /(\d{1,2})\/(\d{1,2})\/(\d{4})[,\s]+(\d{1,2}):(\d{2})(?::(\d{2}))?/,
    );
    if (!match) return null;
    const [, dd, mm, yyyy, hh, min, ss] = match;
    const d = new Date(
      Number(yyyy), Number(mm) - 1, Number(dd),
      Number(hh), Number(min), Number(ss || 0),
    );
    ts = d.getTime();
  }
  const hour = new Date(ts).getHours();
  if (hour >= 6 && hour < 12) return "time:morning";
  if (hour >= 12 && hour < 18) return "time:afternoon";
  if (hour >= 18 && hour < 22) return "time:evening";
  return "time:night";
}

function sourceTag(source: string): string | null {
  if (!source) return null;
  const s = String(source).toLowerCase();
  if (s.includes("file")) return "source:file";
  if (s.includes("live") || s.includes("mic")) return "source:live";
  return `source:${s.replace(/[^a-z0-9-]+/g, "-").replace(/^-|-$/g, "")}`;
}

// Returns tags to display as chips. Intentionally empty by default: the
// metadata these tags used to encode (duration, date, source, starred) is
// already shown elsewhere in the History row, so chips would duplicate
// information and add cognitive load without improving retrieval. The
// function is kept as a hook for one future AI-derived content tag
// (`topic:*`) once kon-llm wires up real llama-cpp-2 in Phase 3.
export function deriveAutoTags(_item: TranscriptEntry): string[] {
  return [];
}

export function normaliseTag(raw: string): string {
  return String(raw || "").trim().toLowerCase().replace(/\s+/g, "-");
}

// Build the flat frontmatter object that represents a transcript's metadata.
// Shown in the expanded History row and serialised when exporting to .md.
export function buildFrontmatter(item: TranscriptEntry | null) {
  if (!item) return {};
  const auto = deriveAutoTags(item);
  const manual = Array.isArray(item.manualTags) ? item.manualTags : [];
  const llm = Array.isArray(item.llmTags) ? item.llmTags : [];
  const tags = Array.from(new Set([
    ...auto,
    ...manual.map(normaliseTag),
    ...llm.map(normaliseTag),
  ])).filter(Boolean);
  const wordCount = item.text ? item.text.trim().split(/\s+/).filter(Boolean).length : 0;
  return {
    id: item.id,
    title: item.title || null,
    date: item.createdAt || item.date || null,
    duration_s: Number.isFinite(item.duration) ? item.duration : null,
    source: item.source || null,
    word_count: wordCount,
    tags,
  };
}

// Escape a YAML scalar. Keeps things simple — quote if it contains any
// character that would otherwise need escaping in plain scalars.
function yamlScalar(value: unknown): string {
  if (value === null || value === undefined) return "null";
  if (typeof value === "number" || typeof value === "boolean") return String(value);
  const s = String(value);
  if (s === "") return '""';
  if (/^[A-Za-z0-9._/:\- ]+$/.test(s) && !/^\s|\s$/.test(s)) return s;
  return `"${s.replace(/\\/g, "\\\\").replace(/"/g, '\\"')}"`;
}

export function serialiseFrontmatter(fm: Record<string, unknown>): string {
  const lines = ["---"];
  for (const [key, value] of Object.entries(fm)) {
    if (Array.isArray(value)) {
      if (value.length === 0) {
        lines.push(`${key}: []`);
      } else {
        lines.push(`${key}:`);
        for (const v of value) lines.push(`  - ${yamlScalar(v)}`);
      }
    } else {
      lines.push(`${key}: ${yamlScalar(value)}`);
    }
  }
  lines.push("---");
  return lines.join("\n");
}

// Produce an Obsidian-flavoured markdown document for a transcript.
export function buildMarkdown(item: TranscriptEntry): string {
  const fm = buildFrontmatter(item);
  const header = serialiseFrontmatter(fm);
  const title = fm.title || "Transcript";
  const body = item?.text || "";
  return `${header}\n\n# ${title}\n\n${body}\n`;
}
import type { TranscriptEntry } from "$lib/types/app";