paperclip/packages/shared/src/frontmatter.ts

export interface MarkdownDoc {
  frontmatter: Record<string, unknown>;
  body: string;
  hasFrontmatter: boolean;
}

export function isPlainRecord(value: unknown): value is Record<string, unknown> {
  return typeof value === "object" && value !== null && !Array.isArray(value);
}

export function asString(value: unknown): string | null {
  if (typeof value !== "string") return null;
  const trimmed = value.trim();
  return trimmed.length > 0 ? trimmed : null;
}

export function asBoolean(value: unknown): boolean | null {
  return typeof value === "boolean" ? value : null;
}

export function asStringArray(value: unknown): string[] | null {
  if (value === undefined) return [];
  if (!Array.isArray(value)) return null;

  const out: string[] = [];
  for (const item of value) {
    const text = asString(item);
    if (!text) return null;
    out.push(text);
  }
  return out;
}

export function parseFrontmatterMarkdown(raw: string): MarkdownDoc {
  const normalized = raw.replace(/\r\n/g, "\n");
  if (!normalized.startsWith("---\n")) {
    return { frontmatter: {}, body: normalized.trim(), hasFrontmatter: false };
  }

  const closing = normalized.indexOf("\n---\n", 4);
  if (closing < 0) {
    return { frontmatter: {}, body: normalized.trim(), hasFrontmatter: false };
  }

  const frontmatterRaw = normalized.slice(4, closing).trim();
  const body = normalized.slice(closing + 5).trim();
  return {
    frontmatter: parseYamlFrontmatter(frontmatterRaw),
    body,
    hasFrontmatter: true,
  };
}

function parseYamlFrontmatter(raw: string): Record<string, unknown> {
  const prepared = prepareYamlLines(raw);
  if (prepared.length === 0) return {};
  const parsed = parseYamlBlock(prepared, 0, prepared[0]!.indent);
  return isPlainRecord(parsed.value) ? parsed.value : {};
}

function prepareYamlLines(raw: string) {
  return raw
    .split("\n")
    .map((line) => ({
      indent: line.match(/^ */)?.[0].length ?? 0,
      content: line.trim(),
    }))
    .filter((line) => line.content.length > 0 && !line.content.startsWith("#"));
}

function parseYamlBlock(
  lines: Array<{ indent: number; content: string }>,
  startIndex: number,
  indentLevel: number,
): { value: unknown; nextIndex: number } {
  let index = startIndex;
  if (index >= lines.length || lines[index]!.indent < indentLevel) {
    return { value: {}, nextIndex: index };
  }

  const isArray = lines[index]!.indent === indentLevel && lines[index]!.content.startsWith("-");
  if (isArray) {
    const values: unknown[] = [];
    while (index < lines.length) {
      const line = lines[index]!;
      if (line.indent < indentLevel) break;
      if (line.indent !== indentLevel || !line.content.startsWith("-")) break;

      const remainder = line.content.slice(1).trim();
      index += 1;
      if (!remainder) {
        const nested = parseYamlBlock(lines, index, indentLevel + 2);
        values.push(nested.value);
        index = nested.nextIndex;
        continue;
      }

      values.push(parseYamlScalar(remainder));
    }
    return { value: values, nextIndex: index };
  }

  const record: Record<string, unknown> = {};
  while (index < lines.length) {
    const line = lines[index]!;
    if (line.indent < indentLevel) break;
    if (line.indent !== indentLevel) {
      index += 1;
      continue;
    }

    const separatorIndex = line.content.indexOf(":");
    if (separatorIndex <= 0) {
      index += 1;
      continue;
    }

    const key = line.content.slice(0, separatorIndex).trim();
    const remainder = line.content.slice(separatorIndex + 1).trim();
    index += 1;
    if (!remainder) {
      const nested = parseYamlBlock(lines, index, indentLevel + 2);
      record[key] = nested.value;
      index = nested.nextIndex;
      continue;
    }
    record[key] = parseYamlScalar(remainder);
  }

  return { value: record, nextIndex: index };
}

function parseYamlScalar(rawValue: string): unknown {
  const trimmed = rawValue.trim();
  if (trimmed === "") return "";
  if (trimmed === "null" || trimmed === "~") return null;
  if (trimmed === "true") return true;
  if (trimmed === "false") return false;
  if (trimmed === "[]") return [];
  if (trimmed === "{}") return {};
  if (/^-?\d+(\.\d)?\d*$/.test(trimmed)) return Number(trimmed);
  if (
    trimmed.startsWith("\"") ||
    trimmed.startsWith("[") ||
    trimmed.startsWith("{")
  ) {
    try {
      return JSON.parse(trimmed);
    } catch {
      return trimmed;
    }
  }
  return trimmed;
}