oc/plugins/memory/frontmatter.ts

// Minimal YAML-subset frontmatter, enough for memory files.
//
// A full YAML parser is deliberately avoided: memory files only need scalars
// and string arrays, and every added dependency is one more thing that can fail
// to load on someone else's machine. This reads what we write and tolerates
// what humans type.

export interface Frontmatter {
  [key: string]: string | number | boolean | string[] | undefined
}

/** Parse a leading `---` block. Returns empty data when there is none. */
export function parseFrontmatter(raw: string): { data: Frontmatter; body: string } {
  // Tolerate a UTF-8 BOM and leading blank lines before the fence.
  const text = raw.replace(/^\uFEFF/, "")
  const match = /^---[ \t]*\r?\n([\s\S]*?)\r?\n---[ \t]*(?:\r?\n|$)/.exec(text)
  if (!match) return { data: {}, body: text.trim() }

  const data: Frontmatter = {}
  let currentKey: string | undefined

  for (const line of match[1].split(/\r?\n/)) {
    if (!line.trim() || line.trim().startsWith("#")) continue

    // `- item` continues the array opened by the previous `key:`.
    const item = /^\s*-\s+(.*)$/.exec(line)
    if (item && currentKey) {
      const prev = data[currentKey]
      const list = Array.isArray(prev) ? prev : []
      list.push(scalar(item[1]))
      data[currentKey] = list
      continue
    }

    const kv = /^([A-Za-z_][\w.-]*)\s*:\s*(.*)$/.exec(line)
    if (!kv) continue
    currentKey = kv[1]
    const value = kv[2].trim()
    if (value === "") {
      // Either an empty scalar or the head of a block list; the `- ` branch
      // above fills it in. Mark it as an empty array so round-tripping works.
      data[currentKey] = []
      continue
    }
    data[currentKey] = value.startsWith("[") ? parseInlineList(value) : scalar(value)
  }

  return { data, body: text.slice(match[0].length).trim() }
}

/** Serialize data + body back to a memory file. Key order is preserved. */
export function stringifyFrontmatter(data: Frontmatter, body: string): string {
  const lines: string[] = []
  for (const [key, value] of Object.entries(data)) {
    if (value === undefined) continue
    if (Array.isArray(value)) {
      if (value.length === 0) {
        lines.push(`${key}: []`)
        continue
      }
      // Arrays are written one item per line: readable in a diff, and immune
      // to quoting problems that inline JSON lists hit with Chinese text.
      lines.push(`${key}:`)
      for (const entry of value) lines.push(`  - ${quoteScalar(entry)}`)
      continue
    }
    lines.push(`${key}: ${quoteScalar(value)}`)
  }
  return `---\n${lines.join("\n")}\n---\n\n${body.trim()}\n`
}

function scalar(raw: string): string | number | boolean {
  const value = unquote(raw.trim())
  if (value === "true") return true
  if (value === "false") return false
  if (/^-?\d+(\.\d+)?$/.test(value)) return Number(value)
  return value
}

function parseInlineList(raw: string): string[] {
  const inner = raw.trim().replace(/^\[/, "").replace(/\]$/, "")
  if (!inner.trim()) return []
  return splitTopLevel(inner).map((part) => String(unquote(part.trim())))
}

/** Split on commas that are not inside quotes. */
function splitTopLevel(input: string): string[] {
  const parts: string[] = []
  let buf = ""
  let quote: string | undefined
  for (const ch of input) {
    if (quote) {
      if (ch === quote) quote = undefined
      else buf += ch
      continue
    }
    if (ch === '"' || ch === "'") {
      quote = ch
      continue
    }
    if (ch === ",") {
      parts.push(buf)
      buf = ""
      continue
    }
    buf += ch
  }
  if (buf.trim()) parts.push(buf)
  return parts
}

function unquote(value: string): string {
  if (value.length >= 2 && ((value[0] === '"' && value.endsWith('"')) || (value[0] === "'" && value.endsWith("'")))) {
    return value.slice(1, -1)
  }
  return value
}

/** Quote only when the value would otherwise not round-trip. */
function quoteScalar(value: string | number | boolean): string {
  if (typeof value === "number" || typeof value === "boolean") return String(value)
  // A bare `:` or a leading marker would be read back as YAML structure.
  if (/^[\s>|*&!%@`#-]|[:#]\s|^$/.test(value)) {
    return `"${value.replace(/\\/g, "\\\\").replace(/"/g, '\\"')}"`
  }
  return value
}