website/server/src/utils/spawnAtlasParse.js

// Spawn atlas parsers — pure functions over strings, no `fs`, no dependencies.
//
// These back the CLI build script (`scripts/buildSpawnAtlas.js`), which is the
// only thing that reads a ServUO tree. Keeping every parser pure and fs-free is
// what lets the test suite cover them in CI, where no ServUO tree exists: the
// tests hand these functions literal XML strings.
//
// Four source shapes, two very different parsing strategies:
//
//   Spawns/*.xml          ~10.5 MB across 13 files, FLAT <Points> records
//                         → streaming regex, never a DOM. See parsePoints().
//   Data/Regions.xml      129 KB, genuinely nested <region> inside <region>
//   Data/Locations/*.xml  nested <parent>/<child>
//   Config/ChampionSpawns.xml  4.8 KB, <spawn>/<location>
//                         → the small recursive tokenizer below.
//
// The server has zero XML dependencies and this adds none. The tokenizer is
// deliberately a *subset* parser: it handles the constructs these four files
// actually use (elements, attributes, self-closing tags, comments, the XML
// declaration, CDATA, the five predefined entities plus numeric refs) and
// nothing else. It is not a general-purpose XML parser and must not be reused
// as one — no namespaces, no DTDs, no entity declarations.

// ── Entities ───────────────────────────────────────────────────────────────

const NAMED_ENTITIES = {
  amp: '&',
  lt: '<',
  gt: '>',
  quot: '"',
  apos: "'",
}

// Region and location names carry apostrophes ("Mondain's Legacy", "Wrong's
// Level 3"), so entity decoding is load-bearing here, not decorative.
function decodeEntities(text) {
  if (!text.includes('&')) return text
  return text.replace(/&(#x?[0-9a-fA-F]+|[a-zA-Z]+);/g, (match, body) => {
    if (body[0] === '#') {
      const code =
        body[1] === 'x' || body[1] === 'X'
          ? Number.parseInt(body.slice(2), 16)
          : Number.parseInt(body.slice(1), 10)
      return Number.isFinite(code) ? String.fromCodePoint(code) : match
    }
    const named = NAMED_ENTITIES[body.toLowerCase()]
    return named === undefined ? match : named
  })
}

// ── The tokenizer ──────────────────────────────────────────────────────────

const ATTR_RE = /([\w:.-]+)\s*=\s*("([^"]*)"|'([^']*)')/g

function parseAttrs(source) {
  const attrs = {}
  ATTR_RE.lastIndex = 0
  let match
  while ((match = ATTR_RE.exec(source)) !== null) {
    const raw = match[3] !== undefined ? match[3] : match[4]
    attrs[match[1]] = decodeEntities(raw)
  }
  return attrs
}

/**
 * Parse a small nested XML document into `{ name, attrs, children, text }`.
 *
 * Intended for Regions.xml / Locations / ChampionSpawns.xml only — never for
 * the multi-megabyte Spawns files. Returns the root element, or `null` for a
 * document with no elements.
 *
 * Mismatched or stray closing tags are ignored rather than thrown on: these are
 * hand-maintained shard config files, and one malformed region should degrade
 * to a missing region, not abort a build that is otherwise fine.
 */
function parseXml(source) {
  const text = String(source)
  const root = { name: '#document', attrs: {}, children: [], text: '' }
  const stack = [root]
  let i = 0

  while (i < text.length) {
    const lt = text.indexOf('<', i)
    if (lt === -1) {
      appendText(stack[stack.length - 1], text.slice(i))
      break
    }
    if (lt > i) appendText(stack[stack.length - 1], text.slice(i, lt))

    // Comment, declaration/DOCTYPE, or CDATA — skipped wholesale.
    if (text.startsWith('<!--', lt)) {
      const end = text.indexOf('-->', lt + 4)
      i = end === -1 ? text.length : end + 3
      continue
    }
    if (text.startsWith('<![CDATA[', lt)) {
      const end = text.indexOf(']]>', lt + 9)
      const stop = end === -1 ? text.length : end
      appendRawText(stack[stack.length - 1], text.slice(lt + 9, stop))
      i = end === -1 ? text.length : end + 3
      continue
    }
    if (text.startsWith('<?', lt)) {
      const end = text.indexOf('?>', lt + 2)
      i = end === -1 ? text.length : end + 2
      continue
    }
    if (text.startsWith('<!', lt)) {
      const end = text.indexOf('>', lt + 2)
      i = end === -1 ? text.length : end + 1
      continue
    }

    const gt = findTagEnd(text, lt)
    if (gt === -1) {
      // Unterminated tag: nothing sane is left to read.
      break
    }
    const inner = text.slice(lt + 1, gt)

    if (inner[0] === '/') {
      const name = inner.slice(1).trim()
      // Pop to the nearest matching open element. If there is no match the tag
      // is stray and we drop it rather than unwinding the whole stack.
      for (let depth = stack.length - 1; depth > 0; depth -= 1) {
        if (stack[depth].name === name) {
          stack.length = depth
          break
        }
      }
      i = gt + 1
      continue
    }

    const selfClosing = inner.endsWith('/')
    const body = selfClosing ? inner.slice(0, -1) : inner
    const space = body.search(/\s/)
    const name = (space === -1 ? body : body.slice(0, space)).trim()
    const node = {
      name,
      attrs: space === -1 ? {} : parseAttrs(body.slice(space)),
      children: [],
      text: '',
    }
    stack[stack.length - 1].children.push(node)
    if (!selfClosing) stack.push(node)
    i = gt + 1
  }

  return root.children.length > 0 ? root.children[0] : null
}

// `>` inside a quoted attribute value must not end the tag.
function findTagEnd(text, from) {
  let quote = null
  for (let i = from + 1; i < text.length; i += 1) {
    const ch = text[i]
    if (quote) {
      if (ch === quote) quote = null
    } else if (ch === '"' || ch === "'") {
      quote = ch
    } else if (ch === '>') {
      return i
    }
  }
  return -1
}

function appendText(node, chunk) {
  if (chunk.trim() === '') return
  appendRawText(node, decodeEntities(chunk))
}

function appendRawText(node, chunk) {
  node.text = node.text ? `${node.text}${chunk}` : chunk
}

function childrenNamed(node, name) {
  if (!node || !node.children) return []
  return node.children.filter((child) => child.name === name)
}

// ── Facet names ────────────────────────────────────────────────────────────
//
// Facets are NOT a fixed list. A shard may add facets, replace them wholesale,
// or rename them when its maps are updated, so nothing here may name Felucca,
// Trammel or any other stock facet. The facet set is whatever the shard's own
// files say it is, discovered at parse time.
//
// The complication is that the sources disagree about spelling for the SAME
// facet and nothing in the files reconciles them: `Spawns/*.xml` `<Map>` and
// `Regions.xml` `<Facet name>` say `TerMur`, while `Data/Locations/*.xml` spells
// it `Ter Mur` and calls Tokuno `Tokuno Islands`. Left unreconciled this fails
// silently — the landmark bucket is keyed differently from the points looking it
// up, so the fallback never fires and every unregioned spawn on those facets
// reads "Wilderness".
//
// Reconciliation is therefore done by MATCHING, not by a lookup table:
// `facetKey()` collapses spelling differences, and `resolveFacetName()` matches
// a loosely-spelled name against the canonical set discovered from the shard's
// own data. A facet nobody else mentions keeps its own name rather than being
// dropped.

/**
 * Collapse a facet name to a comparison key: lowercase, alphanumerics only.
 * `TerMur`, `Ter Mur` and `ter-mur` all key alike.
 */
function facetKey(value) {
  return String(value ?? '')
    .toLowerCase()
    .replace(/[^a-z0-9]+/g, '')
}

/**
 * Build a key → canonical-spelling lookup from the authoritative facet names.
 *
 * The authority is what the spawn records and region definitions actually say,
 * since those are the names the atlas keys everything on. Later names do not
 * overwrite earlier ones, so the first source wins consistently.
 */
function buildFacetIndex(names) {
  const index = new Map()
  for (const name of names) {
    const key = facetKey(name)
    if (key !== '' && !index.has(key)) index.set(key, String(name).trim())
  }
  return index
}

/**
 * Resolve a loosely-spelled facet name against the discovered canonical set.
 *
 * Tried in order: exact key match (`Ter Mur` → `TerMur`), then a prefix match in
 * either direction (`Tokuno Islands` → `Tokuno`), longest candidate first so a
 * more specific facet wins over a shorter one that merely prefixes it.
 *
 * A name matching nothing is returned trimmed rather than dropped — on a shard
 * with a custom facet that is a real facet the atlas simply has no spawns for
 * yet, and inventing a match would be worse than leaving it alone.
 */
function resolveFacetName(value, index) {
  const raw = String(value ?? '').trim()
  const key = facetKey(raw)
  if (key === '') return ''
  if (index.has(key)) return index.get(key)

  let best = null
  for (const [candidateKey, canonical] of index) {
    if (!key.startsWith(candidateKey) && !candidateKey.startsWith(key)) continue
    if (best === null || candidateKey.length > facetKey(best).length) best = canonical
  }
  return best ?? raw
}

// ── Small coercions ────────────────────────────────────────────────────────

function toInt(value, fallback = 0) {
  const n = Number.parseInt(value, 10)
  return Number.isFinite(n) ? n : fallback
}

function toBool(value) {
  return String(value).trim().toLowerCase() === 'true'
}

/**
 * URL-safe slug used as the creature primary key and in `/atlas/:slug`.
 * Spawn type tokens are C# class names, so they are already ASCII-ish; this
 * mainly lowercases and collapses punctuation.
 */
function slugify(value) {
  return String(value)
    .trim()
    .toLowerCase()
    .replace(/[^a-z0-9]+/g, '-')
    .replace(/^-+|-+$/g, '')
}

// ── Objects2 ───────────────────────────────────────────────────────────────

/**
 * Parse a `<Objects2>` value into `[{ type, max }]`.
 *
 * The format is one or more segments joined by `:OBJ=`, each segment being
 * `Type:MX=n:SB=0:RT=0:...` — the type is the token before the first `:`, and
 * every following token is a `KEY=value` pair. Verified against trammel.xml,
 * where a single point carries six types:
 *
 *   Giantserpent:MX=1:...:OBJ=Giantspider:MX=1:...:OBJ=Boar:MX=1:...
 *
 * Splitting on `:` alone would shred this, which is why the `:OBJ=` split comes
 * first. `MX` is that type's own max count and is what the atlas displays;
 * every other flag (spawn/trigger/refractory bookkeeping) is dropped.
 *
 * The type token itself may carry XmlSpawner directives appended to the class
 * name — property assignments after `/` and an amount/argument list after `,`:
 *
 *   Agralem/Name/Agralem      alchemist/z/-50      Fairy,{RND,4,8}
 *   GargishRefugee/hue/34532  greatape,true        GargishRouser,1
 *
 * Taken literally these produce creatures that do not exist ("alchemist/z/-50")
 * AND split real ones in two, because `Fairy` and `Fairy,{RND,4,8}` slug apart —
 * 71 of 845 entries were affected before this was stripped. Only the leading
 * class name identifies the creature, so everything from the first `/` or `,`
 * is dropped.
 */
/** Reduce an XmlSpawner type token to the bare class name. */
function stripSpawnerDirectives(token) {
  const cut = String(token).search(/[/,]/)
  return (cut === -1 ? String(token) : String(token).slice(0, cut)).trim()
}

function parseObjects2(value) {
  const source = String(value ?? '').trim()
  if (source === '') return []

  return source
    .split(':OBJ=')
    .map((segment) => {
      const tokens = segment.split(':')
      const type = stripSpawnerDirectives(tokens.shift() ?? '')
      if (type === '') return null
      let max = 1
      for (const token of tokens) {
        const eq = token.indexOf('=')
        if (eq === -1) continue
        if (token.slice(0, eq).trim().toUpperCase() === 'MX') {
          max = toInt(token.slice(eq + 1), 1)
        }
      }
      return { type, max }
    })
    .filter((entry) => entry !== null)
}

// ── Spawns/*.xml ───────────────────────────────────────────────────────────

const POINT_RE = /<Points>([\s\S]*?)<\/Points>/g

function tagValue(block, name) {
  const match = block.match(new RegExp(`<${name}>([\\s\\S]*?)</${name}>`))
  return match ? decodeEntities(match[1]).trim() : ''
}

/**
 * Parse a `Spawns/<facet>.xml` file into spawn point records.
 *
 * Deliberately regex/streaming and NOT `parseXml` — these files total ~10.5 MB
 * and putting them through a DOM builder would allocate a node per element for
 * ~40 fields on every one of ~6,500 records to keep 14 of them. The records are
 * flat, so a per-record regex sweep is both correct and cheap.
 *
 * Only the fields the site can actually show are kept. Everything to do with
 * triggering, refractory windows, proximity, sequential spawning, sounds and
 * `UniqueId` is dropped here rather than downstream — that is what holds the
 * committed artifact under 1 MB.
 *
 * NOTE: the facet comes from each record's own `<Map>`, never from the file
 * name. `Eodon.xml`, `GravewaterLake.xml` and the other named-area files all
 * carry TerMur/Trammel points, so there are 13 files but only 6 facets.
 */
/**
 * A spawner's respawn window, in seconds.
 *
 * `DelayInSec` decides the unit of `MinDelay`/`MaxDelay`; absent (older files)
 * it is false, which is minutes — the same default XmlSpawner assumes.
 */
function delaySeconds(block) {
  const scale = toBool(tagValue(block, 'DelayInSec')) ? 1 : 60
  return {
    minDelay: toInt(tagValue(block, 'MinDelay')) * scale,
    maxDelay: toInt(tagValue(block, 'MaxDelay')) * scale,
  }
}

function parsePoints(source) {
  const text = String(source)
  const points = []
  POINT_RE.lastIndex = 0
  let match

  while ((match = POINT_RE.exec(text)) !== null) {
    const block = match[1]
    // Reported exactly as written. `<Map>` is the authority the rest of the
    // atlas keys on, so it is never rewritten.
    const facet = tagValue(block, 'Map')
    if (facet === '') continue

    points.push({
      name: tagValue(block, 'Name'),
      facet,
      x: toInt(tagValue(block, 'X')),
      y: toInt(tagValue(block, 'Y')),
      width: toInt(tagValue(block, 'Width')),
      height: toInt(tagValue(block, 'Height')),
      range: toInt(tagValue(block, 'Range')),
      maxCount: toInt(tagValue(block, 'MaxCount')),
      // Normalised to SECONDS here, because the unit is per-record. XmlSpawner
      // writes minutes by default and switches to seconds only when a spawner's
      // delay does not divide into whole minutes, flagging that with
      // `DelayInSec` (XmlSpawner2.cs:7462-7480, read back at :6345-6358). Taken
      // literally the two are indistinguishable — a `5` means five minutes on
      // one spawner and five seconds on the next — so a consumer that assumed
      // either unit would be wrong about the other. Stock ServUO 57.4 has ~30
      // second-flagged spawners, few enough to look like noise and quietly
      // mislabel.
      ...delaySeconds(block),
      // Time-of-day gating: TODMode 0 means "always", in which case the start
      // and end values are meaningless and the site must not render them.
      todStart: toInt(tagValue(block, 'TODStart')),
      todEnd: toInt(tagValue(block, 'TODEnd')),
      todMode: toInt(tagValue(block, 'TODMode')),
      // A spawner switched off in-world spawns nothing; the build filters these
      // out so the atlas describes what actually appears, not what is merely
      // configured. Parsed here so the decision stays in the build script.
      running: toBool(tagValue(block, 'IsRunning')),
      types: parseObjects2(tagValue(block, 'Objects2')),
    })
  }

  return points
}

// ── Data/Regions.xml ───────────────────────────────────────────────────────

/**
 * Flatten `Data/Regions.xml` into `[{ facet, name, type, priority, parent, rects }]`.
 *
 * Regions nest: a `<region>` may contain further `<region>` elements, and the
 * inner ones frequently omit `name` and `priority` (`<region type="CrystalField">`
 * inside "Prism of Light"). Unnamed regions are skipped — they cannot label a
 * spawn point — but their children are still walked, and a child that omits
 * `priority` inherits its parent's rather than defaulting to 0, which would
 * quietly sort it below every top-level region.
 */
function parseRegions(source) {
  const root = parseXml(source)
  const regions = []
  if (!root) return regions

  for (const facetNode of childrenNamed(root, 'Facet')) {
    const facet = (facetNode.attrs.name || '').trim()
    if (facet === '') continue
    walkRegions(facetNode, facet, null, 0, regions)
  }
  return regions
}

function walkRegions(node, facet, parentName, parentPriority, out) {
  for (const regionNode of childrenNamed(node, 'region')) {
    const name = regionNode.attrs.name || ''
    const priority = Object.hasOwn(regionNode.attrs, 'priority')
      ? toInt(regionNode.attrs.priority, parentPriority)
      : parentPriority

    if (name !== '') {
      const rects = childrenNamed(regionNode, 'rect').map((rect) => ({
        x: toInt(rect.attrs.x),
        y: toInt(rect.attrs.y),
        width: toInt(rect.attrs.width),
        height: toInt(rect.attrs.height),
      }))
      // A named region with no rects (some exist purely to carry music or a
      // `go` point) can never contain anything, so it is not worth indexing.
      if (rects.length > 0) {
        out.push({
          facet,
          name,
          type: regionNode.attrs.type || '',
          priority,
          parent: parentName,
          rects,
        })
      }
    }

    walkRegions(regionNode, facet, name === '' ? parentName : name, priority, out)
  }
}

// ── Data/Locations/*.xml ───────────────────────────────────────────────────

/**
 * Flatten a `Data/Locations/<facet>.xml` into landmark points.
 *
 * The file nests `<parent>` arbitrarily deep and puts coordinates only on
 * `<child>`: Trammel → Dungeons → Covetous → "Level 1". The outermost parent is
 * the facet itself and is dropped from `path`; `group` is the innermost
 * enclosing parent ("Covetous"), which is the label worth showing — "Covetous"
 * reads better than "Level 1" when naming where a spawn is.
 */
function parseLocations(source, facetHint = '') {
  const root = parseXml(source)
  const landmarks = []
  if (!root) return landmarks

  for (const top of childrenNamed(root, 'parent')) {
    // The file name (`Data/Locations/termur.xml`) is the more reliable signal
    // and is preferred over the display label inside the file, which is where
    // the `Ter Mur` / `Tokuno Islands` drift lives. Both are carried so the
    // build can fall back to matching the label if the file name resolves to
    // nothing — a shard may well name its files differently from its facets.
    landmarks.push(
      ...collectLocations(top, facetHint || top.attrs.name || '', top.attrs.name || ''),
    )
  }
  return landmarks
}

function collectLocations(top, facet, label) {
  const out = []
  walkLocations(top, facet, [], out)
  for (const landmark of out) landmark.facetLabel = label
  return out
}

function walkLocations(node, facet, path, out) {
  for (const child of childrenNamed(node, 'child')) {
    const name = child.attrs.name || ''
    if (name === '') continue
    out.push({
      facet,
      name,
      group: path.length > 0 ? path[path.length - 1] : name,
      path: [...path],
      x: toInt(child.attrs.x),
      y: toInt(child.attrs.y),
      z: toInt(child.attrs.z),
    })
  }
  for (const parent of childrenNamed(node, 'parent')) {
    const name = parent.attrs.name || ''
    walkLocations(parent, facet, name === '' ? path : [...path, name], out)
  }
}

// ── Config/ChampionSpawns.xml ──────────────────────────────────────────────

/**
 * Parse `Config/ChampionSpawns.xml` into champion altar records.
 *
 * This is the shard's *configured* champion roster — which altars exist, where,
 * and which type each is pinned to. It is static content and distinct from the
 * live `champ.update` feed the bridge already carries: this says "there is an
 * Unholy Terror altar in Deceit", the feed says "it is on level 3 right now".
 *
 * A spawn with no `type` is randomised on every activation, which the site must
 * render as "random" rather than as an empty type.
 */
function parseChampions(source) {
  const root = parseXml(source)
  const champions = []
  if (!root) return champions

  for (const spawnNode of childrenNamed(root, 'spawn')) {
    const location = childrenNamed(spawnNode, 'location')[0]
    const attrs = location ? location.attrs : {}
    champions.push({
      name: spawnNode.attrs.name || '',
      group: spawnNode.attrs.group || '',
      type: spawnNode.attrs.type || '',
      randomType: !spawnNode.attrs.type,
      facet: (attrs.map || '').trim(),
      x: toInt(attrs.x),
      y: toInt(attrs.y),
      z: toInt(attrs.z),
      radius: toInt(attrs.radius),
    })
  }
  return champions
}

// ── Placement ──────────────────────────────────────────────────────────────

const DEFAULT_LANDMARK_RADIUS = 200

function inRect(x, y, rect) {
  return (
    x >= rect.x && x < rect.x + rect.width && y >= rect.y && y < rect.y + rect.height
  )
}

function rectArea(rect) {
  return Math.max(1, rect.width) * Math.max(1, rect.height)
}

/**
 * Group parsed regions and landmarks by facet once, so the per-point resolve
 * below is a scan of one facet instead of the whole world. With ~6,500 points
 * and a few thousand rects this stays comfortably sub-second; there is no need
 * for a spatial index and none is worth the complexity.
 */
function buildPlacementIndex(regions, landmarks) {
  const byFacet = new Map()
  // Keyed on facetKey(), not the raw name, so two spellings of one facet cannot
  // land in separate buckets — the failure that silently emptied the landmark
  // bucket for Ter Mur and Tokuno.
  const facet = (name) => {
    const key = facetKey(name)
    if (!byFacet.has(key)) byFacet.set(key, { regions: [], landmarks: [] })
    return byFacet.get(key)
  }
  for (const region of regions) facet(region.facet).regions.push(region)
  for (const landmark of landmarks) facet(landmark.facet).landmarks.push(landmark)
  return byFacet
}

/**
 * Turn a raw coordinate into a human place name.
 *
 * This is the transform the whole atlas exists for: it is what makes a row read
 * "Lizardman — Despise, Felucca" instead of "Lizardman — 5411, 1234".
 *
 * Resolution order:
 *   1. The highest-`priority` named region whose rect contains the point. Ties
 *      break toward the SMALLEST rect, so a specific room inside a dungeon wins
 *      over the dungeon-wide rect it sits in.
 *   2. Otherwise the nearest landmark within `landmarkRadius` tiles, labelled by
 *      its group ("Covetous"), not the individual marker ("Level 1").
 *   3. Otherwise "Wilderness". The radius cap is what keeps step 3 reachable —
 *      without it the nearest landmark is always *some* landmark, however far,
 *      and open countryside would get labelled with a dungeon on the far side
 *      of the map.
 */
function resolveRegion(x, y, facetName, index, options = {}) {
  const radius = options.landmarkRadius ?? DEFAULT_LANDMARK_RADIUS
  const bucket = index.get(facetKey(facetName))
  const result = { region: null, landmark: null, label: 'Wilderness' }
  if (!bucket) return result

  let best = null
  let bestPriority = -Infinity
  let bestArea = Infinity
  for (const region of bucket.regions) {
    for (const rect of region.rects) {
      if (!inRect(x, y, rect)) continue
      const area = rectArea(rect)
      if (region.priority > bestPriority || (region.priority === bestPriority && area < bestArea)) {
        best = region
        bestPriority = region.priority
        bestArea = area
      }
    }
  }
  if (best) {
    result.region = best.name
    result.label = best.name
    return result
  }

  let nearest = null
  let nearestDistance = Infinity
  const limit = radius * radius
  for (const landmark of bucket.landmarks) {
    const dx = landmark.x - x
    const dy = landmark.y - y
    const distance = dx * dx + dy * dy
    if (distance < nearestDistance) {
      nearest = landmark
      nearestDistance = distance
    }
  }
  if (nearest && nearestDistance <= limit) {
    result.landmark = nearest.group || nearest.name
    result.label = result.landmark
  }
  return result
}

module.exports = {
  parseXml,
  parseObjects2,
  parsePoints,
  parseRegions,
  parseLocations,
  parseChampions,
  buildPlacementIndex,
  resolveRegion,
  facetKey,
  buildFacetIndex,
  resolveFacetName,
  slugify,
  decodeEntities,
  DEFAULT_LANDMARK_RADIUS,
}