PureXML/Sources/Schema/ContentModelGroupDependency.swift

/// Orders the model groups reachable from a set of content models so each group
/// comes after every group it references. The compositional determinism check
/// summarizes groups in this order, so its recursive walk is always a cache hit at a
/// `<group ref>` and never recurses through a reference chain. A chain is FLAT in the
/// schema document (group definitions are siblings, not nested), so it is not bounded
/// by the parser's `maxDepth`; ordering and scanning here are iterative so neither
/// step recurses on the chain length either.
enum GroupDependencyOrder {
    /// Reachable group names in dependency order (dependencies first), by an iterative
    /// post-order DFS from the groups the `models` reference. A name already on the
    /// current path is not re-entered, so a circular reference (illegal, rejected
    /// elsewhere) terminates.
    static func reachable(from models: [PureXML.Model.TreeNode], context: PureXML.Schema.XSDContext) -> [String] {
        var roots: [String] = []
        var seen: Set<String> = []
        for model in models {
            for ref in referencedGroupNames(in: model) where seen.insert(ref).inserted {
                roots.append(ref)
            }
        }
        var order: [String] = []
        var visited: Set<String> = []
        var onPath: Set<String> = []
        var work: [(name: String, exit: Bool)] = roots.reversed().map { ($0, false) }
        while let (name, exit) = work.popLast() {
            if exit {
                onPath.remove(name)
                order.append(name)
                continue
            }
            if visited.contains(name) { continue }
            visited.insert(name)
            onPath.insert(name)
            work.append((name, true))
            for ref in dependencies(of: name, context: context).reversed() where !visited.contains(ref) && !onPath.contains(ref) {
                work.append((ref, false))
            }
        }
        return order
    }

    /// The group names referenced within `node`, by an iterative tree walk (so scanning
    /// a deep model does not itself recurse on depth). It descends compositors but stops
    /// at an `<element>`, exactly as the determinism walk's `summarize` treats an element
    /// as terminal: a group inside an element's inline complex type belongs to THAT type's
    /// own content model (checked separately), not this one, and must not be drawn in.
    private static func referencedGroupNames(in node: PureXML.Model.TreeNode) -> [String] {
        var names: [String] = []
        var stack = [node]
        while let current = stack.popLast() {
            let local = PureXML.Schema.XSDNode.localName(current)
            if local == "group", let ref = PureXML.Schema.XSDNode.attribute(current, "ref") {
                names.append(PureXML.Schema.XSDNode.stripPrefix(ref))
            }
            if local != "element" {
                stack.append(contentsOf: PureXML.Schema.XSDNode.elementChildren(current))
            }
        }
        return names
    }

    /// The groups `name` references. A redefined group's base-model references are added
    /// ONLY when the redefinition actually self-references (`<group ref=name>` inside the
    /// redefinition of `name`): that reference expands to the base model
    /// (`CompWalk.redefineSelfReference`), making the base's groups part of the effective
    /// content model, so they must be ordered first. When the redefinition does NOT
    /// self-reference, the base is fully replaced and dead, and pulling its refs in would
    /// summarise unreachable groups: surfacing a conflict in a dead group is a false
    /// positive, so it is deliberately excluded. This keeps the reachable set identical
    /// to the lazy walk's.
    private static func dependencies(of name: String, context: PureXML.Schema.XSDContext) -> [String] {
        guard let definition = context.groups[name], let model = modelChild(definition) else { return [] }
        var refs = referencedGroupNames(in: model)
        if refs.contains(name), context.redefinedGroups.contains(name), let base = context.baseGroups[name], let baseModel = modelChild(base) {
            refs += referencedGroupNames(in: baseModel)
        }
        return refs
    }

    /// The `sequence`/`choice`/`all` model child of a group definition, if any.
    private static func modelChild(_ definition: PureXML.Model.TreeNode) -> PureXML.Model.TreeNode? {
        PureXML.Schema.XSDNode.elementChildren(definition)
            .first { ["sequence", "choice", "all"].contains(PureXML.Schema.XSDNode.localName($0) ?? "") }
    }
}