PureXML/Sources/Schema/ContentRTN.swift

extension PureXML.Schema {
    /// A call edge: enter the callee sub-program at `calleeStart`, returning to
    /// `returnTo` when the callee's return state is reached. The `actions` reset the
    /// callee's counter scopes on entry (so a shared fragment entered twice does not
    /// carry a stale count); `guards` are the calling occurrence's `belowMaximum`.
    struct ContentCallEdge: Sendable {
        var calleeStart: Int
        var returnTo: Int
        var guards: [ContentCounterGuard] = []
        var actions: [ContentCounterAction] = []
    }

    /// One state of the counted Recursive Transition Network: like ``ContentState``
    /// but a state may also `call` a shared group fragment, and a group fragment's
    /// accept is a `return` (it pops the graph-structured stack to its caller).
    struct ContentRTNState: Sendable {
        var epsilon: [ContentEpsilonEdge] = []
        var calls: [ContentCallEdge] = []
        /// A group fragment's accept: pop the GSS and continue at the caller's
        /// `returnTo`. The top-level program accept is NOT a return.
        var isReturn: Bool = false
        var label: TermLabel?
        var target: Int?
        var elementType: ElementType?
        var valueConstraint: ValueConstraint?
    }

    /// A counted RTN compiled from a ``Particle``: each `<xs:group>` definition
    /// (identified by ``Group/definitionID``) is compiled once and reached by a
    /// `call`, so a multiply-referenced group is shared, not inlined `2^K` times.
    /// `all` groups are validated separately and are not represented here, exactly
    /// as in ``ContentNFA``.
    struct ContentRTN: Sendable {
        var states: [ContentRTNState]
        var counters: [ContentCounterScope]
        var start: Int
        var accept: Int
    }
}

extension PureXML.Schema {
    /// Builds a counted ``ContentRTN`` from a particle, sharing each `definitionID`
    /// group fragment. The occurrence-wrapper shape (reset/loop/exit/increment)
    /// matches ``ContentNFABuilder`` exactly; the only difference is that a group
    /// with a `definitionID` compiles to a `call` into its shared fragment instead
    /// of being inlined.
    struct ContentRTNBuilder {
        private var states: [ContentRTNState] = []
        private var counters: [ContentCounterScope] = []
        /// The compiled (start, accept, counters) of each shared group fragment.
        private var fragments: [Int: ContentNFAFragment] = [:]
        /// Definition ids whose fragment is mid-compilation, to detect a (malformed)
        /// cyclic group definition instead of recurring without bound.
        private var compiling: Set<Int> = []

        static func build(_ particle: PureXML.Schema.Particle) -> ContentRTN {
            var builder = ContentRTNBuilder()
            let fragment = builder.particle(particle)
            return ContentRTN(
                states: builder.states,
                counters: builder.counters,
                start: fragment.start,
                accept: fragment.accept,
            )
        }

        private mutating func addState() -> Int {
            states.append(ContentRTNState())
            return states.count - 1
        }

        private mutating func addEpsilon(
            from source: Int,
            to target: Int,
            guards: [ContentCounterGuard] = [],
            actions: [ContentCounterAction] = [],
        ) {
            states[source].epsilon.append(ContentEpsilonEdge(target: target, guards: guards, actions: actions))
        }

        private mutating func particle(_ particle: PureXML.Schema.Particle) -> ContentNFAFragment {
            let start = addState()
            let loop = addState()
            let accept = addState()
            let counter = counters.count
            let bodyNullable = termIsNullable(particle.term)
            counters.append(ContentCounterScope(range: particle.occurrenceRange, nullableBody: bodyNullable))
            let body = term(particle.term)
            let resetAll = [ContentCounterAction.reset(counter)] + body.counters.map(ContentCounterAction.reset)
            addEpsilon(from: start, to: loop, actions: resetAll)
            addEpsilon(
                from: loop,
                to: accept,
                guards: [.canExit(counter: counter, minimum: particle.occurrenceRange.minimum, nullableBody: bodyNullable)],
            )
            addEpsilon(
                from: loop,
                to: body.start,
                guards: [.belowMaximum(counter: counter, maximum: particle.occurrenceRange.maximum)],
                actions: body.counters.map(ContentCounterAction.reset),
            )
            addEpsilon(from: body.accept, to: loop, actions: [.increment(counter)])
            return ContentNFAFragment(start: start, accept: accept, counters: [counter] + body.counters, nullable: particleIsNullable(particle))
        }

        private mutating func term(_ term: PureXML.Schema.Term) -> ContentNFAFragment {
            switch term {
            case let .element(name, type, _, constraint, _, _):
                let fragment = labeled(.name(name))
                states[fragment.start].elementType = type
                states[fragment.start].valueConstraint = constraint
                return fragment
            case let .wildcard(wildcard):
                return labeled(.wildcard(wildcard))
            case let .group(group):
                if let id = group.definitionID {
                    return call(group, id: id)
                }
                return self.group(group)
            }
        }

        /// A reference to a shared group: a `call` state into the group's fragment
        /// (compiled once), returning to a fresh accept. The callee's counters are
        /// deliberately NOT propagated to the caller: every counter scope is reset on
        /// its own particle's entry edge, which is on the path from the callee's start,
        /// so the shared fragment resets itself on every (re-)entry without the caller
        /// re-listing it. Propagating them would re-list each shared fragment's counters
        /// at every reference, nesting to a `2^K` reset-action list even though the
        /// states stay `O(K)`, which is the whole point of sharing.
        private mutating func call(_ group: PureXML.Schema.Group, id: Int) -> ContentNFAFragment {
            let fragment = groupFragment(group, id: id)
            let callState = addState()
            let returnState = addState()
            states[callState].calls.append(ContentCallEdge(calleeStart: fragment.start, returnTo: returnState))
            return ContentNFAFragment(start: callState, accept: returnState, counters: [], nullable: fragment.nullable)
        }

        /// The shared fragment for a group definition, compiled once and memoized.
        /// Its accept is marked `isReturn`.
        private mutating func groupFragment(_ group: PureXML.Schema.Group, id: Int) -> ContentNFAFragment {
            if let cached = fragments[id] {
                return cached
            }
            // `definitionID` groups are acyclic: XSD forbids a group referencing itself
            // except through an element, and the parser's expansion breaks every cycle at
            // an element boundary, so a fragment is never referenced during its own
            // compilation (the inlining `ContentNFABuilder` relies on the same property).
            // Guard it anyway: a cyclic id would otherwise recur without bound, the exact
            // interactive-safety hazard this matcher exists to remove, so bound the
            // recursion by degrading a (malformed, unreachable) cycle to a terminating
            // empty fragment rather than overflowing the stack.
            guard compiling.insert(id).inserted else { return labeledEmpty() }
            defer { compiling.remove(id) }
            let built = group.compositor == .choice ? choice(group.particles) : sequence(group.particles)
            states[built.accept].isReturn = true
            fragments[id] = built
            return built
        }

        private mutating func group(_ group: PureXML.Schema.Group) -> ContentNFAFragment {
            group.compositor == .choice ? choice(group.particles) : sequence(group.particles)
        }

        private mutating func labeled(_ label: TermLabel) -> ContentNFAFragment {
            let start = addState()
            let accept = addState()
            states[start].label = label
            states[start].target = accept
            return ContentNFAFragment(start: start, accept: accept, counters: [], nullable: false)
        }

        private mutating func sequence(_ particles: [PureXML.Schema.Particle]) -> ContentNFAFragment {
            guard !particles.isEmpty else { return labeledEmpty() }
            var first: Int?
            var last: Int?
            var fragmentCounters: [Int] = []
            var nullable = true
            for member in particles {
                let part = particle(member)
                if let previous = last {
                    addEpsilon(from: previous, to: part.start)
                } else {
                    first = part.start
                }
                last = part.accept
                fragmentCounters.append(contentsOf: part.counters)
                nullable = nullable && part.nullable
            }
            return ContentNFAFragment(start: first ?? addState(), accept: last ?? addState(), counters: fragmentCounters, nullable: nullable)
        }

        private mutating func choice(_ particles: [PureXML.Schema.Particle]) -> ContentNFAFragment {
            let start = addState()
            let accept = addState()
            var fragmentCounters: [Int] = []
            var nullable = false
            for member in particles {
                let part = particle(member)
                addEpsilon(from: start, to: part.start)
                addEpsilon(from: part.accept, to: accept)
                fragmentCounters.append(contentsOf: part.counters)
                nullable = nullable || part.nullable
            }
            return ContentNFAFragment(start: start, accept: accept, counters: fragmentCounters, nullable: nullable)
        }

        private mutating func labeledEmpty() -> ContentNFAFragment {
            let start = addState()
            let accept = addState()
            addEpsilon(from: start, to: accept)
            return ContentNFAFragment(start: start, accept: accept, counters: [], nullable: true)
        }

        private func particleIsNullable(_ particle: PureXML.Schema.Particle) -> Bool {
            particle.occurrenceRange.minimum.isZero || termIsNullable(particle.term)
        }

        private func termIsNullable(_ term: PureXML.Schema.Term) -> Bool {
            switch term {
            case .element, .wildcard:
                false
            case let .group(group):
                switch group.compositor {
                case .sequence, .all:
                    group.particles.allSatisfy(particleIsNullable)
                case .choice:
                    group.particles.contains(where: particleIsNullable)
                }
            }
        }
    }
}