PureYAML/Tests/StreamingScannerPerformanceTests.swift

import Foundation
@testable import PureYAML
import Testing

/// Measures the resumable scanner's checkpoint-and-retry cost (issue #4) against
/// the batch scanner, across a spread of chunk sizes, over the largest real-world
/// fixture. `scanStep()`'s first increment restores the whole scanner and retries
/// a fetch from its start whenever it runs dry, so a token that spans many small
/// chunks is rescanned once per chunk it spans: correct (proven by
/// `StreamingScannerDifferentialTests`) but worst-case quadratic in the number of
/// chunks a single token spans. This measures whether that cost matters in
/// practice before persisted mid-token suspension (a materially larger, riskier
/// change to the scalar-scanning loops) is worth building. Gated: release-mode
/// timing on a 9.5MB fixture is not a default `swift test` concern.
@Suite("Streaming Scanner Performance")
struct StreamingScannerPerformanceTests {
    @Test("measure scanStep() overhead over scanAll() at a spread of chunk sizes")
    func test_measure() throws {
        guard ProcessInfo.processInfo.environment["PUREYAML_STREAMING_PERF_MEASURE"] == "1" else {
            return
        }
        let url = try #require(Bundle.module.url(
            forResource: "github-rest-api",
            withExtension: "yaml",
            subdirectory: "Fixtures/real-yaml",
        ))
        let yaml = try String(contentsOf: url, encoding: .utf8)
        let clock = ContinuousClock()

        var batchScanner = PureYAML.Parsing.LibYAML.Scanner(yaml)
        let batchDuration = try clock.measure {
            _ = try batchScanner.scanAll()
        }
        print("STREAMING-PERF batch bytes=\(yaml.utf8.count) time=\(batchDuration)")

        // Control: the whole input is present from construction (isFinal: true), so
        // ranDry can never be set and the checkpoint is never restored, meaning zero
        // chunking or retry ever happens. Any overhead this still shows over
        // scanAll() is intrinsic to scanStep()'s per-token loop (the checkpoint copy
        // taken before every fetch, and isFrontSafeToRelease's check), not to
        // chunking. This isolates that fixed cost from the chunk-size-dependent
        // rescan cost measured below.
        var noChunkScanner = PureYAML.Parsing.LibYAML.Scanner(yaml, isFinal: true)
        let noChunkDuration = try clock.measure {
            while true {
                switch try noChunkScanner.scanStep() {
                case .token: continue
                case .done: return
                case .needMoreInput: Issue.record("isFinal: true must never report needMoreInput")
                    return
                }
            }
        }
        let noChunkRatio = noChunkDuration / batchDuration
        print("STREAMING-PERF noChunking(control) time=\(noChunkDuration) ratio=\(String(format: "%.2f", noChunkRatio))x")

        for chunkSize in [16, 64, 256, 1024, 4096, 65536, 1_000_000] {
            let duration = try streamingDuration(yaml: yaml, chunkSize: chunkSize, clock: clock)
            let ratio = duration / batchDuration
            print("STREAMING-PERF chunkSize=\(chunkSize) time=\(duration) ratio=\(String(format: "%.2f", ratio))x")
        }
    }
}

private func streamingDuration(yaml: String, chunkSize: Int, clock: ContinuousClock) throws -> Duration {
    let scalars = Array(yaml.unicodeScalars)
    var chunks: [String] = []
    var index = 0
    while index < scalars.count {
        let end = min(index + chunkSize, scalars.count)
        chunks.append(String(String.UnicodeScalarView(scalars[index ..< end])))
        index = end
    }

    return try clock.measure {
        var scanner = PureYAML.Parsing.LibYAML.Scanner("", isFinal: false)
        var nextChunk = 0
        while true {
            switch try scanner.scanStep() {
            case .token:
                continue
            case .done:
                return
            case .needMoreInput:
                if nextChunk < chunks.count {
                    scanner.reader.append(chunks[nextChunk])
                    nextChunk += 1
                } else {
                    scanner.reader.markFinal()
                }
            }
        }
    }
}