//! Dev diagnostics for the debug overlay (Ctrl+Shift+D): system + process
//! CPU, memory, GPU, network rates, and the loudness-normalization state of
//! the active track. Polled by the frontend only while the overlay is
//! visible — nothing here runs otherwise.
//!
//! Process figures aggregate the WHOLE process tree: the WebView2 children
//! do the actual rendering, so app.exe alone would tell a comforting lie.

use std::collections::HashMap;
use std::sync::{Arc, Mutex};
use std::time::Instant;

use serde::Serialize;
use sysinfo::{Networks, Pid, ProcessRefreshKind, ProcessesToUpdate, System};
use tauri::{Manager, State};

use player::StreamProgress;

pub struct DiagState(Mutex<Inner>);

struct Inner {
    sys: System,
    networks: Networks,
    last_net: Instant,
    gpu: Option<GpuCounter>,
    started: Instant,
    /// The ACTIVE track's transfer, straight from the player's own
    /// StreamProgress — the overlay must read download truth at the source,
    /// not the UI store's window-activity-gated mirror.
    current_stream: Option<(u64, Arc<StreamProgress>)>,
    /// On-deck pre-buffer transfers by transfer id, mirrored from the
    /// download event stream (those updates are otherwise swallowed — no
    /// player, no Downloads view). The Instant is set when the transfer
    /// reaches a terminal state, so finished rows linger long enough to be
    /// seen and then fall off.
    preloads: HashMap<u64, (PreloadDl, Option<Instant>)>,
}

/// One on-deck transfer as the overlay sees it.
#[derive(Serialize, Clone)]
#[serde(rename_all = "camelCase")]
pub struct PreloadDl {
    pub username: String,
    /// Full remote path — the frontend matches queue rows by this.
    pub path: String,
    pub state: String,
    /// Remote queue position, when the peer reported one.
    pub place: Option<u32>,
    pub received: u64,
    pub total: u64,
    pub speed_bps: u64,
}

/// Called from the download event stream for every preload update.
pub fn note_preload(app: &tauri::AppHandle, id: u64, dl: PreloadDl, terminal: bool) {
    if let Some(state) = app.try_state::<DiagState>() {
        let finished = if terminal { Some(Instant::now()) } else { None };
        state
            .0
            .lock()
            .expect("diag lock")
            .preloads
            .insert(id, (dl, finished));
    }
}

/// Called when a play path takes the transfer over: it is the CURRENT
/// track's stream from here on (note_stream reports it), not an on-deck row.
pub fn retire_preload(app: &tauri::AppHandle, id: u64) {
    if let Some(state) = app.try_state::<DiagState>() {
        state.0.lock().expect("diag lock").preloads.remove(&id);
    }
}

/// Called by the play paths: this track streams from a peer.
pub fn note_stream(app: &tauri::AppHandle, total: u64, progress: Arc<StreamProgress>) {
    if let Some(state) = app.try_state::<DiagState>() {
        state.0.lock().expect("diag lock").current_stream = Some((total, progress));
    }
}

/// Called by the play paths: this track plays from a complete local file.
pub fn clear_stream(app: &tauri::AppHandle) {
    if let Some(state) = app.try_state::<DiagState>() {
        state.0.lock().expect("diag lock").current_stream = None;
    }
}

pub fn init(app: &tauri::AppHandle) {
    app.manage(DiagState(Mutex::new(Inner {
        sys: System::new(),
        networks: Networks::new_with_refreshed_list(),
        last_net: Instant::now(),
        gpu: GpuCounter::open(),
        started: Instant::now(),
        current_stream: None,
        preloads: HashMap::new(),
    })));
}

#[derive(Serialize)]
#[serde(rename_all = "camelCase")]
pub struct DebugStats {
    /// Whole-process-tree CPU, percent of the whole machine.
    pub cpu_process: f32,
    pub cpu_system: f32,
    /// GPU 3D-engine utilization (Task-Manager-style), if counters opened.
    /// MACHINE-WIDE — includes DWM, browsers, Discord, everything.
    pub gpu_percent: Option<f32>,
    /// Same counters, restricted to OUR process tree — the app's true GPU
    /// share, matching Task Manager's per-process rows. The machine-wide
    /// number above routinely reads 2× this on a busy desktop.
    pub gpu_app_percent: Option<f32>,
    /// Process tree working set / private commit, bytes.
    pub mem_working_set: u64,
    pub mem_private: u64,
    pub mem_system_used: u64,
    pub mem_system_total: u64,
    /// System-wide network rates since the previous poll, bytes/sec.
    pub net_rx_bps: f64,
    pub net_tx_bps: f64,
    pub process_count: usize,
    pub uptime_secs: u64,
    /// Active track's transfer, from the player's own progress handle.
    pub dl_received: Option<u64>,
    pub dl_total: Option<u64>,
    pub dl_done: Option<bool>,
    pub normalization_enabled: bool,
    pub target_lufs: f64,
    pub loudness: Option<crate::loudness::CurrentTrack>,
    /// Main player's live fade-gain (1.0 = full; <1 only during a preview
    /// open/close crossfade). Proves a fade never strands the volume.
    pub main_fade_gain: Option<f32>,
    /// The normalization gain the sink has RIGHT NOW, and the one the audio
    /// thread is slewing toward, both dB. Reported as a pair because the
    /// interesting state during a mid-track correction is the gap between
    /// them: equal means settled, different means a correction is in flight
    /// and the difference is how far it still has to travel.
    pub norm_now_db: Option<f32>,
    pub norm_target_db: Option<f32>,
    /// The preview voices' resting volume (mirrors the app volume; 0 = muted).
    pub preview_volume: Option<f32>,
    /// The active preview clip's loudness-normalization gain in dB.
    pub preview_norm_db: Option<f32>,
    /// On-deck pre-buffer transfers, in arrival order (finished rows linger
    /// ~15s so a completion is visible before it drops off).
    pub preload_dl: Vec<PreloadDl>,
}

#[tauri::command]
pub fn debug_stats(app: tauri::AppHandle, state: State<'_, DiagState>) -> DebugStats {
    let mut inner = state.0.lock().expect("diag lock");
    let inner = &mut *inner;

    inner.sys.refresh_cpu_usage();
    inner.sys.refresh_processes_specifics(
        ProcessesToUpdate::All,
        true,
        ProcessRefreshKind::nothing().with_cpu().with_memory(),
    );

    // Our process tree: app.exe + every descendant (the WebView2 family).
    let me = Pid::from_u32(std::process::id());
    let mut tree = vec![me];
    let mut grew = true;
    while grew {
        grew = false;
        for (pid, proc_) in inner.sys.processes() {
            if let Some(parent) = proc_.parent() {
                if tree.contains(&parent) && !tree.contains(pid) {
                    tree.push(*pid);
                    grew = true;
                }
            }
        }
    }
    let cores = inner.sys.cpus().len().max(1) as f32;
    let mut cpu_process = 0.0f32;
    let mut mem_working_set = 0u64;
    let mut mem_private = 0u64;
    for pid in &tree {
        if let Some(p) = inner.sys.process(*pid) {
            cpu_process += p.cpu_usage(); // % of one core
            mem_working_set += p.memory();
            // sysinfo's virtual_memory() is the raw address space on Windows
            // (WebView reserves terabytes of it) — useless. The meaningful
            // "reserved" figure is the private commit, straight from Win32.
            mem_private += private_commit(pid.as_u32());
        }
    }
    cpu_process /= cores;

    inner.sys.refresh_memory();

    // Network: sysinfo reports bytes since the LAST refresh per interface.
    let elapsed = inner.last_net.elapsed().as_secs_f64().max(0.05);
    inner.last_net = Instant::now();
    inner.networks.refresh(true);
    let (mut rx, mut tx) = (0u64, 0u64);
    for (_, data) in inner.networks.iter() {
        rx += data.received();
        tx += data.transmitted();
    }

    let (normalization_enabled, target_lufs, loudness) = crate::loudness::snapshot(&app);
    let (dl_received, dl_total, dl_done) = match &inner.current_stream {
        Some((total, progress)) => {
            let (received, done) = progress.received_done();
            (Some(received), Some(*total), Some(done))
        }
        None => (None, None, None),
    };

    let tree_u32: Vec<u32> = tree.iter().map(|p| p.as_u32()).collect();
    let gpu_sample = inner.gpu.as_mut().and_then(|g| g.sample(&tree_u32));

    // On-deck transfers: drop terminal rows after they've been visible a
    // while, then report the rest in arrival (transfer-id) order.
    inner
        .preloads
        .retain(|_, v| v.1.is_none_or(|t| t.elapsed().as_secs() < 15));
    let mut preload_ids: Vec<u64> = inner.preloads.keys().copied().collect();
    preload_ids.sort_unstable();
    let preload_dl: Vec<PreloadDl> = preload_ids
        .iter()
        .filter_map(|id| inner.preloads.get(id).map(|(dl, _)| dl.clone()))
        .collect();

    DebugStats {
        cpu_process,
        cpu_system: inner.sys.global_cpu_usage(),
        gpu_percent: gpu_sample.map(|(sys, _)| sys),
        gpu_app_percent: gpu_sample.map(|(_, app)| app),
        mem_working_set,
        mem_private,
        mem_system_used: inner.sys.used_memory(),
        mem_system_total: inner.sys.total_memory(),
        net_rx_bps: rx as f64 / elapsed,
        net_tx_bps: tx as f64 / elapsed,
        process_count: tree.len(),
        uptime_secs: inner.started.elapsed().as_secs(),
        dl_received,
        dl_total,
        dl_done,
        normalization_enabled,
        target_lufs,
        loudness,
        norm_now_db: app
            .try_state::<crate::playback::PlayerState>()
            .map(|s| s.player.norm_gain_now_target_db().0),
        norm_target_db: app
            .try_state::<crate::playback::PlayerState>()
            .map(|s| s.player.norm_gain_now_target_db().1),
        preview_volume: app
            .try_state::<crate::preview::PreviewState>()
            .map(|s| crate::preview::target_volume(&s)),
        preview_norm_db: app
            .try_state::<crate::preview::PreviewState>()
            .map(|s| crate::preview::active_norm_db(&s)),
        main_fade_gain: app
            .try_state::<crate::playback::PlayerState>()
            .map(|p| p.player.fade_gain()),
        preload_dl,
    }
}

/// Private commit ("reserved") of one process, bytes. 0 if unreadable.
fn private_commit(pid: u32) -> u64 {
    use windows::Win32::Foundation::CloseHandle;
    use windows::Win32::System::ProcessStatus::{
        K32GetProcessMemoryInfo, PROCESS_MEMORY_COUNTERS, PROCESS_MEMORY_COUNTERS_EX,
    };
    use windows::Win32::System::Threading::{OpenProcess, PROCESS_QUERY_LIMITED_INFORMATION};
    unsafe {
        let Ok(handle) = OpenProcess(PROCESS_QUERY_LIMITED_INFORMATION, false, pid) else {
            return 0;
        };
        let mut counters = PROCESS_MEMORY_COUNTERS_EX::default();
        let ok = K32GetProcessMemoryInfo(
            handle,
            (&mut counters as *mut PROCESS_MEMORY_COUNTERS_EX).cast::<PROCESS_MEMORY_COUNTERS>(),
            std::mem::size_of::<PROCESS_MEMORY_COUNTERS_EX>() as u32,
        )
        .as_bool();
        let _ = CloseHandle(handle);
        if ok {
            counters.PrivateUsage as u64
        } else {
            0
        }
    }
}

// ------------------------------------------------------------ GPU (PDH) ---

/// Total 3D-engine utilization via the PDH "GPU Engine" counter set — the
/// number Task Manager labels "GPU". Instances are per-process-per-engine;
/// summing the 3D ones gives machine-wide utilization. First sample after
/// opening reads as None (PDH rate counters need two collections).
struct GpuCounter {
    query: windows::Win32::System::Performance::PDH_HQUERY,
    counter: windows::Win32::System::Performance::PDH_HCOUNTER,
}

// PDH handles are plain registry-ish handles; the query is only touched
// under the DiagState mutex.
unsafe impl Send for GpuCounter {}

impl GpuCounter {
    fn open() -> Option<GpuCounter> {
        use windows::core::w;
        use windows::Win32::System::Performance::{
            PdhAddEnglishCounterW, PdhOpenQueryW, PDH_HCOUNTER, PDH_HQUERY,
        };
        unsafe {
            let mut query = PDH_HQUERY::default();
            if PdhOpenQueryW(None, 0, &mut query) != 0 {
                return None;
            }
            let mut counter = PDH_HCOUNTER::default();
            let path = w!("\\GPU Engine(*engtype_3D)\\Utilization Percentage");
            if PdhAddEnglishCounterW(query, path, 0, &mut counter) != 0 {
                return None;
            }
            Some(GpuCounter { query, counter })
        }
    }

    /// Returns (machine_total, app_tree_total). Instance names carry the
    /// owning pid — "pid_1234_luid_..._engtype_3D" — so the app's share is
    /// the sum over instances whose pid is in our process tree.
    fn sample(&mut self, app_pids: &[u32]) -> Option<(f32, f32)> {
        use windows::Win32::System::Performance::{
            PdhCollectQueryData, PdhGetFormattedCounterArrayW, PDH_FMT_COUNTERVALUE_ITEM_W,
            PDH_FMT_DOUBLE,
        };
        unsafe {
            if PdhCollectQueryData(self.query) != 0 {
                return None;
            }
            let mut buf_len: u32 = 0;
            let mut count: u32 = 0;
            // Size probe returns PDH_MORE_DATA; then fetch.
            let _ = PdhGetFormattedCounterArrayW(
                self.counter,
                PDH_FMT_DOUBLE,
                &mut buf_len,
                &mut count,
                None,
            );
            if buf_len == 0 {
                return None;
            }
            let mut buf = vec![0u8; buf_len as usize];
            let items = buf.as_mut_ptr() as *mut PDH_FMT_COUNTERVALUE_ITEM_W;
            if PdhGetFormattedCounterArrayW(
                self.counter,
                PDH_FMT_DOUBLE,
                &mut buf_len,
                &mut count,
                Some(items),
            ) != 0
            {
                return None;
            }
            let mut total = 0.0f64;
            let mut app = 0.0f64;
            for i in 0..count as usize {
                let item = &*items.add(i);
                let v = item.FmtValue.Anonymous.doubleValue;
                total += v;
                if !item.szName.is_null() {
                    if let Some(pid) = instance_pid(item.szName) {
                        if app_pids.contains(&pid) {
                            app += v;
                        }
                    }
                }
            }
            Some((total.min(100.0) as f32, app.min(100.0) as f32))
        }
    }
}

/// Parse the pid out of a "pid_1234_luid_…" counter-instance name.
unsafe fn instance_pid(name: windows::core::PWSTR) -> Option<u32> {
    let s = name.to_string().ok()?;
    let rest = s.strip_prefix("pid_")?;
    let digits: String = rest.chars().take_while(|c| c.is_ascii_digit()).collect();
    digits.parse().ok()
}

impl Drop for GpuCounter {
    fn drop(&mut self) {
        use windows::Win32::System::Performance::PdhCloseQuery;
        unsafe {
            let _ = PdhCloseQuery(self.query);
        }
    }
}