//! Copies of what a run is about to overwrite (PLAN.md §5.3).
//!
//! ## Scoped by what cannot be fetched again
//!
//! Most of what this installer writes is replaceable: the sidecar binary and every overlay file are
//! re-downloadable and hash-named in the bundle, and the sidecar's database is overwhelmingly a
//! projection of shard state that the sweeps repopulate. Backing it up would be bulk with little
//! recovery value, and the bulk is not free: it would bury the two things that matter.
//!
//! That reasoning used to be stated two ways that are no longer true, and the correction is worth
//! keeping rather than quietly deleting:
//!
//! - It said the database is safe because `store.rs` creates every table `IF NOT EXISTS`. That held
//!   only while every schema change added a whole *table*. Protocol 4 adds a *column* to a table
//!   that already exists, which `IF NOT EXISTS` cannot do, so `link` now carries a real migration
//!   (`PRAGMA user_version` steps). A run can therefore change the database's structure, not just
//!   its contents.
//! - It said every table holds state the sweeps repopulate. `events` does not: it is never pruned,
//!   and the website backfills the events it missed from `GET /history` on every reconnect. So a
//!   lost database costs the gap-recovery window for anything that happened while the site was down.
//!
//! The decision is unchanged — this still does not copy the database — because the argument against
//! backing up unbounded bulk survives both corrections: `events` grows without limit, the migration
//! is transactional and additive, and the website holds its own durable copy of everything it has
//! already ingested. Only the *reason* was wrong. Whether that table should be pruned or protected
//! is a question for `link`, on its own merits, not something to settle inside a backup policy.
//!
//! What a run can destroy irrecoverably is short:
//!
//! 1. **The operator's own edits to a file the overlay owns.** `Bridge.cfg` is deliberately kept
//!    (PLAN.md §5 Phase 1), but every `.cs` file and `Scripts.csproj` is overwritten
//!    *unconditionally and by design* — so the one place this tool knowingly discards work is the
//!    one place it should keep a copy first.
//! 2. **A stock ServUO file the patch tier edits.** `patches/originals/` already holds the
//!    pre-*tier* copy and is never overwritten, which is the right revert target; it is not a
//!    record of what the file looked like *this morning*, after the operator's own later edits.
//! 3. **`sidecar.toml`**, whose token the website already holds. Mint a new one and the site's
//!    saved configuration starts answering `401` with nothing on the sidecar to explain why.
//!
//! ## What decides whether a backup happens
//!
//! **Whether this run is about to overwrite something** — not which verb was typed and not whether
//! a prior record exists. PLAN.md §5.3 framed it as "`update`, and `install` over an existing
//! record", on the reasoning that a first install overwrites nothing. That reasoning does not
//! survive contact with `INSTALL.md` Appendix A2, which documents deploying the overlay **by hand**:
//! a first `install` over such a tree finds `.cs` files that differ, plans them as `Change`, and
//! overwrites them with no record anywhere of what was there. So the test is the direct one, and a
//! genuine first install onto a clean tree still writes nothing because there is nothing to copy.
//!
//! ## Restoring is printed, not done
//!
//! Same rule as the uninstall report, and for the same reason: the installer cannot know what has
//! changed since, and a restore that puts an old `.cs` file back over a newer overlay eats work
//! rather than saving it. The path and the manifest are what this module hands over.

use anyhow::{Context, Result};
use serde::{Deserialize, Serialize};
use std::fs;
use std::path::{Path, PathBuf};

use crate::paths::Layout;
use crate::util;

/// How many backup directories survive. Older ones are pruned as new ones are written.
///
/// An unbounded directory of ServUO source copies on a shard host is its own support problem, and
/// the value of an old backup falls off a cliff: what an operator reaches for is "before this
/// upgrade", occasionally "before the one before". Three is that, plus one.
pub const KEEP: usize = 3;

/// The `schema` written into `manifest.json`, so a future reader can tell shapes apart.
const SCHEMA: u32 = 1;

/// Why a file was copied. Recorded per entry, because "what did this upgrade touch" is answered
/// very differently by an overlay file and by a stock ServUO file the patch tier edited.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Reason {
    /// An overlay file whose on-disk content the sync is about to replace.
    OverlayChange,
    /// A stock ServUO file the patch tier is about to edit.
    PatchTarget,
    /// A companion `.cs` the tier copies in, which already existed in the tree.
    PatchCompanion,
    /// `sidecar.toml` — the token the website holds.
    SidecarConfig,
}

impl Reason {
    fn as_str(self) -> &'static str {
        match self {
            Self::OverlayChange => "overlay-change",
            Self::PatchTarget => "patch-target",
            Self::PatchCompanion => "patch-companion",
            Self::SidecarConfig => "sidecar-config",
        }
    }

    /// Which sub-directory of the backup the copy lands under.
    ///
    /// The two roots are kept apart because a path is only meaningful relative to one of them, and
    /// without the split a state file could collide with a tree file of the same name.
    fn root_dir(self) -> &'static str {
        match self {
            Self::SidecarConfig => "state",
            _ => "servuo",
        }
    }
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct Manifest {
    pub schema: u32,
    /// RFC 3339, when the backup was taken.
    pub taken: String,
    /// `install` or `update` — the verb that displaced these files.
    pub command: String,
    pub installer: String,
    /// The bundle in the record before this run, when there was one.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub bundle_from: Option<String>,
    /// The bundle this run is moving to.
    pub bundle_to: String,
    pub servuo_root: String,
    pub files: Vec<Entry>,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct Entry {
    /// Where the copy sits inside the backup directory, `/`-separated.
    pub path: String,
    /// Where it was copied from, absolute, as it was on this host.
    pub source: String,
    pub sha256: String,
    pub reason: String,
}

/// One run's backup. Created up front and handed to each stage that writes.
///
/// **The directory is created lazily, on the first capture.** A run that overwrites nothing must
/// leave nothing behind — an empty dated directory per run would be indistinguishable from a
/// backup that failed to record anything, and would push real ones out of the retention window.
pub struct Session {
    dir: PathBuf,
    enabled: bool,
    started: bool,
    root: PathBuf,
    layout: Layout,
    command: &'static str,
    bundle_from: Option<String>,
    bundle_to: String,
    taken: String,
    entries: Vec<Entry>,
}

impl Session {
    /// `enabled` is false for `--verify` (a dry run must not create state, the same rule that keeps
    /// it away from `--print-config`) and for `--no-backup`.
    pub fn new(
        layout: &Layout,
        root: &Path,
        command: &'static str,
        bundle_from: Option<String>,
        bundle_to: String,
        enabled: bool,
    ) -> Self {
        let taken = chrono::Utc::now();
        Self {
            // Colons are not legal in a Windows path component, so the stamp is the basic ISO 8601
            // form. It still sorts lexicographically, which is what the pruning relies on.
            dir: layout
                .backups_dir()
                .join(taken.format("%Y%m%dT%H%M%SZ").to_string()),
            enabled,
            started: false,
            root: root.to_path_buf(),
            layout: layout.clone(),
            command,
            bundle_from,
            bundle_to,
            taken: taken.to_rfc3339_opts(chrono::SecondsFormat::Secs, true),
            entries: Vec::new(),
        }
    }

    /// True once something has actually been copied.
    pub fn has_entries(&self) -> bool {
        !self.entries.is_empty()
    }

    /// Copies `source` into this backup, if it exists and backups are enabled.
    ///
    /// A file that does not exist is not an error and not an entry: the caller asks for anything it
    /// *may* be about to overwrite, and "there was nothing there" is the common answer on a first
    /// install.
    pub fn capture(&mut self, source: &Path, reason: Reason) -> Result<()> {
        if !self.enabled || !source.exists() {
            return Ok(());
        }

        let rel = self.relative_to_root(source, reason);
        let dest = self.dir.join(reason.root_dir()).join(&rel);
        if dest.exists() {
            // Two stages can name the same file — a patch target that is also a companion path, or
            // a re-entrant caller. First copy wins: it is the one taken furthest from any write.
            return Ok(());
        }

        if !self.started {
            fs::create_dir_all(&self.dir).with_context(|| {
                format!("cannot create the backup directory {}", self.dir.display())
            })?;
            self.started = true;
        }
        if let Some(parent) = dest.parent() {
            fs::create_dir_all(parent)
                .with_context(|| format!("cannot create {}", parent.display()))?;
        }

        fs::copy(source, &dest).with_context(|| {
            format!(
                "cannot back up {} before overwriting it. Re-run with --no-backup to proceed \
                 without a copy",
                source.display()
            )
        })?;

        self.entries.push(Entry {
            path: format!(
                "{}/{}",
                reason.root_dir(),
                rel.replace(std::path::MAIN_SEPARATOR, "/")
            ),
            source: source.display().to_string(),
            sha256: util::sha256_file(source)?,
            reason: reason.as_str().to_string(),
        });
        Ok(())
    }

    /// Writes `manifest.json` and prunes older backups. Returns the directory when one was written.
    ///
    /// The manifest is written **last**, so a directory carrying one is a complete backup. Pruning
    /// only considers directories that have one, for the same reason: a run interrupted mid-copy
    /// must not be able to evict a good backup by being newer than it.
    pub fn finish(mut self) -> Result<Option<PathBuf>> {
        if !self.started {
            return Ok(None);
        }

        self.entries.sort_by(|a, b| a.path.cmp(&b.path));
        let manifest = Manifest {
            schema: SCHEMA,
            taken: self.taken.clone(),
            command: self.command.to_string(),
            installer: env!("CARGO_PKG_VERSION").to_string(),
            bundle_from: self.bundle_from.clone(),
            bundle_to: self.bundle_to.clone(),
            servuo_root: self.root.display().to_string(),
            files: self.entries.clone(),
        };
        let body = serde_json::to_string_pretty(&manifest)? + "\n";
        util::write_atomic(&manifest_path(&self.dir), body.as_bytes())
            .context("cannot write the backup manifest")?;

        prune(&self.layout, KEEP)?;
        Ok(Some(self.dir.clone()))
    }

    /// The path a captured file takes inside the backup, relative to the root it belongs to.
    fn relative_to_root(&self, source: &Path, reason: Reason) -> String {
        let rel = match reason.root_dir() {
            "servuo" => source.strip_prefix(&self.root).unwrap_or(source),
            _ => source
                .strip_prefix(&self.layout.state_dir)
                .unwrap_or(source),
        };
        // An absolute path outside the root it was filed under would escape the backup directory
        // when joined. Falling back to the file name keeps the copy inside; the manifest still
        // records exactly where it came from.
        if rel.is_absolute() || rel.as_os_str().is_empty() {
            return source
                .file_name()
                .map(|n| n.to_string_lossy().to_string())
                .unwrap_or_else(|| "file".to_string());
        }
        rel.to_string_lossy().to_string()
    }
}

fn manifest_path(dir: &Path) -> PathBuf {
    dir.join("manifest.json")
}

/// Every complete backup on this host, newest first.
pub fn list(layout: &Layout) -> Vec<PathBuf> {
    let mut dirs: Vec<PathBuf> = match fs::read_dir(layout.backups_dir()) {
        Ok(entries) => entries
            .filter_map(|e| e.ok())
            .map(|e| e.path())
            .filter(|p| manifest_path(p).is_file())
            .collect(),
        Err(_) => Vec::new(),
    };
    // The stamp is fixed-width and zero-padded, so lexicographic order is chronological order.
    dirs.sort();
    dirs.reverse();
    dirs
}

/// Reads one backup's manifest.
pub fn read_manifest(dir: &Path) -> Result<Manifest> {
    let body = fs::read_to_string(manifest_path(dir))
        .with_context(|| format!("cannot read {}", manifest_path(dir).display()))?;
    serde_json::from_str(&body)
        .with_context(|| format!("{} is not a backup manifest", manifest_path(dir).display()))
}

/// Removes all but the `keep` newest complete backups.
pub fn prune(layout: &Layout, keep: usize) -> Result<()> {
    for old in list(layout).into_iter().skip(keep) {
        fs::remove_dir_all(&old)
            .with_context(|| format!("cannot remove the old backup {}", old.display()))?;
    }
    Ok(())
}

/// Deletes every backup. Reached only from `uninstall --purge`, alongside the config, the database
/// and the cached patch set — they are all the same kind of thing: the only offline record of what
/// was here before.
pub fn remove_all(layout: &Layout) -> Result<()> {
    let dir = layout.backups_dir();
    if dir.exists() {
        fs::remove_dir_all(&dir).with_context(|| format!("cannot remove {}", dir.display()))?;
    }
    Ok(())
}

#[cfg(test)]
mod tests {
    use super::*;
    use crate::util::TempDir;

    fn layout_in(root: &Path) -> Layout {
        let mut layout = crate::paths::layout();
        layout.state_dir = root.join("state");
        layout
    }

    fn write(path: &Path, body: &str) {
        fs::create_dir_all(path.parent().unwrap()).unwrap();
        fs::write(path, body).unwrap();
    }

    #[test]
    fn a_run_that_overwrites_nothing_leaves_nothing_behind() {
        let tmp = TempDir::new("backup-empty").unwrap();
        let layout = layout_in(tmp.path());
        let root = tmp.path().join("ServUO");
        let mut session = Session::new(&layout, &root, "install", None, "2026.08.05".into(), true);
        // Nothing on disk to copy — the common first-install case.
        session
            .capture(
                &root.join("Scripts/Custom/Bridge/BridgeLink.cs"),
                Reason::OverlayChange,
            )
            .unwrap();
        assert!(session.finish().unwrap().is_none());
        assert!(
            !layout.backups_dir().exists(),
            "an empty dated directory would be indistinguishable from a failed backup"
        );
    }

    #[test]
    fn a_captured_file_is_copied_verbatim_and_recorded() {
        let tmp = TempDir::new("backup-capture").unwrap();
        let layout = layout_in(tmp.path());
        let root = tmp.path().join("ServUO");
        let source = root.join("Scripts/Custom/Bridge/BridgeLink.cs");
        write(&source, "the operator's own edit\n");
        write(&layout.sidecar_config(), "[web]\nauth_token = \"secret\"\n");

        let mut session = Session::new(
            &layout,
            &root,
            "update",
            Some("2026.08.04".into()),
            "2026.08.05".into(),
            true,
        );
        session.capture(&source, Reason::OverlayChange).unwrap();
        session
            .capture(&layout.sidecar_config(), Reason::SidecarConfig)
            .unwrap();
        let dir = session.finish().unwrap().expect("a backup was taken");

        let copy = dir.join("servuo/Scripts/Custom/Bridge/BridgeLink.cs");
        assert_eq!(
            fs::read_to_string(&copy).unwrap(),
            "the operator's own edit\n"
        );
        assert!(dir.join("state/sidecar.toml").is_file());

        let manifest = read_manifest(&dir).unwrap();
        assert_eq!(manifest.command, "update");
        assert_eq!(manifest.bundle_from.as_deref(), Some("2026.08.04"));
        assert_eq!(manifest.files.len(), 2);
        let overlay = manifest
            .files
            .iter()
            .find(|f| f.reason == "overlay-change")
            .unwrap();
        // The path inside the backup is always `/`-separated, so a manifest written on Windows
        // reads the same as one written on Linux.
        assert_eq!(overlay.path, "servuo/Scripts/Custom/Bridge/BridgeLink.cs");
        assert_eq!(overlay.sha256, util::sha256_file(&source).unwrap());
        assert!(overlay.source.contains("BridgeLink.cs"));
    }

    #[test]
    fn the_first_copy_of_a_file_wins() {
        // Two stages can name the same path. The earlier capture is the one taken furthest from
        // any write, so a later one must not overwrite it with content that has already changed.
        let tmp = TempDir::new("backup-twice").unwrap();
        let layout = layout_in(tmp.path());
        let root = tmp.path().join("ServUO");
        let source = root.join("Server/EventSink.cs");
        write(&source, "before\n");

        let mut session = Session::new(&layout, &root, "install", None, "2026.08.05".into(), true);
        session.capture(&source, Reason::PatchTarget).unwrap();
        write(&source, "after\n");
        session.capture(&source, Reason::PatchTarget).unwrap();
        let dir = session.finish().unwrap().unwrap();

        assert_eq!(
            fs::read_to_string(dir.join("servuo/Server/EventSink.cs")).unwrap(),
            "before\n"
        );
        assert_eq!(read_manifest(&dir).unwrap().files.len(), 1);
    }

    #[test]
    fn disabled_sessions_write_nothing() {
        let tmp = TempDir::new("backup-off").unwrap();
        let layout = layout_in(tmp.path());
        let root = tmp.path().join("ServUO");
        let source = root.join("Scripts/Custom/Bridge/BridgeLink.cs");
        write(&source, "content\n");

        let mut session = Session::new(&layout, &root, "install", None, "2026.08.05".into(), false);
        session.capture(&source, Reason::OverlayChange).unwrap();
        assert!(session.finish().unwrap().is_none());
        assert!(!layout.backups_dir().exists());
    }

    #[test]
    fn pruning_keeps_the_newest_and_ignores_incomplete_directories() {
        let tmp = TempDir::new("backup-prune").unwrap();
        let layout = layout_in(tmp.path());
        for stamp in ["20260801T000000Z", "20260802T000000Z", "20260803T000000Z"] {
            write(
                &layout.backups_dir().join(stamp).join("manifest.json"),
                "{\"schema\":1}",
            );
        }
        // A run interrupted before its manifest was written. It must neither be listed nor be able
        // to evict a complete backup by being newer.
        write(
            &layout.backups_dir().join("20260804T000000Z/servuo/x.cs"),
            "half a copy\n",
        );

        assert_eq!(list(&layout).len(), 3);
        prune(&layout, 2).unwrap();

        let kept: Vec<String> = list(&layout)
            .iter()
            .map(|p| p.file_name().unwrap().to_string_lossy().to_string())
            .collect();
        assert_eq!(kept, vec!["20260803T000000Z", "20260802T000000Z"]);
        assert!(
            layout.backups_dir().join("20260804T000000Z").exists(),
            "an incomplete directory is left for a human to look at, not silently deleted"
        );
    }

    #[test]
    fn purge_removes_every_backup() {
        let tmp = TempDir::new("backup-purge").unwrap();
        let layout = layout_in(tmp.path());
        write(
            &layout.backups_dir().join("20260801T000000Z/manifest.json"),
            "{\"schema\":1}",
        );
        remove_all(&layout).unwrap();
        assert!(!layout.backups_dir().exists());
        // Removing what is not there is not an error: `uninstall --purge` runs on hosts that never
        // took a backup.
        remove_all(&layout).unwrap();
    }
}