use crate::dirstate::entry::TruncatedTimestamp;

use crate::dirstate::status::IgnoreFnType;

use crate::dirstate_tree::dirstate_map::BorrowedPath;

use crate::dirstate_tree::dirstate_map::ChildNodesRef;

use crate::dirstate_tree::dirstate_map::DirstateMap;

use crate::dirstate_tree::dirstate_map::NodeData;

use crate::dirstate_tree::dirstate_map::NodeRef;

use crate::dirstate_tree::on_disk::DirstateV2ParseError;

use crate::matchers::get_ignore_function;

use crate::matchers::Matcher;

use crate::utils::files::get_bytes_from_os_string;

use crate::utils::files::get_path_from_bytes;

use crate::utils::hg_path::HgPath;

use crate::BadMatch;

use crate::DirstateStatus;

use crate::EntryState;

use crate::HgPathBuf;

use crate::PatternFileWarning;

use crate::StatusError;

use crate::StatusOptions;

use micro_timer::timed;

use rayon::prelude::*;

use sha1::{Digest, Sha1};

use std::borrow::Cow;

use std::io;

use std::path::Path;

use std::path::PathBuf;

use std::sync::Mutex;

use std::time::SystemTime;

/// Returns the status of the working directory compared to its parent

/// changeset.

///

/// This algorithm is based on traversing the filesystem tree (`fs` in function

/// and variable names) and dirstate tree at the same time. The core of this

/// traversal is the recursive `traverse_fs_directory_and_dirstate` function

/// and its use of `itertools::merge_join_by`. When reaching a path that only

/// exists in one of the two trees, depending on information requested by

/// `options` we may need to traverse the remaining subtree.

#[timed]

pub fn status<'tree, 'on_disk: 'tree>(

    dmap: &'tree mut DirstateMap<'on_disk>,

    matcher: &(dyn Matcher + Sync),

    root_dir: PathBuf,

    ignore_files: Vec<PathBuf>,

    options: StatusOptions,

) -> Result<(DirstateStatus<'on_disk>, Vec<PatternFileWarning>), StatusError> {

    let (ignore_fn, warnings, patterns_changed): (IgnoreFnType, _, _) =

        if options.list_ignored || options.list_unknown {

            let mut hasher = Sha1::new();

            let (ignore_fn, warnings) = get_ignore_function(

                ignore_files,

                &root_dir,

                &mut |pattern_bytes| hasher.update(pattern_bytes),

            )?;

            let new_hash = *hasher.finalize().as_ref();

            let changed = new_hash != dmap.ignore_patterns_hash;

            dmap.ignore_patterns_hash = new_hash;

            (ignore_fn, warnings, Some(changed))

        } else {

            (Box::new(|&_| true), vec![], None)

        };

    let common = StatusCommon {

        dmap,

        options,

        matcher,

        ignore_fn,

        ignore_patterns_have_changed: patterns_changed,

        new_cachable_directories: Default::default(),

        outated_cached_directories: Default::default(),

    };

    let is_at_repo_root = true;

    let hg_path = &BorrowedPath::OnDisk(HgPath::new(""));

    let has_ignored_ancestor = false;

    let root_cached_mtime = None;

    let root_dir_metadata = None;

    // If the path we have for the repository root is a symlink, do follow it.

    // (As opposed to symlinks within the working directory which are not

    // followed, using `std::fs::symlink_metadata`.)

    common.traverse_fs_directory_and_dirstate(

        has_ignored_ancestor,

        dmap.root.as_ref(),

        hg_path,

        &root_dir,

        root_dir_metadata,

        root_cached_mtime,

        is_at_repo_root,

    )?;

    let mut outcome = common.outcome.into_inner().unwrap();

    let new_cachable = common.new_cachable_directories.into_inner().unwrap();

    let outdated = common.outated_cached_directories.into_inner().unwrap();

    outcome.dirty = common.ignore_patterns_have_changed == Some(true)

        || !outdated.is_empty()

        || !new_cachable.is_empty();

    // Remove outdated mtimes before adding new mtimes, in case a given

    // directory is both

    for path in &outdated {

        let node = dmap.get_or_insert(path)?;

        if let NodeData::CachedDirectory { .. } = &node.data {

            node.data = NodeData::None

        }

    }

    for (path, mtime) in &new_cachable {

        let node = dmap.get_or_insert(path)?;

        match &node.data {

            NodeData::Entry(_) => {} // Don’t overwrite an entry

            NodeData::CachedDirectory { .. } | NodeData::None => {

                node.data = NodeData::CachedDirectory { mtime: *mtime }

            }

        }

    }

    Ok((outcome, warnings))

}

/// Bag of random things needed by various parts of the algorithm. Reduces the

/// number of parameters passed to functions.

struct StatusCommon<'a, 'tree, 'on_disk: 'tree> {

    dmap: &'tree DirstateMap<'on_disk>,

    options: StatusOptions,

    matcher: &'a (dyn Matcher + Sync),

    ignore_fn: IgnoreFnType<'a>,

    outcome: Mutex<DirstateStatus<'on_disk>>,

    new_cachable_directories:

        Mutex<Vec<(Cow<'on_disk, HgPath>, TruncatedTimestamp)>>,

    outated_cached_directories: Mutex<Vec<Cow<'on_disk, HgPath>>>,

    /// Whether ignore files like `.hgignore` have changed since the previous

    /// time a `status()` call wrote their hash to the dirstate. `None` means

    /// we don’t know as this run doesn’t list either ignored or uknown files

    /// and therefore isn’t reading `.hgignore`.

    ignore_patterns_have_changed: Option<bool>,

    /// The current time at the start of the `status()` algorithm, as measured

    /// and possibly truncated by the filesystem.

    filesystem_time_at_status_start: Option<SystemTime>,

}

impl<'a, 'tree, 'on_disk> StatusCommon<'a, 'tree, 'on_disk> {

    fn read_dir(

        &self,

        hg_path: &HgPath,

        fs_path: &Path,

        is_at_repo_root: bool,

    ) -> Result<Vec<DirEntry>, ()> {

        DirEntry::read_dir(fs_path, is_at_repo_root)

            .map_err(|error| self.io_error(error, hg_path))

    }

    fn io_error(&self, error: std::io::Error, hg_path: &HgPath) {

        let errno = error.raw_os_error().expect("expected real OS error");

        self.outcome

            .lock()

            .unwrap()

            .bad

            .push((hg_path.to_owned().into(), BadMatch::OsError(errno)))

    }

    fn check_for_outdated_directory_cache(

        &self,

        dirstate_node: &NodeRef<'tree, 'on_disk>,

    ) -> Result<(), DirstateV2ParseError> {

        if self.ignore_patterns_have_changed == Some(true)

            && dirstate_node.cached_directory_mtime()?.is_some()

        {

            self.outated_cached_directories.lock().unwrap().push(

                dirstate_node

                    .full_path_borrowed(self.dmap.on_disk)?

                    .detach_from_tree(),

            )

        }

        Ok(())

    }

    /// If this returns true, we can get accurate results by only using

    /// `symlink_metadata` for child nodes that exist in the dirstate and don’t

    /// need to call `read_dir`.

    fn can_skip_fs_readdir(

        &self,

        directory_metadata: Option<&std::fs::Metadata>,

        cached_directory_mtime: Option<TruncatedTimestamp>,

    ) -> bool {

        if !self.options.list_unknown && !self.options.list_ignored {

            // All states that we care about listing have corresponding

            // dirstate entries.

            // This happens for example with `hg status -mard`.

            return true;

        }

        if !self.options.list_ignored

            && self.ignore_patterns_have_changed == Some(false)

        {

            if let Some(cached_mtime) = cached_directory_mtime {

                // The dirstate contains a cached mtime for this directory, set

                // by a previous run of the `status` algorithm which found this

                // directory eligible for `read_dir` caching.

                if let Some(meta) = directory_metadata {

                    if cached_mtime

                        .likely_equal_to_mtime_of(meta)

                        .unwrap_or(false)

                    {

                        // The mtime of that directory has not changed

                        // since then, which means that the results of

                        // `read_dir` should also be unchanged.

                        return true;

                    }

                }

            }

        }

        false

    }

    /// Returns whether all child entries of the filesystem directory have a

    /// corresponding dirstate node or are ignored.

    fn traverse_fs_directory_and_dirstate(

        &self,

        has_ignored_ancestor: bool,

        dirstate_nodes: ChildNodesRef<'tree, 'on_disk>,

        directory_hg_path: &BorrowedPath<'tree, 'on_disk>,

        directory_fs_path: &Path,

        directory_metadata: Option<&std::fs::Metadata>,

        cached_directory_mtime: Option<TruncatedTimestamp>,

        is_at_repo_root: bool,

    ) -> Result<bool, DirstateV2ParseError> {

        if self.can_skip_fs_readdir(directory_metadata, cached_directory_mtime)

        {

            dirstate_nodes

                .par_iter()

                .map(|dirstate_node| {

                    let fs_path = directory_fs_path.join(get_path_from_bytes(

                        dirstate_node.base_name(self.dmap.on_disk)?.as_bytes(),

                    ));

                    match std::fs::symlink_metadata(&fs_path) {

                        Ok(fs_metadata) => self.traverse_fs_and_dirstate(

                            &fs_path,

                            &fs_metadata,

                            dirstate_node,

                            has_ignored_ancestor,

                        ),

                        Err(e) if e.kind() == std::io::ErrorKind::NotFound => {

                            self.traverse_dirstate_only(dirstate_node)

                        }

                        Err(error) => {

                            let hg_path =

                                dirstate_node.full_path(self.dmap.on_disk)?;

                            Ok(self.io_error(error, hg_path))

                        }

                    }

                })

                .collect::<Result<_, _>>()?;

            // We don’t know, so conservatively say this isn’t the case

            let children_all_have_dirstate_node_or_are_ignored = false;

            return Ok(children_all_have_dirstate_node_or_are_ignored);

        }

        let mut fs_entries = if let Ok(entries) = self.read_dir(

            directory_hg_path,

            directory_fs_path,

            is_at_repo_root,

        ) {

            entries

        } else {

            // Treat an unreadable directory (typically because of insufficient

            // permissions) like an empty directory. `self.read_dir` has

            // already called `self.io_error` so a warning will be emitted.

            Vec::new()

        };

        // `merge_join_by` requires both its input iterators to be sorted:

        let dirstate_nodes = dirstate_nodes.sorted();

        // `sort_unstable_by_key` doesn’t allow keys borrowing from the value:

        // https://github.com/rust-lang/rust/issues/34162

        fs_entries.sort_unstable_by(|e1, e2| e1.base_name.cmp(&e2.base_name));

        // Propagate here any error that would happen inside the comparison

        // callback below

        for dirstate_node in &dirstate_nodes {

            dirstate_node.base_name(self.dmap.on_disk)?;

        }

        itertools::merge_join_by(

            dirstate_nodes,

            &fs_entries,

            |dirstate_node, fs_entry| {

                // This `unwrap` never panics because we already propagated

                // those errors above

                dirstate_node

                    .base_name(self.dmap.on_disk)

                    .unwrap()

                    .cmp(&fs_entry.base_name)

            },

        )

        .par_bridge()

        .map(|pair| {

            use itertools::EitherOrBoth::*;

            let has_dirstate_node_or_is_ignored;

            match pair {

                Both(dirstate_node, fs_entry) => {

                    self.traverse_fs_and_dirstate(

                        &fs_entry.full_path,

                        &fs_entry.metadata,

                        dirstate_node,

                        has_ignored_ancestor,

                    )?;

                    has_dirstate_node_or_is_ignored = true

                }

                Left(dirstate_node) => {

                    self.traverse_dirstate_only(dirstate_node)?;

                    has_dirstate_node_or_is_ignored = true;

                }

                Right(fs_entry) => {

                    has_dirstate_node_or_is_ignored = self.traverse_fs_only(

                        has_ignored_ancestor,

                        directory_hg_path,

                        fs_entry,

                    )

                }

            }

            Ok(has_dirstate_node_or_is_ignored)

        })

        .try_reduce(|| true, |a, b| Ok(a && b))

    }

    fn traverse_fs_and_dirstate(

        &self,

        fs_path: &Path,

        fs_metadata: &std::fs::Metadata,

        dirstate_node: NodeRef<'tree, 'on_disk>,

        has_ignored_ancestor: bool,