// discovery.rs

//

// Copyright 2019 Georges Racinet <georges.racinet@octobus.net>

//

// This software may be used and distributed according to the terms of the

// GNU General Public License version 2 or any later version.

//! Discovery operations

//!

//! This is a Rust counterpart to the `partialdiscovery` class of

//! `mercurial.setdiscovery`

use super::{Graph, GraphError, Revision, NULL_REVISION};

use crate::{ancestors::MissingAncestors, dagops, FastHashMap};

use rand::seq::SliceRandom;

use rand::{thread_rng, RngCore, SeedableRng};

use std::cmp::{max, min};

use std::collections::{HashSet, VecDeque};

type Rng = rand_pcg::Pcg32;

pub struct PartialDiscovery<G: Graph + Clone> {

    target_heads: Option<Vec<Revision>>,

    graph: G, // plays the role of self._repo

    common: MissingAncestors<G>,

    undecided: Option<HashSet<Revision>>,

    children_cache: Option<FastHashMap<Revision, Vec<Revision>>>,

    missing: HashSet<Revision>,

    rng: Rng,

    respect_size: bool,

    randomize: bool,

}

pub struct DiscoveryStats {

    pub undecided: Option<usize>,

}

/// Update an existing sample to match the expected size

///

/// The sample is updated with revisions exponentially distant from each

/// element of `heads`.

///

/// If a target size is specified, the sampling will stop once this size is

/// reached. Otherwise sampling will happen until roots of the <revs> set are

/// reached.

///

/// - `revs`: set of revs we want to discover (if None, `assume` the whole dag

///   represented by `parentfn`

/// - `heads`: set of DAG head revs

/// - `sample`: a sample to update

/// - `parentfn`: a callable to resolve parents for a revision

/// - `quicksamplesize`: optional target size of the sample

fn update_sample<I>(

    revs: Option<&HashSet<Revision>>,

    heads: impl IntoIterator<Item = Revision>,

    sample: &mut HashSet<Revision>,

    parentsfn: impl Fn(Revision) -> Result<I, GraphError>,

    quicksamplesize: Option<usize>,

) -> Result<(), GraphError>

where

    I: Iterator<Item = Revision>,

{

    let mut distances: FastHashMap<Revision, u32> = FastHashMap::default();

    let mut visit: VecDeque<Revision> = heads.into_iter().collect();

    let mut factor: u32 = 1;

    let mut seen: HashSet<Revision> = HashSet::new();

    while let Some(current) = visit.pop_front() {

        if !seen.insert(current) {

            continue;

        }

        let d = *distances.entry(current).or_insert(1);

        if d > factor {

            factor *= 2;

        }

        if d == factor {

            sample.insert(current);

            if let Some(sz) = quicksamplesize {

                if sample.len() >= sz {

                    return Ok(());

                }

            }

        }

        for p in parentsfn(current)? {

            if let Some(revs) = revs {

                if !revs.contains(&p) {

                    continue;

                }

            }

            distances.entry(p).or_insert(d + 1);

            visit.push_back(p);

        }

    }

    Ok(())

}

struct ParentsIterator {

    parents: [Revision; 2],

    cur: usize,

}

impl ParentsIterator {

    fn graph_parents(

        graph: &impl Graph,

        r: Revision,

    ) -> Result<ParentsIterator, GraphError> {

        Ok(ParentsIterator {

            parents: graph.parents(r)?,

            cur: 0,

        })

    }

}

impl Iterator for ParentsIterator {

    type Item = Revision;

    fn next(&mut self) -> Option<Revision> {

        if self.cur > 1 {

            return None;

        }

        let rev = self.parents[self.cur];

        self.cur += 1;

        if rev == NULL_REVISION {

            return self.next();

        }

        Some(rev)

    }

}

impl<G: Graph + Clone> PartialDiscovery<G> {

    /// Create a PartialDiscovery object, with the intent

    /// of comparing our `::<target_heads>` revset to the contents of another

    /// repo.

    ///

    /// For now `target_heads` is passed as a vector, and will be used

    /// at the first call to `ensure_undecided()`.

    ///

    /// If we want to make the signature more flexible,

    /// we'll have to make it a type argument of `PartialDiscovery` or a trait

    /// object since we'll keep it in the meanwhile

    ///

    /// The `respect_size` boolean controls how the sampling methods

    /// will interpret the size argument requested by the caller. If it's

    /// `false`, they are allowed to produce a sample whose size is more

    /// appropriate to the situation (typically bigger).

    ///

    /// The `randomize` boolean affects sampling, and specifically how

    /// limiting or last-minute expanding is been done:

    ///

    /// If `true`, both will perform random picking from `self.undecided`.

    /// This is currently the best for actual discoveries.

    ///

    /// If `false`, a reproductible picking strategy is performed. This is

    /// useful for integration tests.

    pub fn new(

        graph: G,

        target_heads: Vec<Revision>,

        respect_size: bool,

        randomize: bool,

    ) -> Self {

        if randomize {

            thread_rng().fill_bytes(&mut seed);

        }

        Self::new_with_seed(graph, target_heads, seed, respect_size, randomize)

    }

    pub fn new_with_seed(

        graph: G,

        target_heads: Vec<Revision>,

        respect_size: bool,

        randomize: bool,

    ) -> Self {

        PartialDiscovery {

            undecided: None,

            children_cache: None,

            target_heads: Some(target_heads),

            graph: graph.clone(),

            common: MissingAncestors::new(graph, vec![]),

            missing: HashSet::new(),

            rng: Rng::from_seed(seed),

            respect_size: respect_size,

            randomize: randomize,

        }

    }

    /// Extract at most `size` random elements from sample and return them

    /// as a vector

    fn limit_sample(

        &mut self,

        mut sample: Vec<Revision>,

        size: usize,

    ) -> Vec<Revision> {

        if !self.randomize {

            sample.sort();

            sample.truncate(size);

            return sample;

        }

        let sample_len = sample.len();

        if sample_len <= size {

            return sample;

        }

        let rng = &mut self.rng;

        let dropped_size = sample_len - size;

        let limited_slice = if size < dropped_size {

            sample.partial_shuffle(rng, size).0

        } else {

            sample.partial_shuffle(rng, dropped_size).1

        };

        limited_slice.to_owned()

    }

    /// Register revisions known as being common

    pub fn add_common_revisions(

        &mut self,

        common: impl IntoIterator<Item = Revision>,

    ) -> Result<(), GraphError> {

        let before_len = self.common.get_bases().len();

        self.common.add_bases(common);

        if self.common.get_bases().len() == before_len {

            return Ok(());

        }

        if let Some(ref mut undecided) = self.undecided {

            self.common.remove_ancestors_from(undecided)?;

        }

        Ok(())

    }

    /// Register revisions known as being missing

    ///

    /// # Performance note

    ///

    /// Except in the most trivial case, the first call of this method has

    /// the side effect of computing `self.undecided` set for the first time,

    /// and the related caches it might need for efficiency of its internal

    /// computation. This is typically faster if more information is

    /// available in `self.common`. Therefore, for good performance, the

    /// caller should avoid calling this too early.

    pub fn add_missing_revisions(

        &mut self,

        missing: impl IntoIterator<Item = Revision>,

    ) -> Result<(), GraphError> {

        let mut tovisit: VecDeque<Revision> = missing.into_iter().collect();

        if tovisit.is_empty() {

            return Ok(());

        }

        self.ensure_children_cache()?;

        self.ensure_undecided()?; // for safety of possible future refactors

        let children = self.children_cache.as_ref().unwrap();

        let mut seen: HashSet<Revision> = HashSet::new();

        let undecided_mut = self.undecided.as_mut().unwrap();

        while let Some(rev) = tovisit.pop_front() {

            if !self.missing.insert(rev) {

                // either it's known to be missing from a previous

                // invocation, and there's no need to iterate on its

                // children (we now they are all missing)

                // or it's from a previous iteration of this loop

                // and its children have already been queued

                continue;

            }

            undecided_mut.remove(&rev);

            match children.get(&rev) {

                None => {

                    continue;

                }

                Some(this_children) => {

                    for child in this_children.iter().cloned() {

                        if seen.insert(child) {

                            tovisit.push_back(child);

                        }

                    }

                }

            }

        }

        Ok(())

    }

    /// Do we have any information about the peer?

    pub fn has_info(&self) -> bool {

        self.common.has_bases()

    }

    /// Did we acquire full knowledge of our Revisions that the peer has?

    pub fn is_complete(&self) -> bool {

        self.undecided.as_ref().map_or(false, |s| s.is_empty())

    }

    /// Return the heads of the currently known common set of revisions.

    ///

    /// If the discovery process is not complete (see `is_complete()`), the

    /// caller must be aware that this is an intermediate state.

    ///

    /// On the other hand, if it is complete, then this is currently

    /// the only way to retrieve the end results of the discovery process.

    ///

    /// We may introduce in the future an `into_common_heads` call that

    /// would be more appropriate for normal Rust callers, dropping `self`

    /// if it is complete.

    pub fn common_heads(&self) -> Result<HashSet<Revision>, GraphError> {

        self.common.bases_heads()

    }

    /// Force first computation of `self.undecided`

    ///

    /// After this, `self.undecided.as_ref()` and `.as_mut()` can be

    /// unwrapped to get workable immutable or mutable references without

    /// any panic.

    ///

    /// This is an imperative call instead of an access with added lazyness

    /// to reduce easily the scope of mutable borrow for the caller,

    /// compared to undecided(&'a mut self) -> &'a… that would keep it

    /// as long as the resulting immutable one.

    fn ensure_undecided(&mut self) -> Result<(), GraphError> {

        if self.undecided.is_some() {

            return Ok(());

        }

        let tgt = self.target_heads.take().unwrap();

        self.undecided =

            Some(self.common.missing_ancestors(tgt)?.into_iter().collect());

        Ok(())

    }

    fn ensure_children_cache(&mut self) -> Result<(), GraphError> {

        if self.children_cache.is_some() {

            return Ok(());

        }

        self.ensure_undecided()?;

        let mut children: FastHashMap<Revision, Vec<Revision>> =

            FastHashMap::default();

        for &rev in self.undecided.as_ref().unwrap() {

            for p in ParentsIterator::graph_parents(&self.graph, rev)? {

                children.entry(p).or_insert_with(|| Vec::new()).push(rev);

            }

        }

        self.children_cache = Some(children);

        Ok(())

    }

    /// Provide statistics about the current state of the discovery process

    pub fn stats(&self) -> DiscoveryStats {

        DiscoveryStats {

            undecided: self.undecided.as_ref().map(|s| s.len()),

        }

    }

    pub fn take_quick_sample(

        &mut self,

        headrevs: impl IntoIterator<Item = Revision>,

        size: usize,

    ) -> Result<Vec<Revision>, GraphError> {

        self.ensure_undecided()?;

        let mut sample = {

            let undecided = self.undecided.as_ref().unwrap();