view rust/hg-core/src/dirstate/dirstate_map.rs @ 47330:73f23e7610f8

dirstate-tree: Remove DirstateMap::iter_node_data_mut

In an upcoming changeset we want DirstateMap to be able to work directly
with nodes in their "on disk" representation, without always allocating
corresponding in-memory data structures. Nodes would have two possible
representations: one immutable "on disk" refering to the bytes buffer
of the contents of the .hg/dirstate file, and one mutable with HashMap
like the curren data structure.

These nodes would have copy-on-write semantics: when an immutable node
would need to be mutated, instead we allocate new mutable node for it and
its ancestors.

A mutable iterator of the entire tree would still be possible, but it would
become much more expensive since we’d need to allocate mutable nodes for
everything.

Instead, remove this iterator. It was only used to clear ambiguous mtimes
while serializing the `DirstateMap`. Instead clearing and serialization are
now two separate passes. Clearing first uses an immutable iterator to collect
the paths of nodes that need to be cleared, then accesses only those nodes
mutably.

Differential Revision: https://phab.mercurial-scm.org/D10744

// dirstate_map.rs
//
// Copyright 2019 Raphaël Gomès <[e-mail]>
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.

use crate::dirstate::parsers::Timestamp;
use crate::{
    dirstate::EntryState,
    pack_dirstate, parse_dirstate,
    utils::hg_path::{HgPath, HgPathBuf},
    CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateMapError,
    DirstateParents, StateMap,
};
use micro_timer::timed;
use std::collections::HashSet;
use std::iter::FromIterator;
use std::ops::Deref;

#[derive(Default)]
pub struct DirstateMap {
    state_map: StateMap,
    pub copy_map: CopyMap,
    pub dirs: Option<DirsMultiset>,
    pub all_dirs: Option<DirsMultiset>,
    non_normal_set: Option<HashSet<HgPathBuf>>,
    other_parent_set: Option<HashSet<HgPathBuf>>,
}

/// Should only really be used in python interface code, for clarity
impl Deref for DirstateMap {
    type Target = StateMap;

    fn deref(&self) -> &Self::Target {
        &self.state_map
    }
}

impl FromIterator<(HgPathBuf, DirstateEntry)> for DirstateMap {
    fn from_iter<I: IntoIterator<Item = (HgPathBuf, DirstateEntry)>>(
        iter: I,
    ) -> Self {
        Self {
            state_map: iter.into_iter().collect(),
            ..Self::default()
        }
    }
}

impl DirstateMap {
    pub fn new() -> Self {
        Self::default()
    }

    pub fn clear(&mut self) {
        self.state_map = StateMap::default();
        self.copy_map.clear();
        self.non_normal_set = None;
        self.other_parent_set = None;
    }

    /// Add a tracked file to the dirstate
    pub fn add_file(
        &mut self,
        filename: &HgPath,
        old_state: EntryState,
        entry: DirstateEntry,
    ) -> Result<(), DirstateMapError> {
        if old_state == EntryState::Unknown || old_state == EntryState::Removed
        {
            if let Some(ref mut dirs) = self.dirs {
                dirs.add_path(filename)?;
            }
        }
        if old_state == EntryState::Unknown {
            if let Some(ref mut all_dirs) = self.all_dirs {
                all_dirs.add_path(filename)?;
            }
        }
        self.state_map.insert(filename.to_owned(), entry.to_owned());

        if entry.is_non_normal() {
            self.get_non_normal_other_parent_entries()
                .0
                .insert(filename.to_owned());
        }

        if entry.is_from_other_parent() {
            self.get_non_normal_other_parent_entries()
                .1
                .insert(filename.to_owned());
        }
        Ok(())
    }

    /// Mark a file as removed in the dirstate.
    ///
    /// The `size` parameter is used to store sentinel values that indicate
    /// the file's previous state.  In the future, we should refactor this
    /// to be more explicit about what that state is.
    pub fn remove_file(
        &mut self,
        filename: &HgPath,
        old_state: EntryState,
        size: i32,
    ) -> Result<(), DirstateMapError> {
        if old_state != EntryState::Unknown && old_state != EntryState::Removed
        {
            if let Some(ref mut dirs) = self.dirs {
                dirs.delete_path(filename)?;
            }
        }
        if old_state == EntryState::Unknown {
            if let Some(ref mut all_dirs) = self.all_dirs {
                all_dirs.add_path(filename)?;
            }
        }

        self.state_map.insert(
            filename.to_owned(),
            DirstateEntry {
                state: EntryState::Removed,
                mode: 0,
                size,
                mtime: 0,
            },
        );
        self.get_non_normal_other_parent_entries()
            .0
            .insert(filename.to_owned());
        Ok(())
    }

    /// Remove a file from the dirstate.
    /// Returns `true` if the file was previously recorded.
    pub fn drop_file(
        &mut self,
        filename: &HgPath,
        old_state: EntryState,
    ) -> Result<bool, DirstateMapError> {
        let exists = self.state_map.remove(filename).is_some();

        if exists {
            if old_state != EntryState::Removed {
                if let Some(ref mut dirs) = self.dirs {
                    dirs.delete_path(filename)?;
                }
            }
            if let Some(ref mut all_dirs) = self.all_dirs {
                all_dirs.delete_path(filename)?;
            }
        }
        self.get_non_normal_other_parent_entries()
            .0
            .remove(filename);

        Ok(exists)
    }

    pub fn clear_ambiguous_times(
        &mut self,
        filenames: Vec<HgPathBuf>,
        now: i32,
    ) {
        for filename in filenames {
            if let Some(entry) = self.state_map.get_mut(&filename) {
                if entry.clear_ambiguous_mtime(now) {
                    self.get_non_normal_other_parent_entries()
                        .0
                        .insert(filename.to_owned());
                }
            }
        }
    }

    pub fn non_normal_entries_remove(&mut self, key: impl AsRef<HgPath>) {
        self.get_non_normal_other_parent_entries()
            .0
            .remove(key.as_ref());
    }

    pub fn non_normal_entries_union(
        &mut self,
        other: HashSet<HgPathBuf>,
    ) -> Vec<HgPathBuf> {
        self.get_non_normal_other_parent_entries()
            .0
            .union(&other)
            .map(ToOwned::to_owned)
            .collect()
    }

    pub fn get_non_normal_other_parent_entries(
        &mut self,
    ) -> (&mut HashSet<HgPathBuf>, &mut HashSet<HgPathBuf>) {
        self.set_non_normal_other_parent_entries(false);
        (
            self.non_normal_set.as_mut().unwrap(),
            self.other_parent_set.as_mut().unwrap(),
        )
    }

    /// Useful to get immutable references to those sets in contexts where
    /// you only have an immutable reference to the `DirstateMap`, like when
    /// sharing references with Python.
    ///
    /// TODO, get rid of this along with the other "setter/getter" stuff when
    /// a nice typestate plan is defined.
    ///
    /// # Panics
    ///
    /// Will panic if either set is `None`.
    pub fn get_non_normal_other_parent_entries_panic(
        &self,
    ) -> (&HashSet<HgPathBuf>, &HashSet<HgPathBuf>) {
        (
            self.non_normal_set.as_ref().unwrap(),
            self.other_parent_set.as_ref().unwrap(),
        )
    }

    pub fn set_non_normal_other_parent_entries(&mut self, force: bool) {
        if !force
            && self.non_normal_set.is_some()
            && self.other_parent_set.is_some()
        {
            return;
        }
        let mut non_normal = HashSet::new();
        let mut other_parent = HashSet::new();

        for (filename, entry) in self.state_map.iter() {
            if entry.is_non_normal() {
                non_normal.insert(filename.to_owned());
            }
            if entry.is_from_other_parent() {
                other_parent.insert(filename.to_owned());
            }
        }
        self.non_normal_set = Some(non_normal);
        self.other_parent_set = Some(other_parent);
    }

    /// Both of these setters and their uses appear to be the simplest way to
    /// emulate a Python lazy property, but it is ugly and unidiomatic.
    /// TODO One day, rewriting this struct using the typestate might be a
    /// good idea.
    pub fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
        if self.all_dirs.is_none() {
            self.all_dirs = Some(DirsMultiset::from_dirstate(
                self.state_map.iter(),
                None,
            )?);
        }
        Ok(())
    }

    pub fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
        if self.dirs.is_none() {
            self.dirs = Some(DirsMultiset::from_dirstate(
                self.state_map.iter(),
                Some(EntryState::Removed),
            )?);
        }
        Ok(())
    }

    pub fn has_tracked_dir(
        &mut self,
        directory: &HgPath,
    ) -> Result<bool, DirstateMapError> {
        self.set_dirs()?;
        Ok(self.dirs.as_ref().unwrap().contains(directory))
    }

    pub fn has_dir(
        &mut self,
        directory: &HgPath,
    ) -> Result<bool, DirstateMapError> {
        self.set_all_dirs()?;
        Ok(self.all_dirs.as_ref().unwrap().contains(directory))
    }

    #[timed]
    pub fn read(
        &mut self,
        file_contents: &[u8],
    ) -> Result<Option<DirstateParents>, DirstateError> {
        if file_contents.is_empty() {
            return Ok(None);
        }

        let (parents, entries, copies) = parse_dirstate(file_contents)?;
        self.state_map.extend(
            entries
                .into_iter()
                .map(|(path, entry)| (path.to_owned(), entry)),
        );
        self.copy_map.extend(
            copies
                .into_iter()
                .map(|(path, copy)| (path.to_owned(), copy.to_owned())),
        );
        Ok(Some(parents.clone()))
    }

    pub fn pack(
        &mut self,
        parents: DirstateParents,
        now: Timestamp,
    ) -> Result<Vec<u8>, DirstateError> {
        let packed =
            pack_dirstate(&mut self.state_map, &self.copy_map, parents, now)?;

        self.set_non_normal_other_parent_entries(true);
        Ok(packed)
    }
}

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

    #[test]
    fn test_dirs_multiset() {
        let mut map = DirstateMap::new();
        assert!(map.dirs.is_none());
        assert!(map.all_dirs.is_none());

        assert_eq!(map.has_dir(HgPath::new(b"nope")).unwrap(), false);
        assert!(map.all_dirs.is_some());
        assert!(map.dirs.is_none());

        assert_eq!(map.has_tracked_dir(HgPath::new(b"nope")).unwrap(), false);
        assert!(map.dirs.is_some());
    }

    #[test]
    fn test_add_file() {
        let mut map = DirstateMap::new();

        assert_eq!(0, map.len());

        map.add_file(
            HgPath::new(b"meh"),
            EntryState::Normal,
            DirstateEntry {
                state: EntryState::Normal,
                mode: 1337,
                mtime: 1337,
                size: 1337,
            },
        )
        .unwrap();

        assert_eq!(1, map.len());
        assert_eq!(0, map.get_non_normal_other_parent_entries().0.len());
        assert_eq!(0, map.get_non_normal_other_parent_entries().1.len());
    }

    #[test]
    fn test_non_normal_other_parent_entries() {
        let mut map: DirstateMap = [
            (b"f1", (EntryState::Removed, 1337, 1337, 1337)),
            (b"f2", (EntryState::Normal, 1337, 1337, -1)),
            (b"f3", (EntryState::Normal, 1337, 1337, 1337)),
            (b"f4", (EntryState::Normal, 1337, -2, 1337)),
            (b"f5", (EntryState::Added, 1337, 1337, 1337)),
            (b"f6", (EntryState::Added, 1337, 1337, -1)),
            (b"f7", (EntryState::Merged, 1337, 1337, -1)),
            (b"f8", (EntryState::Merged, 1337, 1337, 1337)),
            (b"f9", (EntryState::Merged, 1337, -2, 1337)),
            (b"fa", (EntryState::Added, 1337, -2, 1337)),
            (b"fb", (EntryState::Removed, 1337, -2, 1337)),
        ]
        .iter()
        .map(|(fname, (state, mode, size, mtime))| {
            (
                HgPathBuf::from_bytes(fname.as_ref()),
                DirstateEntry {
                    state: *state,
                    mode: *mode,
                    size: *size,
                    mtime: *mtime,
                },
            )
        })
        .collect();

        let mut non_normal = [
            b"f1", b"f2", b"f5", b"f6", b"f7", b"f8", b"f9", b"fa", b"fb",
        ]
        .iter()
        .map(|x| HgPathBuf::from_bytes(x.as_ref()))
        .collect();

        let mut other_parent = HashSet::new();
        other_parent.insert(HgPathBuf::from_bytes(b"f4"));
        let entries = map.get_non_normal_other_parent_entries();

        assert_eq!(
            (&mut non_normal, &mut other_parent),
            (entries.0, entries.1)
        );
    }
}