comparison rust/hg-core/src/dirstate_tree/on_disk.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

47329:717a94b423b9

//! the nodes representing the files and directories at the root of the
//! repository. Each node is also fixed-size, defined by the `Node` struct.
//! Nodes in turn contain slices to variable-size paths, and to their own child
//! nodes (if any) for nested files and directories.

use crate::dirstate::parsers::clear_ambiguous_mtime;
use crate::dirstate::parsers::Timestamp;
use crate::dirstate_tree::dirstate_map::{self, DirstateMap};
use crate::dirstate_tree::path_with_basename::WithBasename;
use crate::errors::HgError;
use crate::utils::hg_path::HgPath;
use crate::DirstateEntry;

}

pub(super) fn write(
    dirstate_map: &mut DirstateMap,
    parents: DirstateParents,
    now: Timestamp,
) -> Result<Vec<u8>, DirstateError> {
    // TODO: how do we want to handle this in 2038?
    let now: i32 = now.0.try_into().expect("time overflow");

    let header_len = std::mem::size_of::<Header>();

    // This ignores the space for paths, and for nodes without an entry.
    // TODO: better estimate? Skip the `Vec` and write to a file directly?
    let size_guess = header_len

    // Keep space for the header. We’ll fill it out at the end when we know the
    // actual offset for the root nodes.
    out.resize(header_len, 0_u8);

    let root = write_nodes(&mut dirstate_map.root, now, &mut out)?;

    let header = Header {
        marker: *V2_FORMAT_MARKER,
        parents: parents,
        root,

    };
    out[..header_len].copy_from_slice(header.as_bytes());
    Ok(out)
}

/// Serialize the dirstate to the `v2` format after clearing ambigous `mtime`s.
fn write_nodes(
    nodes: &mut dirstate_map::ChildNodes,
    now: i32,
    out: &mut Vec<u8>,
) -> Result<ChildNodes, DirstateError> {
    // `dirstate_map::ChildNodes` is a `HashMap` with undefined iteration
    // order. Sort to enable binary search in the written file.
    let nodes = dirstate_map::Node::sorted(nodes);

    // First accumulate serialized nodes in a `Vec`
    let mut on_disk_nodes = Vec::with_capacity(nodes.len());
    for (full_path, node) in nodes {
        on_disk_nodes.push(Node {
            children: write_nodes(&mut node.children, now, out)?,
            tracked_descendants_count: node.tracked_descendants_count.into(),
            full_path: write_slice::<u8>(
                full_path.full_path().as_bytes(),
                out,
            ),

                    start: 0.into(),
                    len: 0.into(),
                }
            },
            entry: if let Some(entry) = &mut node.entry {
                clear_ambiguous_mtime(entry, now);
                OptEntry {
                    state: entry.state.into(),
                    mode: entry.mode.into(),
                    mtime: entry.mtime.into(),
                    size: entry.size.into(),

47330:73f23e7610f8

//! the nodes representing the files and directories at the root of the
//! repository. Each node is also fixed-size, defined by the `Node` struct.
//! Nodes in turn contain slices to variable-size paths, and to their own child
//! nodes (if any) for nested files and directories.

use crate::dirstate_tree::dirstate_map::{self, DirstateMap};
use crate::dirstate_tree::path_with_basename::WithBasename;
use crate::errors::HgError;
use crate::utils::hg_path::HgPath;
use crate::DirstateEntry;

}

pub(super) fn write(
    dirstate_map: &mut DirstateMap,
    parents: DirstateParents,
) -> Result<Vec<u8>, DirstateError> {
    let header_len = std::mem::size_of::<Header>();

    // This ignores the space for paths, and for nodes without an entry.
    // TODO: better estimate? Skip the `Vec` and write to a file directly?
    let size_guess = header_len

    // Keep space for the header. We’ll fill it out at the end when we know the
    // actual offset for the root nodes.
    out.resize(header_len, 0_u8);

    let root = write_nodes(&mut dirstate_map.root, &mut out)?;

    let header = Header {
        marker: *V2_FORMAT_MARKER,
        parents: parents,
        root,

    };
    out[..header_len].copy_from_slice(header.as_bytes());
    Ok(out)
}

fn write_nodes(
    nodes: &mut dirstate_map::ChildNodes,
    out: &mut Vec<u8>,
) -> Result<ChildNodes, DirstateError> {
    // `dirstate_map::ChildNodes` is a `HashMap` with undefined iteration
    // order. Sort to enable binary search in the written file.
    let nodes = dirstate_map::Node::sorted(nodes);

    // First accumulate serialized nodes in a `Vec`
    let mut on_disk_nodes = Vec::with_capacity(nodes.len());
    for (full_path, node) in nodes {
        on_disk_nodes.push(Node {
            children: write_nodes(&mut node.children, out)?,
            tracked_descendants_count: node.tracked_descendants_count.into(),
            full_path: write_slice::<u8>(
                full_path.full_path().as_bytes(),
                out,
            ),

                    start: 0.into(),
                    len: 0.into(),
                }
            },
            entry: if let Some(entry) = &mut node.entry {
                OptEntry {
                    state: entry.state.into(),
                    mode: entry.mode.into(),
                    mtime: entry.mtime.into(),
                    size: entry.size.into(),