view rust/hg-core/src/operations/cat.rs @ 47353:73ddcedeaadf

dirstate-tree: Change status() results to not borrow DirstateMap The `status` function takes a `&'tree mut DirstateMap<'on_disk>` parameter. `'on_disk` borrows a read-only byte buffer with the contents of the `.hg/dirstate` file. `DirstateMap` internally uses represents file paths as `std::borrow::Cow<'on_disk, HgPath>`, which borrows the byte buffer when possible and allocates an owned string if not, such as for files added to the dirstate after it was loaded from disk. Previously the return type of of `status` has a `'tree`?lifetime, meaning it could borrow all paths from the `DirstateMap`. With this changeset, that lifetime is changed to `'on_disk` meaning that only paths from the byte buffer can be borrowed, and paths allocated by `DirstateMap` must be copied. Usually most paths are in the byte buffer, and most paths are not part of the return value of `status`, so the number of extra copies should be small. This change will enable `status` to mutate the `DirstateMap` after it has finished constructing its return value. Previously such mutation would be prevented by possible on-going borrows. Differential Revision: https://phab.mercurial-scm.org/D10824
author Simon Sapin <simon.sapin@octobus.net>
date Fri, 28 May 2021 20:07:27 +0200
parents b1f2c2b336ec
children d44740725b95
line wrap: on
line source

// list_tracked_files.rs
//
// Copyright 2020 Antoine Cezar <antoine.cezar@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.

use std::path::PathBuf;

use crate::repo::Repo;
use crate::revlog::changelog::Changelog;
use crate::revlog::manifest::Manifest;
use crate::revlog::path_encode::path_encode;
use crate::revlog::revlog::Revlog;
use crate::revlog::revlog::RevlogError;
use crate::revlog::Node;
use crate::utils::files::get_path_from_bytes;
use crate::utils::hg_path::{HgPath, HgPathBuf};

pub struct CatOutput {
    /// Whether any file in the manifest matched the paths given as CLI
    /// arguments
    pub found_any: bool,
    /// The contents of matching files, in manifest order
    pub concatenated: Vec<u8>,
    /// Which of the CLI arguments did not match any manifest file
    pub missing: Vec<HgPathBuf>,
    /// The node ID that the given revset was resolved to
    pub node: Node,
}

const METADATA_DELIMITER: [u8; 2] = [b'\x01', b'\n'];

/// Output the given revision of files
///
/// * `root`: Repository root
/// * `rev`: The revision to cat the files from.
/// * `files`: The files to output.
pub fn cat<'a>(
    repo: &Repo,
    revset: &str,
    files: &'a [HgPathBuf],
) -> Result<CatOutput, RevlogError> {
    let rev = crate::revset::resolve_single(revset, repo)?;
    let changelog = Changelog::open(repo)?;
    let manifest = Manifest::open(repo)?;
    let changelog_entry = changelog.get_rev(rev)?;
    let node = *changelog
        .node_from_rev(rev)
        .expect("should succeed when changelog.get_rev did");
    let manifest_node =
        Node::from_hex_for_repo(&changelog_entry.manifest_node()?)?;
    let manifest_entry = manifest.get_node(manifest_node.into())?;
    let mut bytes = vec![];
    let mut matched = vec![false; files.len()];
    let mut found_any = false;

    for (manifest_file, node_bytes) in manifest_entry.files_with_nodes() {
        for (cat_file, is_matched) in files.iter().zip(&mut matched) {
            if cat_file.as_bytes() == manifest_file.as_bytes() {
                *is_matched = true;
                found_any = true;
                let index_path = store_path(manifest_file, b".i");
                let data_path = store_path(manifest_file, b".d");

                let file_log =
                    Revlog::open(repo, &index_path, Some(&data_path))?;
                let file_node = Node::from_hex_for_repo(node_bytes)?;
                let file_rev = file_log.get_node_rev(file_node.into())?;
                let data = file_log.get_rev_data(file_rev)?;
                if data.starts_with(&METADATA_DELIMITER) {
                    let end_delimiter_position = data
                        [METADATA_DELIMITER.len()..]
                        .windows(METADATA_DELIMITER.len())
                        .position(|bytes| bytes == METADATA_DELIMITER);
                    if let Some(position) = end_delimiter_position {
                        let offset = METADATA_DELIMITER.len() * 2;
                        bytes.extend(data[position + offset..].iter());
                    }
                } else {
                    bytes.extend(data);
                }
            }
        }
    }

    let missing: Vec<_> = files
        .iter()
        .zip(&matched)
        .filter(|pair| !*pair.1)
        .map(|pair| pair.0.clone())
        .collect();
    Ok(CatOutput {
        found_any,
        concatenated: bytes,
        missing,
        node,
    })
}

fn store_path(hg_path: &HgPath, suffix: &[u8]) -> PathBuf {
    let encoded_bytes =
        path_encode(&[b"data/", hg_path.as_bytes(), suffix].concat());
    get_path_from_bytes(&encoded_bytes).into()
}