view rust/hg-core/src/operations/cat.rs @ 51929:f2832de2a46c

interfaces: introduce and use a protocol class for the `bdiff` module This is allowed by PEP 544[1], and we basically follow the example there. The class here is copied from `mercurial.pure.bdiff`, and the implementation removed. There are several modules that have a few different implementations, and the implementation chosen is controlled by `HGMODULEPOLICY`. The module is loaded via `mercurial/policy.py`, and has been inferred by pytype as `Any` up to this point. Therefore it and PyCharm were blind to all functions on the module, and their signatures. Also, having multiple instances of the same module allows their signatures to get out of sync. Introducing a protocol class allows the loaded module that is stored in a variable to be given type info, which cascades through the various places it is used. This change alters 11 *.pyi files, for example. In theory, this would also allow us to ensure the various implementations of the same module are kept in alignment- simply import the module in a test module, attempt to pass it to a function that uses the corresponding protocol as an argument, and run pytype on it. In practice, this doesn't work (yet). PyCharm (erroneously) flags imported modules being passed where a protocol class is used[2]. Pytype has problems the other way- it fails to detect when a module that doesn't adhere to the protocol is passed to a protocol argument. The good news is that mypy properly detects this case. The bad news is that mypy spews a bunch of other errors when importing even simple modules, like the various `bdiff` modules. Therefore I'm punting on the tests for now because the type info around a loaded module in PyCharm is a clear win by itself. [1] https://peps.python.org/pep-0544/#modules-as-implementations-of-protocols [2] https://youtrack.jetbrains.com/issue/PY-58679/Support-modules-implementing-protocols
author Matt Harbison <matt_harbison@yahoo.com>
date Sat, 28 Sep 2024 19:12:18 -0400
parents 1928b770e3e7
children bd8081e9fd62
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 crate::repo::Repo;
use crate::revlog::Node;
use crate::revlog::RevlogError;

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

use crate::errors::HgError;
use crate::manifest::Manifest;
use crate::manifest::ManifestEntry;
use itertools::put_back;
use itertools::PutBack;
use std::cmp::Ordering;

pub struct CatOutput<'a> {
    /// 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 results: Vec<(&'a HgPath, Vec<u8>)>,
    /// Which of the CLI arguments did not match any manifest file
    pub missing: Vec<&'a HgPath>,
    /// The node ID that the given revset was resolved to
    pub node: Node,
}

// Find an item in an iterator over a sorted collection.
fn find_item<'a>(
    i: &mut PutBack<impl Iterator<Item = Result<ManifestEntry<'a>, HgError>>>,
    needle: &HgPath,
) -> Result<Option<Node>, HgError> {
    loop {
        match i.next() {
            None => return Ok(None),
            Some(result) => {
                let entry = result?;
                match needle.as_bytes().cmp(entry.path.as_bytes()) {
                    Ordering::Less => {
                        i.put_back(Ok(entry));
                        return Ok(None);
                    }
                    Ordering::Greater => continue,
                    Ordering::Equal => return Ok(Some(entry.node_id()?)),
                }
            }
        }
    }
}

// Tuple of (missing, found) paths in the manifest
type ManifestQueryResponse<'a> = (Vec<(&'a HgPath, Node)>, Vec<&'a HgPath>);

fn find_files_in_manifest<'query>(
    manifest: &Manifest,
    query: impl Iterator<Item = &'query HgPath>,
) -> Result<ManifestQueryResponse<'query>, HgError> {
    let mut manifest = put_back(manifest.iter());
    let mut res = vec![];
    let mut missing = vec![];

    for file in query {
        match find_item(&mut manifest, file)? {
            None => missing.push(file),
            Some(item) => res.push((file, item)),
        }
    }
    Ok((res, missing))
}

/// 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,
    mut files: Vec<&'a HgPath>,
) -> Result<CatOutput<'a>, RevlogError> {
    let rev = crate::revset::resolve_single(revset, repo)?;
    let manifest = repo.manifest_for_rev(rev.into())?;
    let node = *repo
        .changelog()?
        .node_from_rev(rev.into())
        .expect("should succeed when repo.manifest did");
    let mut results: Vec<(&'a HgPath, Vec<u8>)> = vec![];
    let mut found_any = false;

    files.sort_unstable();

    let (found, missing) =
        find_files_in_manifest(&manifest, files.into_iter())?;

    for (file_path, file_node) in found {
        found_any = true;
        let file_log = repo.filelog(file_path)?;
        results.push((
            file_path,
            file_log.data_for_node(file_node)?.into_file_data()?,
        ));
    }

    Ok(CatOutput {
        found_any,
        results,
        missing,
        node,
    })
}