ahab/src/commands/link/check.rs

use fs_err::{read_dir, read_link};
use std::ffi::OsString;
use std::os::unix::ffi::{OsStrExt, OsStringExt};
use std::path::{Path, PathBuf};

use anyhow::{Result, anyhow};

use super::store::{Leads, Repo, leads, resolve, symlink_metadata_opt};
use crate::cli::link as cli;
use crate::cmd::{Cmd, LsFiles};
use crate::ctx::Ctx;
use crate::output::{line, text, write_bytes};

// whether anything is outside the store, which main turns into an exit code
pub fn check(ctx: &Ctx, args: &cli::Check) -> Result<bool> {
    let repo = Repo::discover(ctx, args.store.root())?;
    let pathspecs = relative_pathspecs(&repo, &args.paths)?;

    let mut exposed = Vec::new();
    // git lists untracked and ignored separately
    for (mark, ignored) in [(UNTRACKED, false), (IGNORED, true)] {
        for entry in list_others(ctx, &repo, ignored, &pathspecs)? {
            // --directory collapses a wholly untracked dir into `dir/`
            match entry.strip_suffix(b"/") {
                Some(dir) => exposed.extend(walk(&repo, &path_from(dir), mark)?.1),
                None => exposed.extend(classify(&repo, &path_from(&entry), mark)?),
            }
        }
    }

    // and says nothing about tracked paths, where a symlink out still counts
    for entry in list_tracked(ctx, &repo, &pathspecs)? {
        exposed.extend(classify_tracked(&repo, &path_from(&entry))?);
    }

    exposed.sort_by(|a, b| a.name.cmp(&b.name));

    if args.porcelain || args.null {
        print_porcelain(&exposed, args.null);
    } else {
        print_listing(&repo, &exposed);
    }

    Ok(!exposed.is_empty())
}

fn print_porcelain(exposed: &[Exposed], null: bool) {
    // -z is the format for scripts that must survive any filename, so its
    // records are written as the bytes a path actually is. a filename can hold
    // an arrow but not a NUL, as `git status -z` also assumes
    if null {
        for item in exposed {
            let mut record = item.code().into_bytes();
            record.push(b' ');
            record.extend_from_slice(item.name.as_os_str().as_bytes());

            if let Some(dest) = &item.dest {
                record.push(0);
                record.extend_from_slice(dest.as_os_str().as_bytes());
            }

            record.push(0);
            write_bytes(&record);
        }

        return;
    }

    for item in exposed {
        match &item.dest {
            Some(dest) => text!(
                "{} {} -> {}\n",
                item.code(),
                item.name.display(),
                dest.display()
            ),
            None => text!("{} {}\n", item.code(), item.name.display()),
        }
    }
}

fn print_listing(repo: &Repo, exposed: &[Exposed]) {
    line!("store: {}", repo.store.display());

    if exposed.is_empty() {
        line!("nothing outside the store, a sandbox would see tracked files only");
        return;
    }

    let sections = [
        (
            "Untracked paths a sandbox can read:",
            "  (use \"ahab link add <path>...\" to move them into the store)",
            Section::Content(UNTRACKED),
        ),
        (
            "Ignored paths a sandbox can read:",
            "  (use \"ahab link add <path>...\" to move them into the store)",
            Section::Content(IGNORED),
        ),
        (
            "Symlinks leading outside the store:",
            "  (their contents are not in the repository either way)",
            Section::Elsewhere,
        ),
    ];

    for (heading, hint, section) in sections {
        let mut items = exposed.iter().filter(|item| section.holds(item)).peekable();
        if items.peek().is_none() {
            continue;
        }

        line!("\n{heading}\n{hint}");
        for item in items {
            match &item.dest {
                Some(dest) => line!("\t{} -> {}", item.name.display(), dest.display()),
                None => line!("\t{}", item.name.display()),
            }
        }
    }
}

enum Section {
    Content(char),
    Elsewhere,
}

impl Section {
    fn holds(&self, item: &Exposed) -> bool {
        match self {
            Self::Content(mark) => item.dest.is_none() && item.mark == *mark,
            Self::Elsewhere => item.dest.is_some(),
        }
    }
}

// status codes as `git status --porcelain` spells them
const UNTRACKED: char = '?';
const IGNORED: char = '!';
const ELSEWHERE: char = '>';
// no git equivalent: a tracked path, which only ever appears as a symlink out
const TRACKED: char = 'T';

struct Exposed {
    mark: char,
    name: PathBuf,
    dest: Option<PathBuf>,
}

impl Exposed {
    fn content(mark: char, name: PathBuf) -> Self {
        Self {
            mark,
            name,
            dest: None,
        }
    }

    fn code(&self) -> String {
        let second = if self.dest.is_some() {
            ELSEWHERE
        } else {
            self.mark
        };
        format!("{}{second}", self.mark)
    }
}

fn classify(repo: &Repo, rel: &Path, mark: char) -> Result<Option<Exposed>> {
    let src = repo.root.join(rel);
    let name = rel.to_path_buf();

    let Some(meta) = symlink_metadata_opt(&src)? else {
        return Ok(None);
    };
    if !meta.is_symlink() {
        return Ok(Some(Exposed::content(mark, name)));
    }

    let dest = read_link(&src)?;
    if dest == repo.store.join(rel) {
        // it names the store, but what the store holds there can be a symlink of
        // its own leading straight back out, which is not being held at all
        return Ok(match leads(&src, &repo.store) {
            Leads::Inside | Leads::Dangling => None,
            Leads::Outside(end) => Some(Exposed {
                mark,
                name,
                dest: Some(end),
            }),
        });
    }

    Ok(Some(Exposed {
        mark,
        name,
        dest: Some(dest),
    }))
}

// git tracks symlinks, so one can lead out of the repository without ever
// showing up in an untracked or ignored listing; `add` cannot externalize it
// either, so all check can do is say it is there
fn classify_tracked(repo: &Repo, rel: &Path) -> Result<Option<Exposed>> {
    let src = repo.root.join(rel);

    let Some(meta) = symlink_metadata_opt(&src)? else {
        return Ok(None);
    };
    if !meta.is_symlink() {
        return Ok(None);
    }

    Ok(match leads(&src, &repo.root) {
        Leads::Inside | Leads::Dangling => None,
        Leads::Outside(end) => Some(Exposed {
            mark: TRACKED,
            name: rel.to_path_buf(),
            dest: Some(end),
        }),
    })
}

fn walk(repo: &Repo, rel: &Path, mark: char) -> Result<(usize, Vec<Exposed>)> {
    let dir = repo.root.join(rel);
    let mut handled = 0;
    let mut exposed = Vec::new();

    for entry in read_dir(&dir)? {
        let entry = entry?;
        let child = rel.join(entry.file_name());

        if entry.file_type()?.is_dir() {
            let (below, inside) = walk(repo, &child, mark)?;
            handled += below;
            exposed.extend(inside);
            continue;
        }

        match classify(repo, &child, mark)? {
            Some(item) => exposed.push(item),
            None => handled += 1,
        }
    }

    // nothing below is in the store, so collapse to one line -- unless some of
    // it leads out of the repository, which is a different thing to report and
    // carries a destination the one line would drop
    let all_content = exposed.iter().all(|item| item.dest.is_none());

    if handled == 0 && !exposed.is_empty() && all_content {
        let mut name = rel.as_os_str().to_owned();
        name.push("/");

        return Ok((0, vec![Exposed::content(mark, PathBuf::from(name))]));
    }

    Ok((handled, exposed))
}

fn relative_pathspecs(repo: &Repo, paths: &[PathBuf]) -> Result<Vec<PathBuf>> {
    let mut specs = Vec::with_capacity(paths.len());

    for path in paths {
        let abs = resolve(path)?;
        let rel = abs.strip_prefix(&repo.root).map_err(|_| {
            anyhow!(
                "{} is outside the repository {}",
                abs.display(),
                repo.root.display()
            )
        })?;

        if rel.as_os_str().is_empty() {
            return Ok(Vec::new());
        }
        specs.push(rel.to_path_buf());
    }

    Ok(specs)
}

fn list_others(
    ctx: &Ctx,
    repo: &Repo,
    ignored: bool,
    pathspecs: &[PathBuf],
) -> Result<Vec<Vec<u8>>> {
    let mut listing = LsFiles::untracked(&repo.root).limited_to(pathspecs);
    if ignored {
        listing = listing.ignored();
    }

    Ok(split_nul(&listing.capture_bytes(ctx)?))
}

fn list_tracked(ctx: &Ctx, repo: &Repo, pathspecs: &[PathBuf]) -> Result<Vec<Vec<u8>>> {
    let listing = LsFiles::tracked(&repo.root).limited_to(pathspecs);

    Ok(split_nul(&listing.capture_bytes(ctx)?))
}

// every listing check reads is asked for with -z, and kept as the bytes git
// wrote: a path is not obliged to be utf-8, and one that is not used to fail
// the whole listing rather than the one entry
fn split_nul(out: &[u8]) -> Vec<Vec<u8>> {
    out.split(|byte| *byte == 0)
        .filter(|record| !record.is_empty())
        .map(<[u8]>::to_vec)
        .collect()
}

fn path_from(bytes: &[u8]) -> PathBuf {
    PathBuf::from(OsString::from_vec(bytes.to_vec()))
}