annotate rust/rhg/src/commands/status.rs @ 48443:112184713852

rhg: Set second_ambiguous as needed in post-status fixup

This fixes an intermittent bug that manifested only in test-revert.t,
and unfortunately not on CI. On a fast enough machine we could have:

1. A file is modified
2. `rhg status` writes an updated dirstate-v1
3. The same file is modified again

… all within the same integer second. Because the dirstate-v1 file format
does not store sub-second precision, step 2 must write the file’s mtime
as "unknown" because of the possibility of step 3.

However, most of the code now handles timestamps with nanosecond precision
in order to take advantage of it in dirstate-v2. `second_ambiguous` must
be set for timestamps that become ambiguous if sub-second precision is dropped
(such as through serialization in dirstate-v1 format).

Differential Revision: https://phab.mercurial-scm.org/D11889

// status.rs
//
// Copyright 2020, Georges Racinet <[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::error::CommandError;
use crate::ui::Ui;
use crate::utils::path_utils::relativize_paths;
use clap::{Arg, SubCommand};
use format_bytes::format_bytes;
use hg;
use hg::config::Config;
use hg::dirstate::has_exec_bit;
use hg::dirstate::TruncatedTimestamp;
use hg::dirstate::RANGE_MASK_31BIT;
use hg::errors::{HgError, IoResultExt};
use hg::lock::LockError;
use hg::manifest::Manifest;
use hg::matchers::AlwaysMatcher;
use hg::repo::Repo;
use hg::utils::files::get_bytes_from_os_string;
use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
use hg::{HgPathCow, StatusOptions};
use log::{info, warn};
use std::io;

pub const HELP_TEXT: &str = "
Show changed files in the working directory

This is a pure Rust version of `hg status`.

Some options might be missing, check the list below.
";

pub fn args() -> clap::App<'static, 'static> {
    SubCommand::with_name("status")
        .alias("st")
        .about(HELP_TEXT)
        .arg(
            Arg::with_name("all")
                .help("show status of all files")
                .short("-A")
                .long("--all"),
        )
        .arg(
            Arg::with_name("modified")
                .help("show only modified files")
                .short("-m")
                .long("--modified"),
        )
        .arg(
            Arg::with_name("added")
                .help("show only added files")
                .short("-a")
                .long("--added"),
        )
        .arg(
            Arg::with_name("removed")
                .help("show only removed files")
                .short("-r")
                .long("--removed"),
        )
        .arg(
            Arg::with_name("clean")
                .help("show only clean files")
                .short("-c")
                .long("--clean"),
        )
        .arg(
            Arg::with_name("deleted")
                .help("show only deleted files")
                .short("-d")
                .long("--deleted"),
        )
        .arg(
            Arg::with_name("unknown")
                .help("show only unknown (not tracked) files")
                .short("-u")
                .long("--unknown"),
        )
        .arg(
            Arg::with_name("ignored")
                .help("show only ignored files")
                .short("-i")
                .long("--ignored"),
        )
        .arg(
            Arg::with_name("no-status")
                .help("hide status prefix")
                .short("-n")
                .long("--no-status"),
        )
}

/// Pure data type allowing the caller to specify file states to display
#[derive(Copy, Clone, Debug)]
pub struct DisplayStates {
    pub modified: bool,
    pub added: bool,
    pub removed: bool,
    pub clean: bool,
    pub deleted: bool,
    pub unknown: bool,
    pub ignored: bool,
}

pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
    modified: true,
    added: true,
    removed: true,
    clean: false,
    deleted: true,
    unknown: true,
    ignored: false,
};

pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
    modified: true,
    added: true,
    removed: true,
    clean: true,
    deleted: true,
    unknown: true,
    ignored: true,
};

impl DisplayStates {
    pub fn is_empty(&self) -> bool {
        !(self.modified
            || self.added
            || self.removed
            || self.clean
            || self.deleted
            || self.unknown
            || self.ignored)
    }
}

pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
    let status_enabled_default = false;
    let status_enabled = invocation.config.get_option(b"rhg", b"status")?;
    if !status_enabled.unwrap_or(status_enabled_default) {
        return Err(CommandError::unsupported(
            "status is experimental in rhg (enable it with 'rhg.status = true' \
            or enable fallback with 'rhg.on-unsupported = fallback')"
        ));
    }

    // TODO: lift these limitations
    if invocation.config.get_bool(b"ui", b"tweakdefaults")? {
        return Err(CommandError::unsupported(
            "ui.tweakdefaults is not yet supported with rhg status",
        ));
    }
    if invocation.config.get_bool(b"ui", b"statuscopies")? {
        return Err(CommandError::unsupported(
            "ui.statuscopies is not yet supported with rhg status",
        ));
    }
    if invocation
        .config
        .get(b"commands", b"status.terse")
        .is_some()
    {
        return Err(CommandError::unsupported(
            "status.terse is not yet supported with rhg status",
        ));
    }

    let ui = invocation.ui;
    let config = invocation.config;
    let args = invocation.subcommand_args;
    let display_states = if args.is_present("all") {
        // TODO when implementing `--quiet`: it excludes clean files
        // from `--all`
        ALL_DISPLAY_STATES
    } else {
        let requested = DisplayStates {
            modified: args.is_present("modified"),
            added: args.is_present("added"),
            removed: args.is_present("removed"),
            clean: args.is_present("clean"),
            deleted: args.is_present("deleted"),
            unknown: args.is_present("unknown"),
            ignored: args.is_present("ignored"),
        };
        if requested.is_empty() {
            DEFAULT_DISPLAY_STATES
        } else {
            requested
        }
    };
    let no_status = args.is_present("no-status");

    let repo = invocation.repo?;

    if repo.has_sparse() || repo.has_narrow() {
        return Err(CommandError::unsupported(
            "rhg status is not supported for sparse checkouts or narrow clones yet"
        ));
    }

    let mut dmap = repo.dirstate_map_mut()?;

    let options = StatusOptions {
        // we're currently supporting file systems with exec flags only
        // anyway
        check_exec: true,
        list_clean: display_states.clean,
        list_unknown: display_states.unknown,
        list_ignored: display_states.ignored,
        collect_traversed_dirs: false,
    };
    let ignore_file = repo.working_directory_vfs().join(".hgignore"); // TODO hardcoded
    let (mut ds_status, pattern_warnings) = dmap.status(
        &AlwaysMatcher,
        repo.working_directory_path().to_owned(),
        vec![ignore_file],
        options,
    )?;
    if !pattern_warnings.is_empty() {
        warn!("Pattern warnings: {:?}", &pattern_warnings);
    }

    if !ds_status.bad.is_empty() {
        warn!("Bad matches {:?}", &(ds_status.bad))
    }
    if !ds_status.unsure.is_empty() {
        info!(
            "Files to be rechecked by retrieval from filelog: {:?}",
            &ds_status.unsure
        );
    }
    let mut fixup = Vec::new();
    if !ds_status.unsure.is_empty()
        && (display_states.modified || display_states.clean)
    {
        let p1 = repo.dirstate_parents()?.p1;
        let manifest = repo.manifest_for_node(p1).map_err(|e| {
            CommandError::from((e, &*format!("{:x}", p1.short())))
        })?;
        for to_check in ds_status.unsure {
            if unsure_is_modified(repo, &manifest, &to_check)? {
                if display_states.modified {
                    ds_status.modified.push(to_check);
                }
            } else {
                if display_states.clean {
                    ds_status.clean.push(to_check.clone());
                }
                fixup.push(to_check.into_owned())
            }
        }
    }
    if display_states.modified {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.modified,
            b"M",
        )?;
    }
    if display_states.added {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.added,
            b"A",
        )?;
    }
    if display_states.removed {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.removed,
            b"R",
        )?;
    }
    if display_states.deleted {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.deleted,
            b"!",
        )?;
    }
    if display_states.unknown {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.unknown,
            b"?",
        )?;
    }
    if display_states.ignored {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.ignored,
            b"I",
        )?;
    }
    if display_states.clean {
        display_status_paths(
            ui,
            repo,
            config,
            no_status,
            &mut ds_status.clean,
            b"C",
        )?;
    }

    let mut dirstate_write_needed = ds_status.dirty;
    let filesystem_time_at_status_start = ds_status
        .filesystem_time_at_status_start
        .map(TruncatedTimestamp::from);

    if (fixup.is_empty() || filesystem_time_at_status_start.is_none())
        && !dirstate_write_needed
    {
        // Nothing to update
        return Ok(());
    }

    // Update the dirstate on disk if we can
    let with_lock_result =
        repo.try_with_wlock_no_wait(|| -> Result<(), CommandError> {
            if let Some(mtime_boundary) = filesystem_time_at_status_start {
                for hg_path in fixup {
                    use std::os::unix::fs::MetadataExt;
                    let fs_path = hg_path_to_path_buf(&hg_path)
                        .expect("HgPath conversion");
                    // Specifically do not reuse `fs_metadata` from
                    // `unsure_is_clean` which was needed before reading
                    // contents. Here we access metadata again after reading
                    // content, in case it changed in the meantime.
                    let fs_metadata = repo
                        .working_directory_vfs()
                        .symlink_metadata(&fs_path)?;
                    if let Some(mtime) =
                        TruncatedTimestamp::for_reliable_mtime_of(
                            &fs_metadata,
                            &mtime_boundary,
                        )
                        .when_reading_file(&fs_path)?
                    {
                        let mode = fs_metadata.mode();
                        let size = fs_metadata.len() as u32 & RANGE_MASK_31BIT;
                        let mut entry = dmap
                            .get(&hg_path)?
                            .expect("ambiguous file not in dirstate");
                        entry.set_clean(mode, size, mtime);
                        dmap.add_file(&hg_path, entry)?;
                        dirstate_write_needed = true
                    }
                }
            }
            drop(dmap); // Avoid "already mutably borrowed" RefCell panics
            if dirstate_write_needed {
                repo.write_dirstate()?
            }
            Ok(())
        });
    match with_lock_result {
        Ok(closure_result) => closure_result?,
        Err(LockError::AlreadyHeld) => {
            // Not updating the dirstate is not ideal but not critical:
            // don’t keep our caller waiting until some other Mercurial
            // process releases the lock.
        }
        Err(LockError::Other(HgError::IoError { error, .. }))
            if error.kind() == io::ErrorKind::PermissionDenied =>
        {
            // `hg status` on a read-only repository is fine
        }
        Err(LockError::Other(error)) => {
            // Report other I/O errors
            Err(error)?
        }
    }
    Ok(())
}

// Probably more elegant to use a Deref or Borrow trait rather than
// harcode HgPathBuf, but probably not really useful at this point
fn display_status_paths(
    ui: &Ui,
    repo: &Repo,
    config: &Config,
    no_status: bool,
    paths: &mut [HgPathCow],
    status_prefix: &[u8],
) -> Result<(), CommandError> {
    paths.sort_unstable();
    let mut relative: bool = config.get_bool(b"ui", b"relative-paths")?;
    relative = config
        .get_option(b"commands", b"status.relative")?
        .unwrap_or(relative);
    let print_path = |path: &[u8]| {
        // TODO optim, probably lots of unneeded copies here, especially
        // if out stream is buffered
        if no_status {
            ui.write_stdout(&format_bytes!(b"{}\n", path))
        } else {
            ui.write_stdout(&format_bytes!(b"{} {}\n", status_prefix, path))
        }
    };

    if relative && !ui.plain() {
        relativize_paths(repo, paths.iter().map(Ok), |path| {
            print_path(&path)
        })?;
    } else {
        for path in paths {
            print_path(path.as_bytes())?
        }
    }
    Ok(())
}

/// Check if a file is modified by comparing actual repo store and file system.
///
/// This meant to be used for those that the dirstate cannot resolve, due
/// to time resolution limits.
fn unsure_is_modified(
    repo: &Repo,
    manifest: &Manifest,
    hg_path: &HgPath,
) -> Result<bool, HgError> {
    let vfs = repo.working_directory_vfs();
    let fs_path = hg_path_to_path_buf(hg_path).expect("HgPath conversion");
    let fs_metadata = vfs.symlink_metadata(&fs_path)?;
    let is_symlink = fs_metadata.file_type().is_symlink();
    // TODO: Also account for `FALLBACK_SYMLINK` and `FALLBACK_EXEC` from the
    // dirstate
    let fs_flags = if is_symlink {
        Some(b'l')
    } else if has_exec_bit(&fs_metadata) {
        Some(b'x')
    } else {
        None
    };

    let entry = manifest
        .find_file(hg_path)?
        .expect("ambgious file not in p1");
    if entry.flags != fs_flags {
        return Ok(true);
    }
    let filelog = repo.filelog(hg_path)?;
    let filelog_entry =
        filelog.data_for_node(entry.node_id()?).map_err(|_| {
            HgError::corrupted("filelog missing node from manifest")
        })?;
    let contents_in_p1 = filelog_entry.data()?;

    let fs_contents = if is_symlink {
        get_bytes_from_os_string(vfs.read_link(fs_path)?.into_os_string())
    } else {
        vfs.read(fs_path)?
    };
    Ok(contents_in_p1 != &*fs_contents)
}