annotate rust/hg-core/src/revlog/changelog.rs @ 49063:cc132255261b

rust-changelog: remove special parsing of empty changelog data for null rev

For the null revision, `Revlog::get_rev_data()` will return an empty
string (of bytes). We currently handle that case in
`ChangelogRevisionData::manifest_node()`. However, it's going to be
ugly to have special handling for the null revision for each future
method on `ChangelogRevisionData`. This patch therefore restructures
the code so we instead initialize the struct with valid data for the
null revision.

Differential Revision: https://phab.mercurial-scm.org/D12438

use crate::errors::HgError;
use crate::repo::Repo;
use crate::revlog::revlog::{Revlog, RevlogError};
use crate::revlog::Revision;
use crate::revlog::{Node, NodePrefix};

/// A specialized `Revlog` to work with `changelog` data format.
pub struct Changelog {
    /// The generic `revlog` format.
    pub(crate) revlog: Revlog,
}

impl Changelog {
    /// Open the `changelog` of a repository given by its root.
    pub fn open(repo: &Repo) -> Result<Self, HgError> {
        let revlog = Revlog::open(repo, "00changelog.i", None)?;
        Ok(Self { revlog })
    }

    /// Return the `ChangelogEntry` for the given node ID.
    pub fn data_for_node(
        &self,
        node: NodePrefix,
    ) -> Result<ChangelogRevisionData, RevlogError> {
        let rev = self.revlog.rev_from_node(node)?;
        self.data_for_rev(rev)
    }

    /// Return the `ChangelogEntry` of the given revision number.
    pub fn data_for_rev(
        &self,
        rev: Revision,
    ) -> Result<ChangelogRevisionData, RevlogError> {
        let bytes = self.revlog.get_rev_data(rev)?.into_owned();
        if bytes.is_empty() {
            Ok(ChangelogRevisionData::null())
        } else {
            Ok(ChangelogRevisionData::new(bytes))
        }
    }

    pub fn node_from_rev(&self, rev: Revision) -> Option<&Node> {
        self.revlog.node_from_rev(rev)
    }
}

/// `Changelog` entry which knows how to interpret the `changelog` data bytes.
#[derive(Debug)]
pub struct ChangelogRevisionData {
    /// The data bytes of the `changelog` entry.
    bytes: Vec<u8>,
}

impl ChangelogRevisionData {
    fn new(bytes: Vec<u8>) -> Self {
        Self { bytes }
    }

    fn null() -> Self {
        Self::new(
            b"0000000000000000000000000000000000000000\n\n0 0\n\n".to_vec(),
        )
    }

    /// Return an iterator over the lines of the entry.
    pub fn lines(&self) -> impl Iterator<Item = &[u8]> {
        self.bytes.split(|b| b == &b'\n')
    }

    /// Return the node id of the `manifest` referenced by this `changelog`
    /// entry.
    pub fn manifest_node(&self) -> Result<Node, HgError> {
        let manifest_node_hex =
            self.lines().next().expect("Empty iterator from split()?");
        Node::from_hex_for_repo(manifest_node_hex)
    }
}