comparison rust/hg-core/src/revlog/changelog.rs @ 49096:07ec9f4f24bf

changelog: avoid copying changeset data into `ChangesetRevisionData`

Differential Revision: https://phab.mercurial-scm.org/D12548

49095:b97835b2e2d4

use crate::revlog::{Node, NodePrefix};
use crate::utils::hg_path::HgPath;
use crate::vfs::Vfs;
use itertools::Itertools;
use std::ascii::escape_default;
use std::fmt::{Debug, Formatter};

/// A specialized `Revlog` to work with `changelog` data format.
pub struct Changelog {
    /// The generic `revlog` format.

    /// 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).map_err(|err| {
                RevlogError::Other(HgError::CorruptedRepository(format!(

    }
}

/// `Changelog` entry which knows how to interpret the `changelog` data bytes.
#[derive(PartialEq)]
pub struct ChangelogRevisionData {
    /// The data bytes of the `changelog` entry.
    bytes: Vec<u8>,
    /// The end offset for the hex manifest (not including the newline)
    manifest_end: usize,
    /// The end offset for the user+email (not including the newline)
    user_end: usize,
    /// The end offset for the timestamp+timezone+extras (not including the

    timestamp_end: usize,
    /// The end offset for the file list (not including the newline)
    files_end: usize,
}

impl ChangelogRevisionData {
    fn new(bytes: Vec<u8>) -> Result<Self, HgError> {
        let mut line_iter = bytes.split(|b| b == &b'\n');
        let manifest_end = line_iter
            .next()
            .expect("Empty iterator from split()?")
            .len();

            files_end,
        })
    }

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

    /// Return an iterator over the lines of the entry.
    pub fn lines(&self) -> impl Iterator<Item = &[u8]> {

    pub fn description(&self) -> &[u8] {
        &self.bytes[self.files_end + 2..]
    }
}

impl Debug for ChangelogRevisionData {
    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
        f.debug_struct("ChangelogRevisionData")
            .field("bytes", &debug_bytes(&self.bytes))
            .field("manifest", &debug_bytes(&self.bytes[..self.manifest_end]))
            .field(

    use pretty_assertions::assert_eq;

    #[test]
    fn test_create_changelogrevisiondata_invalid() {
        // Completely empty
        assert!(ChangelogRevisionData::new(b"abcd".to_vec()).is_err());
        // No newline after manifest
        assert!(ChangelogRevisionData::new(b"abcd".to_vec()).is_err());
        // No newline after user
        assert!(ChangelogRevisionData::new(b"abcd\n".to_vec()).is_err());
        // No newline after timestamp
        assert!(ChangelogRevisionData::new(b"abcd\n\n0 0".to_vec()).is_err());
        // Missing newline after files
        assert!(ChangelogRevisionData::new(
            b"abcd\n\n0 0\nfile1\nfile2".to_vec()
        )
        .is_err(),);
        // Only one newline after files
        assert!(ChangelogRevisionData::new(
            b"abcd\n\n0 0\nfile1\nfile2\n".to_vec()
        )
        .is_err(),);
    }

    #[test]
    fn test_create_changelogrevisiondata() {
        let data = ChangelogRevisionData::new(
            b"0123456789abcdef0123456789abcdef01234567
Some One <[e-mail]>
0 0
file1
file2

some
commit
message"
                .to_vec(),
        )
        .unwrap();
        assert_eq!(
            data.manifest_node().unwrap(),
            Node::from_hex("0123456789abcdef0123456789abcdef01234567")
                .unwrap()

49096:07ec9f4f24bf

use crate::revlog::{Node, NodePrefix};
use crate::utils::hg_path::HgPath;
use crate::vfs::Vfs;
use itertools::Itertools;
use std::ascii::escape_default;
use std::borrow::Cow;
use std::fmt::{Debug, Formatter};

/// A specialized `Revlog` to work with `changelog` data format.
pub struct Changelog {
    /// The generic `revlog` format.

    /// 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)?;
        if bytes.is_empty() {
            Ok(ChangelogRevisionData::null())
        } else {
            Ok(ChangelogRevisionData::new(bytes).map_err(|err| {
                RevlogError::Other(HgError::CorruptedRepository(format!(

    }
}

/// `Changelog` entry which knows how to interpret the `changelog` data bytes.
#[derive(PartialEq)]
pub struct ChangelogRevisionData<'changelog> {
    /// The data bytes of the `changelog` entry.
    bytes: Cow<'changelog, [u8]>,
    /// The end offset for the hex manifest (not including the newline)
    manifest_end: usize,
    /// The end offset for the user+email (not including the newline)
    user_end: usize,
    /// The end offset for the timestamp+timezone+extras (not including the

    timestamp_end: usize,
    /// The end offset for the file list (not including the newline)
    files_end: usize,
}

impl<'changelog> ChangelogRevisionData<'changelog> {
    fn new(bytes: Cow<'changelog, [u8]>) -> Result<Self, HgError> {
        let mut line_iter = bytes.split(|b| b == &b'\n');
        let manifest_end = line_iter
            .next()
            .expect("Empty iterator from split()?")
            .len();

            files_end,
        })
    }

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

    /// Return an iterator over the lines of the entry.
    pub fn lines(&self) -> impl Iterator<Item = &[u8]> {

    pub fn description(&self) -> &[u8] {
        &self.bytes[self.files_end + 2..]
    }
}

impl Debug for ChangelogRevisionData<'_> {
    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
        f.debug_struct("ChangelogRevisionData")
            .field("bytes", &debug_bytes(&self.bytes))
            .field("manifest", &debug_bytes(&self.bytes[..self.manifest_end]))
            .field(

    use pretty_assertions::assert_eq;

    #[test]
    fn test_create_changelogrevisiondata_invalid() {
        // Completely empty
        assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd")).is_err());
        // No newline after manifest
        assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd")).is_err());
        // No newline after user
        assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd\n")).is_err());
        // No newline after timestamp
        assert!(
            ChangelogRevisionData::new(Cow::Borrowed(b"abcd\n\n0 0")).is_err()
        );
        // Missing newline after files
        assert!(ChangelogRevisionData::new(Cow::Borrowed(
            b"abcd\n\n0 0\nfile1\nfile2"
        ))
        .is_err(),);
        // Only one newline after files
        assert!(ChangelogRevisionData::new(Cow::Borrowed(
            b"abcd\n\n0 0\nfile1\nfile2\n"
        ))
        .is_err(),);
    }

    #[test]
    fn test_create_changelogrevisiondata() {
        let data = ChangelogRevisionData::new(Cow::Borrowed(
            b"0123456789abcdef0123456789abcdef01234567
Some One <[e-mail]>
0 0
file1
file2

some
commit
message",
        ))
        .unwrap();
        assert_eq!(
            data.manifest_node().unwrap(),
            Node::from_hex("0123456789abcdef0123456789abcdef01234567")
                .unwrap()