comparison rust/hg-core/src/revlog/node.rs @ 46428:5893706af3de

rust: Simplify error type for reading hex node IDs

If a string is not valid hexadecimal it’s not that useful to track the precise reason.

Differential Revision: https://phab.mercurial-scm.org/D9861

46427:6380efb82191

//!
//! In Mercurial code base, it is customary to call "a node" the binary SHA
//! of a revision.

use bytes_cast::BytesCast;
use hex::{self, FromHex, FromHexError};
use std::convert::TryFrom;
use std::fmt;

/// The length in bytes of a `Node`
///

/// All other callers outside of unit tests should just handle `Node` values
/// and never make any assumption on the actual length, using [`nybbles_len`]
/// if they need a loop boundary.
///
/// All methods that create a `Node` either take a type that enforces
/// the size or fail immediately at runtime with [`ExactLengthRequired`].
///
/// [`nybbles_len`]: #method.nybbles_len
/// [`ExactLengthRequired`]: struct.NodeError#variant.ExactLengthRequired
#[derive(Clone, Debug, PartialEq, BytesCast)]
#[repr(transparent)]
pub struct Node {
    data: NodeData,
}

        }
        Ok(())
    }
}

#[derive(Debug, PartialEq)]
pub enum NodeError {
    ExactLengthRequired(usize, String),
    PrefixTooLong(String),
    HexError(FromHexError, String),
}

/// Low level utility function, also for prefixes
fn get_nybble(s: &[u8], i: usize) -> u8 {
    if i % 2 == 0 {
        s[i / 2] >> 4

    ///
    /// Exact length is required.
    ///
    /// To be used in FFI and I/O only, in order to facilitate future
    /// changes of hash format.
    pub fn from_hex(hex: impl AsRef<[u8]>) -> Result<Node, NodeError> {
        Ok(NodeData::from_hex(hex.as_ref())
            .map_err(|e| NodeError::from((e, hex)))?
            .into())
    }

    /// Provide access to binary data
    ///
    /// This is needed by FFI layers, for instance to return expected
    /// binary values to Python.
    pub fn as_bytes(&self) -> &[u8] {
        &self.data
    }
}

impl<T: AsRef<[u8]>> From<(FromHexError, T)> for NodeError {
    fn from(err_offender: (FromHexError, T)) -> Self {
        let (err, offender) = err_offender;
        let offender = String::from_utf8_lossy(offender.as_ref()).into_owned();
        match err {
            FromHexError::InvalidStringLength => {
                NodeError::ExactLengthRequired(NODE_NYBBLES_LENGTH, offender)
            }
            _ => NodeError::HexError(err, offender),
        }
    }
}

/// The beginning of a binary revision SHA.
///

    /// Similarly to `hex::decode`, can be used with Unicode string types
    /// (`String`, `&str`) as well as bytes.
    ///
    /// To be used in FFI and I/O only, in order to facilitate future
    /// changes of hash format.
    pub fn from_hex(hex: impl AsRef<[u8]>) -> Result<Self, NodeError> {
        let hex = hex.as_ref();
        let len = hex.len();
        if len > NODE_NYBBLES_LENGTH {
            return Err(NodeError::PrefixTooLong(
                String::from_utf8_lossy(hex).to_owned().to_string(),
            ));
        }

        let is_odd = len % 2 == 1;
        let even_part = if is_odd { &hex[..len - 1] } else { hex };
        let mut buf: Vec<u8> =
            Vec::from_hex(&even_part).map_err(|e| (e, hex))?;

        if is_odd {
            let latest_char = char::from(hex[len - 1]);
            let latest_nybble = latest_char.to_digit(16).ok_or_else(|| {
                (
                    FromHexError::InvalidHexCharacter {
                        c: latest_char,
                        index: len - 1,
                    },
                    hex,
                )
            })? as u8;
            buf.push(latest_nybble << 4);
        }
        Ok(NodePrefix { buf, is_odd })
    }

        hex_pad_right("0123456789abcdeffedcba9876543210deadbeef")
    }

    #[test]
    fn test_node_from_hex() {
        assert_eq!(Node::from_hex(&sample_node_hex()), Ok(sample_node()));

        let mut short = hex_pad_right("0123");
        short.pop();
        short.pop();
        assert_eq!(
            Node::from_hex(&short),
            Err(NodeError::ExactLengthRequired(NODE_NYBBLES_LENGTH, short)),
        );

        let not_hex = hex_pad_right("012... oops");
        assert_eq!(
            Node::from_hex(&not_hex),
            Err(NodeError::HexError(
                FromHexError::InvalidHexCharacter { c: '.', index: 3 },
                not_hex,
            )),
        );
    }

    #[test]
    fn test_node_encode_hex() {
        assert_eq!(format!("{:x}", sample_node()), sample_node_hex());
    }

    #[test]
    fn test_prefix_from_hex() -> Result<(), NodeError> {
        assert_eq!(
            NodePrefix::from_hex("0e1")?,
            NodePrefix {
                buf: vec![14, 16],
                is_odd: true

        Ok(())
    }

    #[test]
    fn test_prefix_from_hex_errors() {
        assert_eq!(
            NodePrefix::from_hex("testgr"),
            Err(NodeError::HexError(
                FromHexError::InvalidHexCharacter { c: 't', index: 0 },
                "testgr".to_string()
            ))
        );
        let mut long = format!("{:x}", NULL_NODE);
        long.push('c');
        match NodePrefix::from_hex(&long)
            .expect_err("should be refused as too long")
        {
            NodeError::PrefixTooLong(s) => assert_eq!(s, long),
            err => panic!(format!("Should have been TooLong, got {:?}", err)),
        }
    }

    #[test]
    fn test_is_prefix_of() -> Result<(), NodeError> {
        let mut node_data = [0; NODE_BYTES_LENGTH];
        node_data[0] = 0x12;
        node_data[1] = 0xca;
        let node = Node::from(node_data);
        assert!(NodePrefix::from_hex("12")?.borrow().is_prefix_of(&node));

        assert!(!NodePrefix::from_hex("12d")?.borrow().is_prefix_of(&node));
        Ok(())
    }

    #[test]
    fn test_get_nybble() -> Result<(), NodeError> {
        let prefix = NodePrefix::from_hex("dead6789cafe")?;
        assert_eq!(prefix.borrow().get_nybble(0), 13);
        assert_eq!(prefix.borrow().get_nybble(7), 9);
        Ok(())
    }

46428:5893706af3de

//!
//! In Mercurial code base, it is customary to call "a node" the binary SHA
//! of a revision.

use bytes_cast::BytesCast;
use hex::{self, FromHex};
use std::convert::TryFrom;
use std::fmt;

/// The length in bytes of a `Node`
///

/// All other callers outside of unit tests should just handle `Node` values
/// and never make any assumption on the actual length, using [`nybbles_len`]
/// if they need a loop boundary.
///
/// All methods that create a `Node` either take a type that enforces
/// the size or return an error at runtime.
///
/// [`nybbles_len`]: #method.nybbles_len
#[derive(Clone, Debug, PartialEq, BytesCast)]
#[repr(transparent)]
pub struct Node {
    data: NodeData,
}

        }
        Ok(())
    }
}

#[derive(Debug)]
pub struct FromHexError;

/// Low level utility function, also for prefixes
fn get_nybble(s: &[u8], i: usize) -> u8 {
    if i % 2 == 0 {
        s[i / 2] >> 4

    ///
    /// Exact length is required.
    ///
    /// To be used in FFI and I/O only, in order to facilitate future
    /// changes of hash format.
    pub fn from_hex(hex: impl AsRef<[u8]>) -> Result<Node, FromHexError> {
        Ok(NodeData::from_hex(hex.as_ref())
            .map_err(|_| FromHexError)?
            .into())
    }

    /// Provide access to binary data
    ///
    /// This is needed by FFI layers, for instance to return expected
    /// binary values to Python.
    pub fn as_bytes(&self) -> &[u8] {
        &self.data
    }
}

/// The beginning of a binary revision SHA.
///

    /// Similarly to `hex::decode`, can be used with Unicode string types
    /// (`String`, `&str`) as well as bytes.
    ///
    /// To be used in FFI and I/O only, in order to facilitate future
    /// changes of hash format.
    pub fn from_hex(hex: impl AsRef<[u8]>) -> Result<Self, FromHexError> {
        let hex = hex.as_ref();
        let len = hex.len();
        if len > NODE_NYBBLES_LENGTH {
            return Err(FromHexError);
        }

        let is_odd = len % 2 == 1;
        let even_part = if is_odd { &hex[..len - 1] } else { hex };
        let mut buf: Vec<u8> =
            Vec::from_hex(&even_part).map_err(|_| FromHexError)?;

        if is_odd {
            let latest_char = char::from(hex[len - 1]);
            let latest_nybble =
                latest_char.to_digit(16).ok_or_else(|| FromHexError)? as u8;
            buf.push(latest_nybble << 4);
        }
        Ok(NodePrefix { buf, is_odd })
    }

        hex_pad_right("0123456789abcdeffedcba9876543210deadbeef")
    }

    #[test]
    fn test_node_from_hex() {
        assert_eq!(Node::from_hex(&sample_node_hex()).unwrap(), sample_node());

        let mut short = hex_pad_right("0123");
        short.pop();
        short.pop();
        assert!(Node::from_hex(&short).is_err());

        let not_hex = hex_pad_right("012... oops");
        assert!(Node::from_hex(&not_hex).is_err(),);
    }

    #[test]
    fn test_node_encode_hex() {
        assert_eq!(format!("{:x}", sample_node()), sample_node_hex());
    }

    #[test]
    fn test_prefix_from_hex() -> Result<(), FromHexError> {
        assert_eq!(
            NodePrefix::from_hex("0e1")?,
            NodePrefix {
                buf: vec![14, 16],
                is_odd: true

        Ok(())
    }

    #[test]
    fn test_prefix_from_hex_errors() {
        assert!(NodePrefix::from_hex("testgr").is_err());
        let mut long = format!("{:x}", NULL_NODE);
        long.push('c');
        assert!(NodePrefix::from_hex(&long).is_err())
    }

    #[test]
    fn test_is_prefix_of() -> Result<(), FromHexError> {
        let mut node_data = [0; NODE_BYTES_LENGTH];
        node_data[0] = 0x12;
        node_data[1] = 0xca;
        let node = Node::from(node_data);
        assert!(NodePrefix::from_hex("12")?.borrow().is_prefix_of(&node));

        assert!(!NodePrefix::from_hex("12d")?.borrow().is_prefix_of(&node));
        Ok(())
    }

    #[test]
    fn test_get_nybble() -> Result<(), FromHexError> {
        let prefix = NodePrefix::from_hex("dead6789cafe")?;
        assert_eq!(prefix.borrow().get_nybble(0), 13);
        assert_eq!(prefix.borrow().get_nybble(7), 9);
        Ok(())
    }