##// END OF EJS Templates
phabricator: treat non-utf-8 text files as binary as phabricator requires...
phabricator: treat non-utf-8 text files as binary as phabricator requires Phabricator can't cope with text files that are not UTF-8, so requires them to be submitted as binary files instead. This has the unfortunate effect of making them practically unreviewable in Phabricator since it will only display the separate versions of the file in other views, not a diff. `phabread`ing such submissions are similar, since it will just output the binary patch, but `hg import` copes with it fine and `hg diff` afterwards will show the actual changes. It is still a marked improvement over trying to submit them as text, which just leads to corruption (Phabricator will either output ? or HTML entities for non-UTF-8 characters, depending on context). Running decode on the whole file like this seems slightly unfortunate, but I'm not aware of a better way. Needs to be done to p1() version as well to detect conversions to UTF-8. Differential Revision: https://phab.mercurial-scm.org/D7054

File last commit:

r43479:1ca3823a default
r43557:06a33a50 default
Show More
parsers.rs
176 lines | 5.2 KiB | application/rls-services+xml | RustLexer
// parsers.rs
//
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.
//! Bindings for the `hg::dirstate::parsers` module provided by the
//! `hg-core` package.
//!
//! From Python, this will be seen as `mercurial.rustext.parsers`
//!
use cpython::{
exc, PyBytes, PyDict, PyErr, PyInt, PyModule, PyResult, PyTuple, Python,
PythonObject, ToPyObject,
};
use hg::{
pack_dirstate, parse_dirstate, utils::hg_path::HgPathBuf,
DirstatePackError, DirstateParents, DirstateParseError, PARENT_SIZE,
};
use std::collections::HashMap;
use std::convert::TryInto;
use crate::dirstate::{extract_dirstate, make_dirstate_tuple};
use std::time::Duration;
fn parse_dirstate_wrapper(
py: Python,
dmap: PyDict,
copymap: PyDict,
st: PyBytes,
) -> PyResult<PyTuple> {
let mut dirstate_map = HashMap::new();
let mut copies = HashMap::new();
match parse_dirstate(&mut dirstate_map, &mut copies, st.data(py)) {
Ok(parents) => {
for (filename, entry) in &dirstate_map {
dmap.set_item(
py,
PyBytes::new(py, filename.as_ref()),
make_dirstate_tuple(py, entry)?,
)?;
}
for (path, copy_path) in copies {
copymap.set_item(
py,
PyBytes::new(py, path.as_ref()),
PyBytes::new(py, copy_path.as_ref()),
)?;
}
Ok(
(PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
.to_py_object(py),
)
}
Err(e) => Err(PyErr::new::<exc::ValueError, _>(
py,
match e {
DirstateParseError::TooLittleData => {
"too little data for parents".to_string()
}
DirstateParseError::Overflow => {
"overflow in dirstate".to_string()
}
DirstateParseError::CorruptedEntry(e) => e,
DirstateParseError::Damaged => {
"dirstate appears to be damaged".to_string()
}
},
)),
}
}
fn pack_dirstate_wrapper(
py: Python,
dmap: PyDict,
copymap: PyDict,
pl: PyTuple,
now: PyInt,
) -> PyResult<PyBytes> {
let p1 = pl.get_item(py, 0).extract::<PyBytes>(py)?;
let p1: &[u8] = p1.data(py);
let p2 = pl.get_item(py, 1).extract::<PyBytes>(py)?;
let p2: &[u8] = p2.data(py);
let mut dirstate_map = extract_dirstate(py, &dmap)?;
let copies: Result<HashMap<HgPathBuf, HgPathBuf>, PyErr> = copymap
.items(py)
.iter()
.map(|(key, value)| {
Ok((
HgPathBuf::from_bytes(key.extract::<PyBytes>(py)?.data(py)),
HgPathBuf::from_bytes(value.extract::<PyBytes>(py)?.data(py)),
))
})
.collect();
if p1.len() != PARENT_SIZE || p2.len() != PARENT_SIZE {
return Err(PyErr::new::<exc::ValueError, _>(
py,
"expected a 20-byte hash".to_string(),
));
}
match pack_dirstate(
&mut dirstate_map,
&copies?,
DirstateParents {
p1: p1.try_into().unwrap(),
p2: p2.try_into().unwrap(),
},
Duration::from_secs(now.as_object().extract::<u64>(py)?),
) {
Ok(packed) => {
for (filename, entry) in &dirstate_map {
dmap.set_item(
py,
PyBytes::new(py, filename.as_ref()),
make_dirstate_tuple(py, entry)?,
)?;
}
Ok(PyBytes::new(py, &packed))
}
Err(error) => Err(PyErr::new::<exc::ValueError, _>(
py,
match error {
DirstatePackError::CorruptedParent => {
"expected a 20-byte hash".to_string()
}
DirstatePackError::CorruptedEntry(e) => e,
DirstatePackError::BadSize(expected, actual) => {
format!("bad dirstate size: {} != {}", actual, expected)
}
},
)),
}
}
/// Create the module, with `__package__` given from parent
pub fn init_parsers_module(py: Python, package: &str) -> PyResult<PyModule> {
let dotted_name = &format!("{}.parsers", package);
let m = PyModule::new(py, dotted_name)?;
m.add(py, "__package__", package)?;
m.add(py, "__doc__", "Parsers - Rust implementation")?;
m.add(
py,
"parse_dirstate",
py_fn!(
py,
parse_dirstate_wrapper(dmap: PyDict, copymap: PyDict, st: PyBytes)
),
)?;
m.add(
py,
"pack_dirstate",
py_fn!(
py,
pack_dirstate_wrapper(
dmap: PyDict,
copymap: PyDict,
pl: PyTuple,
now: PyInt
)
),
)?;
let sys = PyModule::import(py, "sys")?;
let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
sys_modules.set_item(py, dotted_name, &m)?;
Ok(m)
}