Skip to content

Implement latin_1 in Rust #3046

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Oct 1, 2021
Merged

Implement latin_1 in Rust #3046

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0f889ce
Implement latin_1 in Rust
fanninpm Sep 24, 2021
7d322b7
Simplify latin_1 decode function
fanninpm Sep 24, 2021
4375307
Streamline latin_1_encode fast path
fanninpm Sep 24, 2021
a100178
Account for `0x80..=0xff` range in memory
fanninpm Sep 24, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
75 changes: 75 additions & 0 deletions common/src/encodings.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,6 +172,81 @@ pub mod utf8 {
}
}

pub mod latin_1 {
use super::*;

pub const ENCODING_NAME: &str = "latin-1";

const ERR_REASON: &str = "ordinal not in range(256)";

#[inline]
pub fn encode<E: ErrorHandler>(s: &str, errors: &E) -> Result<Vec<u8>, E::Error> {
let full_data = s;
let mut data = s;
let mut char_data_index = 0;
let mut out = Vec::<u8>::new();
loop {
match data
.char_indices()
.enumerate()
.find(|(_, (_, c))| !c.is_ascii())
{
None => {
out.extend_from_slice(data.as_bytes());
break;
}
Some((char_i, (byte_i, ch))) => {
out.extend_from_slice(&data.as_bytes()[..byte_i]);
let char_start = char_data_index + char_i;
if (ch as u32) <= 255 {
out.push(ch as u8);
let char_restart = char_start + 1;
data = crate::str::try_get_chars(full_data, char_restart..)
.ok_or_else(|| errors.error_oob_restart(char_restart))?;
char_data_index = char_restart;
} else {
// number of non-latin_1 chars between the first non-latin_1 char and the next latin_1 char
let non_latin_1_run_length = data[byte_i..]
.chars()
.take_while(|c| (*c as u32) > 255)
.count();
let char_range = char_start..char_start + non_latin_1_run_length;
let (replace, char_restart) = errors.handle_encode_error(
full_data,
char_range.clone(),
ERR_REASON,
)?;
match replace {
EncodeReplace::Str(s) => {
if s.as_ref().chars().any(|c| (c as u32) > 255) {
return Err(
errors.error_encoding(full_data, char_range, ERR_REASON)
);
}
out.extend_from_slice(s.as_ref().as_bytes());
}
EncodeReplace::Bytes(b) => {
out.extend_from_slice(b.as_ref());
}
}
data = crate::str::try_get_chars(full_data, char_restart..)
.ok_or_else(|| errors.error_oob_restart(char_restart))?;
char_data_index = char_restart;
}
continue;
}
}
}
Ok(out)
}

pub fn decode<E: ErrorHandler>(data: &[u8], _errors: &E) -> Result<(String, usize), E::Error> {
let out: String = data.iter().map(|c| *c as char).collect();
let out_len = out.len();
Ok((out, out_len))
}
}

pub mod ascii {
use super::*;
use ::ascii::AsciiStr;
Expand Down
21 changes: 13 additions & 8 deletions vm/src/stdlib/codecs.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,6 +315,19 @@ mod _codecs {
do_codec!(utf8::decode, args, vm)
}

#[pyfunction]
fn latin_1_encode(args: EncodeArgs, vm: &VirtualMachine) -> EncodeResult {
if args.s.is_ascii() {
return Ok((args.s.as_str().as_bytes().to_vec(), args.s.byte_len()));
}
do_codec!(latin_1::encode, args, vm)
}

#[pyfunction]
fn latin_1_decode(args: DecodeArgsNoFinal, vm: &VirtualMachine) -> DecodeResult {
do_codec!(latin_1::decode, args, vm)
}

#[pyfunction]
fn ascii_encode(args: EncodeArgs, vm: &VirtualMachine) -> EncodeResult {
if args.s.is_ascii() {
Expand Down Expand Up @@ -353,14 +366,6 @@ mod _codecs {
}};
}

#[pyfunction]
fn latin_1_encode(args: FuncArgs, vm: &VirtualMachine) -> PyResult {
delegate_pycodecs!(latin_1_encode, args, vm)
}
#[pyfunction]
fn latin_1_decode(args: FuncArgs, vm: &VirtualMachine) -> PyResult {
delegate_pycodecs!(latin_1_decode, args, vm)
}
#[pyfunction]
fn mbcs_encode(args: FuncArgs, vm: &VirtualMachine) -> PyResult {
delegate_pycodecs!(mbcs_encode, args, vm)
Expand Down