lexer: encode \u escapes using locale encoding #51
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,102 @@ | ||
| // This file is part of the uutils awk package. | ||
| // | ||
| // For the full copyright and license information, please view the LICENSE | ||
| // files that was distributed with this source code. | ||
|
|
||
| //! Locale-aware encoding for `\u` escape sequences, matching gawk behavior. | ||
| //! | ||
| //! See: <https://www.gnu.org/software/gawk/manual/html_node/Escape-Sequences.html> | ||
|
|
||
| use encoding_rs::{EncoderResult, Encoding, UTF_8}; | ||
|
|
||
| /// Character encoding derived from the process locale (`LC_*` / `LANG`). | ||
| #[derive(Clone, Copy, Debug, PartialEq, Eq)] | ||
| pub struct LocaleEncoding { | ||
| encoding: &'static Encoding, | ||
| /// `C` / `POSIX` locales only accept ASCII via `\u`. | ||
| ascii_only: bool, | ||
| } | ||
|
|
||
| impl LocaleEncoding { | ||
| pub fn utf8() -> Self { | ||
| Self { encoding: UTF_8, ascii_only: false } | ||
| } | ||
|
|
||
| /// `C` / `POSIX` locale: `\u` only encodes code points in ASCII. | ||
| pub fn ascii() -> Self { | ||
| Self { encoding: UTF_8, ascii_only: true } | ||
| } | ||
|
|
||
| /// ISO-8859-1 (Latin-1). | ||
| pub fn iso_8859_1() -> Self { | ||
| Self { | ||
| encoding: Encoding::for_label(b"iso-8859-1").unwrap_or(UTF_8), | ||
| ascii_only: false, | ||
| } | ||
| } | ||
|
|
||
| /// Detect encoding from `LC_ALL`, `LC_CTYPE`, or `LANG`. | ||
| pub fn detect() -> Self { | ||
| let name = std::env::var("LC_ALL") | ||
| .or_else(|_| std::env::var("LC_CTYPE")) | ||
| .or_else(|_| std::env::var("LANG")) | ||
| .unwrap_or_else(|_| "C.UTF-8".to_string()); | ||
| from_locale_name(&name) | ||
| } | ||
|
|
||
| /// Encode a Unicode scalar value for a `\u` escape in the current locale. | ||
| /// | ||
| /// Invalid code points and characters that cannot be represented in the | ||
| /// locale encoding become `?`, matching gawk. | ||
| pub fn encode_unicode_escape(self, codepoint: u32) -> Vec<u8> { | ||
|
Collaborator
There was a problem hiding this comment. It would be more optimal if the user specifies the out-buffer as an argument, so we aren't allocating for each character just to then copy it into the arena. |
||
| if codepoint > 0x0010_FFFF || (0xD800..=0xDFFF).contains(&codepoint) { | ||
| return vec![b'?']; | ||
| } | ||
|
|
||
| let c = char::from_u32(codepoint).unwrap(); | ||
|
|
||
| if self.ascii_only && codepoint > 0x7F { | ||
| return vec![b'?']; | ||
| } | ||
|
Comment on lines
+52
to
+60
Collaborator
There was a problem hiding this comment. We can remove the let c = match char::try_from(codepoint) {
Ok(c) if !self.ascii_only || c.is_ascii() => c,
_ => return vec![b'?'],
}; |
||
|
|
||
| if self.encoding == UTF_8 && !self.ascii_only { | ||
| let mut buf = [0u8; 4]; | ||
| return c.encode_utf8(&mut buf).as_bytes().to_vec(); | ||
| } | ||
|
|
||
| let mut encoder = self.encoding.new_encoder(); | ||
| let mut buf = [0u8; 8]; | ||
| let ch = c.to_string(); | ||
| match encoder.encode_from_utf8_without_replacement(&ch, &mut buf, true) { | ||
| (EncoderResult::InputEmpty, _, written) if written > 0 => buf[..written].to_vec(), | ||
| _ => vec![b'?'], | ||
| } | ||
| } | ||
| } | ||
|
|
||
| impl Default for LocaleEncoding { | ||
| fn default() -> Self { | ||
| Self::utf8() | ||
| } | ||
| } | ||
|
|
||
| fn from_locale_name(name: &str) -> LocaleEncoding { | ||
|
Collaborator
There was a problem hiding this comment. Shouldn't this just be a method (constructor) of |
||
| let lower = name.to_ascii_lowercase(); | ||
| let extension = lower.rsplit_once('.').map(|(_, ext)| ext); | ||
| if lower == "c" || lower == "posix" || extension == Some("c") || extension == Some("posix") { | ||
|
Collaborator
There was a problem hiding this comment. Could be made more readable with something like this: let is_ascii = |c| matches!(c, "c" | "posix");
if is_ascii(&*lower) || extension.is_some_and(is_ascii) {
return LocaleEncoding::ascii();
} |
||
| return LocaleEncoding::ascii(); | ||
| } | ||
|
|
||
| let charset = name.rsplit('.').next().unwrap_or(name); | ||
| let label = charset.to_ascii_lowercase().replace('_', "-"); | ||
|
|
||
| if label.contains("utf-8") || label == "utf8" { | ||
| return LocaleEncoding::utf8(); | ||
| } | ||
|
|
||
| if let Some(encoding) = Encoding::for_label(label.as_bytes()) { | ||
| LocaleEncoding { encoding, ascii_only: false } | ||
| } else { | ||
| LocaleEncoding::utf8() | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It would be more optimal to fetch them all with
var_os(), and then combine it withstr's fallible UTF-8 check, so we can just pass astrof"C.UTF-8"otherwise.