- Notifications
You must be signed in to change notification settings - Fork44
Add API to correct defective combining character sequences#98
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.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
Open
Jules-Bertholet wants to merge3 commits intounicode-rs:masterChoose a base branch
base:master
Could not load branches
Branch not found:{{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline, and old review comments may become outdated.
Uh oh!
There was an error while loading.Please reload this page.
Open
Changes fromall commits
Commits
Show all changes
3 commits Select commitHold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Jump to
Jump to file
Failed to load files.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Diff view
Diff view
There are no files selected for viewing
107 changes: 106 additions & 1 deletionscripts/unicode.py
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
176 changes: 176 additions & 0 deletionssrc/correct_ccs.rs
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 +1,176 @@ | ||
| #[cfg(not(feature = "std"))] | ||
| use alloc::collections::VecDeque; | ||
| use core::iter::FusedIterator; | ||
| #[cfg(feature = "std")] | ||
| use std::collections::VecDeque; | ||
| use crate::{lookups, tables}; | ||
| #[derive(Clone, Copy, Debug, PartialEq, Eq)] | ||
| enum CcsKind { | ||
| /// A CCS base character (graphic character other than combining mark). | ||
| Base, | ||
| /// A combining character other than a `Default_Ignorable_Code_Point`. | ||
| NonIgnorableCombining, | ||
| /// A default-ignorable combining character, ZWJ, or ZWNJ. | ||
| IgnorableCombining, | ||
| } | ||
| impl CcsKind { | ||
| fn of(c: char) -> Option<Self> { | ||
| if c == '\u{200C}' || c == '\u{200D}' { | ||
| // ZWNJ || ZWJ | ||
| Some(CcsKind::IgnorableCombining) | ||
| } else if lookups::is_combining_mark(c) { | ||
| if tables::is_default_ignorable_mark(c) { | ||
| Some(CcsKind::IgnorableCombining) | ||
| } else { | ||
| Some(CcsKind::NonIgnorableCombining) | ||
| } | ||
| } else if tables::not_in_ccs(c) { | ||
| None | ||
| } else { | ||
| Some(CcsKind::Base) | ||
| } | ||
| } | ||
| } | ||
| /// An iterator over the string that corrects | ||
| /// [defective combining character sequences](https://www.unicode.org/versions/Unicode15.0.0/UnicodeStandard-15.0.pdf#I6.1.36487) | ||
| /// by inserting U+00A0 NO-BREAK SPACE in front of them. | ||
| /// | ||
| /// For the purposes of this iterator, private use characters and unassigned codepoints | ||
| /// are considered valid base characters, | ||
| /// so combining character sequences that follow such will not be modified. | ||
| /// | ||
| /// In addition, combining character sequences that consist entirely of `Default_Ignorable_Code_Point`s | ||
| /// will not be modified. (Because of this, this iterator may buffer up to the entire length of its input; | ||
| /// it is *not* "stream-safe" *even if* used with [`StreamSafe`][crate::StreamSafe]). | ||
| #[derive(Clone, Debug)] | ||
| pub struct CorrectDefectiveCcs<I> { | ||
| /// Whether the last character emitted was part of a CCS. | ||
| in_ccs: bool, | ||
| buffer: VecDeque<Option<char>>, | ||
| /// Whether the last character in `buffer` is part of a CCS. | ||
| /// (Updated only when `is_ccs` is set from false to true). | ||
| end_of_buffer_in_ccs: bool, | ||
| iter: I, | ||
| } | ||
| impl<I: Iterator<Item = char>> Iterator for CorrectDefectiveCcs<I> { | ||
| type Item = char; | ||
| fn next(&mut self) -> Option<Self::Item> { | ||
| if self.in_ccs { | ||
| if let Some(c) = self.buffer.pop_front() { | ||
| // Empty buffer | ||
| if self.buffer.is_empty() { | ||
| self.in_ccs = self.end_of_buffer_in_ccs; | ||
| } | ||
| c | ||
| } else { | ||
| // Forward from inner iterator | ||
| let c = self.iter.next(); | ||
| if c.map_or(true, tables::not_in_ccs) { | ||
| self.in_ccs = false; | ||
| } | ||
| c | ||
| } | ||
| } else { | ||
| if self.buffer.is_empty() { | ||
| // We don't have a buffer of default ignorable combining characters built up | ||
| let c = self.iter.next()?; | ||
| match CcsKind::of(c) { | ||
| // Character not in CCS, just forward it | ||
| None => return Some(c), | ||
| // Character starts non-defective CCS, | ||
| // label ourselves as in CCS and forward it | ||
| Some(CcsKind::Base) => { | ||
| self.in_ccs = true; | ||
| return Some(c); | ||
| } | ||
| // Character starts defective CCS and is not default-ignorable. | ||
| // Put it in the buffer to emit on next iteration, | ||
| // mark ourselves as in CCS, | ||
| // and emit NO-BREAK SPACE | ||
| Some(CcsKind::NonIgnorableCombining) => { | ||
| self.in_ccs = true; | ||
| self.end_of_buffer_in_ccs = true; | ||
| self.buffer.push_back(Some(c)); | ||
| return Some('\u{00A0}'); // NO-BREAK SPACE | ||
| } | ||
| // Character starts defective CCS and is default-ignorable. | ||
| // Put it in the buffer, and fall through to loop below | ||
| // to find out whether we emit a NO-BREAK SPACE first. | ||
| Some(CcsKind::IgnorableCombining) => { | ||
| self.buffer.push_back(Some(c)); | ||
| } | ||
| } | ||
| } | ||
| loop { | ||
| // We do have a buffer of default ignorable combining characters built up, | ||
| // and we need to figure out whether to emit a NO-BREAK SPACE first. | ||
| let c = self.iter.next(); | ||
| match c.and_then(CcsKind::of) { | ||
| // Inner iterator yielded character outside CCS (or `None`). | ||
| // Emit the built-up buffer with no leading NO-BREAK SPACE. | ||
| None => { | ||
| self.in_ccs = true; | ||
| self.end_of_buffer_in_ccs = false; | ||
| let ret = self.buffer.pop_front().unwrap(); | ||
| self.buffer.push_back(c); | ||
| return ret; | ||
| } | ||
| // Inner iterator yielded character that starts a new CCS. | ||
| // Emit the built-up buffer with no leading NO-BREAK SPACE. | ||
| Some(CcsKind::Base) => { | ||
| self.in_ccs = true; | ||
| self.end_of_buffer_in_ccs = true; | ||
| let ret = self.buffer.pop_front().unwrap(); | ||
| self.buffer.push_back(c); | ||
| return ret; | ||
| } | ||
| // Inner iterator yielded non-ignorable combining character. | ||
| // Emit the built-up buffer with leading NO-BREAK SPACE. | ||
| Some(CcsKind::NonIgnorableCombining) => { | ||
| self.in_ccs = true; | ||
| self.end_of_buffer_in_ccs = true; | ||
| self.buffer.push_back(c); | ||
| return Some('\u{00A0}'); // NO-BREAK SPACE | ||
| } | ||
| // Inner iterator yielded ignorable combining character. | ||
| // Add it to the buffer, don't emit anything. | ||
| Some(CcsKind::IgnorableCombining) => { | ||
| self.buffer.push_back(c); | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| impl<I: Iterator<Item = char> + FusedIterator> FusedIterator for CorrectDefectiveCcs<I> {} | ||
| impl<I> CorrectDefectiveCcs<I> { | ||
| pub(crate) fn new(iter: I) -> Self { | ||
| Self { | ||
| in_ccs: false, | ||
| buffer: VecDeque::new(), | ||
| end_of_buffer_in_ccs: false, | ||
| iter, | ||
| } | ||
| } | ||
| } |
Oops, something went wrong.
Uh oh!
There was an error while loading.Please reload this page.
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.