Implementation of Unicode Bidi Algo #5
Draft
Conversation
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
pauloamed
commented
Jul 10, 2025
|
|
||
| namespace Karm::Icu { | ||
|
|
||
| usize const PLANE_SIZE = 65536; // 2^16 |
pauloamed
commented
Jul 10, 2025
| import requests | ||
|
|
||
| UNICODE_MAX = 0x10FFFF | ||
| BLOCK_SIZE = 128 |
| @@ -0,0 +1,128 @@ | |||
| BRACKET(0x0028,0x0029,'o') | |||
There was a problem hiding this comment.
add script that generated this file
| namespace Karm::Icu { | ||
|
|
||
| test$("bidi") { | ||
| Slice<char> strip(Slice<char> row) { |
There was a problem hiding this comment.
move this to somewhere else?
| testCount++; | ||
| } | ||
|
|
||
| if(testCount != 91707) { |
There was a problem hiding this comment.
91707 = EXPECTED_TEST_COUNT
| return isIsolateInitiator(type) or type == BidiType::PDI or type == BidiType::B or type == BidiType::S or type == BidiType::WS or type == BidiType::ON; | ||
| } | ||
|
|
||
| Rune getPairedBracket(Rune r) { |
There was a problem hiding this comment.
move this to ucd.cpp
| return level + 2; | ||
| }; | ||
|
|
||
| auto incrementOverflowEmbeddingCountIfOverFlowIsolateCountZero = [&]() { |
There was a problem hiding this comment.
overkill to have this as a separate lambda?
| return levels; | ||
| } | ||
|
|
||
| inline bool removeDueToX9(BidiType c) { |
There was a problem hiding this comment.
this is not super consistent with the implementation notes
| // https://unicode.org/reports/tr9/#BD13 | ||
| struct IsolatingRunSequence { | ||
| Vec<urange> levelRuns; | ||
| BidiType sos = BidiType::L; //< Start-of-sequence type (L or R) |
There was a problem hiding this comment.
remove this comment, spec should be enough
| // https://unicode.org/reports/tr9/#Resolving_Weak_Types | ||
| void resolveWeakTypes(MutSlice<BidiType> paragraph, IsolatingRunSequence const& isolatingRunSequence) { | ||
| // W1. Examine each nonspacing mark (NSM) in the isolating run sequence, ... | ||
| // could be an OPT |
|
|
||
| BidiType applyNeutralTypesScopeChanges(BidiType type) { | ||
| // Within this scope, bidirectional types EN and AN are treated as R. | ||
| if (type == BidiType::R or type == BidiType::AN or type == BidiType::EN) |
There was a problem hiding this comment.
no need to check for R
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
No description provided.