Current text splitters are designed for English and don’t handle Arabic-specific characters correctly — Arabic punctuation (،, ؟, ؛), kashida (ـ), and diacritics cause incorrect chunk boundaries in Arabic RAG pipelines.
I’d like to add an ArabicTextSplitter that handles these correctly. Happy to implement it — wanted to get maintainer feedback before opening a PR.
Use case: Arabic RAG applications where incorrect chunking directly hurts retrieval quality.