@@ -670,15 +670,15 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
670670 };
671671
672672 static const std::map<int , int > k_ucat_cpt = {
673- { llama_codepoint_flags::LLAMA_NUMBER, 0xD1 },
674- { llama_codepoint_flags::LLAMA_LETTER, 0xD2 },
673+ { llama_codepoint_flags::LLAMA_NUMBER, 0xD1 },
674+ { llama_codepoint_flags::LLAMA_LETTER, 0xD2 },
675675 { llama_codepoint_flags::LLAMA_PUNCTUATION, 0xD3 },
676676 };
677677
678678 static const std::map<int , std::string> k_ucat_map = {
679- { llama_codepoint_flags::LLAMA_NUMBER, " \x30 -\x39 " }, // 0-9
680- { llama_codepoint_flags::LLAMA_LETTER, " \x41 -\x5A\x61 -\x7A " }, // A-Za-z
681- { llama_codepoint_flags::LLAMA_PUNCTUATION, " \x21 -\x23\x25 -\x2A\x2C -\x2F\x3A -\x3B\x3F -\x40\\\x5B -\\\x5D\x5F\\\x7B\\\x7D " }, // !-#%-*,-/:-;?-@\[-\]_\{\}
679+ { llama_codepoint_flags::LLAMA_NUMBER, " \x30 -\x39 " }, // 0-9
680+ { llama_codepoint_flags::LLAMA_LETTER, " \x41 -\x5A\x61 -\x7A " }, // A-Za-z
681+ { llama_codepoint_flags::LLAMA_PUNCTUATION, " \x21 -\x23\x25 -\x2A\x2C -\x2F\x3A -\x3B\x3F -\x40\\\x5B -\\\x5D\x5F\\\x7B\\\x7D " }, // !-#%-*,-/:-;?-@\[-\]_\{\}
682682 };
683683
684684 // compute collapsed codepoints only if needed by at least one regex
0 commit comments