unicode : add custom Qwen2 regex handler to fix segfault on long input (ggml-org#21257)

* unicode : add custom Qwen2 regex handler to fix segfault on long input

std::regex uses recursive backtracking internally, which causes a stack
overflow (segfault) when tokenizing long sequences of repeated characters
(e.g. 43K 'A's). The Qwen2 tokenizer regex differs from Llama3 only in
the digit pattern (\p{N} vs \p{N}{1,3}), so it was falling through to
the std::regex fallback path instead of using a custom handler.

Add unicode_regex_split_custom_qwen2() following the established pattern
used by gpt2, llama3, kimi_k2, and afmoe custom handlers.

Closes: ggml-org#21113

* cont : remove TODO comment

* cont : update comment to reflect original regex

* use the correct regex in the comment this time... [no ci]

---------

Co-authored-by: Aldehir Rojas <hello@alde.dev>

Author: 2 people

src/unicode.cpp

@@ -470,6 +470,141 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
     return bpe_offsets;
 }
 
+// Qwen2 system regex: "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+static std::vector<size_t> unicode_regex_split_custom_qwen2(const std::string & text, const std::vector<size_t> & offsets) {
+    std::vector<size_t> bpe_offsets; // store the offset of each word
+    bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
+
+    const auto cpts = unicode_cpts_from_utf8(text);
+
+    size_t start = 0;
+    for (auto offset : offsets) {
+        const size_t offset_ini = start;
+        const size_t offset_end = start + offset;
+        assert(offset_end <= cpts.size());
+        start = offset_end;
+
+        static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
+        auto _get_cpt = [&] (const size_t pos) -> uint32_t {
+            return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
+        };
+
+        auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
+            return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
+        };
+
+        size_t _prev_end = offset_ini;
+        auto _add_token = [&] (const size_t end) -> size_t {
+            assert(_prev_end <= end && end <= offset_end);
+            size_t len = end - _prev_end;
+            if (len > 0) {
+                bpe_offsets.push_back(len);
+            }
+            _prev_end = end;
+            //if (len > 0) {
+            //    std::string s = "";
+            //    for(size_t p = end-len; p < end; p++)
+            //        s += unicode_cpt_to_utf8(cpts[p]);
+            //    printf(">>> '%s'\n", s.c_str());
+            //}
+            return len;
+        };
+
+        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
+            const uint32_t cpt = _get_cpt(pos);
+            const auto flags = _get_flags(pos);
+
+            // regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
+            if (cpt == '\'' && pos+1 < offset_end) {
+                uint32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
+                if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
+                    pos += _add_token(pos+2);
+                    continue;
+                }
+                if (pos+2 < offset_end) {
+                    uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
+                    if ((cpt_next == 'r' && cpt_next_next == 'e') ||
+                        (cpt_next == 'v' && cpt_next_next == 'e') ||
+                        (cpt_next == 'l' && cpt_next_next == 'l')) {
+                        pos += _add_token(pos+3);
+                        continue;
+                    }
+                }
+            }
+
+            // regex: [^\r\n\p{L}\p{N}]?\p{L}+
+            if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
+                if (flags.is_letter || _get_flags(pos+1).is_letter) {  // one or more letters
+                    pos++;
+                    while (_get_flags(pos).is_letter) {
+                        pos++;
+                    }
+                    _add_token(pos);
+                    continue;
+                }
+            }
+
+            // regex: \p{N}
+            if (flags.is_number) {
+                pos++;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
+            auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
+            if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags.as_uint()) {
+                pos += (cpt == ' ');
+                while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
+                    flags2 = _get_flags(++pos);
+                }
+                uint32_t cpt2 = _get_cpt(pos);
+                while (cpt2 == '\r' || cpt2 == '\n') {
+                    cpt2 = _get_cpt(++pos);
+                }
+                _add_token(pos);
+                continue;
+            }
+
+            size_t num_whitespaces = 0;
+            size_t last_end_r_or_n = 0;
+            while (_get_flags(pos+num_whitespaces).is_whitespace) {
+                uint32_t cpt2 = _get_cpt(pos+num_whitespaces);
+                if (cpt2 == '\r' || cpt2 == '\n') {
+                    last_end_r_or_n = pos + num_whitespaces + 1;
+                }
+                num_whitespaces++;
+            }
+
+            // regex: \s*[\r\n]+
+            if (last_end_r_or_n > 0) {
+                pos = last_end_r_or_n;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: \s+(?!\S)
+            if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != OUT_OF_RANGE) {
+                pos += num_whitespaces - 1;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: \s+
+            if (num_whitespaces > 0) {
+                pos += num_whitespaces;
+                _add_token(pos);
+                continue;
+            }
+
+            // no matches
+            _add_token(++pos);
+        }
+    }
+
+    return bpe_offsets;
+}
+
 template <typename CharT>
 static std::vector<size_t> unicode_regex_split_stl(const std::basic_string<CharT> & text, const std::basic_string<CharT> & regex, const std::vector<size_t> & offsets) {
     using BidirIt = typename std::basic_string<CharT>::const_iterator;
@@ -790,8 +925,10 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
     } else if (
             regex_expr == "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" ||
             regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
-
         bpe_offsets = unicode_regex_split_custom_llama3(text, offsets);
+    } else if (
+           regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
+        bpe_offsets = unicode_regex_split_custom_qwen2(text, offsets);
     } else if (regex_expr == "\\p{Han}+") {
         // K2's first pattern - handle all K2 patterns together
         bpe_offsets = unicode_regex_split_custom_kimi_k2(text, offsets);