Autoparser - complete refactoring of parser architecture (#18675)

* Autoparser - full single commit squish

* Final pre-merge changes: minor fixes, Kimi 2.5 model parser

common/unicode.cpp

@@ -1,14 +1,18 @@
 #include "unicode.h"
+#include <cassert>
+#include <stdexcept>
+#include <vector>
+#include <string>
 
 // implementation adopted from src/unicode.cpp
 
-size_t utf8_sequence_length(unsigned char first_byte) {
+size_t common_utf8_sequence_length(unsigned char first_byte) {
     const size_t lookup[] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 3, 4 };
     uint8_t highbits = static_cast<uint8_t>(first_byte) >> 4;
     return lookup[highbits];
 }
 
-utf8_parse_result parse_utf8_codepoint(std::string_view input, size_t offset) {
+utf8_parse_result common_parse_utf8_codepoint(std::string_view input, size_t offset) {
     if (offset >= input.size()) {
         return utf8_parse_result(utf8_parse_result::INCOMPLETE);
     }
@@ -62,3 +66,43 @@ utf8_parse_result parse_utf8_codepoint(std::string_view input, size_t offset) {
     // Invalid first byte
     return utf8_parse_result(utf8_parse_result::INVALID);
 }
+
+std::string common_unicode_cpts_to_utf8(const std::vector<uint32_t> & cps) {
+    std::string result;
+    for (size_t i = 0; i < cps.size(); ++i) {
+        result.append(common_unicode_cpt_to_utf8(cps[i]));
+    }
+    return result;
+}
+
+std::string common_unicode_cpt_to_utf8(uint32_t cpt) {
+    std::string result;
+
+    if (/* 0x00 <= cpt && */ cpt <= 0x7f) {
+        result.push_back(cpt);
+        return result;
+    }
+    if (0x80 <= cpt && cpt <= 0x7ff) {
+        result.push_back(0xc0 | ((cpt >> 6) & 0x1f));
+        result.push_back(0x80 | (cpt & 0x3f));
+        return result;
+    }
+    if (0x800 <= cpt && cpt <= 0xffff) {
+        result.push_back(0xe0 | ((cpt >> 12) & 0x0f));
+        result.push_back(0x80 | ((cpt >> 6) & 0x3f));
+        result.push_back(0x80 | (cpt & 0x3f));
+        return result;
+    }
+    if (0x10000 <= cpt && cpt <= 0x10ffff) {
+        result.push_back(0xf0 | ((cpt >> 18) & 0x07));
+        result.push_back(0x80 | ((cpt >> 12) & 0x3f));
+        result.push_back(0x80 | ((cpt >> 6) & 0x3f));
+        result.push_back(0x80 | (cpt & 0x3f));
+        return result;
+    }
+
+    throw std::invalid_argument("invalid codepoint");
+}
+
+
+