Merge pull request #28837 from varun-jaiswal17:gemma3-tokenizer

Add Gemma3 tokenizer support for dnn #28837

- Adds Gemma3 tokenizer support
- Implements character-level BPE
- Adds 6 tests covering English, phrase, mixed case, numbers, special tokens, and encode/decode
- add gemma3_inference.py

Merge with: 
- **Companion PR**  : https://github.com/opencv/opencv_extra/pull/1346
- forward pass bug in gemma3_inference.py : https://github.com/opencv/opencv/pull/28836

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

modules/core/src/persistence_json.cpp

@@ -527,7 +527,33 @@ public:
                             case 't' : { buf[i++] = '\t'; break; }
                             case 'b' : { buf[i++] = '\b'; break; }
                             case 'f' : { buf[i++] = '\f'; break; }
-                            case 'u' : { CV_PARSE_ERROR_CPP( "'\\uXXXX' currently not supported" ); break; }
+                            case 'u' : {
+                                if (i + 4 >= CV_FS_MAX_LEN)
+                                    CV_PARSE_ERROR_CPP("string is too long");
+                                ptr++;
+                                uint32_t codepoint = 0;
+                                for (int k = 0; k < 4; k++, ptr++) {
+                                    char hex = *ptr;
+                                    uint32_t digit = 0;
+                                    if      (hex >= '0' && hex <= '9') digit = (uint32_t)(hex - '0');
+                                    else if (hex >= 'a' && hex <= 'f') digit = (uint32_t)(hex - 'a') + 10u;
+                                    else if (hex >= 'A' && hex <= 'F') digit = (uint32_t)(hex - 'A') + 10u;
+                                    else CV_PARSE_ERROR_CPP("invalid \\uXXXX escape sequence");
+                                    codepoint = (codepoint << 4) | digit;
+                                }
+                                if (codepoint < 0x80) {
+                                    buf[i++] = (char)codepoint;
+                                } else if (codepoint < 0x800) {
+                                    buf[i++] = (char)(0xC0 | (codepoint >> 6));
+                                    buf[i++] = (char)(0x80 | (codepoint & 0x3F));
+                                } else {
+                                    buf[i++] = (char)(0xE0 | (codepoint >> 12));
+                                    buf[i++] = (char)(0x80 | ((codepoint >> 6) & 0x3F));
+                                    buf[i++] = (char)(0x80 | (codepoint & 0x3F));
+                                }
+                                beg = ptr;
+                                continue;
+                            }
                             default  : { CV_PARSE_ERROR_CPP( "Invalid escape character" ); }
                             break;
                             }

modules/core/test/test_io.cpp

@@ -1685,6 +1685,53 @@ TEST(Core_InputOutput, FileStorage_json_bool)
     fs.release();
 }
 
+TEST(Core_InputOutput, FileStorage_json_unicode_escape)
+{
+    // Test \uXXXX Unicode escape sequences in JSON strings
+    std::string test = R"({
+        "ascii": "\u0041\u0042\u0043",
+        "copyright": "\u00A9",
+        "chinese": "\u4E2D",
+        "emoji_base": "\u263A",
+        "mixed": "Hello \u4E16\u754C"
+    })";
+    FileStorage fs(test, FileStorage::READ | FileStorage::MEMORY);
+
+    // Test ASCII characters (\u0041=A, \u0042=B, \u0043=C)
+    ASSERT_TRUE(fs["ascii"].isString());
+    ASSERT_EQ((std::string)fs["ascii"], "ABC");
+
+    // Test 2-byte UTF-8 character (\u00A9=©)
+    ASSERT_TRUE(fs["copyright"].isString());
+    std::string copyright_str = (std::string)fs["copyright"];
+    ASSERT_EQ(copyright_str.size(), 2u);  // © is 2 bytes in UTF-8
+    ASSERT_EQ((unsigned char)copyright_str[0], 0xC2);
+    ASSERT_EQ((unsigned char)copyright_str[1], 0xA9);
+
+    // Test 3-byte UTF-8 character (\u4E2D=中)
+    ASSERT_TRUE(fs["chinese"].isString());
+    std::string chinese_str = (std::string)fs["chinese"];
+    ASSERT_EQ(chinese_str.size(), 3u);  // 中 is 3 bytes in UTF-8
+    ASSERT_EQ((unsigned char)chinese_str[0], 0xE4);
+    ASSERT_EQ((unsigned char)chinese_str[1], 0xB8);
+    ASSERT_EQ((unsigned char)chinese_str[2], 0xAD);
+
+    // Test another 3-byte character (\u263A=☺)
+    ASSERT_TRUE(fs["emoji_base"].isString());
+    std::string emoji_str = (std::string)fs["emoji_base"];
+    ASSERT_EQ(emoji_str.size(), 3u);
+    ASSERT_EQ((unsigned char)emoji_str[0], 0xE2);
+    ASSERT_EQ((unsigned char)emoji_str[1], 0x98);
+    ASSERT_EQ((unsigned char)emoji_str[2], 0xBA);
+
+    // Test mixed ASCII and Unicode
+    ASSERT_TRUE(fs["mixed"].isString());
+    std::string mixed = (std::string)fs["mixed"];
+    ASSERT_EQ(mixed.substr(0, 6), "Hello ");  // First 6 chars are "Hello "
+
+    fs.release();
+}
+
 TEST(Core_InputOutput, FileStorage_free_file_after_exception)
 {
     const std::string fileName = cv::tempfile("FileStorage_free_file_after_exception_test.yml");