Fix newmm tokenizer: Thai Character Cluster boundaries and maximal matching

[Copilot]

Implement comprehensive PyThaiNLP-compatible test suite for newmm tokenizer. Tests were failing due to incorrect Thai Character Cluster (TCC) boundary detection and suboptimal tokenization algorithm.

Changes

Thai Character Cluster boundary detection (ThaiCharacterCluster.java)

• Separated leading vowels (เ, แ, โ, ใ, ไ) from following characters
• Leading vowels now correctly start new character clusters rather than continuing previous ones
• Example: "ภาษาไทยเพราะ" now breaks at position 13 (before "เ") allowing "ภาษาไทย" to be recognized

Newmm tokenization algorithm (NewmmTokenizer.java)

• Replaced BFS graph pathfinding with straightforward maximal matching
• Build word graph at TCC boundaries, choose longest dictionary match at each position
• Simplified from ~80 lines to ~40 lines while improving accuracy

Test coverage (NewmmTokenizerTest.java)

• Added testNewmmComprehensive() covering all PyThaiNLP test cases
• Validates null/empty inputs, numeric patterns (IPs, decimals, currency), whitespace handling, special characters

Example

// Previously failed - "ภาษาไทย" was incorrectly split
Tokenize.wordTokenize("ฉันรักภาษาไทยเพราะฉันเป็นคนไทย", null, "newmm", false);
// Before: [ฉัน, รัก, ภา, ษาไทยเพราะฉันเป็น, คนไทย]
// After:  [ฉัน, รัก, ภาษาไทย, เพราะ, ฉัน, เป็น, คนไทย] ✓

// Numeric patterns now handled correctly
Tokenize.wordTokenize("USD1,984.42", null, "newmm", false);
// Returns: [USD, 1,984.42] ✓

All 17 tests pass (9 newmm + 8 trie tests).

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Make passed all test like pythainlp</issue_title>
<issue_description>Make passed all test:

    def test_newmm(self):
        self.assertEqual(newmm.segment(None), [])
        self.assertEqual(newmm.segment(""), [])
        self.assertEqual(
            word_tokenize("ฉันรักภาษาไทยเพราะฉันเป็นคนไทย", engine="newmm"),
            ["ฉัน", "รัก", "ภาษาไทย", "เพราะ", "ฉัน", "เป็น", "คนไทย"],
        )
        self.assertEqual(
            word_tokenize("19...", engine="newmm"),
            ["19", "..."],
        )
        self.assertEqual(
            word_tokenize("19.", engine="newmm"),
            ["19", "."],
        )
        self.assertEqual(
            word_tokenize("19.84", engine="newmm"),
            ["19.84"],
        )
        self.assertEqual(
            word_tokenize("127.0.0.1", engine="newmm"),
            ["127.0.0.1"],
        )
        self.assertEqual(
            word_tokenize("USD1,984.42", engine="newmm"),
            ["USD", "1,984.42"],
        )
        self.assertEqual(
            word_tokenize(
                "สวัสดีครับ สบายดีไหมครับ",
                engine="newmm",
                keep_whitespace=True,
            ),
            ["สวัสดี", "ครับ", " ", "สบายดี", "ไหม", "ครับ"],
        )
        self.assertEqual(
            word_tokenize("จุ๋มง่วงนอนยัง", engine="newmm"),
            ["จุ๋ม", "ง่วงนอน", "ยัง"],
        )
        self.assertEqual(word_tokenize("จุ๋มง่วง", engine="newmm"), ["จุ๋ม", "ง่วง"])
        self.assertEqual(
            word_tokenize("จุ๋ม   ง่วง", engine="newmm", keep_whitespace=False),
            ["จุ๋ม", "ง่วง"],
        )
        self.assertNotIn(
            " ",
            word_tokenize(
                "จุ๋มง่วง",
                keep_whitespace=False,
            ),
        )
        self.assertEqual(
            word_tokenize("(คนไม่เอา)", engine="newmm"),
            ["(", "คน", "ไม่", "เอา", ")"],
        )
        self.assertEqual(
            word_tokenize("กม/ชม", engine="newmm"), ["กม", "/", "ชม"]
        )
        self.assertEqual(
            word_tokenize("สีหน้า(รถ)", engine="newmm"), ["สีหน้า", "(", "รถ", ")"]
        )
```</issue_description>

## Comments on the Issue (you are @copilot in this section)

<comments>
</comments>

• Fixes Make passed all test like pythainlp #5

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.