Function test_unit_utf8_count

scripts/test_stringzilla.py:2002–2028

Test UTF-8 character counting (codepoints, not bytes).

()

def test_unit_utf8_count():
    """Test UTF-8 character counting (codepoints, not bytes)."""
    # ASCII strings: len == utf8_count
    assert sz.utf8_count("hello") == 5
    assert sz.utf8_count("") == 0
    assert sz.utf8_count("a") == 1

    # Multi-byte UTF-8: character count != byte count
    assert sz.utf8_count("café") == 4  # é is 2 bytes but 1 char
    assert sz.utf8_count("日本語") == 3  # Each CJK char is 3 bytes
    assert sz.utf8_count("🎉") == 1  # Emoji is 4 bytes but 1 char
    assert sz.utf8_count("👨‍👩‍👧") == 5  # Family emoji: 3 people + 2 ZWJ

    # Mixed ASCII and multi-byte
    assert sz.utf8_count("hello世界") == 7  # 5 ASCII + 2 CJK
    assert sz.utf8_count("naïve") == 5  # ï is 2 bytes

    # Method form on Str
    assert sz.Str("café").utf8_count() == 4

    # Bytes input
    assert sz.utf8_count(b"caf\xc3\xa9") == 4  # café in UTF-8 bytes

    # Various multi-byte sequences
    assert sz.utf8_count("αβγδ") == 4  # Greek letters (2 bytes each)
    assert sz.utf8_count("АБВГ") == 4  # Cyrillic letters (2 bytes each)
    assert sz.utf8_count("𐍈") == 1  # Gothic letter (4 bytes)


def test_utf8_splitlines_iter():