Message Encoding

import re

# GSM-7 basic character set
GSM7_BASIC = set(
    "@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ ÆæßÉ"
    " !\"#¤%&'()*+,-./0123456789:;<=>?"
    "¡ABCDEFGHIJKLMNOPQRSTUVWXYZ"
    "ÄÖÑܧ¿abcdefghijklmnopqrstuvwxyz"
    "äöñüà"
)
GSM7_EXTENDED = set("^{}\\[~]|€")

def calculate_segments(text: str) -> dict:
    """Calculate encoding and segment count for an SMS message."""
    is_gsm7 = all(c in GSM7_BASIC or c in GSM7_EXTENDED for c in text)

    if is_gsm7:
        # Count extended chars as 2
        char_count = sum(2 if c in GSM7_EXTENDED else 1 for c in text)
        if char_count <= 160:
            segments = 1
        else:
            segments = -(-char_count // 153)  # ceiling division
        return {"encoding": "GSM-7", "char_count": char_count, "segments": segments}
    else:
        # UTF-16: emojis count as 2 chars (surrogate pairs)
        char_count = 0
        for c in text:
            char_count += 2 if ord(c) > 0xFFFF else 1
        if char_count <= 70:
            segments = 1
        else:
            segments = -(-char_count // 67)
        return {"encoding": "UTF-16", "char_count": char_count, "segments": segments}

# Example usage
result = calculate_segments("Hello, world!")
print(f"Encoding: {result['encoding']}, Segments: {result['segments']}")
# Output: Encoding: GSM-7, Segments: 1

result = calculate_segments("Hello 😀")
print(f"Encoding: {result['encoding']}, Segments: {result['segments']}")
# Output: Encoding: UTF-16, Segments: 1