Messaging, Global SMS &
Telecom Infrastructure APIs

import unicodedata

# Production GSM-7 Sanitizer: Prevents Accidental UCS-2 Segment Multipliers
GSM_7_CHARS = set(
    "@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ\x1bÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>?"
    "¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑܧ¿abcdefghijklmnopqrstuvwxyzäöñüà"
)

def sanitize_and_audit_sms(message_body: str) -> dict:
    # Replace smart quotes and typographic dashes with GSM-7 equivalents
    normalized = (
        message_body.replace('“', '"').replace('”', '"')
        .replace('‘', "'").replace('’', "'")
        .replace('', '-').replace('–', '-')
    )
    
    # Check for rogue Unicode characters triggering UCS-2
    non_gsm_chars = [c for c in normalized if c not in GSM_7_CHARS]
    is_ucs2 = len(non_gsm_chars) > 0
    
    char_count = len(normalized)
    if is_ucs2:
        # UCS-2: 70 chars for single, 67 chars per concatenated segment
        segments = 1 if char_count <= 70 else -(-char_count // 67)
    else:
        # GSM-7: 160 chars for single, 153 chars per concatenated segment
        segments = 1 if char_count <= 160 else -(-char_count // 153)
        
    return {
        "sanitized_body": normalized,
        "char_count": char_count,
        "encoding": "UCS-2 (Expensive!)" if is_ucs2 else "GSM-7 (Optimal)",
        "billable_segments": segments,
        "rogue_characters": non_gsm_chars
    }

Frequently Asked Questions

Commonly evaluated trade-offs, contractual pitfalls, and latency optimization rules.