StreamLens/analyzer/protocols/decoders/base.py

"""
Base classes for Chapter 10 data type decoders
"""

from abc import ABC, abstractmethod
from typing import Dict, Any, Optional, List, Union
from dataclasses import dataclass
import struct


@dataclass
class DecodedPayload:
    """Container for decoded Chapter 10 payload data"""
    data_type: int
    data_type_name: str
    format_version: int
    decoded_data: Dict[str, Any]
    raw_payload: bytes
    errors: List[str]
    metadata: Dict[str, Any]
    
    def __post_init__(self):
        if self.errors is None:
            self.errors = []
        if self.metadata is None:
            self.metadata = {}


class DataTypeDecoder(ABC):
    """Abstract base class for Chapter 10 data type decoders"""
    
    def __init__(self):
        self.supported_formats: List[int] = []
        self.data_type_base: int = 0x00
        self.data_type_name: str = "Unknown"
    
    @abstractmethod
    def can_decode(self, data_type: int) -> bool:
        """Check if this decoder can handle the given data type"""
        pass
    
    @abstractmethod
    def decode(self, payload: bytes, ch10_header: Dict[str, Any]) -> Optional[DecodedPayload]:
        """Decode the payload data"""
        pass
    
    def get_data_type_name(self, data_type: int) -> str:
        """Get human-readable name for data type"""
        return f"{self.data_type_name} Format {data_type & 0x0F}"
    
    def _parse_intra_packet_header(self, payload: bytes, offset: int = 0) -> Optional[Dict[str, Any]]:
        """Parse common intra-packet header (IPH)"""
        if len(payload) < offset + 8:
            return None
        
        try:
            # Standard IPH format
            iph_time = struct.unpack('<I', payload[offset:offset+4])[0]
            reserved = struct.unpack('<H', payload[offset+4:offset+6])[0]
            iph_length = struct.unpack('<H', payload[offset+6:offset+8])[0]
            
            return {
                'iph_time': iph_time,
                'reserved': reserved,
                'iph_length': iph_length,
                'data_start': offset + 8
            }
        except struct.error:
            return None
    
    def _safe_unpack(self, format_str: str, data: bytes, offset: int = 0) -> Optional[tuple]:
        """Safely unpack binary data with error handling"""
        try:
            size = struct.calcsize(format_str)
            if len(data) < offset + size:
                return None
            return struct.unpack(format_str, data[offset:offset+size])
        except struct.error:
            return None


class ContainerDecoder(DataTypeDecoder):
    """Decoder for containerized data formats"""
    
    def decode_container(self, payload: bytes, ch10_header: Dict[str, Any]) -> List[DecodedPayload]:
        """Decode multiple embedded packets from container"""
        decoded_packets = []
        offset = 0
        
        while offset < len(payload):
            # Look for embedded CH-10 sync pattern
            sync_offset = self._find_sync_pattern(payload, offset)
            if sync_offset is None:
                break
                
            # Parse embedded header
            embedded_header = self._parse_embedded_header(payload, sync_offset)
            if not embedded_header:
                break
                
            # Extract embedded payload
            embedded_payload = self._extract_embedded_payload(payload, sync_offset, embedded_header)
            if embedded_payload:
                # Recursively decode embedded packet
                decoded = self.decode(embedded_payload, embedded_header)
                if decoded:
                    decoded_packets.append(decoded)
            
            # Move to next packet
            offset = sync_offset + embedded_header.get('packet_length', 24)
        
        return decoded_packets
    
    def _find_sync_pattern(self, data: bytes, start_offset: int = 0) -> Optional[int]:
        """Find CH-10 sync pattern in data"""
        sync_pattern = 0xEB25
        for offset in range(start_offset, len(data) - 1):
            if offset + 2 <= len(data):
                word = struct.unpack('<H', data[offset:offset+2])[0]
                if word == sync_pattern:
                    return offset
        return None
    
    def _parse_embedded_header(self, data: bytes, offset: int) -> Optional[Dict[str, Any]]:
        """Parse embedded CH-10 header"""
        if len(data) < offset + 24:
            return None
            
        try:
            sync_pattern = struct.unpack('<H', data[offset:offset+2])[0]
            channel_id = struct.unpack('<H', data[offset+2:offset+4])[0]
            packet_length = struct.unpack('<I', data[offset+4:offset+8])[0]
            data_length = struct.unpack('<I', data[offset+8:offset+12])[0]
            data_type = struct.unpack('<H', data[offset+12:offset+14])[0]
            flags = struct.unpack('<H', data[offset+14:offset+16])[0]
            time_bytes = data[offset+16:offset+22]
            time_counter = int.from_bytes(time_bytes, 'little')
            sequence = struct.unpack('<H', data[offset+22:offset+24])[0]
            
            return {
                'sync_pattern': sync_pattern,
                'channel_id': channel_id,
                'packet_length': packet_length,
                'data_length': data_length,
                'data_type': data_type,
                'packet_flags': flags,
                'relative_time_counter': time_counter,
                'sequence_number': sequence
            }
        except struct.error:
            return None
    
    def _extract_embedded_payload(self, data: bytes, header_offset: int, 
                                  header: Dict[str, Any]) -> Optional[bytes]:
        """Extract payload from embedded packet"""
        payload_start = header_offset + 24
        payload_length = header.get('data_length', 0)
        
        if payload_start + payload_length > len(data):
            return None
            
        return data[payload_start:payload_start + payload_length]