M8-T07: extract reusable P1 parser

This commit is contained in:
2026-08-23 21:22:05 +02:00
parent 5855fff451
commit ffc693e995
5 changed files with 354 additions and 188 deletions
+192
View File
@@ -0,0 +1,192 @@
"""Pure, privacy-preserving parser for DSMR and WarmteLink P1 telegrams."""
from __future__ import annotations
from dataclasses import dataclass, field as dataclass_field
from decimal import Decimal, InvalidOperation
from enum import StrEnum
import hashlib
import re
_OBIS_LINE = re.compile(r"^(?P<code>\d+-\d+:\d+\.\d+\.\d+)(?P<values>(?:\([^)]*\))*)$")
_NUMBER_WITH_UNIT = re.compile(r"^(?P<number>[+-]?\d+(?:\.\d+)?)(?:\*(?P<unit>.+))?$")
_CHANNEL_OBIS = re.compile(r"^0-(?P<channel>[1-9]\d*):(24|96)\.")
_EQUIPMENT_ID_CODES = re.compile(r"^0-(?:0|[1-9]\d*):96\.1\.[01]$")
class IntegrityStatus(StrEnum):
"""Whether a frame has a verifiable standard DSMR checksum."""
VALID = "valid"
INVALID = "invalid"
UNVERIFIABLE = "unverifiable"
class P1ParseError(ValueError):
"""A parse error whose message never includes telegram contents."""
@dataclass(frozen=True)
class ObisField:
"""One sanitized OBIS line, including values not understood by the parser."""
code: str
raw_values: tuple[str, ...]
value: Decimal | None = None
unit: str | None = None
comparison_token: str | None = dataclass_field(default=None, repr=False)
@dataclass(frozen=True)
class P1Channel:
"""Fields associated with one M-Bus channel, without its raw identifier."""
number: int
device_type: str | None
equipment_fingerprint: str | None = dataclass_field(repr=False)
readings: tuple[ObisField, ...]
@dataclass(frozen=True)
class P1Telegram:
"""A parsed telegram with only sanitized, persistence-safe data."""
frame_length: int
integrity: IntegrityStatus
integrity_reason: str
timestamp: str | None
equipment_fingerprint: str | None = dataclass_field(repr=False)
fields: tuple[ObisField, ...]
channels: tuple[P1Channel, ...]
class TelegramFramer:
"""Incrementally extract newline-terminated variable-length telegrams."""
def __init__(self) -> None:
self._buffer = bytearray()
def feed(self, chunk: bytes) -> list[bytes]:
"""Append *chunk* and return every complete frame now available."""
self._buffer.extend(chunk)
frames: list[bytes] = []
while (bang := self._buffer.find(b"!")) >= 0:
newline = self._buffer.find(b"\n", bang)
if newline < 0:
break
standard_start = self._buffer.find(b"/")
start = standard_start if 0 <= standard_start < bang else 0
frames.append(bytes(self._buffer[start : newline + 1]))
del self._buffer[: newline + 1]
return frames
def dsmr_crc16(data: bytes) -> int:
"""Return the DSMR CRC-16 over *data* (normally from ``/`` through ``!``)."""
crc = 0
for byte in data:
crc ^= byte
for _ in range(8):
crc = (crc >> 1) ^ 0xA001 if crc & 1 else crc >> 1
return crc & 0xFFFF
def parse_telegram(frame: bytes) -> P1Telegram:
"""Parse one complete frame without retaining raw telegram bytes or IDs."""
bang = frame.find(b"!")
if bang < 0:
raise P1ParseError("telegram has no footer marker")
body = frame[:bang]
footer = frame[bang + 1 :].rstrip(b"\r\n")
integrity, reason = _integrity(frame, bang, footer)
fields, identifiers = _parse_obis_fields(body)
timestamp = _field_value(fields, "0-0:1.0.0")
return P1Telegram(
frame_length=len(frame),
integrity=integrity,
integrity_reason=reason,
timestamp=timestamp,
equipment_fingerprint=identifiers.get("0-0:96.1.1"),
fields=tuple(fields),
channels=_parse_channels(fields, identifiers),
)
def _integrity(frame: bytes, bang: int, footer: bytes) -> tuple[IntegrityStatus, str]:
if not frame.startswith(b"/"):
return IntegrityStatus.UNVERIFIABLE, "missing standard DSMR '/' header"
if len(footer) != 4 or not all(chr(byte) in "0123456789abcdefABCDEF" for byte in footer):
return IntegrityStatus.UNVERIFIABLE, "footer is not a four-digit hexadecimal CRC"
expected = int(footer, 16)
actual = dsmr_crc16(frame[: bang + 1])
if actual == expected:
return IntegrityStatus.VALID, "CRC16 verified from '/' through '!'"
return IntegrityStatus.INVALID, f"CRC16 mismatch: expected {expected:04X}, calculated {actual:04X}"
def _parse_obis_fields(body: bytes) -> tuple[list[ObisField], dict[str, str]]:
fields: list[ObisField] = []
identifiers: dict[str, str] = {}
for line in body.decode("ascii", errors="replace").splitlines()[1:]:
match = _OBIS_LINE.fullmatch(line)
if not match:
continue
code = match.group("code")
raw_values = tuple(re.findall(r"\(([^)]*)\)", match.group("values")))
if _EQUIPMENT_ID_CODES.fullmatch(code):
comparison_token = _fingerprint(raw_values[-1]) if raw_values else None
if comparison_token is not None:
identifiers[code] = comparison_token
fields.append(ObisField(code, ("<redacted>",), comparison_token=comparison_token))
continue
value, unit = _numeric_value(raw_values)
fields.append(ObisField(code, raw_values, value, unit))
return fields, identifiers
def _fingerprint(identifier: str) -> str:
"""Hash an identifier locally; callers never receive its original value."""
return hashlib.sha256(identifier.encode("ascii", errors="replace")).hexdigest()
def _numeric_value(raw_values: tuple[str, ...]) -> tuple[Decimal | None, str | None]:
if not raw_values:
return None, None
match = _NUMBER_WITH_UNIT.fullmatch(raw_values[-1])
if not match:
return None, None
try:
return Decimal(match.group("number")), match.group("unit")
except InvalidOperation:
return None, None
def _field_value(fields: list[ObisField], code: str) -> str | None:
field = next((item for item in fields if item.code == code), None)
return field.raw_values[-1] if field and field.raw_values else None
def _parse_channels(fields: list[ObisField], identifiers: dict[str, str]) -> tuple[P1Channel, ...]:
by_channel: dict[int, list[ObisField]] = {}
for field in fields:
match = _CHANNEL_OBIS.match(field.code)
if match:
by_channel.setdefault(int(match.group("channel")), []).append(field)
return tuple(
P1Channel(
number=number,
device_type=_field_value(channel_fields, f"0-{number}:24.1.0"),
equipment_fingerprint=identifiers.get(f"0-{number}:96.1.0"),
readings=tuple(
field
for field in channel_fields
if field.code == f"0-{number}:24.2.1" and field.value is not None
),
)
for number, channel_fields in sorted(by_channel.items())
)