Coverage for src/copytrading_engine/sources/evidence.py: 88%

41 statements  

« prev     ^ index     » next       coverage.py v7.16.2, created at 2026-11-16 16:55 +0000

1"""Pure bounds and normalization for source-owned ingress evidence.""" 

2 

3import json 

4import re 

5from collections.abc import Sequence 

6 

7from pydantic import JsonValue 

8 

9from copytrading_engine.shared.payload_capture import CaptureStatus 

10from copytrading_engine.shared.raw_message import RawMessage 

11from copytrading_engine.sources.application import AttachmentReference 

12 

13MAX_SOURCE_EVENT_BYTES = 64 * 1024 

14MAX_ATTACHMENTS_PER_MESSAGE = 10 

15OMITTED_ATTACHMENT_ID = "__additional_attachments_omitted__" 

16_ATTACHMENT_ID = re.compile(r"^[A-Za-z0-9_-]{1,128}$") 

17_EVIDENCE_ID = re.compile(r"^[0-9a-f]{32}$") 

18 

19 

20def normalized_source_event(event: RawMessage) -> dict[str, JsonValue]: 

21 return { 

22 "event_type": "raw_message", 

23 "content": event.text, 

24 "embeds": [], 

25 "attachments": [], 

26 "attachments_omitted": 0, 

27 } 

28 

29 

30def bounded_source_event(payload: JsonValue) -> tuple[str | None, CaptureStatus, int]: 

31 serialized = json.dumps(payload, ensure_ascii=False, separators=(",", ":")) 

32 size = len(serialized.encode("utf-8")) 

33 if size <= MAX_SOURCE_EVENT_BYTES: 

34 return serialized, "complete", size 

35 return None, "oversize", size 

36 

37 

38def is_evidence_id(value: str) -> bool: 

39 return bool(_EVIDENCE_ID.fullmatch(value)) 

40 

41 

42def bounded_attachments( 

43 attachments: Sequence[AttachmentReference], 

44) -> tuple[tuple[AttachmentReference, ...], int]: 

45 selected = [] 

46 used_ids: set[str] = set() 

47 for index, item in enumerate(attachments[:MAX_ATTACHMENTS_PER_MESSAGE]): 

48 candidate = item.attachment_id 

49 if not _ATTACHMENT_ID.fullmatch(candidate) or candidate == OMITTED_ATTACHMENT_ID: 49 ↛ 50line 49 didn't jump to line 50 because the condition on line 49 was never true

50 candidate = f"attachment-{index + 1}" 

51 base = candidate[:128] 

52 identifier = base 

53 suffix = 1 

54 while identifier in used_ids: 54 ↛ 55line 54 didn't jump to line 55 because the condition on line 54 was never true

55 ending = f"-{suffix}" 

56 identifier = base[: 128 - len(ending)] + ending 

57 suffix += 1 

58 used_ids.add(identifier) 

59 filename = "".join(character for character in item.filename if ord(character) >= 32)[:255] 

60 content_type = item.content_type[:255] if item.content_type is not None else None 

61 selected.append( 

62 AttachmentReference( 

63 attachment_id=identifier, 

64 filename=filename, 

65 content_type=content_type, 

66 declared_size=item.declared_size, 

67 url=item.url, 

68 ) 

69 ) 

70 return tuple(selected), max(0, len(attachments) - len(selected))