Files
C.E.L_Slide_test2/src/json_utils.py
T
Kyeongmin 265d70ed91 refactor(#28): IMP-28 L4 _parse_json dedup (4 modules -> src/json_utils)
Consolidate duplicate _parse_json helpers from content_editor.py /
design_director.py / kei_client.py (fuller form) and pipeline.py (simple form)
into shared src/json_utils.parse_json (strict superset). All 18 call-sites
preserved via `parse_json as _parse_json` alias import; no behavior change.

- src/json_utils.py (new): shared helper, fenced/plain-fence/bare-brace patterns
  + list-prefix cleanup fallback.
- tests/test_json_utils.py (new): 9 unit tests pinning parser semantics.
- src/content_editor.py / design_director.py: remove local helper +
  unused `import json` / `import re`.
- src/kei_client.py / pipeline.py: remove local helper; `json` / `re` retained
  (used elsewhere).

Targeted tests 9 passed; full pytest 374 passed (3 pre-existing scripts/
collection errors reproduce on baseline 909bf75, IMP-28 unrelated).
2026-05-20 20:44:19 +09:00

47 lines
1.4 KiB
Python

"""JSON 추출 공용 유틸리티.
Kei / Claude API 응답 텍스트에서 JSON 객체를 추출한다.
content_editor, design_director, kei_client, pipeline 공통 헬퍼.
응답이 마크다운 리스트 접두사("- " / "* ")로 감싸진 경우에도 처리.
"""
from __future__ import annotations
import json
import re
from typing import Any
_JSON_PATTERNS: tuple[str, ...] = (
r"```json\s*(.*?)```",
r"```\s*(.*?)```",
r"(\{.*\})",
)
def parse_json(text: str) -> dict[str, Any] | None:
"""텍스트에서 JSON을 추출한다.
Kei API가 마크다운 리스트 접두사(- )를 붙여 응답하는 경우에도 처리.
원본 → 리스트 접두사 제거 버전 순서로 fenced JSON / plain fenced / 베어 brace 패턴을
차례로 시도한다. 모두 실패하면 None.
"""
lines = text.split("\n")
cleaned_lines: list[str] = []
for line in lines:
stripped = line.lstrip()
if stripped.startswith("- ") or stripped.startswith("* "):
cleaned_lines.append(stripped[2:])
else:
cleaned_lines.append(stripped)
cleaned = "\n".join(cleaned_lines)
for target in (text, cleaned):
for pattern in _JSON_PATTERNS:
match = re.search(pattern, target, re.DOTALL)
if match:
try:
return json.loads(match.group(1).strip())
except json.JSONDecodeError:
continue
return None