feat(study): 개념 학습 리더 (Stage A) — 구조 파싱·떠올리기·백링크

이론공부 개선 B→A→C 의 A. 개념노트를 구조(요약/본문/빈출★/관련개념)로 렌더 + 능동 회상(떠올리기) + 관련개념 백링크 + 이전/다음.
- concept_parser: md 골격 파서(273/273 불변식) + 관련개념 백링크 해소(exact→title⊆phrase substring, 과대매치 가드)
- concept_curriculum.concept_detail + GET /api/study/concepts/{id} (개념문서 태그 스코프)
- /study/read/[docId] 리더(MarkdownDoc KaTeX+docimg 재사용·읽기/떠올리기 모드) + 홈 오늘의개념 링크 연결
- 적대리뷰 5건 반영(이중로드·substring 오결선·엔드포인트 스코프·prev/next 결정성·in-flight 가드). 마이그 없음·문제풀이 무접촉

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
hyungi
2026-07-01 11:51:40 +09:00
parent da4a2e81c3
commit f38ec177d7
5 changed files with 487 additions and 2 deletions
+15 -1
View File
@@ -8,7 +8,7 @@ from __future__ import annotations
from typing import Annotated
from fastapi import APIRouter, Depends
from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy.ext.asyncio import AsyncSession
from core.auth import get_current_user
@@ -43,6 +43,20 @@ async def get_today_concepts(
return await cc.today_concepts(session, user.id, topic_id, limit)
@router.get("/concepts/{doc_id}")
async def get_concept_detail(
doc_id: int,
user: Annotated[User, Depends(get_current_user)],
session: Annotated[AsyncSession, Depends(get_session)],
topic_id: int = DEFAULT_TOPIC_ID,
):
"""개념 리더 재료 — 구조 파싱(요약/본문/빈출/관련) + 백링크 해소 + 회독/SR + 이전/다음."""
detail = await cc.concept_detail(session, user.id, topic_id, doc_id)
if detail is None:
raise HTTPException(status_code=404, detail="concept not found")
return detail
@router.post("/concepts/{doc_id}/read")
async def post_concept_read(
doc_id: int,
+77
View File
@@ -18,6 +18,7 @@ from models.document_read import DocumentRead
from models.study_concept_progress import StudyConceptProgress
from models.study_question_progress import StudyQuestionProgress
from models.study_topic import StudyTopic
from services.study.concept_parser import parse_concept, resolve_related
from services.study.sr_schedule import advance, first_due
# 개념 행 조회 — 태그로 개념문서 필터 + 회독 진행 LEFT JOIN. md_content 는 전송 안 하고
@@ -205,3 +206,79 @@ async def mark_read(
await session.commit()
await session.refresh(prog)
return {"ok": True, "review_stage": prog.review_stage, "due_at": prog.due_at}
_CONCEPT_ONE_SQL = text(
"""
SELECT d.id AS doc_id, d.title AS title, d.md_content AS md_content,
split_part(replace(d.user_tags::text, '"', ''), '/', 3) AS subject,
(d.md_content LIKE '%★★★%') AS f3,
(d.md_content LIKE '%★★%') AS f2,
EXISTS (
SELECT 1 FROM document_reads r
WHERE r.document_id = d.id AND r.user_id = :uid
) AS is_read,
p.review_stage AS review_stage,
p.due_at AS due_at
FROM documents d
LEFT JOIN study_concept_progress p ON p.concept_doc_id = d.id AND p.user_id = :uid
WHERE d.id = :doc_id AND d.deleted_at IS NULL AND d.user_tags::text LIKE :like
"""
)
async def concept_detail(
session: AsyncSession, user_id: int, topic_id: int, doc_id: int
) -> dict | None:
"""개념 리더 재료 — md 구조 파싱 + 관련개념 백링크 해소 + 회독/SR 상태 + 같은 과목 이전/다음."""
name = await _topic_name(session, topic_id)
if not name:
return None
like = f"%@library/{name}/%"
row = (
await session.execute(
_CONCEPT_ONE_SQL, {"uid": user_id, "doc_id": doc_id, "like": like}
)
).mappings().first()
if row is None:
return None
parsed = parse_concept(row["md_content"] or "")
# 백링크 해소 + 이전/다음 = 같은 토픽 개념 title 인덱스(회독 rows 재사용)
idx = await _concept_rows(session, user_id, name)
title_index = [(r["doc_id"], r["title"], r["subject"]) for r in idx]
resolved = resolve_related(parsed["related"], title_index)
# 이전/다음 = 같은 과목, title 순
same = sorted(
[(r["doc_id"], r["title"]) for r in idx if r["subject"] == row["subject"]],
key=lambda x: (x[1] or "", x[0]),
)
ids = [d for d, _ in same]
prev_id = next_id = None
if doc_id in ids:
pos = ids.index(doc_id)
if pos > 0:
prev_id = ids[pos - 1]
if pos < len(ids) - 1:
next_id = ids[pos + 1]
freq = 3 if row["f3"] else (2 if row["f2"] else 1)
return {
"doc_id": row["doc_id"],
"db_title": row["title"],
"title": parsed["title"] or row["title"],
"subject": row["subject"],
"freq": freq,
"summary": parsed["summary"],
"body": parsed["body"],
"bincheol": parsed["bincheol"],
"related": resolved,
"is_read": row["is_read"],
"review_stage": row["review_stage"],
"due_at": row["due_at"],
"prev_id": prev_id,
"next_id": next_id,
}
+175
View File
@@ -0,0 +1,175 @@
"""concept_parser — 개념노트 markdown 구조 파서 + 관련개념 백링크 해소 (이론 리더용).
정찰 실측 불변식(273/273): 개념노트는 고정 골격을 100% 따름 —
# {H1 제목} (첫 줄, DB title 과 다른 표시용 제목)
> **한 줄 요약**: {요약} (blockquote, 라벨 고정)
## {본문 라벨} ... (BODY, 자유 라벨 H2 0~N, 트레일 ★ 가능)
## 빈출 포인트 (항상, 관련개념 직전)
## 관련 개념 (항상, 문서 최종 섹션)
코드펜스(``` ASCII 도식) 내부의 ##/- 는 무시. 헤딩 트레일 ★ 는 스트립(라벨 정규화).
'빈출 포인트'/'관련 개념' 앵커만 이름으로 잡고 나머지 BODY 는 순서·위치로 처리(라벨 화이트리스트 금지).
순수 함수 · LLM 0.
"""
from __future__ import annotations
import re
_FENCE = re.compile(r"^\s*```")
_H1 = re.compile(r"^#\s+(.+?)\s*$")
_H2 = re.compile(r"^##\s+(.+?)\s*$") # ### 는 매칭 안 됨(## 뒤 \s 요구)
_SUMMARY = re.compile(r"^>\s*\*\*한 줄 요약\*\*:\s*(.+)$")
_STAR_SUFFIX = re.compile(r"\s*★+\s*$")
_TRAIL_STARS = re.compile(r"★+\s*$")
_BINCHEOL_ITEM = re.compile(r"^\s*-\s+(★*)\s*(.+)$")
_RELATED_ITEM = re.compile(r"^\s*-\s+(.+)$")
_PAREN = re.compile(r"\s*\(.*$") # 괄호부터 끝(clarifier 힌트 절단)
_NUM_PREFIX = re.compile(r"^\d+_")
_STRIP_SYM = re.compile(r"[\s_·,./()\-]")
_ANCHOR_BINCHEOL = "빈출 포인트"
_ANCHOR_RELATED = "관련 개념"
def parse_concept(md: str) -> dict:
"""개념노트 md → {title, summary, body[{label,stars,md}], bincheol[{tier,text}], related[{raw,phrase,hint}]}."""
lines = (md or "").split("\n")
title: str | None = None
summary: str | None = None
body: list[dict] = []
bincheol_lines: list[str] = []
related_lines: list[str] = []
in_fence = False
zone = "pre" # pre | body | bincheol | related
body_cur: dict | None = None
def emit(line: str) -> None:
if body_cur is not None:
body_cur["_lines"].append(line)
elif zone == "bincheol":
bincheol_lines.append(line)
elif zone == "related":
related_lines.append(line)
# pre-zone 내용(요약 앞 잡음)은 버림
for ln in lines:
if _FENCE.match(ln):
in_fence = not in_fence
emit(ln)
continue
if in_fence:
emit(ln)
continue
if title is None:
m = _H1.match(ln)
if m:
title = m.group(1).strip()
continue
if summary is None:
m = _SUMMARY.match(ln)
if m:
summary = m.group(1).strip()
continue
m2 = _H2.match(ln)
if m2:
raw_label = m2.group(1).strip()
star_m = _TRAIL_STARS.search(raw_label)
stars = len(star_m.group(0).strip()) if star_m else 0
label = _STAR_SUFFIX.sub("", raw_label).strip()
if label == _ANCHOR_BINCHEOL:
zone = "bincheol"
body_cur = None
continue
if label == _ANCHOR_RELATED:
zone = "related"
body_cur = None
continue
body_cur = {"label": label, "stars": stars, "_lines": []}
body.append(body_cur)
zone = "body"
continue
emit(ln)
body_out = []
for s in body:
text = "\n".join(s["_lines"]).strip()
if text or s["label"]:
body_out.append({"label": s["label"], "stars": s["stars"], "md": text})
bincheol = []
for ln in bincheol_lines:
m = _BINCHEOL_ITEM.match(ln)
if m:
bincheol.append({"tier": len(m.group(1)), "text": m.group(2).strip()})
related = []
for ln in related_lines:
m = _RELATED_ITEM.match(ln)
if m:
raw = m.group(1).strip()
phrase = _PAREN.sub("", raw).strip()
hint = raw[len(phrase):].strip() if len(raw) > len(phrase) else ""
if phrase:
related.append({"raw": raw, "phrase": phrase, "hint": hint})
return {
"title": title,
"summary": summary,
"body": body_out,
"bincheol": bincheol,
"related": related,
}
def _normalize(s: str) -> str:
"""해소용 정규화: NN_ 접두 제거 → 소문자 → 공백/기호 제거. 영문은 lowercase 유지."""
s = _NUM_PREFIX.sub("", s or "")
s = s.lower()
s = _STRIP_SYM.sub("", s)
return s
def resolve_related(related: list[dict], title_index: list[tuple]) -> list[dict]:
"""관련개념 구절 → 개념 doc 해소. title_index = [(doc_id, title, subject), ...].
다단 fallback(정찰 ~79%): 정규화 exact → 양방향 substring(≥2자 가드) → 미해소=dangling(doc_id None).
"""
norm_exact: dict[str, int] = {}
norm_list: list[tuple[str, int, str]] = []
for did, ttl, _subj in title_index:
n = _normalize(ttl)
if n:
norm_exact.setdefault(n, did)
norm_list.append((n, did, ttl))
out = []
for it in related:
pn = _normalize(it["phrase"])
did: int | None = None
rtitle: str | None = None
if pn and len(pn) >= 2:
if pn in norm_exact:
did = norm_exact[pn]
else:
# substring 폴백: title-norm ⊆ phrase-norm 방향만(짧은 phrase 가 더 큰 title 을
# 삼키는 오결선 방지, 예: '염산'→'염산나트륨' X) + 길이차 최소(가장 구체적) +
# doc_id tiebreak(순서 무관 결정성). 후보 없으면 dangling(doc_id None).
cands = [
(abs(len(n) - len(pn)), cand, ttl)
for n, cand, ttl in norm_list
if len(n) >= 2 and n in pn
]
if cands:
cands.sort(key=lambda c: (c[0], c[1]))
_, did, rtitle = cands[0]
if did is not None and rtitle is None:
rtitle = next((t for d, t, _ in title_index if d == did), None)
out.append(
{"phrase": it["phrase"], "hint": it["hint"], "doc_id": did, "title": rtitle}
)
return out