feat: 뉴스 전용 페이지 + 분류 격리 + 읽음 상태

- /news 전용 페이지: 신문사 필터, 읽지않음 필터, 시간순 리스트, 미리보기 - 뉴스 분류 격리: ai_domain='News', classify 제거, embed만 등록 - is_read: 클릭 시 자동 읽음, 전체 읽음 API - documents 목록에서 뉴스 제외 (source_channel != 'news') - nav에 뉴스 링크 추가 - GET /api/news/articles, POST /api/news/mark-all-read Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 14:16:00 +09:00
parent cd5f1c526d
commit 7ca3abf17c
7 changed files with 280 additions and 9 deletions
--- a/app/api/documents.py
+++ b/app/api/documents.py
@@ -43,6 +43,7 @@ class DocumentResponse(BaseModel):
    derived_path: str | None
    original_format: str | None
    conversion_status: str | None
+    is_read: bool | None
    review_status: str | None
    edit_url: str | None
    preview_status: str | None
@@ -146,8 +147,8 @@ async def list_documents(
    source: str | None = None,
    format: str | None = None,
 ):
-    """문서 목록 조회 (페이지네이션 + 필터)"""
-    query = select(Document).where(Document.deleted_at == None)
+    """문서 목록 조회 (페이지네이션 + 필터, 뉴스 제외)"""
+    query = select(Document).where(Document.deleted_at == None, Document.source_channel != "news")

    if domain:
        # prefix 매칭: Industrial_Safety 클릭 시 하위 전부 포함
--- a/app/api/news.py
+++ b/app/api/news.py
@@ -98,6 +98,62 @@ async def delete_source(
    return {"message": f"소스 {source_id} 삭제됨"}


+@router.get("/articles")
+async def list_articles(
+    user: Annotated[User, Depends(get_current_user)],
+    session: Annotated[AsyncSession, Depends(get_session)],
+    source: str | None = None,
+    unread_only: bool = False,
+    page: int = 1,
+    page_size: int = 30,
+):
+    """뉴스 기사 목록"""
+    from sqlalchemy import func
+    from models.document import Document
+
+    query = select(Document).where(
+        Document.source_channel == "news",
+        Document.deleted_at == None,
+    )
+    if source:
+        query = query.where(Document.ai_sub_group == source)
+    if unread_only:
+        query = query.where(Document.is_read == False)
+
+    count_q = select(func.count()).select_from(query.subquery())
+    total = (await session.execute(count_q)).scalar()
+
+    query = query.order_by(Document.is_read.asc(), Document.created_at.desc())
+    query = query.offset((page - 1) * page_size).limit(page_size)
+    result = await session.execute(query)
+    items = result.scalars().all()
+
+    from api.documents import DocumentResponse
+    return {
+        "items": [DocumentResponse.model_validate(doc) for doc in items],
+        "total": total,
+        "page": page,
+    }
+
+
+@router.post("/mark-all-read")
+async def mark_all_read(
+    user: Annotated[User, Depends(get_current_user)],
+    session: Annotated[AsyncSession, Depends(get_session)],
+):
+    """전체 읽음 처리"""
+    from sqlalchemy import update
+    from models.document import Document
+
+    result = await session.execute(
+        update(Document)
+        .where(Document.source_channel == "news", Document.is_read == False)
+        .values(is_read=True)
+    )
+    await session.commit()
+    return {"marked": result.rowcount}
+
+
@router.post("/collect")
 async def trigger_collect(
    user: Annotated[User, Depends(get_current_user)],
--- a/app/models/document.py
+++ b/app/models/document.py
@@ -3,7 +3,7 @@
 from datetime import datetime

 from pgvector.sqlalchemy import Vector
-from sqlalchemy import BigInteger, DateTime, Enum, String, Text
+from sqlalchemy import BigInteger, Boolean, DateTime, Enum, String, Text
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.orm import Mapped, mapped_column

@@ -55,6 +55,9 @@ class Document(Base):
    original_format: Mapped[str | None] = mapped_column(String(20))
    conversion_status: Mapped[str | None] = mapped_column(String(20), default="none")

+    # 읽음 상태 (뉴스용)
+    is_read: Mapped[bool | None] = mapped_column(Boolean, default=False)
+
    # 승인/삭제
    review_status: Mapped[str | None] = mapped_column(String(20), default="pending")
    deleted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
--- a/app/workers/news_collector.py
+++ b/app/workers/news_collector.py
@@ -139,6 +139,7 @@ async def _fetch_rss(session, source: NewsSource) -> int:
            continue

        category = _normalize_category(source.category or "")
+        source_short = source.name.split(" ")[0]  # "경향신문 문화" → "경향신문"

        doc = Document(
            file_path=f"news/{source.name}/{article_id}",
@@ -154,14 +155,14 @@ async def _fetch_rss(session, source: NewsSource) -> int:
            data_origin="external",
            edit_url=link,
            review_status="approved",
+            ai_domain="News",
+            ai_sub_group=source_short,
+            ai_tags=[f"News/{source_short}/{category}"],
        )
        session.add(doc)
        await session.flush()

-        # classify + embed 큐 등록 (extract 불필요)
-        session.add(ProcessingQueue(document_id=doc.id, stage="classify", status="pending"))
-
-        # 30일 이내만 embed
+        # embed만 등록 (classify 불필요 — 소스/분야 이미 확정)
        days_old = (datetime.now(timezone.utc) - pub_dt).days
        if days_old <= 30:
            session.add(ProcessingQueue(document_id=doc.id, stage="embed", status="pending"))
@@ -219,6 +220,7 @@ async def _fetch_api(session, source: NewsSource) -> int:
            continue

        category = _normalize_category(article.get("section", source.category or ""))
+        source_short = source.name.split(" ")[0]

        doc = Document(
            file_path=f"news/{source.name}/{article_id}",
@@ -234,12 +236,13 @@ async def _fetch_api(session, source: NewsSource) -> int:
            data_origin="external",
            edit_url=link,
            review_status="approved",
+            ai_domain="News",
+            ai_sub_group=source_short,
+            ai_tags=[f"News/{source_short}/{category}"],
        )
        session.add(doc)
        await session.flush()

-        session.add(ProcessingQueue(document_id=doc.id, stage="classify", status="pending"))
-
        days_old = (datetime.now(timezone.utc) - pub_dt).days
        if days_old <= 30:
            session.add(ProcessingQueue(document_id=doc.id, stage="embed", status="pending"))
--- a/frontend/src/routes/+layout.svelte
+++ b/frontend/src/routes/+layout.svelte
@@ -76,6 +76,7 @@
          <a href="/documents" class="text-xs hover:text-[var(--accent)]">문서</a>
        </div>
        <div class="flex items-center gap-3">
+          <a href="/news" class="text-xs text-[var(--text-dim)] hover:text-[var(--text)]">뉴스</a>
          <a href="/inbox" class="text-xs text-[var(--text-dim)] hover:text-[var(--text)]">Inbox</a>
          <a href="/settings" class="text-xs text-[var(--text-dim)] hover:text-[var(--text)]">설정</a>
          <button
--- a/frontend/src/routes/news/+page.svelte
+++ b/frontend/src/routes/news/+page.svelte
@@ -0,0 +1,198 @@
+<script>
+  import { onMount } from 'svelte';
+  import { api } from '$lib/api';
+  import { addToast } from '$lib/stores/ui';
+  import { marked } from 'marked';
+  import DOMPurify from 'dompurify';
+
+  function renderMd(text) {
+    return DOMPurify.sanitize(marked(text), {
+      USE_PROFILES: { html: true },
+      FORBID_TAGS: ['style', 'script'],
+      FORBID_ATTR: ['onerror', 'onclick'],
+      ALLOW_UNKNOWN_PROTOCOLS: false,
+    });
+  }
+
+  let articles = $state([]);
+  let total = $state(0);
+  let loading = $state(true);
+  let selectedArticle = $state(null);
+  let filterSource = $state('');
+  let showUnreadOnly = $state(false);
+  let sources = $state([]);
+  let currentPage = $state(1);
+
+  onMount(async () => {
+    try {
+      const srcData = await api('/news/sources');
+      // 신문사별 유니크
+      const names = new Set();
+      srcData.forEach(s => names.add(s.name.split(' ')[0]));
+      sources = [...names];
+    } catch (e) {}
+    loadArticles();
+  });
+
+  async function loadArticles() {
+    loading = true;
+    try {
+      const params = new URLSearchParams();
+      params.set('page', String(currentPage));
+      params.set('page_size', '30');
+      if (filterSource) params.set('source', filterSource);
+      if (showUnreadOnly) params.set('unread_only', 'true');
+
+      const data = await api(`/news/articles?${params}`);
+      articles = data.items;
+      total = data.total;
+    } catch (err) {
+      addToast('error', '뉴스 로딩 실패');
+    } finally {
+      loading = false;
+    }
+  }
+
+  function selectArticle(article) {
+    selectedArticle = article;
+    if (!article.is_read) markRead(article);
+  }
+
+  async function markRead(article) {
+    try {
+      await api(`/documents/${article.id}`, {
+        method: 'PATCH',
+        body: JSON.stringify({ is_read: true }),
+      });
+      article.is_read = true;
+      articles = [...articles];
+    } catch (e) {}
+  }
+
+  async function markAllRead() {
+    try {
+      const result = await api('/news/mark-all-read', { method: 'POST' });
+      addToast('success', `${result.marked}건 읽음 처리`);
+      articles = articles.map(a => ({ ...a, is_read: true }));
+    } catch (e) {
+      addToast('error', '실패');
+    }
+  }
+
+  function timeAgo(dateStr) {
+    const diff = Date.now() - new Date(dateStr).getTime();
+    const mins = Math.floor(diff / 60000);
+    if (mins < 60) return `${mins}분 전`;
+    const hours = Math.floor(mins / 60);
+    if (hours < 24) return `${hours}시간 전`;
+    const days = Math.floor(hours / 24);
+    return `${days}일 전`;
+  }
+
+  $effect(() => {
+    const _s = filterSource;
+    const _u = showUnreadOnly;
+    currentPage = 1;
+    loadArticles();
+  });
+</script>
+
+<div class="flex h-full">
+  <!-- 좌측 필터 -->
+  <div class="w-48 shrink-0 border-r border-[var(--border)] bg-[var(--sidebar-bg)] p-3 overflow-y-auto">
+    <h2 class="text-xs font-semibold text-[var(--text-dim)] uppercase mb-3">필터</h2>
+
+    <button
+      onclick={() => { filterSource = ''; }}
+      class="w-full text-left px-2 py-1.5 rounded text-sm mb-1 {filterSource === '' ? 'bg-[var(--accent)]/15 text-[var(--accent)]' : 'text-[var(--text-dim)] hover:bg-[var(--surface)]'}"
+    >📰 전체</button>
+
+    {#each sources as src}
+      <button
+        onclick={() => { filterSource = src; }}
+        class="w-full text-left px-2 py-1.5 rounded text-sm mb-0.5 {filterSource === src ? 'bg-[var(--accent)]/15 text-[var(--accent)]' : 'text-[var(--text-dim)] hover:bg-[var(--surface)]'}"
+      >{src}</button>
+    {/each}
+
+    <hr class="my-3 border-[var(--border)]">
+
+    <label class="flex items-center gap-2 px-2 text-xs text-[var(--text-dim)]">
+      <input type="checkbox" bind:checked={showUnreadOnly} class="rounded">
+      읽지 않음만
+    </label>
+  </div>
+
+  <!-- 메인 -->
+  <div class="flex-1 flex flex-col min-h-0">
+    <!-- 상단 바 -->
+    <div class="flex items-center justify-between px-4 py-2 border-b border-[var(--border)] shrink-0">
+      <span class="text-xs text-[var(--text-dim)]">{total}건</span>
+      <button
+        onclick={markAllRead}
+        class="text-xs text-[var(--text-dim)] hover:text-[var(--accent)] px-2 py-1 rounded border border-[var(--border)]"
+      >전체 읽음</button>
+    </div>
+
+    <!-- 상단: 기사 리스트 -->
+    <div class="overflow-y-auto {selectedArticle ? 'h-[40%] shrink-0 border-b border-[var(--border)]' : 'flex-1'}">
+      {#if loading}
+        <div class="p-4 space-y-2">
+          {#each Array(5) as _}
+            <div class="h-12 bg-[var(--surface)] rounded animate-pulse"></div>
+          {/each}
+        </div>
+      {:else if articles.length === 0}
+        <div class="text-center py-16 text-[var(--text-dim)]">
+          <p class="text-sm">뉴스가 없습니다</p>
+        </div>
+      {:else}
+        {#each articles as article}
+          <button
+            onclick={() => selectArticle(article)}
+            class="w-full text-left px-4 py-2.5 border-b border-[var(--border)]/30 hover:bg-[var(--surface)] transition-colors
+              {selectedArticle?.id === article.id ? 'bg-[var(--accent)]/5 border-l-2 border-l-[var(--accent)]' : ''}"
+          >
+            <div class="flex items-start gap-2">
+              <span class="mt-1 text-[10px] {article.is_read ? 'text-[var(--text-dim)]' : 'text-[var(--accent)]'}">
+                {article.is_read ? '○' : '●'}
+              </span>
+              <div class="min-w-0">
+                <p class="text-sm truncate {article.is_read ? 'text-[var(--text-dim)]' : 'font-medium'}">{article.title}</p>
+                <div class="flex items-center gap-2 mt-0.5 text-[10px] text-[var(--text-dim)]">
+                  <span>{article.ai_sub_group || ''}</span>
+                  {#if article.ai_tags?.length}
+                    <span>{article.ai_tags[0]?.split('/').pop()}</span>
+                  {/if}
+                  <span>{timeAgo(article.created_at)}</span>
+                </div>
+              </div>
+            </div>
+          </button>
+        {/each}
+      {/if}
+    </div>
+
+    <!-- 하단: 기사 미리보기 -->
+    {#if selectedArticle}
+      <div class="flex-1 overflow-y-auto p-5 bg-[var(--surface)]">
+        <h2 class="text-lg font-bold mb-2">{selectedArticle.title}</h2>
+        <div class="flex items-center gap-2 mb-4 text-xs text-[var(--text-dim)]">
+          <span>{selectedArticle.ai_sub_group}</span>
+          <span>·</span>
+          <span>{timeAgo(selectedArticle.created_at)}</span>
+        </div>
+        <div class="markdown-body mb-4">
+          {@html renderMd(selectedArticle.extracted_text || '')}
+        </div>
+        {#if selectedArticle.edit_url}
+          <a
+            href={selectedArticle.edit_url}
+            target="_blank"
+            rel="noopener noreferrer"
+            class="inline-flex items-center gap-2 px-4 py-2 bg-[var(--accent)] text-white rounded-lg hover:bg-[var(--accent-hover)] text-sm"
+          >원문 보기 →</a>
+        {/if}
+      </div>
+    {/if}
+  </div>
+</div>
--- a/migrations/013_news_features.sql
+++ b/migrations/013_news_features.sql
@@ -0,0 +1,9 @@
+-- 읽음 상태
+ALTER TABLE documents ADD COLUMN IF NOT EXISTS is_read BOOLEAN DEFAULT false;
+
+-- 뉴스 인덱스
+CREATE INDEX IF NOT EXISTS idx_documents_is_read ON documents(is_read) WHERE source_channel = 'news';
+CREATE INDEX IF NOT EXISTS idx_news_feed ON documents(source_channel, created_at DESC);
+
+-- 기존 뉴스 재분류 (taxonomy에서 분리)
+UPDATE documents SET ai_domain = 'News', ai_sub_group = '' WHERE source_channel = 'news';