feat(library): doc_purpose 필드 + 자료실 업로드 기능

지식/업무 문서 1차 구분을 위한 doc_purpose(business|knowledge) 추가. - 마이그레이션: document_purpose enum + 컬럼 - AI 분류: docPurpose 자동 추론 (빈 값만 채움) - 업로드 API: doc_purpose + library_path Form 파라미터 - 자료실 업로드: business 기본값 + 선택 경로 자동 태깅 - FileInfoView: 용도 select (수동 변경, 실패 롤백) - DocumentCard: 업무/참조 배지 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 15:26:59 +09:00
parent 96ab2369a7
commit 5c58778a41
8 changed files with 142 additions and 3 deletions
@@ -6,7 +6,7 @@ from pathlib import Path
 from typing import Annotated
 from urllib.parse import quote

-from fastapi import APIRouter, Depends, HTTPException, Query, UploadFile, status
+from fastapi import APIRouter, Depends, Form, HTTPException, Query, UploadFile, status
 from fastapi.responses import FileResponse
 from pydantic import BaseModel
 from sqlalchemy import func, select
@@ -53,6 +53,7 @@ class DocumentResponse(BaseModel):
    preview_status: str | None
    source_channel: str | None
    data_origin: str | None
+    doc_purpose: str | None
    extracted_at: datetime | None
    ai_processed_at: datetime | None
    embedded_at: datetime | None
@@ -81,6 +82,7 @@ class DocumentUpdate(BaseModel):
    edit_url: str | None = None
    source_channel: str | None = None
    data_origin: str | None = None
+    doc_purpose: str | None = None
    pinned: bool | None = None


@@ -396,8 +398,29 @@ async def upload_document(
    file: UploadFile,
    user: Annotated[User, Depends(get_current_user)],
    session: Annotated[AsyncSession, Depends(get_session)],
+    doc_purpose: str | None = Form(None, description="business | knowledge"),
+    library_path: str | None = Form(None, description="자료실 경로 (자동 @library/ 태깅)"),
 ):
    """파일 업로드 → Inbox 저장 + DB 등록 + 처리 큐 등록"""
+    from core.library import LIBRARY_PREFIX, normalize_library_path
+
+    # doc_purpose 검증
+    if doc_purpose is not None:
+        doc_purpose = doc_purpose.strip().lower()
+        if doc_purpose == "":
+            doc_purpose = None
+        elif doc_purpose not in ("business", "knowledge"):
+            raise HTTPException(status_code=400, detail="doc_purpose는 business 또는 knowledge만 가능")
+
+    # library_path 검증 + 정규화
+    library_tag = None
+    if library_path:
+        try:
+            normalized = normalize_library_path(library_path)
+            library_tag = f"{LIBRARY_PREFIX}{normalized}"
+        except ValueError as e:
+            raise HTTPException(status_code=400, detail=f"잘못된 자료실 경로: {e}")
+
    if not file.filename:
        raise HTTPException(status_code=400, detail="파일명이 필요합니다")

@@ -439,6 +462,8 @@ async def upload_document(
        file_type="immutable",
        title=target.stem,
        source_channel="manual",
+        doc_purpose=doc_purpose,
+        user_tags=[library_tag] if library_tag else [],
    )
    session.add(doc)
    await session.flush()
@@ -477,6 +502,12 @@ async def update_document(
        except (TypeError, ValueError) as e:
            raise HTTPException(status_code=400, detail=str(e))

+    # doc_purpose 검증
+    if "doc_purpose" in update_data:
+        val = update_data["doc_purpose"]
+        if val is not None and val not in ("business", "knowledge"):
+            raise HTTPException(status_code=400, detail="doc_purpose는 business 또는 knowledge만 가능")
+
    for field, value in update_data.items():
        setattr(doc, field, value)
    doc.updated_at = datetime.now(timezone.utc)
@@ -93,6 +93,10 @@ class Document(Base):
    data_origin: Mapped[str | None] = mapped_column(
        Enum("work", "external", name="data_origin")
    )
+    # 용도 구분 (우선순위: 수동 수정 > 업로드 명시값 > AI 추론)
+    doc_purpose: Mapped[str | None] = mapped_column(
+        Enum("business", "knowledge", name="document_purpose")
+    )
    title: Mapped[str | None] = mapped_column(Text)

    # 타임스탬프
@@ -8,7 +8,8 @@ You are a document classification AI. Analyze the document below and respond ONL
  "tags": ["tag1", "tag2"],
  "importance": "medium",
  "sourceChannel": "inbox_route",
-  "dataOrigin": "work or external"
+  "dataOrigin": "work or external",
+  "docPurpose": "business or knowledge"
 }

 ## Domain Taxonomy (select the most specific leaf node)
@@ -89,5 +90,12 @@ Reference, Standard, Manual, Drawing, Template, Note, Academic_Paper, Law_Docume
 - work: company-related (TK, Technicalkorea, factory, production)
 - external: external reference (news, papers, laws, general info)

+## docPurpose
+- business: 업무 수행에 직접 사용 (양식, 보고서, 체크리스트, 제출물, 계획서)
+- knowledge: 참조·학습·보관 목적 (법령, 논문, 기사, 레퍼런스, 기술 문서, 교육 자료)
+- Template, Checklist, Report, Specification → business 가능성 높음
+- Academic_Paper, Law_Document, Reference, Standard → knowledge 가능성 높음
+- Meeting_Minutes, Memo → 문맥 판단 (실행 기록이면 business, 참조용이면 knowledge)
+
 ## Document to classify
 {document_text}
@@ -107,6 +107,12 @@ async def process(document_id: int, session: AsyncSession) -> None:
        if parsed.get("dataOrigin") and not doc.data_origin:
            doc.data_origin = parsed["dataOrigin"]

+        # 용도 (AI는 빈 값만 채움 — 수동/업로드 명시값 우선)
+        if parsed.get("docPurpose") and not doc.doc_purpose:
+            purpose = parsed["docPurpose"]
+            if purpose in ("business", "knowledge"):
+                doc.doc_purpose = purpose
+
        # ─── 요약 ───
        summary = await client.summarize(doc.extracted_text[:15000])
        doc.ai_summary = strip_thinking(summary)
@@ -142,7 +142,11 @@
    {#if doc.score !== undefined}
      <span class="text-accent font-medium">{(doc.score * 100).toFixed(0)}%</span>
    {/if}
-    {#if doc.data_origin}
+    {#if doc.doc_purpose}
+      <span class="hidden sm:inline px-1.5 py-0.5 rounded {doc.doc_purpose === 'business' ? 'bg-blue-900/30 text-blue-400' : 'bg-emerald-900/30 text-emerald-400'}">
+        {doc.doc_purpose === 'business' ? '업무' : '참조'}
+      </span>
+    {:else if doc.data_origin}
      <span class="hidden sm:inline px-1.5 py-0.5 rounded {doc.data_origin === 'work' ? 'bg-blue-900/30 text-blue-400' : 'bg-gray-800 text-gray-400'}">
        {doc.data_origin}
      </span>
@@ -1,5 +1,8 @@
 <script>
  // Phase E.1 — 파일 메타 정보 read-only 표시.
+  import { api } from '$lib/api';
+  import { addToast } from '$lib/stores/toast';
+
  let { doc } = $props();

  function formatDate(dateStr) {
@@ -17,6 +20,22 @@
    if (bytes < 1048576) return `${(bytes / 1024).toFixed(0)}KB`;
    return `${(bytes / 1048576).toFixed(1)}MB`;
  }
+
+  async function updatePurpose(e) {
+    const val = e.target.value || null;
+    const prev = doc.doc_purpose;
+    doc.doc_purpose = val;
+    try {
+      await api(`/documents/${doc.id}`, {
+        method: 'PATCH',
+        body: JSON.stringify({ doc_purpose: val }),
+      });
+      addToast('success', '용도 변경됨');
+    } catch {
+      doc.doc_purpose = prev;
+      addToast('error', '용도 변경 실패');
+    }
+  }
 </script>

 <div>
@@ -44,6 +63,20 @@
        <dd class="text-text">{doc.data_origin}</dd>
      </div>
    {/if}
+    <div class="flex justify-between items-center">
+      <dt class="text-dim">용도</dt>
+      <dd>
+        <select
+          value={doc.doc_purpose || ''}
+          onchange={updatePurpose}
+          class="bg-bg border border-default rounded px-1 py-0.5 text-xs text-text outline-none focus:border-accent"
+        >
+          <option value="">미분류</option>
+          <option value="business">업무용</option>
+          <option value="knowledge">참조용</option>
+        </select>
+      </dd>
+    </div>
    <div class="flex justify-between">
      <dt class="text-dim">등록일</dt>
      <dd class="text-text">{formatDate(doc.created_at)}</dd>
@@ -12,6 +12,7 @@
    ExternalLink,
    Download,
    FileText,
+    Upload,
  } from 'lucide-svelte';
  import DocumentCard from '$lib/components/DocumentCard.svelte';
  import FormatIcon from '$lib/components/FormatIcon.svelte';
@@ -151,6 +152,41 @@
    window.open(`/api/documents/${doc.id}/preview?token=${getAccessToken()}&download=true`);
  }

+  // ─── 업로드 ───
+
+  let fileInput;
+  let uploadingCount = $state(0);
+
+  async function handleUpload(e) {
+    const files = Array.from(e.target.files || []);
+    if (files.length === 0) return;
+
+    uploadingCount = files.length;
+    let success = 0;
+
+    for (const file of files) {
+      const formData = new FormData();
+      formData.append('file', file);
+      formData.append('doc_purpose', 'business');
+      if (activePath) formData.append('library_path', activePath);
+      try {
+        await api('/documents/', { method: 'POST', body: formData });
+        success++;
+      } catch {
+        addToast('error', `${file.name} 업로드 실패`);
+      }
+    }
+
+    uploadingCount = 0;
+    fileInput.value = '';
+
+    if (success > 0) {
+      addToast('success', `${success}건 업로드 완료`);
+      loadTree();
+      loadDocs();
+    }
+  }
+
  // ─── 검색 debounce ───

  let searchInput = $state(activeQ);
@@ -273,6 +309,18 @@
    <main class="lg:col-span-7 xl:col-span-8">
      <!-- 컨트롤 바 -->
      <div class="flex flex-wrap items-center gap-2 mb-4">
+        <!-- 업로드 -->
+        <input type="file" multiple bind:this={fileInput} onchange={handleUpload} class="hidden" />
+        <Button
+          variant="secondary"
+          size="sm"
+          icon={Upload}
+          onclick={() => fileInput.click()}
+          disabled={uploadingCount > 0}
+        >
+          {uploadingCount > 0 ? `업로드 중 (${uploadingCount})` : '업로드'}
+        </Button>
+
        <!-- 정렬 -->
        <select
          value={activeSort}
@@ -0,0 +1,5 @@
+-- 문서 용도 구분: business(업무용) | knowledge(참조용)
+-- 기존 문서는 NULL → AI 재분류 시 점진 채움
+-- 우선순위: 수동 수정 > 업로드 시 명시값 > AI 추론
+CREATE TYPE document_purpose AS ENUM ('business', 'knowledge');
+ALTER TABLE documents ADD COLUMN doc_purpose document_purpose;