Simplify hwpx: plain UTF-8 text with .hwpx extension

app.py

@@ -306,99 +306,21 @@ def generate(req: GenerateRequest):
 
 @app.post("/download/hwpx")
 def download_hwpx(req: HwpxRequest):
-    """텍스트를 HWPX(한글과컴퓨터) 파일로 변환해 다운로드."""
-    import io
+    """텍스트를 .hwpx 파일로 다운로드 (UTF-8 텍스트, 확장자 .hwpx)."""
     import re
-    import zipfile
     from urllib.parse import quote
-    from xml.sax.saxutils import escape as xe
     from fastapi.responses import Response
 
-    lines = req.text.split("\n")
-
-    CONTAINER = (
-        '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n'
-        '<container xmlns="urn:oasis:names:tc:opendocument:xmlns:container">\n'
-        '  <rootfiles>\n'
-        '    <rootfile full-path="Contents/content.hpf" media-type="application/hwp+zip"/>\n'
-        '  </rootfiles>\n'
-        '</container>'
-    )
-    HPF = (
-        '<?xml version="1.0" encoding="UTF-8"?>\n'
-        '<opf:package xmlns:opf="http://www.idpf.org/2007/opf" version="2.0">\n'
-        '  <opf:metadata>'
-        '<dc:title xmlns:dc="http://purl.org/dc/elements/1.1/"/>'
-        '<dc:language xmlns:dc="http://purl.org/dc/elements/1.1/">ko</dc:language>'
-        '</opf:metadata>\n'
-        '  <opf:manifest>\n'
-        '    <opf:item id="header" href="header.xml" media-type="application/xml"/>\n'
-        '    <opf:item id="section0" href="section0.xml" media-type="application/xml"/>\n'
-        '  </opf:manifest>\n'
-        '  <opf:spine><opf:itemref idref="section0"/></opf:spine>\n'
-        '</opf:package>'
-    )
-    HEADER = (
-        '<?xml version="1.0" encoding="UTF-8"?>\n'
-        '<hh:Head xmlns:hh="http://www.hancom.co.kr/hwpml/2011/head"\n'
-        '         xmlns:hf="http://www.hancom.co.kr/hwpml/2011/charshape"\n'
-        '         xmlns:hp="http://www.hancom.co.kr/hwpml/2011/paragraph">\n'
-        '  <hh:RefList>\n'
-        '    <hh:CharShapes>\n'
-        '      <hf:CharShape Id="0" Height="1000" TextColor="0" BoldWeight="400"\n'
-        '                    FaceNameHangul="맑은 고딕" FaceNameLatin="맑은 고딕"\n'
-        '                    FaceNameHanja="맑은 고딕" Ratio="100" Spacing="0"/>\n'
-        '    </hh:CharShapes>\n'
-        '    <hh:ParaShapes>\n'
-        '      <hp:ParaShape Id="0" AlignType="Justify"\n'
-        '                    LineSpacing="160" LineSpacingType="PercentsOfLine"\n'
-        '                    SpaceBefore="0" SpaceAfter="85"/>\n'
-        '    </hh:ParaShapes>\n'
-        '    <hh:Styles>\n'
-        '      <hh:Style Id="0" EngName="Normal" HangulName="바탕글"\n'
-        '                CharPrIDRef="0" ParaPrIDRef="0"/>\n'
-        '    </hh:Styles>\n'
-        '  </hh:RefList>\n'
-        '</hh:Head>'
-    )
-
-    def _para(pid, line):
-        txt = xe(line)
-        run = (f'<hp:Run><hp:RPr CharPrIDRef="0"/><hp:T>{txt}</hp:T></hp:Run>'
-               if txt else "")
-        return (f'  <hp:P Id="{pid}">'
-                f'<hp:PPr ParaPrIDRef="0"/>'
-                f'{run}'
-                f'</hp:P>')
-
-    body = "\n".join(_para(i, l) for i, l in enumerate(lines))
-    SECTION = (
-        '<?xml version="1.0" encoding="UTF-8"?>\n'
-        '<hh:SEC xmlns:hh="http://www.hancom.co.kr/hwpml/2011/section"\n'
-        '        xmlns:hp="http://www.hancom.co.kr/hwpml/2011/paragraph">\n'
-        f'{body}\n'
-        '</hh:SEC>'
-    )
-
-    buf = io.BytesIO()
-    with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as zf:
-        mi = zipfile.ZipInfo("mimetype")
-        mi.compress_type = zipfile.ZIP_STORED
-        zf.writestr(mi, "application/hwp+zip")
-        zf.writestr("META-INF/container.xml", CONTAINER.encode("utf-8"))
-        zf.writestr("Contents/content.hpf", HPF.encode("utf-8"))
-        zf.writestr("Contents/header.xml", HEADER.encode("utf-8"))
-        zf.writestr("Contents/section0.xml", SECTION.encode("utf-8"))
-
-    # 파일명: 출력에서 제목 추출, 없으면 "문서"
     m = re.search(r"^제\s*목\s+(.+)$", req.text, re.MULTILINE)
     title = m.group(1).strip() if m else "문서"
     safe = re.sub(r'[\\/:*?"<>|]', "_", title)[:50]
     encoded = quote(safe, safe="")
 
+    content = req.text.encode("utf-8-sig")  # UTF-8 with BOM
+
     return Response(
-        content=buf.getvalue(),
-        media_type="application/hwp+zip",
+        content=content,
+        media_type="application/octet-stream",
         headers={
             "Content-Disposition": f"attachment; filename*=UTF-8''{encoded}.hwpx",
         },