v8:문서유형 분석등록 및 추출_20260206

handlers/tools/page_setup.py

@@ -0,0 +1,110 @@
+# -*- coding: utf-8 -*-
+"""
+§7 용지 설정 추출 (pagePr + margin)
+
+HWPX 실제 태그:
+  <hp:pagePr landscape="WIDELY" width="59528" height="84188" gutterType="LEFT_ONLY">
+  <hp:margin header="4251" footer="4251" gutter="0"
+             left="5669" right="5669" top="2834" bottom="2834"/>
+
+디폴트값 생성 안 함. 추출 실패 시 None 반환.
+"""
+
+import re
+
+from domain.hwpx.hwpx_utils import hwpunit_to_mm, mm_format, detect_paper_size
+
+
+def extract(raw_xml: dict, parsed: dict = None) -> dict | None:
+    """§7 pagePr + margin에서 용지/여백 정보 추출.
+
+    Returns:
+        {
+            "paper": {"name": "A4", "width_mm": 210.0, "height_mm": 297.0,
+                       "landscape": True/False},
+            "margins": {"top": "10.0mm", "bottom": "10.0mm",
+                        "left": "20.0mm", "right": "20.0mm",
+                        "header": "15.0mm", "footer": "15.0mm",
+                        "gutter": "0.0mm"}
+        }
+        또는 추출 실패 시 None
+    """
+    section_xml = _get_section_xml(raw_xml, parsed)
+    if not section_xml:
+        return None
+
+    result = {}
+
+    # ── 용지 크기 ─────────────────────────────────
+    page_match = re.search(
+        r'<hp:pagePr\b[^>]*'
+        r'\bwidth="(\d+)"[^>]*'
+        r'\bheight="(\d+)"',
+        section_xml
+    )
+    if not page_match:
+        # 속성 순서가 다를 수 있음
+        page_match = re.search(
+            r'<hp:pagePr\b[^>]*'
+            r'\bheight="(\d+)"[^>]*'
+            r'\bwidth="(\d+)"',
+            section_xml
+        )
+        if page_match:
+            h_hu, w_hu = int(page_match.group(1)), int(page_match.group(2))
+        else:
+            return None
+    else:
+        w_hu, h_hu = int(page_match.group(1)), int(page_match.group(2))
+
+    landscape_match = re.search(
+        r'<hp:pagePr\b[^>]*\blandscape="([^"]+)"', section_xml
+    )
+    is_landscape = False
+    if landscape_match:
+        is_landscape = landscape_match.group(1) == "WIDELY"
+
+    paper_name = detect_paper_size(w_hu, h_hu)
+
+    result["paper"] = {
+        "name": paper_name,
+        "width_mm": round(hwpunit_to_mm(w_hu), 1),
+        "height_mm": round(hwpunit_to_mm(h_hu), 1),
+        "landscape": is_landscape,
+    }
+
+    # ── 여백 ──────────────────────────────────────
+    margin_match = re.search(r'<hp:margin\b([^/]*)/>', section_xml)
+    if not margin_match:
+        return result  # 용지 크기는 있으나 여백은 없을 수 있음
+
+    attrs_str = margin_match.group(1)
+    margins = {}
+    for key in ["top", "bottom", "left", "right", "header", "footer", "gutter"]:
+        m = re.search(rf'\b{key}="(\d+)"', attrs_str)
+        if m:
+            margins[key] = mm_format(int(m.group(1)))
+
+    if margins:
+        result["margins"] = margins
+
+    return result
+
+
+def _get_section_xml(raw_xml: dict, parsed: dict = None) -> str | None:
+    """section XML 문자열을 가져온다."""
+    # parsed에서 직접 제공
+    if parsed and parsed.get("section_xml"):
+        return parsed["section_xml"]
+
+    # raw_xml dict에서 section 파일 찾기
+    if isinstance(raw_xml, dict):
+        for name, content in raw_xml.items():
+            if "section" in name.lower() and isinstance(content, str):
+                return content
+
+    # raw_xml이 문자열이면 그대로
+    if isinstance(raw_xml, str):
+        return raw_xml
+
+    return None