v8:문서유형 분석등록 및 추출_20260206

2026-02-20 11:46:52 +09:00
parent db6532b33c
commit c3e9e29205
57 changed files with 22138 additions and 1421 deletions
--- a/handlers/tools/border_fill.py
+++ b/handlers/tools/border_fill.py
@@ -0,0 +1,127 @@
+# -*- coding: utf-8 -*-
+"""
+§2 테두리/배경(BorderFill) 추출
+
+HWPX 실제 태그 (header.xml):
+  <hh:borderFill id="3" threeD="0" shadow="0" centerLine="NONE" ...>
+    <hh:leftBorder type="SOLID" width="0.12 mm" color="#000000"/>
+    <hh:rightBorder type="SOLID" width="0.12 mm" color="#000000"/>
+    <hh:topBorder type="SOLID" width="0.12 mm" color="#000000"/>
+    <hh:bottomBorder type="SOLID" width="0.12 mm" color="#000000"/>
+    <hh:diagonal type="SOLID" width="0.1 mm" color="#000000"/>
+    <hc:fillBrush>
+      <hc:winBrush faceColor="#EDEDED" hatchColor="#FFE7E7E7" alpha="0"/>
+    </hc:fillBrush>
+  </hh:borderFill>
+
+디폴트값 생성 안 함.
+"""
+
+import re
+
+from domain.hwpx.hwpx_utils import BORDER_TYPE_TO_CSS, hwpx_border_to_css
+
+
+def extract(raw_xml: dict, parsed: dict = None) -> dict | None:
+    """§2 borderFill 전체 추출 → id별 dict.
+
+    Returns:
+        {
+            3: {
+                "id": 3,
+                "left":   {"type": "SOLID", "width": "0.12 mm", "color": "#000000"},
+                "right":  {"type": "SOLID", "width": "0.12 mm", "color": "#000000"},
+                "top":    {"type": "SOLID", "width": "0.12 mm", "color": "#000000"},
+                "bottom": {"type": "SOLID", "width": "0.12 mm", "color": "#000000"},
+                "diagonal": {"type": "SOLID", "width": "0.1 mm", "color": "#000000"},
+                "background": "#EDEDED",      # fillBrush faceColor
+                "css": {                       # 편의: 미리 변환된 CSS
+                    "border-left": "0.12mm solid #000000",
+                    ...
+                    "background-color": "#EDEDED",
+                }
+            },
+            ...
+        }
+        또는 추출 실패 시 None
+    """
+    header_xml = _get_header_xml(raw_xml, parsed)
+    if not header_xml:
+        return None
+
+    blocks = re.findall(
+        r'<hh:borderFill\b([^>]*)>(.*?)</hh:borderFill>',
+        header_xml, re.DOTALL
+    )
+
+    if not blocks:
+        return None
+
+    result = {}
+    for attrs_str, inner in blocks:
+        id_m = re.search(r'\bid="(\d+)"', attrs_str)
+        if not id_m:
+            continue
+        bf_id = int(id_m.group(1))
+
+        item = {"id": bf_id}
+
+        # 4방향 + diagonal
+        for side, tag in [
+            ("left",     "leftBorder"),
+            ("right",    "rightBorder"),
+            ("top",      "topBorder"),
+            ("bottom",   "bottomBorder"),
+            ("diagonal", "diagonal"),
+        ]:
+            # 태그 전체를 먼저 찾고, 속성을 개별 추출 (순서 무관)
+            tag_m = re.search(rf'<hh:{tag}\b([^/]*?)/?>', inner)
+            if tag_m:
+                tag_attrs = tag_m.group(1)
+                t = re.search(r'\btype="([^"]+)"', tag_attrs)
+                w = re.search(r'\bwidth="([^"]+)"', tag_attrs)
+                c = re.search(r'\bcolor="([^"]+)"', tag_attrs)
+                item[side] = {
+                    "type": t.group(1) if t else "NONE",
+                    "width": w.group(1).replace(" ", "") if w else "0.12mm",
+                    "color": c.group(1) if c else "#000000",
+                }
+
+        # 배경 (fillBrush > winBrush faceColor)
+        bg_m = re.search(
+            r'<hc:winBrush\b[^>]*\bfaceColor="([^"]+)"', inner
+        )
+        if bg_m:
+            face = bg_m.group(1)
+            if face and face.lower() != "none":
+                item["background"] = face
+
+        # CSS 편의 변환
+        css = {}
+        for side in ["left", "right", "top", "bottom"]:
+            border_data = item.get(side)
+            if border_data:
+                css[f"border-{side}"] = hwpx_border_to_css(border_data)
+            else:
+                css[f"border-{side}"] = "none"
+            # border_data가 없으면 CSS에도 넣지 않음
+
+        if "background" in item:
+            css["background-color"] = item["background"]
+
+        if css:
+            item["css"] = css
+
+        result[bf_id] = item
+
+    return result if result else None
+
+
+def _get_header_xml(raw_xml: dict, parsed: dict = None) -> str | None:
+    if parsed and parsed.get("header_xml"):
+        return parsed["header_xml"]
+    if isinstance(raw_xml, dict):
+        for name, content in raw_xml.items():
+            if "header" in name.lower() and isinstance(content, str):
+                return content
+    return raw_xml if isinstance(raw_xml, str) else None