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/image.py
+++ b/handlers/tools/image.py
@@ -0,0 +1,98 @@
+# -*- coding: utf-8 -*-
+"""
+이미지/그리기 객체(ShapeObject) 추출
+
+HWPX 실제 태그 (section0.xml):
+  <hp:pic id="..." zOrder="..." ...>
+    <hp:offset x="0" y="0"/>
+    <hp:orgSz width="..." height="..."/>
+    <hp:curSz width="..." height="..."/>
+    <hp:imgRect>
+      <hp:pt x="..." y="..."/>  <!-- 4개 꼭짓점 -->
+    </hp:imgRect>
+    <hp:imgClip .../>
+    <hp:img binaryItemIDRef="image1.JPG" .../>
+  </hp:pic>
+
+  또는 그리기 객체:
+  <hp:container id="..." ...>
+    <hp:offset x="..." y="..."/>
+    ...
+  </hp:container>
+
+디폴트값 생성 안 함.
+"""
+
+import re
+
+from domain.hwpx.hwpx_utils import hwpunit_to_mm
+
+
+def extract(raw_xml: dict, parsed: dict = None) -> list | None:
+    """이미지/그리기 객체 추출.
+
+    Returns:
+        [
+            {
+                "type": "image",
+                "binaryItemRef": "image1.JPG",
+                "width_hu": 28346, "height_hu": 14173,
+                "width_mm": 100.0, "height_mm": 50.0,
+                "offset": {"x": 0, "y": 0},
+            },
+            ...
+        ]
+    """
+    section_xml = _get_section_xml(raw_xml, parsed)
+    if not section_xml:
+        return None
+
+    result = []
+
+    # <hp:pic> 블록
+    pic_blocks = re.finditer(
+        r'<hp:pic\b([^>]*)>(.*?)</hp:pic>',
+        section_xml, re.DOTALL
+    )
+    for pm in pic_blocks:
+        pic_inner = pm.group(2)
+        item = {"type": "image"}
+
+        # binaryItemRef
+        img = re.search(r'<hp:img\b[^>]*\bbinaryItemIDRef="([^"]+)"', pic_inner)
+        if img:
+            item["binaryItemRef"] = img.group(1)
+
+        # curSz (현재 크기)
+        csz = re.search(
+            r'<hp:curSz\b[^>]*\bwidth="(\d+)"[^>]*\bheight="(\d+)"',
+            pic_inner
+        )
+        if csz:
+            w, h = int(csz.group(1)), int(csz.group(2))
+            item["width_hu"] = w
+            item["height_hu"] = h
+            item["width_mm"] = round(hwpunit_to_mm(w), 1)
+            item["height_mm"] = round(hwpunit_to_mm(h), 1)
+
+        # offset
+        off = re.search(
+            r'<hp:offset\b[^>]*\bx="(-?\d+)"[^>]*\by="(-?\d+)"',
+            pic_inner
+        )
+        if off:
+            item["offset"] = {"x": int(off.group(1)), "y": int(off.group(2))}
+
+        result.append(item)
+
+    return result if result else None
+
+
+def _get_section_xml(raw_xml: dict, parsed: dict = None) -> str | None:
+    if parsed and parsed.get("section_xml"):
+        return parsed["section_xml"]
+    if isinstance(raw_xml, dict):
+        for name, content in raw_xml.items():
+            if "section" in name.lower() and isinstance(content, str):
+                return content
+    return raw_xml if isinstance(raw_xml, str) else None