v8:문서유형 분석등록 및 추출_20260206

handlers/tools/char_style.py

@@ -0,0 +1,133 @@
+# -*- coding: utf-8 -*-
+"""
+§4 글자 모양(CharShape) 추출
+
+HWPX 실제 태그 (header.xml):
+  <hh:charPr id="0" height="1000" textColor="#000000" shadeColor="none"
+             useFontSpace="0" useKerning="0" symMark="NONE" borderFillIDRef="2">
+    <hh:fontRef hangul="7" latin="6" hanja="6" .../>
+    <hh:ratio hangul="100" latin="100" .../>
+    <hh:spacing hangul="0" latin="0" .../>
+    <hh:relSz hangul="100" latin="100" .../>
+    <hh:offset hangul="0" latin="0" .../>
+    <hh:bold/>                              <!-- 존재하면 bold -->
+    <hh:italic/>                            <!-- 존재하면 italic -->
+    <hh:underline type="NONE" shape="SOLID" color="#000000"/>
+    <hh:strikeout shape="NONE" color="#000000"/>
+  </hh:charPr>
+
+디폴트값 생성 안 함.
+"""
+
+import re
+
+from domain.hwpx.hwpx_utils import charsize_to_pt
+
+
+def extract(raw_xml: dict, parsed: dict = None) -> list | None:
+    """§4 charPr 전체 목록 추출.
+
+    Returns:
+        [
+            {
+                "id": 0,
+                "height_pt": 10.0,
+                "textColor": "#000000",
+                "bold": False,
+                "italic": False,
+                "underline": "NONE",
+                "strikeout": "NONE",
+                "fontRef": {"hangul": 7, "latin": 6, ...},
+                "ratio": {"hangul": 100, "latin": 100, ...},
+                "spacing": {"hangul": 0, "latin": 0, ...},
+                "borderFillIDRef": 2,
+            },
+            ...
+        ]
+    """
+    header_xml = _get_header_xml(raw_xml, parsed)
+    if not header_xml:
+        return None
+
+    # charPr 블록 추출 (self-closing이 아닌 블록)
+    blocks = re.findall(
+        r'<hh:charPr\b([^>]*)>(.*?)</hh:charPr>',
+        header_xml, re.DOTALL
+    )
+
+    if not blocks:
+        return None
+
+    result = []
+    for attrs_str, inner in blocks:
+        item = {}
+
+        # 속성 파싱
+        id_m = re.search(r'\bid="(\d+)"', attrs_str)
+        if id_m:
+            item["id"] = int(id_m.group(1))
+
+        height_m = re.search(r'\bheight="(\d+)"', attrs_str)
+        if height_m:
+            item["height_pt"] = charsize_to_pt(int(height_m.group(1)))
+
+        color_m = re.search(r'\btextColor="([^"]+)"', attrs_str)
+        if color_m:
+            item["textColor"] = color_m.group(1)
+
+        shade_m = re.search(r'\bshadeColor="([^"]+)"', attrs_str)
+        if shade_m and shade_m.group(1) != "none":
+            item["shadeColor"] = shade_m.group(1)
+
+        bf_m = re.search(r'\bborderFillIDRef="(\d+)"', attrs_str)
+        if bf_m:
+            item["borderFillIDRef"] = int(bf_m.group(1))
+
+        # bold / italic (태그 존재 여부로 판단)
+        item["bold"] = bool(re.search(r'<hh:bold\s*/?>',  inner))
+        item["italic"] = bool(re.search(r'<hh:italic\s*/?>',  inner))
+
+        # fontRef
+        fr = re.search(r'<hh:fontRef\b([^/]*)/>', inner)
+        if fr:
+            item["fontRef"] = _parse_lang_attrs(fr.group(1))
+
+        # ratio
+        ra = re.search(r'<hh:ratio\b([^/]*)/>', inner)
+        if ra:
+            item["ratio"] = _parse_lang_attrs(ra.group(1))
+
+        # spacing
+        sp = re.search(r'<hh:spacing\b([^/]*)/>', inner)
+        if sp:
+            item["spacing"] = _parse_lang_attrs(sp.group(1))
+
+        # underline
+        ul = re.search(r'<hh:underline\b[^>]*\btype="([^"]+)"', inner)
+        if ul:
+            item["underline"] = ul.group(1)
+
+        # strikeout
+        so = re.search(r'<hh:strikeout\b[^>]*\bshape="([^"]+)"', inner)
+        if so:
+            item["strikeout"] = so.group(1)
+
+        result.append(item)
+
+    return result if result else None
+
+
+def _parse_lang_attrs(attrs_str: str) -> dict:
+    """hangul="7" latin="6" ... → {"hangul": 7, "latin": 6, ...}"""
+    pairs = re.findall(r'(\w+)="(-?\d+)"', attrs_str)
+    return {k: int(v) for k, v in pairs}
+
+
+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