v8:문서유형 분석등록 및 추출_20260206

handlers/tools/font.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+"""
+§3 글꼴(FaceName) 추출
+
+HWPX 실제 태그 (header.xml):
+  <hh:fontface lang="HANGUL" fontCnt="9">
+    <hh:font id="0" face="돋움" type="TTF" isEmbedded="0">
+    <hh:font id="1" face="맑은 고딕" type="TTF" isEmbedded="0">
+  </hh:fontface>
+  <hh:fontface lang="LATIN" fontCnt="9">
+    <hh:font id="0" face="돋움" type="TTF" isEmbedded="0">
+  </hh:fontface>
+
+디폴트값 생성 안 함. 추출 실패 시 None 반환.
+"""
+
+import re
+
+
+def extract(raw_xml: dict, parsed: dict = None) -> dict | None:
+    """§3 fontface에서 언어별 글꼴 정의 추출.
+
+    Returns:
+        {
+            "HANGUL": [{"id": 0, "face": "돋움", "type": "TTF"}, ...],
+            "LATIN":  [{"id": 0, "face": "돋움", "type": "TTF"}, ...],
+            "HANJA":  [...],
+            ...
+        }
+        또는 추출 실패 시 None
+    """
+    header_xml = _get_header_xml(raw_xml, parsed)
+    if not header_xml:
+        return None
+
+    result = {}
+
+    # fontface 블록을 lang별로 추출
+    fontface_blocks = re.findall(
+        r'<hh:fontface\b[^>]*\blang="([^"]+)"[^>]*>(.*?)</hh:fontface>',
+        header_xml, re.DOTALL
+    )
+
+    if not fontface_blocks:
+        return None
+
+    for lang, block_content in fontface_blocks:
+        fonts = []
+        font_matches = re.finditer(
+            r'<hh:font\b[^>]*'
+            r'\bid="(\d+)"[^>]*'
+            r'\bface="([^"]+)"[^>]*'
+            r'\btype="([^"]+)"',
+            block_content
+        )
+        for fm in font_matches:
+            fonts.append({
+                "id": int(fm.group(1)),
+                "face": fm.group(2),
+                "type": fm.group(3),
+            })
+
+        if fonts:
+            result[lang] = fonts
+
+    return result if result else None
+
+
+def _get_header_xml(raw_xml: dict, parsed: dict = None) -> str | None:
+    """header.xml 문자열을 가져온다."""
+    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
+
+    if isinstance(raw_xml, str):
+        return raw_xml
+
+    return None