From a1326d582f4c0920f949764a924afb104fdee86e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=EC=9D=B4=EA=B2=BD=EB=AF=BC?= Date: Thu, 5 Mar 2026 14:38:08 +0900 Subject: [PATCH] Hierarchy Fix: Purpose/Domain/File - HWP Cleaning Rules --- .../문서 변환/Domain/General_HWP_특수문자_보정규칙_v01.md | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 02. Prompts/진행과정/문서 변환/Domain/General_HWP_특수문자_보정규칙_v01.md diff --git a/02. Prompts/진행과정/문서 변환/Domain/General_HWP_특수문자_보정규칙_v01.md b/02. Prompts/진행과정/문서 변환/Domain/General_HWP_특수문자_보정규칙_v01.md new file mode 100644 index 0000000..c4e683f --- /dev/null +++ b/02. Prompts/진행과정/문서 변환/Domain/General_HWP_특수문자_보정규칙_v01.md @@ -0,0 +1,10 @@ +--- +source: D:\for python\hwp_test\hwp_logic.py +category: domain +--- + +## HWP 특수문자 및 제어코드 보정 규칙 + +1. **제어코드 제거:** `[\x00-\x08\x0b\x0c\x0e-\x1f]` 패턴 제거. +2. **기호 변환:** `○`, `●`, `□` -> `-` (리스트), `※` -> `> ` (인용구). +3. **인코딩:** CP949 원본은 반드시 UTF-8 변환 후 입력.