helper-hwp 0.5.0__tar.gz

helper_hwp-0.5.0/LICENSE

@@ -0,0 +1,214 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as original works of authorship. For the purposes of this
+   License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work
+
+Copyright 2025 helper_hwp contributors
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+---
+
+This project is based on and distributed under the Apache License 2.0.
+You are free to use, modify, and distribute this software.
+
+When using or distributing this software, please include attribution:
+Source: https://github.com/c0z0c/helper_hwp
+
+---
+
+본 프로젝트는 Apache License 2.0 하에 배포됩니다.
+
+- 누구나 자유롭게 사용할 수 있습니다
+- 누구나 자유롭게 수정할 수 있습니다
+- 상업적 이용이 가능합니다
+- 재배포가 가능합니다
+
+사용 시 출처를 표기해 주세요:
+출처: https://github.com/c0z0c/helper_hwp
+
+라이센스 전문은 위의 영문 내용을 참조하시기 바랍니다.

helper_hwp-0.5.0/PKG-INFO

@@ -0,0 +1,134 @@
+Metadata-Version: 2.4
+Name: helper-hwp
+Version: 0.5.0
+Summary: Python HWP 파일 파서 및 텍스트 추출 라이브러리
+Author-email: c0z0c <c0z0c.dev@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/c0z0c/helper_hwp
+Project-URL: Repository, https://github.com/c0z0c/helper_hwp
+Project-URL: Issues, https://github.com/c0z0c/helper_hwp/issues
+Keywords: hwp,hancom,hangul,parser,text-extraction
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: olefile>=0.46
+Requires-Dist: pycryptodome>=3.15.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Dynamic: license-file
+
+# helper_hwp
+
+Python으로 작성된 HWP (한글 문서) 파일 파서 및 텍스트 추출 라이브러리입니다.
+
+## 특징
+
+- HWP 5.x 포맷 지원 (CFB 기반)
+- 텍스트 추출 및 마크다운 변환
+- 표, 페이지 단위 파싱 지원
+- 단위 변환 유틸리티 제공 (HWPUNIT ↔ cm/inch/px)
+
+## 설치
+
+```bash
+pip install helper-hwp
+```
+
+또는 소스에서 설치:
+
+```bash
+git clone https://github.com/c0z0c/helper_hwp.git
+cd helper_hwp
+pip install -e .
+```
+
+## 빠른 시작
+
+### 텍스트 추출
+
+```python
+from helper_hwp import hwp_to_txt
+
+# HWP 파일에서 텍스트 추출
+text = hwp_to_txt('example.hwp')
+print(text)
+```
+
+### 마크다운 변환
+
+```python
+from helper_hwp import hwp_to_markdown
+
+# HWP 파일을 마크다운으로 변환
+markdown = hwp_to_markdown('example.hwp')
+print(markdown)
+```
+
+### 문서 객체 사용
+
+```python
+from helper_hwp import open_hwp
+
+# HWP 문서 열기
+doc = open_hwp('example.hwp')
+
+# 문단 단위 순회
+for paragraph in doc.iter_paragraphs():
+    print(paragraph.text)
+
+# 표 단위 순회
+for table in doc.iter_tables():
+    print(table.rows)
+```
+
+## 사용 예제
+
+더 많은 예제는 [examples](examples/) 디렉토리를 참조하세요:
+
+- [텍스트 추출 예제](examples/example_hwp_to_txt.py)
+- [마크다운 변환 예제](examples/example_hwp_to_markdown.py)
+- [태그 순회 예제](examples/example_iter_tags.py)
+
+## 문서
+
+- [사용자 가이드](docs/USER_GUIDE.md) - 기본 사용법 및 예제
+- [개발자 문서](docs/DEVELOPER.md) - 프로젝트 구조 및 개발 가이드
+
+## 요구사항
+
+- Python 3.8 이상
+- olefile >= 0.46
+- pycryptodome >= 3.15.0
+
+## 라이센스
+
+이 프로젝트는 Apache License 2.0 라이센스 하에 배포됩니다.
+
+누구나 자유롭게 사용하고 수정할 수 있으며, 사용 시 출처를 표기해 주세요.
+
+출처: https://github.com/c0z0c/helper_hwp
+
+자세한 내용은 [LICENSE](LICENSE) 파일을 참조하세요.
+
+## 기여
+
+프로젝트에 대한 기여를 환영합니다! 기여 방법은 [개발자 문서](docs/DEVELOPER.md)를 참조하세요.
+
+## 변경 이력
+
+변경 이력은 [CHANGELOG.md](CHANGELOG.md)를 참조하세요.

helper_hwp-0.5.0/README.md

@@ -0,0 +1,100 @@
+# helper_hwp
+
+Python으로 작성된 HWP (한글 문서) 파일 파서 및 텍스트 추출 라이브러리입니다.
+
+## 특징
+
+- HWP 5.x 포맷 지원 (CFB 기반)
+- 텍스트 추출 및 마크다운 변환
+- 표, 페이지 단위 파싱 지원
+- 단위 변환 유틸리티 제공 (HWPUNIT ↔ cm/inch/px)
+
+## 설치
+
+```bash
+pip install helper-hwp
+```
+
+또는 소스에서 설치:
+
+```bash
+git clone https://github.com/c0z0c/helper_hwp.git
+cd helper_hwp
+pip install -e .
+```
+
+## 빠른 시작
+
+### 텍스트 추출
+
+```python
+from helper_hwp import hwp_to_txt
+
+# HWP 파일에서 텍스트 추출
+text = hwp_to_txt('example.hwp')
+print(text)
+```
+
+### 마크다운 변환
+
+```python
+from helper_hwp import hwp_to_markdown
+
+# HWP 파일을 마크다운으로 변환
+markdown = hwp_to_markdown('example.hwp')
+print(markdown)
+```
+
+### 문서 객체 사용
+
+```python
+from helper_hwp import open_hwp
+
+# HWP 문서 열기
+doc = open_hwp('example.hwp')
+
+# 문단 단위 순회
+for paragraph in doc.iter_paragraphs():
+    print(paragraph.text)
+
+# 표 단위 순회
+for table in doc.iter_tables():
+    print(table.rows)
+```
+
+## 사용 예제
+
+더 많은 예제는 [examples](examples/) 디렉토리를 참조하세요:
+
+- [텍스트 추출 예제](examples/example_hwp_to_txt.py)
+- [마크다운 변환 예제](examples/example_hwp_to_markdown.py)
+- [태그 순회 예제](examples/example_iter_tags.py)
+
+## 문서
+
+- [사용자 가이드](docs/USER_GUIDE.md) - 기본 사용법 및 예제
+- [개발자 문서](docs/DEVELOPER.md) - 프로젝트 구조 및 개발 가이드
+
+## 요구사항
+
+- Python 3.8 이상
+- olefile >= 0.46
+- pycryptodome >= 3.15.0
+
+## 라이센스
+
+이 프로젝트는 Apache License 2.0 라이센스 하에 배포됩니다.
+
+누구나 자유롭게 사용하고 수정할 수 있으며, 사용 시 출처를 표기해 주세요.
+
+출처: https://github.com/c0z0c/helper_hwp
+
+자세한 내용은 [LICENSE](LICENSE) 파일을 참조하세요.
+
+## 기여
+
+프로젝트에 대한 기여를 환영합니다! 기여 방법은 [개발자 문서](docs/DEVELOPER.md)를 참조하세요.
+
+## 변경 이력
+
+변경 이력은 [CHANGELOG.md](CHANGELOG.md)를 참조하세요.

helper_hwp-0.5.0/helper_hwp.egg-info/PKG-INFO

@@ -0,0 +1,134 @@
+Metadata-Version: 2.4
+Name: helper-hwp
+Version: 0.5.0
+Summary: Python HWP 파일 파서 및 텍스트 추출 라이브러리
+Author-email: c0z0c <c0z0c.dev@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/c0z0c/helper_hwp
+Project-URL: Repository, https://github.com/c0z0c/helper_hwp
+Project-URL: Issues, https://github.com/c0z0c/helper_hwp/issues
+Keywords: hwp,hancom,hangul,parser,text-extraction
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: olefile>=0.46
+Requires-Dist: pycryptodome>=3.15.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Dynamic: license-file
+
+# helper_hwp
+
+Python으로 작성된 HWP (한글 문서) 파일 파서 및 텍스트 추출 라이브러리입니다.
+
+## 특징
+
+- HWP 5.x 포맷 지원 (CFB 기반)
+- 텍스트 추출 및 마크다운 변환
+- 표, 페이지 단위 파싱 지원
+- 단위 변환 유틸리티 제공 (HWPUNIT ↔ cm/inch/px)
+
+## 설치
+
+```bash
+pip install helper-hwp
+```
+
+또는 소스에서 설치:
+
+```bash
+git clone https://github.com/c0z0c/helper_hwp.git
+cd helper_hwp
+pip install -e .
+```
+
+## 빠른 시작
+
+### 텍스트 추출
+
+```python
+from helper_hwp import hwp_to_txt
+
+# HWP 파일에서 텍스트 추출
+text = hwp_to_txt('example.hwp')
+print(text)
+```
+
+### 마크다운 변환
+
+```python
+from helper_hwp import hwp_to_markdown
+
+# HWP 파일을 마크다운으로 변환
+markdown = hwp_to_markdown('example.hwp')
+print(markdown)
+```
+
+### 문서 객체 사용
+
+```python
+from helper_hwp import open_hwp
+
+# HWP 문서 열기
+doc = open_hwp('example.hwp')
+
+# 문단 단위 순회
+for paragraph in doc.iter_paragraphs():
+    print(paragraph.text)
+
+# 표 단위 순회
+for table in doc.iter_tables():
+    print(table.rows)
+```
+
+## 사용 예제
+
+더 많은 예제는 [examples](examples/) 디렉토리를 참조하세요:
+
+- [텍스트 추출 예제](examples/example_hwp_to_txt.py)
+- [마크다운 변환 예제](examples/example_hwp_to_markdown.py)
+- [태그 순회 예제](examples/example_iter_tags.py)
+
+## 문서
+
+- [사용자 가이드](docs/USER_GUIDE.md) - 기본 사용법 및 예제
+- [개발자 문서](docs/DEVELOPER.md) - 프로젝트 구조 및 개발 가이드
+
+## 요구사항
+
+- Python 3.8 이상
+- olefile >= 0.46
+- pycryptodome >= 3.15.0
+
+## 라이센스
+
+이 프로젝트는 Apache License 2.0 라이센스 하에 배포됩니다.
+
+누구나 자유롭게 사용하고 수정할 수 있으며, 사용 시 출처를 표기해 주세요.
+
+출처: https://github.com/c0z0c/helper_hwp
+
+자세한 내용은 [LICENSE](LICENSE) 파일을 참조하세요.
+
+## 기여
+
+프로젝트에 대한 기여를 환영합니다! 기여 방법은 [개발자 문서](docs/DEVELOPER.md)를 참조하세요.
+
+## 변경 이력
+
+변경 이력은 [CHANGELOG.md](CHANGELOG.md)를 참조하세요.

helper_hwp-0.5.0/helper_hwp.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+LICENSE
+README.md
+pyproject.toml
+helper_hwp.egg-info/PKG-INFO
+helper_hwp.egg-info/SOURCES.txt
+helper_hwp.egg-info/dependency_links.txt
+helper_hwp.egg-info/requires.txt
+helper_hwp.egg-info/top_level.txt
+tests/test_hwp_iter_tags.py
+tests/test_hwp_to_markdown.py
+tests/test_hwp_to_markdown_pdf.py
+tests/test_hwp_to_txt.py

helper_hwp-0.5.0/helper_hwp.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

helper_hwp-0.5.0/helper_hwp.egg-info/requires.txt

@@ -0,0 +1,9 @@
+olefile>=0.46
+pycryptodome>=3.15.0
+
+[dev]
+pytest>=7.0.0
+pytest-cov>=4.0.0
+black>=23.0.0
+ruff>=0.1.0
+mypy>=1.0.0

helper_hwp-0.5.0/helper_hwp.egg-info/top_level.txt

@@ -0,0 +1 @@
+helper_hwp

helper_hwp-0.5.0/pyproject.toml

@@ -0,0 +1,71 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "helper-hwp"
+version = "0.5.0"
+description = "Python HWP 파일 파서 및 텍스트 추출 라이브러리"
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "Apache-2.0"}
+authors = [
+    {name = "c0z0c", email = "c0z0c.dev@gmail.com"}
+]
+keywords = ["hwp", "hancom", "hangul", "parser", "text-extraction"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing",
+]
+
+dependencies = [
+    "olefile>=0.46",           # CFB (Compound File Binary) 파싱
+    "pycryptodome>=3.15.0",    # AES 암호화 해제
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "black>=23.0.0",
+    "ruff>=0.1.0",
+    "mypy>=1.0.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/c0z0c/helper_hwp"
+Repository = "https://github.com/c0z0c/helper_hwp"
+Issues = "https://github.com/c0z0c/helper_hwp/issues"
+
+[tool.setuptools]
+py-modules = ["helper_hwp"]
+
+[tool.black]
+line-length = 100
+target-version = ['py38']
+
+[tool.ruff]
+line-length = 100
+target-version = "py38"
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = "--cov=helper_hwp --cov-report=html --cov-report=term-missing"

helper_hwp-0.5.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

helper_hwp-0.5.0/tests/test_hwp_iter_tags.py

@@ -0,0 +1,350 @@
+"""
+test.hwp를 open_hwp()로 문단 단위로 텍스트 추출하는 데모
+
+사용법:
+    python test_helper_hwp.py
+"""
+
+import sys
+import os
+import struct
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+# UTF-8 출력 설정 (Windows 콘솔 대응)
+if sys.platform == 'win32':
+    import io
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
+    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8', errors='replace')
+
+from helper_hwp import open_hwp, ElementType, IterMode
+
+
+def estimate_table_size(table) -> tuple:
+    """일반 텍스트 테이블 크기 추정"""
+    if table.rows and table.cols:
+        # 기본 셀 크기 가정
+        default_cell_width = 3.0  # cm
+        default_cell_height = 0.8  # cm
+        
+        estimated_width = table.cols * default_cell_width
+        estimated_height = table.rows * default_cell_height
+        
+        return (estimated_width, estimated_height)
+    return (None, None)
+
+
+def main():
+    # test.hwp 파일 경로
+    test_file = "test.hwp"
+
+    # 파일 존재 확인
+    if not os.path.exists(test_file):
+        print(f"오류: {test_file} 파일을 찾을 수 없습니다.")
+        print(f"현재 디렉토리: {os.getcwd()}")
+        print(f"\n사용 가능한 HWP 파일:")
+        for file in os.listdir('.'):
+            if file.endswith('.hwp'):
+                print(f"  - {file}")
+        return
+
+    print("=" * 80)
+    print("open_hwp() 데모 - test.hwp 태그 기반 순회")
+    print("=" * 80)
+
+    output_file = "test_helper_hwp.txt"
+    with open(output_file, 'w', encoding='utf-8') as f:
+
+        # Context Manager로 파일 로드
+        f.write(f"\n[1] 파일 로딩: {test_file}")
+        with open_hwp(test_file) as hwp:
+            # 파일 정보 출력
+            f.write(f"\n[2] 파일 정보")
+            f.write(f"  - 버전: {hwp.version}")
+            f.write(f"  - 압축: {hwp.compressed}")
+            f.write(f"  - 암호화: {hwp.encrypted}")
+            f.write(f"  - 섹션 수: {len(hwp.sections)}")
+            f.write(f"  - 순회 모드: {hwp.iter_mode.value}")
+            f.write(f"  - 글자 모양 수: {len(hwp._hwp.char_shapes)}개")
+
+            # iter_tags()로 문서 요소 순회
+            f.write(f"\n[3] 태그 기반 순회 - iter_tags()")
+            element_counts = {}
+            paragraphs = []
+            tables = []
+            page_breaks = []
+            footers = []
+            headers = []
+            page_defs = []
+
+            for element_type, element in hwp.iter_tags():
+                element_counts[element_type] = element_counts.get(element_type, 0) + 1
+                
+                if element_type == ElementType.PARAGRAPH:
+                    paragraphs.append(element)
+                elif element_type == ElementType.TABLE:
+                    tables.append(element)
+                elif element_type == ElementType.PAGE_BREAK:
+                    page_breaks.append(element)
+                elif element_type == ElementType.FOOTER:
+                    footers.append(element)
+                elif element_type == ElementType.HEADER:
+                    headers.append(element)
+                elif element_type == ElementType.PAGE_DEF:
+                    page_defs.append(element)
+
+            f.write(f"  > 요소 통계:")
+            for elem_type, count in element_counts.items():
+                f.write(f"    - {elem_type.value}: {count}개")
+
+            # 문단 통계
+            f.write(f"\n[4] 문단 통계")
+            total_chars = sum(len(p.text) for p in paragraphs)
+            avg_chars = total_chars / len(paragraphs) if paragraphs else 0
+            max_chars = max(len(p.text) for p in paragraphs) if paragraphs else 0
+            min_chars = min(len(p.text) for p in paragraphs) if paragraphs else 0
+            
+            # 서식 정보 통계
+            font_sizes = [p.char_shape.font_size for p in paragraphs if p.char_shape]
+            bold_count = sum(1 for p in paragraphs if p.char_shape and p.char_shape.bold)
+            italic_count = sum(1 for p in paragraphs if p.char_shape and p.char_shape.italic)
+
+            f.write(f"  - 총 문자 수: {total_chars:,}자")
+            f.write(f"  - 평균 문단 길이: {avg_chars:.1f}자")
+            f.write(f"  - 최대 문단 길이: {max_chars}자")
+            f.write(f"  - 최소 문단 길이: {min_chars}자")
+            if font_sizes:
+                f.write(f"  - 평균 글꼴 크기: {sum(font_sizes)/len(font_sizes):.1f}pt")
+                f.write(f"  - 굵게 문단: {bold_count}개")
+                f.write(f"  - 기울임 문단: {italic_count}개")
+
+            # 문단별 텍스트 출력 (처음 5개만)
+            f.write(f"\n[5] 문단별 텍스트 출력 (처음 5개)")
+            f.write("=" * 80)
+
+            for i, para in enumerate(paragraphs[:5], 1):
+                f.write(f"\n문단 {i} ({len(para.text)}자):")
+                if para.char_shape:
+                    f.write(f"  [글꼴: {para.char_shape.font_size}pt, 굵게: {para.char_shape.bold}, 기울임: {para.char_shape.italic}]")
+                # 확장 속성: 글자별 서식 정보
+                if para.char_shapes:
+                    f.write(f"  [확장] 글자별 서식 ({len(para.char_shapes)}개):")
+                    for pos, shape in para.char_shapes:
+                        f.write(f"    위치 {pos}: {shape.font_size}pt, 굵게 {shape.bold}, 기울임 {shape.italic}")
+                f.write(f"{para.text}")
+                f.write("-" * 80)
+
+            if len(paragraphs) > 5:
+                f.write(f"\n... ({len(paragraphs) - 5}개 문단 생략)")
+
+            # 테이블 정보
+            if tables:
+                f.write(f"\n[6] 테이블 정보")
+                f.write(f"  > 총 {len(tables)}개 테이블 발견")
+                for i, table in enumerate(tables, 1):
+                    f.write(f"    테이블 {i}: code={table.code}")
+            
+            # 페이지 구분
+            if page_breaks:
+                f.write(f"\n[7] 페이지 구분")
+                f.write(f"  > 총 {len(page_breaks)}개 페이지 구분 발견")
+
+            # 머리말 정보
+            if headers:
+                f.write(f"\n[8] 머리말 정보")
+                f.write(f"  > 총 {len(headers)}개 머리말 발견")
+                for i, header in enumerate(headers, 1):
+                    f.write(f"    머리말 {i}: code={header.code}")
+                    if hasattr(header, 'control_id'):
+                        f.write(f", control_id=0x{header.control_id:08X}")
+
+            # 꼬리말 정보
+            if footers:
+                f.write(f"\n[9] 꼬리말 정보")
+                f.write(f"  > 총 {len(footers)}개 꼬리말 발견")
+                for i, footer in enumerate(footers, 1):
+                    f.write(f"    꼬리말 {i}: code={footer.code}")
+                    if hasattr(footer, 'control_id'):
+                        f.write(f", control_id=0x{footer.control_id:08X}")
+
+            # 페이지 정의 정보
+            if page_defs:
+                f.write(f"\n[10] 페이지 정의 (PAGE_DEF)")
+                f.write(f"  > 총 {len(page_defs)}개 페이지 정의 발견")
+                for i, page_def in enumerate(page_defs, 1):
+                    f.write(f"    페이지 정의 {i}: code={page_def.code}")
+
+            # 전체 텍스트 추출
+            f.write(f"\n[11] 전체 텍스트 추출 - to_text()")
+            full_text = hwp.to_text()
+            f.write(f"  > 총 {len(full_text):,}자 추출")
+
+            index = 1
+            for element_type, element in hwp.iter_tags():
+                # 확장 제어 디버깅 정보 출력
+                # if element_type in [ElementType.TABLE, ElementType.EQUATION, ElementType.PICTURE]:
+                #     control_id = element.control_id if hasattr(element, 'control_id') else None
+                #     control_id_str = f"0x{control_id:08X}" if control_id else "None"
+                #     f.write(f"*** 타입: {element_type.value}, 코드: {element.code}, Control ID: {control_id_str}, 데이터: {element.data[:20] if element.data else None}\n")
+                
+                if element_type == ElementType.PARAGRAPH:
+                    f.write(f"[문단 {index}]\n")
+                    if hasattr(element, 'char_shape') and element.char_shape:
+                        f.write(f"[서식(max): {element.char_shape.font_size}pt, 굵게: {element.char_shape.bold}]\n")
+                    # 확장 속성: 글자별 상세 서식
+                    if hasattr(element, 'char_shapes') and element.char_shapes and len(element.char_shapes) > 1:
+                        f.write(f"[상세] 글자별 서식 변경 지점:\n")
+                        for pos, shape in element.char_shapes:
+                            f.write(f"  위치 {pos}: {shape.font_size}pt, 굵게 {shape.bold}\n")
+                    f.write(f"{element.text}\n\n")
+                elif element_type == ElementType.TABLE:
+                    # tables.append(element)
+                    f.write(f"[표 {index}]\n")
+                    f.write(f"  - Table Index: {element.table_index}\n")
+                    f.write(f"  - Control ID: {element.control_id or element.get_control_id()}\n")
+                    f.write(f"  - code: {element.code}\n")
+                    if element.rows is not None:
+                        f.write(f"  - 행/열: {element.rows} x {element.cols} (cell_count={element.cell_count})\n")
+                    
+                    # 크기 출력 (실제 크기 또는 추정 크기)
+                    if element.width is not None:
+                        # 실제 크기 (도형 개체 테이블)
+                        width_px = element.to_px(element.width, dpi=96)
+                        height_px = element.to_px(element.height, dpi=96)
+                        f.write(f"  - 크기(cm): {element.width_cm:.2f}cm x {element.height_cm:.2f}cm\n")
+                        f.write(f"  - 크기(px): {width_px}px x {height_px}px (96 DPI)\n")
+                    else:
+                        # 추정 크기 (일반 텍스트 테이블)
+                        est_width, est_height = estimate_table_size(element)
+                        if est_width:
+                            # cm를 픽셀로 변환 (1 inch = 2.54 cm, 96 DPI)
+                            est_width_px = int(est_width / 2.54 * 96)
+                            est_height_px = int(est_height / 2.54 * 96)
+                            f.write(f"  - 크기(추정cm): ~{est_width:.2f}cm x ~{est_height:.2f}cm\n")
+                            f.write(f"  - 크기(추정px): ~{est_width_px}px x ~{est_height_px}px (96 DPI)\n")
+                    
+                    # 위치 출력 (cm와 픽셀 둘 다)
+                    if element.x is not None:
+                        x_px = element.to_px(element.x, dpi=96)
+                        y_px = element.to_px(element.y, dpi=96)
+                        f.write(f"  - 위치(cm): X={element.to_cm(element.x):.2f}cm, Y={element.to_cm(element.y):.2f}cm\n")
+                        f.write(f"  - 위치(px): X={x_px}px, Y={y_px}px (96 DPI)\n")
+                    else:
+                        f.write(f"  - 위치: 텍스트 흐름 (자동 배치)\n")
+                    
+                    f.write(f"\n")
+                elif element_type == ElementType.PAGE_BREAK:
+                    f.write(f"[페이지구분 {index}]\n")
+                elif element_type == ElementType.SECTION:
+                    f.write(f"[섹션 {index}]\n")
+                elif element_type == ElementType.HEADER:
+                    f.write(f"[머리말 {index}]\n")
+                elif element_type == ElementType.FOOTER:
+                    f.write(f"[꼬리말 {index}]\n")
+                    if hasattr(element, 'control_id'):
+                        f.write(f"  - Control ID: 0x{element.control_id:08X}\n")
+                    f.write(f"  - code: {element.code}\n")
+                    # 꼬리말 내용이 있는지 확인
+                    if hasattr(element, 'data') and element.data:
+                        f.write(f"  - 데이터 길이: {len(element.data)} bytes\n")
+                elif element_type == ElementType.FOOTNOTE:
+                    f.write(f"[각주 {index}]\n")
+                elif element_type == ElementType.ENDNOTE:
+                    f.write(f"[미주 {index}]\n")
+                elif element_type == ElementType.COMMENT:
+                    f.write(f"[메모 {index}]\n")
+                elif element_type == ElementType.SHAPE:
+                    f.write(f"[도형 {index}]\n")
+                elif element_type == ElementType.PICTURE:
+                    f.write(f"[그림 {index}]\n")
+                elif element_type == ElementType.OLE:
+                    f.write(f"[OLE {index}]\n")
+                elif element_type == ElementType.EQUATION:
+                    f.write(f"[수식 {index}]\n")
+                elif element_type == ElementType.HYPERLINK:
+                    f.write(f"[하이퍼링크 {index}]\n")
+                elif element_type == ElementType.SHAPE_COMPONENT:
+                    f.write(f"[도형요소 {index}]\n")
+                elif element_type == ElementType.LIST_HEADER:
+                    f.write(f"[리스트헤더 {index}]\n")
+                elif element_type == ElementType.PAGE_DEF:
+                    f.write(f"[페이지정의 {index}]\n")
+                    f.write(f"  - code: {element.code}\n")
+                    if hasattr(element, 'data') and element.data:
+                        f.write(f"  - 데이터 길이: {len(element.data)} bytes\n")
+                        # 꼬리말 여백 정보 (offset 16-19, HWPUNIT 4 bytes)
+                        if len(element.data) >= 20:
+                            footer_margin = struct.unpack('<I', element.data[16:20])[0]
+                            f.write(f"  - 꼬리말 여백: {footer_margin} HWPUNIT\n")
+                elif element_type == ElementType.CTRL_HEADER:
+                    f.write(f"[컨트롤헤더 {index}]\n")
+                elif element_type == ElementType.CTRL_DATA:
+                    f.write(f"[컨트롤데이터 {index}]\n")
+                elif element_type == ElementType.CAPTION:
+                    f.write(f"[캡션 {index}]\n")
+                elif element_type == ElementType.BOOKMARK:
+                    f.write(f"[책갈피 {index}]\n")
+                elif element_type == ElementType.FIELD:
+                    f.write(f"[필드 {index}]\n")
+                elif element_type == ElementType.AUTO_NUMBER:
+                    f.write(f"[자동번호/쪽번호 {index}]\n")
+                    if hasattr(element, 'control_id') and element.control_id:
+                        f.write(f"  - Control ID: 0x{element.control_id:08X}\n")
+                    f.write(f"  - code: {element.code}\n")
+                    if hasattr(element, 'data') and element.data:
+                        # 자동 번호 데이터 파싱 (12 bytes: 속성 4 + 번호 2 + 기호들 6)
+                        if len(element.data) >= 12:
+                            attrs = struct.unpack('<I', element.data[0:4])[0]
+                            number = struct.unpack('<H', element.data[4:6])[0]
+                            number_type = attrs & 0xF  # bit 0~3: 번호 종류
+                            number_format = (attrs >> 4) & 0xFF  # bit 4~11: 번호 모양
+                            
+                            type_names = {0: "쪽 번호", 1: "각주 번호", 2: "미주 번호", 
+                                         3: "그림 번호", 4: "표 번호", 5: "수식 번호"}
+                            f.write(f"  - 번호 종류: {type_names.get(number_type, f'알수없음({number_type})')}\n")
+                            f.write(f"  - 번호: {number}\n")
+                            f.write(f"  - 번호 모양: {number_format}\n")
+                elif element_type == ElementType.NEW_NUMBER:
+                    f.write(f"[새번호지정 {index}]\n")
+                    if hasattr(element, 'control_id') and element.control_id:
+                        f.write(f"  - Control ID: 0x{element.control_id:08X}\n")
+                    f.write(f"  - code: {element.code}\n")
+                    if hasattr(element, 'data') and element.data:
+                        # 새 번호 지정 데이터 파싱 (8 bytes: 속성 4 + 번호 2)
+                        if len(element.data) >= 6:
+                            attrs = struct.unpack('<I', element.data[0:4])[0]
+                            number = struct.unpack('<H', element.data[4:6])[0]
+                            number_type = attrs & 0xF  # bit 0~3: 번호 종류
+                            
+                            type_names = {0: "쪽 번호", 1: "각주 번호", 2: "미주 번호", 
+                                         3: "그림 번호", 4: "표 번호", 5: "수식 번호"}
+                            f.write(f"  - 번호 종류: {type_names.get(number_type, f'알수없음({number_type})')}\n")
+                            f.write(f"  - 새 시작 번호: {number}\n")
+                elif element_type == ElementType.PAGE_NUM_POS:
+                    f.write(f"[쪽번호위치 {index}]\n")
+                    if hasattr(element, 'control_id') and element.control_id:
+                        f.write(f"  - Control ID: 0x{element.control_id:08X}\n")
+                    f.write(f"  - code: {element.code}\n")
+                    if hasattr(element, 'data') and element.data:
+                        # 쪽 번호 위치 데이터 파싱 (12 bytes)
+                        if len(element.data) >= 12:
+                            attrs = struct.unpack('<I', element.data[0:4])[0]
+                            position = (attrs >> 8) & 0xF  # bit 8~11: 위치
+                            positions = {0: "없음", 1: "왼쪽 위", 2: "가운데 위", 3: "오른쪽 위",
+                                        4: "왼쪽 아래", 5: "가운데 아래", 6: "오른쪽 아래",
+                                        7: "바깥쪽 위", 8: "바깥쪽 아래", 9: "안쪽 위", 10: "안쪽 아래"}
+                            f.write(f"  - 표시 위치: {positions.get(position, f'알수없음({position})')}\n")
+                else:
+                    f.write(f"[알수없음 {element_type.value} {index}]\n")
+                
+                index += 1
+
+            f.write(f"\n[12] 파일 저장")
+            f.write(f"  > 저장 완료: {output_file}")
+
+    print("\n" + "=" * 80)
+    print("완료!")
+    print("=" * 80)
+
+
+if __name__ == "__main__":
+    main()

helper_hwp-0.5.0/tests/test_hwp_to_markdown.py

@@ -0,0 +1,26 @@
+"""hwp_to_markdown 함수 테스트"""
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from helper_hwp import hwp_to_markdown
+
+def test_hwp_to_markdown():
+    hwp_path = Path(__file__).parent / "test.hwp"
+    md_path = Path(__file__).parent / "test_hwp_to_markdown.md"
+    
+    # HWP에서 마크다운 추출
+    markdown = hwp_to_markdown(str(hwp_path))
+    
+    # 파일로 저장
+    with open(md_path, 'w', encoding='utf-8') as f:
+        f.write(markdown)
+    
+    print(f"변환 완료: {md_path}")
+    print(f"\n=== 출력 내용 ({len(markdown)} 글자) ===")
+    print(markdown[:1000])
+
+if __name__ == "__main__":
+    test_hwp_to_markdown()

helper_hwp-0.5.0/tests/test_hwp_to_markdown_pdf.py

@@ -0,0 +1,112 @@
+import sys
+import platform
+import shutil
+from pathlib import Path
+import pypandoc
+from matplotlib import font_manager
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from helper_hwp import hwp_to_markdown
+
+def get_available_korean_font() -> str:
+    """시스템에서 사용 가능한 한글 폰트 반환
+    
+    Returns:
+        str: 사용 가능한 폰트명
+        
+    Raises:
+        SystemExit: 한글 폰트가 없을 경우
+    """
+    system = platform.system()
+    
+    # 우선순위별 폰트 목록 (유니코드 포괄 범위 우선)
+    if system == "Windows":
+        font_candidates = ["Arial Unicode MS", "NotoSans CJK KR", "Malgun Gothic", "맑은 고딕"]
+        install_url = "https://github.com/notofonts/noto-cjk/releases (Noto Sans CJK)"
+    else:  # Linux/macOS
+        font_candidates = ["Noto Sans CJK KR", "NanumGothic"]
+        install_url = "sudo apt install fonts-noto-cjk (Ubuntu/Debian)"
+    
+    # 시스템 폰트 목록 조회
+    available_fonts = {f.name for f in font_manager.fontManager.ttflist}
+    
+    # 우선순위대로 확인
+    for font in font_candidates:
+        if font in available_fonts:
+            return font
+    
+    # 폰트 없음
+    print(f"\n[오류] 한글 폰트를 찾을 수 없습니다.")
+    print(f"설치 필요: {', '.join(font_candidates[:2])}")
+    print(f"설치 방법: {install_url}")
+    sys.exit(1)
+
+def test_hwp_to_markdown_pdf() -> None:
+    """HWP → Markdown → PDF 변환 테스트 (한글 지원)"""
+    # XeLaTeX 경로 확인 및 설정
+    xelatex_path = shutil.which("xelatex")
+    
+    if not xelatex_path:
+        # Windows MiKTeX 기본 경로 확인
+        miktex_paths = [
+            r"C:\Program Files\MiKTeX\miktex\bin\x64",
+            r"C:\Program Files (x86)\MiKTeX\miktex\bin\x64",
+            r"C:\Users\{}\AppData\Local\Programs\MiKTeX\miktex\bin\x64".format(Path.home().name),
+        ]
+        
+        for miktex_bin in miktex_paths:
+            if Path(miktex_bin).exists():
+                import os
+                os.environ["PATH"] = f"{miktex_bin};{os.environ['PATH']}"
+                xelatex_path = shutil.which("xelatex")
+                if xelatex_path:
+                    print(f"XeLaTeX 경로 설정: {miktex_bin}")
+                    break
+        
+        if not xelatex_path:
+            print("\n[오류] XeLaTeX을 찾을 수 없습니다.")
+            print("MiKTeX 설치: https://miktex.org/download")
+            print("\n수동 PATH 추가:")
+            print('  setx PATH "%PATH%;C:\\Program Files\\MiKTeX\\miktex\\bin\\x64"')
+            sys.exit(1)
+    
+    hwp_path = Path(__file__).parent / "test.hwp"
+    pdf_path = Path(__file__).parent / "test_hwp_to_markdown_pdf.pdf"
+    md_path = Path(__file__).parent / "test_hwp_to_markdown_pdf.md"
+    header_path = Path(__file__).parent / "test_hwp_to_markdown_pdf.tex"
+    
+    md_content = hwp_to_markdown(str(hwp_path))
+    md_path.write_text(md_content, encoding="utf-8")
+    
+    mainfont = get_available_korean_font()
+    bold_font = f"{mainfont} Bold" if "Malgun Gothic" in mainfont else mainfont
+    print(f"사용 폰트: {mainfont}")
+    
+    # LaTeX 헤더 파일 생성
+    header_content = (
+        r"\usepackage{fontspec}" "\n"
+        rf"\setmainfont{{{mainfont}}}[BoldFont={{{bold_font}}}]" "\n"
+        rf"\setsansfont{{{mainfont}}}" "\n"
+        rf"\setmonofont{{{mainfont}}}" "\n"
+        r"\usepackage{xeCJK}" "\n"
+        rf"\setCJKmainfont{{{mainfont}}}[BoldFont={{{bold_font}}}]" "\n"
+        r"\usepackage[margin=1cm]{geometry}"
+    )
+    header_path.write_text(header_content, encoding="utf-8")
+    
+    pypandoc.convert_file(
+        str(md_path),
+        "pdf",
+        outputfile=str(pdf_path),
+        extra_args=[
+            "--pdf-engine=xelatex",
+            f"--include-in-header={header_path}",
+        ],
+    )
+    
+    print(f"변환 완료: {md_path}")
+    print(f"변환 완료: {pdf_path}")
+
+if __name__ == "__main__":
+    test_hwp_to_markdown_pdf()

helper_hwp-0.5.0/tests/test_hwp_to_txt.py

@@ -0,0 +1,26 @@
+"""hwp_to_txt 함수 테스트"""
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from helper_hwp import hwp_to_txt
+
+def test_hwp_to_txt():
+    hwp_path = Path(__file__).parent / "test.hwp"
+    txt_path = Path(__file__).parent / "test_hwp_to_txt.txt"
+    
+    # HWP에서 텍스트 추출
+    text = hwp_to_txt(str(hwp_path))
+    
+    # 파일로 저장
+    with open(txt_path, 'w', encoding='utf-8') as f:
+        f.write(text)
+    
+    print(f"변환 완료: {txt_path}")
+    print(f"\n=== 출력 내용 ({len(text)} 글자) ===")
+    print(text[:500])
+
+if __name__ == "__main__":
+    test_hwp_to_txt()