python-hwpx 2.10.1__tar.gz → 2.10.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {python_hwpx-2.10.1/src/python_hwpx.egg-info → python_hwpx-2.10.2}/PKG-INFO +49 -1
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/README.md +48 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/pyproject.toml +1 -1
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/document.py +8 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/document.py +147 -2
- python_hwpx-2.10.2/src/hwpx/tools/markdown_export.py +488 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/table_navigation.py +77 -1
- {python_hwpx-2.10.1 → python_hwpx-2.10.2/src/python_hwpx.egg-info}/PKG-INFO +49 -1
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/python_hwpx.egg-info/SOURCES.txt +2 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_document_formatting.py +42 -0
- python_hwpx-2.10.2/tests/test_markdown_export.py +436 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_table_navigation.py +57 -31
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/LICENSE +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/NOTICE +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/setup.cfg +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/__init__.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/authoring.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/builder/__init__.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/builder/core.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/builder/report.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/data/Skeleton.hwpx +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/form_fill.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/opc/package.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/opc/relationships.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/opc/xml_utils.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/__init__.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/body.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/common.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/header.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/header_part.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/memo.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/namespaces.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/paragraph.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/parser.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/schema.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/section.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/table.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/oxml/utils.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/package.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/presets/__init__.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/presets/proposal.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/py.typed +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/template_formfit.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/templates.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/__init__.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/_schemas/header.xsd +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/_schemas/section.xsd +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/archive_cli.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/exporter.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/generic_inventory.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/id_integrity.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/object_finder.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/package_validator.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/page_guard.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/recover.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/repair.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/report_parser.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/report_utils.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/roundtrip_diff.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/table_cleanup.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/template_analyzer.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/text_extract_cli.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/text_extractor.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/hwpx/tools/validator.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/python_hwpx.egg-info/dependency_links.txt +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/python_hwpx.egg-info/entry_points.txt +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/python_hwpx.egg-info/requires.txt +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/src/python_hwpx.egg-info/top_level.txt +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_builder_core.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_builder_plan_v2.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_builder_vertical_slice.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_coverage_promotion.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_coverage_targets.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_deviations_registry.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_document_context_manager.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_document_plan.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_document_plan_computed_fields.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_document_save_api.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_form_fill_split_run.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_gap_closure_tools.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_government_report_preset.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_government_table_profile.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_hp_tab_support.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_hwpxlib_corpus_read.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_id_generator_range.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_id_integrity.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_inline_models.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_integration_hwpx_compatibility.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_integration_roundtrip.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_memo_and_style_editing.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_namespace_handling.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_new_features.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_opc_package.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_oxml_parsing.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_packaging_license_metadata.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_packaging_py_typed.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_paragraph_section_management.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_proposal_preset.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_recover_broken_zip.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_repair_repack.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_report_parser.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_report_utils.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_repr_snapshots.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_roundtrip_fidelity.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_section_headers.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_skeleton_template_ids.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_split_merged_cell.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_table_cleanup.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_tables_default_border.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_template_formfit.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_text_extractor_annotations.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_validation_severity.py +0 -0
- {python_hwpx-2.10.1 → python_hwpx-2.10.2}/tests/test_version_metadata.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: python-hwpx
|
|
3
|
-
Version: 2.10.
|
|
3
|
+
Version: 2.10.2
|
|
4
4
|
Summary: 한글 없이 HWPX 문서를 열고, 편집하고, 생성하고, 검증하는 Python 자동화 라이브러리
|
|
5
5
|
Author: python-hwpx Maintainers
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -115,6 +115,47 @@ hwpx-validate-package 보고서.hwpx
|
|
|
115
115
|
hwpx-analyze-template 보고서.hwpx
|
|
116
116
|
```
|
|
117
117
|
|
|
118
|
+
### 4. 풍부한 Markdown 변환 (서식·표·각주·이미지 보존)
|
|
119
|
+
|
|
120
|
+
`export_markdown()`는 단순 평문 추출이고, `export_rich_markdown()`는 인라인 서식(`**굵게**`, `*기울임*`, `~~취소선~~`),
|
|
121
|
+
표(중첩 포함, colspan/rowspan 안전), 도형 텍스트, 이미지, 각주/미주, 하이퍼링크, 제목(`#`/`##`) 자동 감지까지 보존한다.
|
|
122
|
+
|
|
123
|
+
```python
|
|
124
|
+
from hwpx import HwpxDocument
|
|
125
|
+
|
|
126
|
+
doc = HwpxDocument.open("보고서.hwpx")
|
|
127
|
+
|
|
128
|
+
md = doc.export_rich_markdown(
|
|
129
|
+
image_dir="out/images", # BinData 이미지를 디스크에 추출
|
|
130
|
+
image_ref_prefix="images/", # 마크다운 내  경로 접두
|
|
131
|
+
detect_headings=True, # Ⅰ./1. 패턴 기반 #/## 자동
|
|
132
|
+
)
|
|
133
|
+
print(md)
|
|
134
|
+
```
|
|
135
|
+
|
|
136
|
+
문자열·경로·바이트도 그대로 받는다:
|
|
137
|
+
|
|
138
|
+
```python
|
|
139
|
+
from hwpx.tools.markdown_export import export_markdown
|
|
140
|
+
|
|
141
|
+
md = export_markdown("보고서.hwpx") # 경로
|
|
142
|
+
md = export_markdown(open("a.hwpx", "rb").read()) # bytes
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
### 5. 각주 본문에 혼합 서식 / 하이퍼링크 추가
|
|
146
|
+
|
|
147
|
+
`HwpxOxmlNote`에 `body_paragraph`, `add_run`, `add_hyperlink` helper가 있어 각주 본문을
|
|
148
|
+
직접 paragraph로 다루지 않고도 인라인 서식·링크를 손쉽게 채울 수 있다.
|
|
149
|
+
|
|
150
|
+
```python
|
|
151
|
+
para = section.paragraphs[0]
|
|
152
|
+
note = para.add_footnote("") # 빈 각주 생성 후 본문 구성
|
|
153
|
+
note.add_run("자세한 내용은 ", )
|
|
154
|
+
note.add_run("정부 공식 사이트", bold=True)
|
|
155
|
+
note.add_run("를 참고하라: ")
|
|
156
|
+
note.add_hyperlink("https://www.kasa.go.kr", "우주항공청")
|
|
157
|
+
```
|
|
158
|
+
|
|
118
159
|
처음에는 `open/new -> edit/extract -> save_to_path` 흐름만 잡으면 된다. 패키지 구조, XML 파트, 템플릿 회귀 점검은 필요할 때만 확장하면 된다.
|
|
119
160
|
|
|
120
161
|
## 어디부터 읽으면 되나
|
|
@@ -244,6 +285,7 @@ doc.set_footer_text("1 / 10", page_type="BOTH")
|
|
|
244
285
|
# 표 셀 병합·분할
|
|
245
286
|
table.merge_cells(0, 0, 1, 1) # (0,0)~(1,1) 병합
|
|
246
287
|
table.set_cell_text(0, 0, "병합된 셀", logical=True, split_merged=True)
|
|
288
|
+
table.set_cell_text(0, 0, "line 1\nline 2", split_paragraphs=True)
|
|
247
289
|
|
|
248
290
|
# 양식형 표 자동 채우기
|
|
249
291
|
form = doc.add_table(2, 2)
|
|
@@ -257,6 +299,12 @@ doc.fill_by_path({
|
|
|
257
299
|
})
|
|
258
300
|
```
|
|
259
301
|
|
|
302
|
+
`doc.paragraphs`의 인덱스는 본문 직속 문단 0-based 기준입니다. 표 안 문단은
|
|
303
|
+
본문 `paragraph_index`에 섞지 않고 `get_table_map()`의 cell `location`
|
|
304
|
+
(`table_index`, `row`, `col`, `cell_paragraph_index`)으로 다룹니다.
|
|
305
|
+
`get_table_map()`은 `caption_text`와 `preceding_paragraph_text`를 분리해
|
|
306
|
+
반환하고, 셀 미리보기의 여러 문단은 `\n`으로 유지합니다.
|
|
307
|
+
|
|
260
308
|
### 🔍 텍스트 추출 & 검색
|
|
261
309
|
|
|
262
310
|
```python
|
|
@@ -79,6 +79,47 @@ hwpx-validate-package 보고서.hwpx
|
|
|
79
79
|
hwpx-analyze-template 보고서.hwpx
|
|
80
80
|
```
|
|
81
81
|
|
|
82
|
+
### 4. 풍부한 Markdown 변환 (서식·표·각주·이미지 보존)
|
|
83
|
+
|
|
84
|
+
`export_markdown()`는 단순 평문 추출이고, `export_rich_markdown()`는 인라인 서식(`**굵게**`, `*기울임*`, `~~취소선~~`),
|
|
85
|
+
표(중첩 포함, colspan/rowspan 안전), 도형 텍스트, 이미지, 각주/미주, 하이퍼링크, 제목(`#`/`##`) 자동 감지까지 보존한다.
|
|
86
|
+
|
|
87
|
+
```python
|
|
88
|
+
from hwpx import HwpxDocument
|
|
89
|
+
|
|
90
|
+
doc = HwpxDocument.open("보고서.hwpx")
|
|
91
|
+
|
|
92
|
+
md = doc.export_rich_markdown(
|
|
93
|
+
image_dir="out/images", # BinData 이미지를 디스크에 추출
|
|
94
|
+
image_ref_prefix="images/", # 마크다운 내  경로 접두
|
|
95
|
+
detect_headings=True, # Ⅰ./1. 패턴 기반 #/## 자동
|
|
96
|
+
)
|
|
97
|
+
print(md)
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
문자열·경로·바이트도 그대로 받는다:
|
|
101
|
+
|
|
102
|
+
```python
|
|
103
|
+
from hwpx.tools.markdown_export import export_markdown
|
|
104
|
+
|
|
105
|
+
md = export_markdown("보고서.hwpx") # 경로
|
|
106
|
+
md = export_markdown(open("a.hwpx", "rb").read()) # bytes
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
### 5. 각주 본문에 혼합 서식 / 하이퍼링크 추가
|
|
110
|
+
|
|
111
|
+
`HwpxOxmlNote`에 `body_paragraph`, `add_run`, `add_hyperlink` helper가 있어 각주 본문을
|
|
112
|
+
직접 paragraph로 다루지 않고도 인라인 서식·링크를 손쉽게 채울 수 있다.
|
|
113
|
+
|
|
114
|
+
```python
|
|
115
|
+
para = section.paragraphs[0]
|
|
116
|
+
note = para.add_footnote("") # 빈 각주 생성 후 본문 구성
|
|
117
|
+
note.add_run("자세한 내용은 ", )
|
|
118
|
+
note.add_run("정부 공식 사이트", bold=True)
|
|
119
|
+
note.add_run("를 참고하라: ")
|
|
120
|
+
note.add_hyperlink("https://www.kasa.go.kr", "우주항공청")
|
|
121
|
+
```
|
|
122
|
+
|
|
82
123
|
처음에는 `open/new -> edit/extract -> save_to_path` 흐름만 잡으면 된다. 패키지 구조, XML 파트, 템플릿 회귀 점검은 필요할 때만 확장하면 된다.
|
|
83
124
|
|
|
84
125
|
## 어디부터 읽으면 되나
|
|
@@ -208,6 +249,7 @@ doc.set_footer_text("1 / 10", page_type="BOTH")
|
|
|
208
249
|
# 표 셀 병합·분할
|
|
209
250
|
table.merge_cells(0, 0, 1, 1) # (0,0)~(1,1) 병합
|
|
210
251
|
table.set_cell_text(0, 0, "병합된 셀", logical=True, split_merged=True)
|
|
252
|
+
table.set_cell_text(0, 0, "line 1\nline 2", split_paragraphs=True)
|
|
211
253
|
|
|
212
254
|
# 양식형 표 자동 채우기
|
|
213
255
|
form = doc.add_table(2, 2)
|
|
@@ -221,6 +263,12 @@ doc.fill_by_path({
|
|
|
221
263
|
})
|
|
222
264
|
```
|
|
223
265
|
|
|
266
|
+
`doc.paragraphs`의 인덱스는 본문 직속 문단 0-based 기준입니다. 표 안 문단은
|
|
267
|
+
본문 `paragraph_index`에 섞지 않고 `get_table_map()`의 cell `location`
|
|
268
|
+
(`table_index`, `row`, `col`, `cell_paragraph_index`)으로 다룹니다.
|
|
269
|
+
`get_table_map()`은 `caption_text`와 `preceding_paragraph_text`를 분리해
|
|
270
|
+
반환하고, 셀 미리보기의 여러 문단은 `\n`으로 유지합니다.
|
|
271
|
+
|
|
224
272
|
### 🔍 텍스트 추출 & 검색
|
|
225
273
|
|
|
226
274
|
```python
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "python-hwpx"
|
|
7
|
-
version = "2.10.
|
|
7
|
+
version = "2.10.2"
|
|
8
8
|
description = "한글 없이 HWPX 문서를 열고, 편집하고, 생성하고, 검증하는 Python 자동화 라이브러리"
|
|
9
9
|
readme = { file = "README.md", content-type = "text/markdown" }
|
|
10
10
|
license = "Apache-2.0"
|
|
@@ -1472,6 +1472,14 @@ class HwpxDocument:
|
|
|
1472
1472
|
from .tools.exporter import export_markdown
|
|
1473
1473
|
return export_markdown(self, **kwargs) # type: ignore[arg-type]
|
|
1474
1474
|
|
|
1475
|
+
def export_rich_markdown(self, **kwargs: object) -> str:
|
|
1476
|
+
"""Export rich Markdown preserving inline styles, tables, footnotes, hyperlinks, images, and shape text.
|
|
1477
|
+
|
|
1478
|
+
Keyword args forwarded to :func:`~hwpx.tools.markdown_export.export_markdown`.
|
|
1479
|
+
"""
|
|
1480
|
+
from .tools.markdown_export import export_markdown as _rich
|
|
1481
|
+
return _rich(self, **kwargs) # type: ignore[arg-type]
|
|
1482
|
+
|
|
1475
1483
|
# ------------------------------------------------------------------
|
|
1476
1484
|
# Validation
|
|
1477
1485
|
# ------------------------------------------------------------------
|
|
@@ -1872,6 +1872,68 @@ class HwpxOxmlNote:
|
|
|
1872
1872
|
t.text = _sanitize_text(value)
|
|
1873
1873
|
self.paragraph.section.mark_dirty()
|
|
1874
1874
|
|
|
1875
|
+
@property
|
|
1876
|
+
def body_paragraph(self) -> "HwpxOxmlParagraph":
|
|
1877
|
+
"""Return the note's body ``<hp:p>`` wrapped as :class:`HwpxOxmlParagraph`.
|
|
1878
|
+
|
|
1879
|
+
The body lives inside ``<hp:subList>`` and is distinct from
|
|
1880
|
+
:attr:`paragraph`, which is the *hosting* paragraph (where the note
|
|
1881
|
+
marker is inserted). Use this to add runs with mixed formatting
|
|
1882
|
+
directly into the note body:
|
|
1883
|
+
|
|
1884
|
+
>>> note = para.add_footnote("기본 ")
|
|
1885
|
+
>>> note.add_run("청색", char_pr_id_ref=5)
|
|
1886
|
+
"""
|
|
1887
|
+
p = self.element.find(f".//{_HP}p")
|
|
1888
|
+
if p is None:
|
|
1889
|
+
raise ValueError("note has no body paragraph element")
|
|
1890
|
+
return HwpxOxmlParagraph(p, self.paragraph.section)
|
|
1891
|
+
|
|
1892
|
+
def add_run(
|
|
1893
|
+
self,
|
|
1894
|
+
text: str = "",
|
|
1895
|
+
*,
|
|
1896
|
+
char_pr_id_ref: str | int | None = None,
|
|
1897
|
+
bold: bool = False,
|
|
1898
|
+
italic: bool = False,
|
|
1899
|
+
underline: bool = False,
|
|
1900
|
+
color: str | None = None,
|
|
1901
|
+
font: str | None = None,
|
|
1902
|
+
size: int | float | None = None,
|
|
1903
|
+
highlight: str | None = None,
|
|
1904
|
+
strike: bool | None = None,
|
|
1905
|
+
attributes: dict[str, str] | None = None,
|
|
1906
|
+
) -> "HwpxOxmlRun":
|
|
1907
|
+
"""Append a run to the note body paragraph (delegates to body_paragraph.add_run)."""
|
|
1908
|
+
return self.body_paragraph.add_run(
|
|
1909
|
+
text,
|
|
1910
|
+
char_pr_id_ref=char_pr_id_ref,
|
|
1911
|
+
bold=bold,
|
|
1912
|
+
italic=italic,
|
|
1913
|
+
underline=underline,
|
|
1914
|
+
color=color,
|
|
1915
|
+
font=font,
|
|
1916
|
+
size=size,
|
|
1917
|
+
highlight=highlight,
|
|
1918
|
+
strike=strike,
|
|
1919
|
+
attributes=attributes,
|
|
1920
|
+
)
|
|
1921
|
+
|
|
1922
|
+
def add_hyperlink(
|
|
1923
|
+
self,
|
|
1924
|
+
url: str,
|
|
1925
|
+
display_text: str,
|
|
1926
|
+
*,
|
|
1927
|
+
char_pr_id_ref: str | int | None = None,
|
|
1928
|
+
) -> "HwpxOxmlInlineObject":
|
|
1929
|
+
"""Append a hyperlink to the note body paragraph.
|
|
1930
|
+
|
|
1931
|
+
Convenience wrapper around ``body_paragraph.add_hyperlink``.
|
|
1932
|
+
"""
|
|
1933
|
+
return self.body_paragraph.add_hyperlink(
|
|
1934
|
+
url, display_text, char_pr_id_ref=char_pr_id_ref
|
|
1935
|
+
)
|
|
1936
|
+
|
|
1875
1937
|
|
|
1876
1938
|
def _default_sublist_attributes() -> dict[str, str]:
|
|
1877
1939
|
"""Return standard attributes for a ``<hp:subList>`` element.
|
|
@@ -2425,6 +2487,9 @@ class HwpxOxmlTableCell:
|
|
|
2425
2487
|
|
|
2426
2488
|
@property
|
|
2427
2489
|
def text(self) -> str:
|
|
2490
|
+
paragraphs = self.paragraphs
|
|
2491
|
+
if paragraphs:
|
|
2492
|
+
return "\n".join(paragraph.text or "" for paragraph in paragraphs)
|
|
2428
2493
|
parts: list[str] = []
|
|
2429
2494
|
for t_elem in self.element.findall(f".//{_HP}t"):
|
|
2430
2495
|
if t_elem.text:
|
|
@@ -2433,8 +2498,79 @@ class HwpxOxmlTableCell:
|
|
|
2433
2498
|
|
|
2434
2499
|
@text.setter
|
|
2435
2500
|
def text(self, value: str) -> None:
|
|
2501
|
+
self.set_text(value)
|
|
2502
|
+
|
|
2503
|
+
def _first_run_char_pr_id_ref(self) -> str:
|
|
2504
|
+
for paragraph in self.paragraphs:
|
|
2505
|
+
for run in paragraph.runs:
|
|
2506
|
+
if run.char_pr_id_ref is not None:
|
|
2507
|
+
return str(run.char_pr_id_ref)
|
|
2508
|
+
return "0"
|
|
2509
|
+
|
|
2510
|
+
def _paragraph_format_attrs(self, paragraph: "HwpxOxmlParagraph" | None = None) -> dict[str, str]:
|
|
2511
|
+
source = paragraph.element if paragraph is not None else None
|
|
2512
|
+
attrs = dict(_default_cell_paragraph_attributes())
|
|
2513
|
+
if source is not None:
|
|
2514
|
+
for key in ("paraPrIDRef", "styleIDRef", "pageBreak", "columnBreak", "merged"):
|
|
2515
|
+
value = source.get(key)
|
|
2516
|
+
if value is not None:
|
|
2517
|
+
attrs[key] = value
|
|
2518
|
+
attrs["id"] = _paragraph_id()
|
|
2519
|
+
return attrs
|
|
2520
|
+
|
|
2521
|
+
def _run_char_pr_for_line(self, paragraphs: Sequence["HwpxOxmlParagraph"], index: int) -> str:
|
|
2522
|
+
if index < len(paragraphs):
|
|
2523
|
+
for run in paragraphs[index].runs:
|
|
2524
|
+
if run.char_pr_id_ref is not None:
|
|
2525
|
+
return str(run.char_pr_id_ref)
|
|
2526
|
+
return self._first_run_char_pr_id_ref()
|
|
2527
|
+
|
|
2528
|
+
def _set_split_paragraph_text(self, value: str) -> None:
|
|
2529
|
+
sublist = self._ensure_sublist()
|
|
2530
|
+
existing = self.paragraphs
|
|
2531
|
+
lines = (value or "").replace("\r\n", "\n").replace("\r", "\n").split("\n")
|
|
2532
|
+
if not lines:
|
|
2533
|
+
lines = [""]
|
|
2534
|
+
|
|
2535
|
+
for paragraph in list(sublist.findall(f"{_HP}p")):
|
|
2536
|
+
sublist.remove(paragraph)
|
|
2537
|
+
|
|
2538
|
+
for index, line in enumerate(lines):
|
|
2539
|
+
source = existing[index] if index < len(existing) else existing[0] if existing else None
|
|
2540
|
+
paragraph = _append_child(sublist, f"{_HP}p", self._paragraph_format_attrs(source))
|
|
2541
|
+
run = _append_child(
|
|
2542
|
+
paragraph,
|
|
2543
|
+
f"{_HP}run",
|
|
2544
|
+
{"charPrIDRef": self._run_char_pr_for_line(existing, index)},
|
|
2545
|
+
)
|
|
2546
|
+
_append_text_with_tabs(run, line)
|
|
2547
|
+
|
|
2548
|
+
def set_text(
|
|
2549
|
+
self,
|
|
2550
|
+
value: str,
|
|
2551
|
+
*,
|
|
2552
|
+
preserve_format: bool = True,
|
|
2553
|
+
split_paragraphs: bool = False,
|
|
2554
|
+
) -> None:
|
|
2555
|
+
if split_paragraphs:
|
|
2556
|
+
self._set_split_paragraph_text(value)
|
|
2557
|
+
self.element.set("dirty", "1")
|
|
2558
|
+
self.table.mark_dirty()
|
|
2559
|
+
return
|
|
2560
|
+
|
|
2436
2561
|
text_element = self._ensure_text_element()
|
|
2437
2562
|
text_element.text = _sanitize_text(value)
|
|
2563
|
+
for node in self.element.findall(f".//{_HP}t"):
|
|
2564
|
+
if node is text_element:
|
|
2565
|
+
continue
|
|
2566
|
+
if node.text:
|
|
2567
|
+
node.text = ""
|
|
2568
|
+
if not preserve_format:
|
|
2569
|
+
run = text_element
|
|
2570
|
+
while run is not None and _element_local_name(run) != "run":
|
|
2571
|
+
run = run.getparent() if hasattr(run, "getparent") else None
|
|
2572
|
+
if run is not None:
|
|
2573
|
+
run.set("charPrIDRef", "0")
|
|
2438
2574
|
self.element.set("dirty", "1")
|
|
2439
2575
|
self.table.mark_dirty()
|
|
2440
2576
|
|
|
@@ -2898,6 +3034,8 @@ class HwpxOxmlTable:
|
|
|
2898
3034
|
*,
|
|
2899
3035
|
logical: bool = False,
|
|
2900
3036
|
split_merged: bool = False,
|
|
3037
|
+
preserve_format: bool = True,
|
|
3038
|
+
split_paragraphs: bool = False,
|
|
2901
3039
|
) -> None:
|
|
2902
3040
|
if logical:
|
|
2903
3041
|
entry = self._grid_entry(row_index, col_index)
|
|
@@ -2907,7 +3045,11 @@ class HwpxOxmlTable:
|
|
|
2907
3045
|
cell = entry.cell
|
|
2908
3046
|
else:
|
|
2909
3047
|
cell = self.cell(row_index, col_index)
|
|
2910
|
-
cell.
|
|
3048
|
+
cell.set_text(
|
|
3049
|
+
text,
|
|
3050
|
+
preserve_format=preserve_format,
|
|
3051
|
+
split_paragraphs=split_paragraphs,
|
|
3052
|
+
)
|
|
2911
3053
|
|
|
2912
3054
|
def split_merged_cell(
|
|
2913
3055
|
self, row_index: int, col_index: int
|
|
@@ -3797,7 +3939,10 @@ class HwpxOxmlParagraph:
|
|
|
3797
3939
|
sublist = _append_child(note_element, f"{_HP}subList", _default_sublist_attributes())
|
|
3798
3940
|
p_attrs = {"id": _paragraph_id(), **_DEFAULT_PARAGRAPH_ATTRS}
|
|
3799
3941
|
paragraph = _append_child(sublist, f"{_HP}p", p_attrs)
|
|
3800
|
-
|
|
3942
|
+
# 본문 run의 charPrIDRef도 인자를 따라가도록 적용 (host run과 동일 스타일).
|
|
3943
|
+
# None이면 "0"(default).
|
|
3944
|
+
body_cpr = "0" if char_pr_id_ref is None else str(char_pr_id_ref)
|
|
3945
|
+
note_run = _append_child(paragraph, f"{_HP}run", {"charPrIDRef": body_cpr})
|
|
3801
3946
|
t = _append_child(note_run, f"{_HP}t", {})
|
|
3802
3947
|
t.text = _sanitize_text(text)
|
|
3803
3948
|
self.section.mark_dirty()
|