doc-page-extractor 0.0.1__tar.gz → 0.0.2__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.

Potentially problematic release.

This version of doc-page-extractor might be problematic. Click here for more details.

Files changed (22) hide show
  1. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/PKG-INFO +4 -2
  2. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/PKG-INFO +4 -2
  3. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/requires.txt +1 -1
  4. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/setup.py +3 -2
  5. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/LICENSE +0 -0
  6. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/README.md +0 -0
  7. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/__init__.py +0 -0
  8. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/clipper.py +0 -0
  9. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/downloader.py +0 -0
  10. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/extractor.py +0 -0
  11. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/layoutreader.py +0 -0
  12. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/ocr.py +0 -0
  13. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/plot.py +0 -0
  14. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/raw_optimizer.py +0 -0
  15. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/rectangle.py +0 -0
  16. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/rotation.py +0 -0
  17. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/types.py +0 -0
  18. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor/utils.py +0 -0
  19. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/SOURCES.txt +0 -0
  20. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/dependency_links.txt +0 -0
  21. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/top_level.txt +0 -0
  22. {doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/setup.cfg +0 -0
{doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/PKG-INFO RENAMED
@@ -1,7 +1,8 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: doc-page-extractor
3
- Version: 0.0.1
3
+ Version: 0.0.2
4
4
  Summary: doc page extractor can identify text and format in images and return structured data.
5
+ Home-page: https://github.com/Moskize91/doc-page-extractor
5
6
  Author: Tao Zeyu
6
7
  Author-email: i@taozeyu.com
7
8
  Description-Content-Type: text/markdown
@@ -12,11 +13,12 @@ Requires-Dist: shapely<3.0,>=2.0.0
12
13
  Requires-Dist: transformers<5.0,>=4.48.0
13
14
  Requires-Dist: doclayout_yolo>=0.0.3
14
15
  Requires-Dist: paddlepaddle<3.0,>=2.6.0
15
- Requires-Dist: paddleocr<3.0,>=2.9.0
16
+ Requires-Dist: paddleocr==2.9.0
16
17
  Dynamic: author
17
18
  Dynamic: author-email
18
19
  Dynamic: description
19
20
  Dynamic: description-content-type
21
+ Dynamic: home-page
20
22
  Dynamic: requires-dist
21
23
  Dynamic: summary
22
24
 
{doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/PKG-INFO RENAMED
@@ -1,7 +1,8 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: doc-page-extractor
3
- Version: 0.0.1
3
+ Version: 0.0.2
4
4
  Summary: doc page extractor can identify text and format in images and return structured data.
5
+ Home-page: https://github.com/Moskize91/doc-page-extractor
5
6
  Author: Tao Zeyu
6
7
  Author-email: i@taozeyu.com
7
8
  Description-Content-Type: text/markdown
@@ -12,11 +13,12 @@ Requires-Dist: shapely<3.0,>=2.0.0
12
13
  Requires-Dist: transformers<5.0,>=4.48.0
13
14
  Requires-Dist: doclayout_yolo>=0.0.3
14
15
  Requires-Dist: paddlepaddle<3.0,>=2.6.0
15
- Requires-Dist: paddleocr<3.0,>=2.9.0
16
+ Requires-Dist: paddleocr==2.9.0
16
17
  Dynamic: author
17
18
  Dynamic: author-email
18
19
  Dynamic: description
19
20
  Dynamic: description-content-type
21
+ Dynamic: home-page
20
22
  Dynamic: requires-dist
21
23
  Dynamic: summary
22
24
 
{doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/doc_page_extractor.egg-info/requires.txt RENAMED
@@ -4,4 +4,4 @@ shapely<3.0,>=2.0.0
4
4
  transformers<5.0,>=4.48.0
5
5
  doclayout_yolo>=0.0.3
6
6
  paddlepaddle<3.0,>=2.6.0
7
- paddleocr<3.0,>=2.9.0
7
+ paddleocr==2.9.0
{doc_page_extractor-0.0.1 → doc_page_extractor-0.0.2}/setup.py RENAMED
@@ -2,9 +2,10 @@ from setuptools import setup, find_packages
2
2
 
3
3
  setup(
4
4
  name="doc-page-extractor",
5
- version="0.0.1",
5
+ version="0.0.2",
6
6
  author="Tao Zeyu",
7
7
  author_email="i@taozeyu.com",
8
+ url="https://github.com/Moskize91/doc-page-extractor",
8
9
  description="doc page extractor can identify text and format in images and return structured data.",
9
10
  packages=find_packages(),
10
11
  long_description=open("./README.md", encoding="utf8").read(),
@@ -16,6 +17,6 @@ setup(
16
17
  "transformers>=4.48.0,<5.0",
17
18
  "doclayout_yolo>=0.0.3",
18
19
  "paddlepaddle>=2.6.0,<3.0",
19
- "paddleocr>=2.9.0,<3.0",
20
+ "paddleocr==2.9.0", # https://github.com/Moskize91/doc-page-extractor/issues/3
20
21
  ],
21
22
  )