1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
|
%global _empty_manifest_terminate_build 0
Name: python-layoutparser
Version: 0.3.4
Release: 1
Summary: A unified toolkit for Deep Learning Based Document Image Analysis
License: Apache-2.0
URL: https://github.com/Layout-Parser/layout-parser
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/95/16/3ff7629fd684047ad9779394aadc7b612c5ae91e41a27f1bad1469e23f05/layoutparser-0.3.4.tar.gz
BuildArch: noarch
Requires: python3-numpy
Requires: python3-opencv-python
Requires: python3-scipy
Requires: python3-pandas
Requires: python3-pillow
Requires: python3-pyyaml
Requires: python3-iopath
Requires: python3-pdfplumber
Requires: python3-pdf2image
Requires: python3-torch
Requires: python3-torchvision
Requires: python3-effdet
Requires: python3-google-cloud-vision
Requires: python3-torch
Requires: python3-torchvision
Requires: python3-effdet
Requires: python3-google-cloud-vision
Requires: python3-pytesseract
Requires: python3-paddlepaddle
Requires: python3-pytesseract
%description
## What is LayoutParser
LayoutParser aims to provide a wide range of tools that aims to streamline Document Image Analysis (DIA) tasks. Please check the LayoutParser [demo video](https://youtu.be/8yA5xB4Dg8c) (1 min) or [full talk](https://www.youtube.com/watch?v=YG0qepPgyGY) (15 min) for details. And here are some key features:
- LayoutParser provides a rich repository of deep learning models for layout detection as well as a set of unified APIs for using them. For example,
<details>
<summary>Perform DL layout detection in 4 lines of code</summary>
```python
import layoutparser as lp
model = lp.AutoLayoutModel('lp://EfficientDete/PubLayNet')
# image = Image.open("path/to/image")
layout = model.detect(image)
```
</details>
- LayoutParser comes with a set of layout data structures with carefully designed APIs that are optimized for document image analysis tasks. For example,
<details>
<summary>Selecting layout/textual elements in the left column of a page</summary>
```python
image_width = image.size[0]
left_column = lp.Interval(0, image_width/2, axis='x')
layout.filter_by(left_column, center=True) # select objects in the left column
```
</details>
<details>
<summary>Performing OCR for each detected Layout Region</summary>
```python
ocr_agent = lp.TesseractAgent()
for layout_region in layout:
image_segment = layout_region.crop(image)
text = ocr_agent.detect(image_segment)
```
</details>
<details>
<summary>Flexible APIs for visualizing the detected layouts</summary>
```python
lp.draw_box(image, layout, box_width=1, show_element_id=True, box_alpha=0.25)
```
</details>
</details>
<details>
<summary>Loading layout data stored in json, csv, and even PDFs</summary>
```python
layout = lp.load_json("path/to/json")
layout = lp.load_csv("path/to/csv")
pdf_layout = lp.load_pdf("path/to/pdf")
```
</details>
- LayoutParser is also a open platform that enables the sharing of layout detection models and DIA pipelines among the community.
<details>
<summary><a href="https://layout-parser.github.io/platform/">Check</a> the LayoutParser open platform</summary>
</details>
<details>
<summary><a href="https://github.com/Layout-Parser/platform">Submit</a> your models/pipelines to LayoutParser</summary>
</details>
## Installation
After several major updates, layoutparser provides various functionalities and deep learning models from different backends. But it still easy to install layoutparser, and we designed the installation method in a way such that you can choose to install only the needed dependencies for your project:
```bash
pip install layoutparser # Install the base layoutparser library with
pip install "layoutparser[layoutmodels]" # Install DL layout model toolkit
pip install "layoutparser[ocr]" # Install OCR toolkit
```
Extra steps are needed if you want to use Detectron2-based models. Please check [installation.md](installation.md) for additional details on layoutparser installation.
## Examples
We provide a series of examples for to help you start using the layout parser library:
1. [Table OCR and Results Parsing](https://github.com/Layout-Parser/layout-parser/blob/main/examples/OCR%20Tables%20and%20Parse%20the%20Output.ipynb): `layoutparser` can be used for conveniently OCR documents and convert the output in to structured data.
2. [Deep Layout Parsing Example](https://github.com/Layout-Parser/layout-parser/blob/main/examples/Deep%20Layout%20Parsing.ipynb): With the help of Deep Learning, `layoutparser` supports the analysis very complex documents and processing of the hierarchical structure in the layouts.
## Contributing
We encourage you to contribute to Layout Parser! Please check out the [Contributing guidelines](.github/CONTRIBUTING.md) for guidelines about how to proceed. Join us!
## Citing `layoutparser`
If you find `layoutparser` helpful to your work, please consider citing our tool and [paper](https://arxiv.org/pdf/2103.15348.pdf) using the following BibTeX entry.
```
@article{shen2021layoutparser,
title={LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis},
author={Shen, Zejiang and Zhang, Ruochen and Dell, Melissa and Lee, Benjamin Charles Germain and Carlson, Jacob and Li, Weining},
journal={arXiv preprint arXiv:2103.15348},
year={2021}
}
```
%package -n python3-layoutparser
Summary: A unified toolkit for Deep Learning Based Document Image Analysis
Provides: python-layoutparser
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-layoutparser
## What is LayoutParser
LayoutParser aims to provide a wide range of tools that aims to streamline Document Image Analysis (DIA) tasks. Please check the LayoutParser [demo video](https://youtu.be/8yA5xB4Dg8c) (1 min) or [full talk](https://www.youtube.com/watch?v=YG0qepPgyGY) (15 min) for details. And here are some key features:
- LayoutParser provides a rich repository of deep learning models for layout detection as well as a set of unified APIs for using them. For example,
<details>
<summary>Perform DL layout detection in 4 lines of code</summary>
```python
import layoutparser as lp
model = lp.AutoLayoutModel('lp://EfficientDete/PubLayNet')
# image = Image.open("path/to/image")
layout = model.detect(image)
```
</details>
- LayoutParser comes with a set of layout data structures with carefully designed APIs that are optimized for document image analysis tasks. For example,
<details>
<summary>Selecting layout/textual elements in the left column of a page</summary>
```python
image_width = image.size[0]
left_column = lp.Interval(0, image_width/2, axis='x')
layout.filter_by(left_column, center=True) # select objects in the left column
```
</details>
<details>
<summary>Performing OCR for each detected Layout Region</summary>
```python
ocr_agent = lp.TesseractAgent()
for layout_region in layout:
image_segment = layout_region.crop(image)
text = ocr_agent.detect(image_segment)
```
</details>
<details>
<summary>Flexible APIs for visualizing the detected layouts</summary>
```python
lp.draw_box(image, layout, box_width=1, show_element_id=True, box_alpha=0.25)
```
</details>
</details>
<details>
<summary>Loading layout data stored in json, csv, and even PDFs</summary>
```python
layout = lp.load_json("path/to/json")
layout = lp.load_csv("path/to/csv")
pdf_layout = lp.load_pdf("path/to/pdf")
```
</details>
- LayoutParser is also a open platform that enables the sharing of layout detection models and DIA pipelines among the community.
<details>
<summary><a href="https://layout-parser.github.io/platform/">Check</a> the LayoutParser open platform</summary>
</details>
<details>
<summary><a href="https://github.com/Layout-Parser/platform">Submit</a> your models/pipelines to LayoutParser</summary>
</details>
## Installation
After several major updates, layoutparser provides various functionalities and deep learning models from different backends. But it still easy to install layoutparser, and we designed the installation method in a way such that you can choose to install only the needed dependencies for your project:
```bash
pip install layoutparser # Install the base layoutparser library with
pip install "layoutparser[layoutmodels]" # Install DL layout model toolkit
pip install "layoutparser[ocr]" # Install OCR toolkit
```
Extra steps are needed if you want to use Detectron2-based models. Please check [installation.md](installation.md) for additional details on layoutparser installation.
## Examples
We provide a series of examples for to help you start using the layout parser library:
1. [Table OCR and Results Parsing](https://github.com/Layout-Parser/layout-parser/blob/main/examples/OCR%20Tables%20and%20Parse%20the%20Output.ipynb): `layoutparser` can be used for conveniently OCR documents and convert the output in to structured data.
2. [Deep Layout Parsing Example](https://github.com/Layout-Parser/layout-parser/blob/main/examples/Deep%20Layout%20Parsing.ipynb): With the help of Deep Learning, `layoutparser` supports the analysis very complex documents and processing of the hierarchical structure in the layouts.
## Contributing
We encourage you to contribute to Layout Parser! Please check out the [Contributing guidelines](.github/CONTRIBUTING.md) for guidelines about how to proceed. Join us!
## Citing `layoutparser`
If you find `layoutparser` helpful to your work, please consider citing our tool and [paper](https://arxiv.org/pdf/2103.15348.pdf) using the following BibTeX entry.
```
@article{shen2021layoutparser,
title={LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis},
author={Shen, Zejiang and Zhang, Ruochen and Dell, Melissa and Lee, Benjamin Charles Germain and Carlson, Jacob and Li, Weining},
journal={arXiv preprint arXiv:2103.15348},
year={2021}
}
```
%package help
Summary: Development documents and examples for layoutparser
Provides: python3-layoutparser-doc
%description help
## What is LayoutParser
LayoutParser aims to provide a wide range of tools that aims to streamline Document Image Analysis (DIA) tasks. Please check the LayoutParser [demo video](https://youtu.be/8yA5xB4Dg8c) (1 min) or [full talk](https://www.youtube.com/watch?v=YG0qepPgyGY) (15 min) for details. And here are some key features:
- LayoutParser provides a rich repository of deep learning models for layout detection as well as a set of unified APIs for using them. For example,
<details>
<summary>Perform DL layout detection in 4 lines of code</summary>
```python
import layoutparser as lp
model = lp.AutoLayoutModel('lp://EfficientDete/PubLayNet')
# image = Image.open("path/to/image")
layout = model.detect(image)
```
</details>
- LayoutParser comes with a set of layout data structures with carefully designed APIs that are optimized for document image analysis tasks. For example,
<details>
<summary>Selecting layout/textual elements in the left column of a page</summary>
```python
image_width = image.size[0]
left_column = lp.Interval(0, image_width/2, axis='x')
layout.filter_by(left_column, center=True) # select objects in the left column
```
</details>
<details>
<summary>Performing OCR for each detected Layout Region</summary>
```python
ocr_agent = lp.TesseractAgent()
for layout_region in layout:
image_segment = layout_region.crop(image)
text = ocr_agent.detect(image_segment)
```
</details>
<details>
<summary>Flexible APIs for visualizing the detected layouts</summary>
```python
lp.draw_box(image, layout, box_width=1, show_element_id=True, box_alpha=0.25)
```
</details>
</details>
<details>
<summary>Loading layout data stored in json, csv, and even PDFs</summary>
```python
layout = lp.load_json("path/to/json")
layout = lp.load_csv("path/to/csv")
pdf_layout = lp.load_pdf("path/to/pdf")
```
</details>
- LayoutParser is also a open platform that enables the sharing of layout detection models and DIA pipelines among the community.
<details>
<summary><a href="https://layout-parser.github.io/platform/">Check</a> the LayoutParser open platform</summary>
</details>
<details>
<summary><a href="https://github.com/Layout-Parser/platform">Submit</a> your models/pipelines to LayoutParser</summary>
</details>
## Installation
After several major updates, layoutparser provides various functionalities and deep learning models from different backends. But it still easy to install layoutparser, and we designed the installation method in a way such that you can choose to install only the needed dependencies for your project:
```bash
pip install layoutparser # Install the base layoutparser library with
pip install "layoutparser[layoutmodels]" # Install DL layout model toolkit
pip install "layoutparser[ocr]" # Install OCR toolkit
```
Extra steps are needed if you want to use Detectron2-based models. Please check [installation.md](installation.md) for additional details on layoutparser installation.
## Examples
We provide a series of examples for to help you start using the layout parser library:
1. [Table OCR and Results Parsing](https://github.com/Layout-Parser/layout-parser/blob/main/examples/OCR%20Tables%20and%20Parse%20the%20Output.ipynb): `layoutparser` can be used for conveniently OCR documents and convert the output in to structured data.
2. [Deep Layout Parsing Example](https://github.com/Layout-Parser/layout-parser/blob/main/examples/Deep%20Layout%20Parsing.ipynb): With the help of Deep Learning, `layoutparser` supports the analysis very complex documents and processing of the hierarchical structure in the layouts.
## Contributing
We encourage you to contribute to Layout Parser! Please check out the [Contributing guidelines](.github/CONTRIBUTING.md) for guidelines about how to proceed. Join us!
## Citing `layoutparser`
If you find `layoutparser` helpful to your work, please consider citing our tool and [paper](https://arxiv.org/pdf/2103.15348.pdf) using the following BibTeX entry.
```
@article{shen2021layoutparser,
title={LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis},
author={Shen, Zejiang and Zhang, Ruochen and Dell, Melissa and Lee, Benjamin Charles Germain and Carlson, Jacob and Li, Weining},
journal={arXiv preprint arXiv:2103.15348},
year={2021}
}
```
%prep
%autosetup -n layoutparser-0.3.4
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-layoutparser -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 0.3.4-1
- Package Spec generated
|
