magic-pdf 0.8.1__py3-none-any.whl → 0.9.0__py3-none-any.whl
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.
- magic_pdf/config/__init__.py +0 -0
- magic_pdf/config/enums.py +7 -0
- magic_pdf/config/exceptions.py +32 -0
- magic_pdf/data/__init__.py +0 -0
- magic_pdf/data/data_reader_writer/__init__.py +12 -0
- magic_pdf/data/data_reader_writer/base.py +51 -0
- magic_pdf/data/data_reader_writer/filebase.py +59 -0
- magic_pdf/data/data_reader_writer/multi_bucket_s3.py +137 -0
- magic_pdf/data/data_reader_writer/s3.py +69 -0
- magic_pdf/data/dataset.py +194 -0
- magic_pdf/data/io/__init__.py +0 -0
- magic_pdf/data/io/base.py +42 -0
- magic_pdf/data/io/http.py +37 -0
- magic_pdf/data/io/s3.py +114 -0
- magic_pdf/data/read_api.py +95 -0
- magic_pdf/data/schemas.py +15 -0
- magic_pdf/data/utils.py +32 -0
- magic_pdf/dict2md/ocr_mkcontent.py +74 -234
- magic_pdf/libs/Constants.py +21 -8
- magic_pdf/libs/MakeContentConfig.py +1 -0
- magic_pdf/libs/boxbase.py +35 -0
- magic_pdf/libs/clean_memory.py +10 -0
- magic_pdf/libs/config_reader.py +53 -23
- magic_pdf/libs/draw_bbox.py +150 -65
- magic_pdf/libs/ocr_content_type.py +2 -0
- magic_pdf/libs/version.py +1 -1
- magic_pdf/model/doc_analyze_by_custom_model.py +77 -32
- magic_pdf/model/magic_model.py +331 -15
- magic_pdf/model/pdf_extract_kit.py +164 -80
- magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py +8 -1
- magic_pdf/model/ppTableModel.py +2 -2
- magic_pdf/model/pp_structure_v2.py +5 -2
- magic_pdf/model/v3/__init__.py +0 -0
- magic_pdf/model/v3/helpers.py +125 -0
- magic_pdf/para/para_split_v3.py +296 -0
- magic_pdf/pdf_parse_by_ocr.py +6 -3
- magic_pdf/pdf_parse_by_txt.py +6 -3
- magic_pdf/pdf_parse_union_core_v2.py +644 -0
- magic_pdf/pipe/AbsPipe.py +5 -1
- magic_pdf/pipe/OCRPipe.py +10 -4
- magic_pdf/pipe/TXTPipe.py +10 -4
- magic_pdf/pipe/UNIPipe.py +16 -7
- magic_pdf/pre_proc/ocr_detect_all_bboxes.py +83 -1
- magic_pdf/pre_proc/ocr_dict_merge.py +27 -2
- magic_pdf/resources/model_config/UniMERNet/demo.yaml +7 -7
- magic_pdf/resources/model_config/model_configs.yaml +5 -13
- magic_pdf/tools/cli.py +14 -1
- magic_pdf/tools/common.py +18 -8
- magic_pdf/user_api.py +25 -6
- magic_pdf/utils/__init__.py +0 -0
- magic_pdf/utils/annotations.py +11 -0
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/LICENSE.md +1 -0
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/METADATA +120 -75
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/RECORD +57 -33
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/WHEEL +0 -0
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/entry_points.txt +0 -0
- {magic_pdf-0.8.1.dist-info → magic_pdf-0.9.0.dist-info}/top_level.txt +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: magic-pdf
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.9.0
|
|
4
4
|
Summary: A practical tool for converting PDF to Markdown
|
|
5
5
|
Home-page: https://github.com/opendatalab/MinerU
|
|
6
6
|
Requires-Python: >=3.9
|
|
@@ -16,13 +16,15 @@ Requires-Dist: pdfminer.six==20231228
|
|
|
16
16
|
Requires-Dist: pydantic<2.8.0,>=2.7.2
|
|
17
17
|
Requires-Dist: PyMuPDF>=1.24.9
|
|
18
18
|
Requires-Dist: scikit-learn>=1.0.2
|
|
19
|
-
Requires-Dist:
|
|
19
|
+
Requires-Dist: torch<=2.3.1,>=2.2.2
|
|
20
|
+
Requires-Dist: transformers
|
|
20
21
|
Provides-Extra: full
|
|
21
|
-
Requires-Dist: unimernet==0.1
|
|
22
|
+
Requires-Dist: unimernet==0.2.1; extra == "full"
|
|
22
23
|
Requires-Dist: ultralytics; extra == "full"
|
|
23
24
|
Requires-Dist: paddleocr==2.7.3; extra == "full"
|
|
24
25
|
Requires-Dist: pypandoc; extra == "full"
|
|
25
26
|
Requires-Dist: struct-eqtable==0.1.0; extra == "full"
|
|
27
|
+
Requires-Dist: doclayout-yolo==0.0.2; extra == "full"
|
|
26
28
|
Requires-Dist: detectron2; extra == "full"
|
|
27
29
|
Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "full"
|
|
28
30
|
Requires-Dist: matplotlib; (platform_system == "Linux" or platform_system == "Darwin") and extra == "full"
|
|
@@ -53,7 +55,9 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
|
|
|
53
55
|
[](https://huggingface.co/spaces/opendatalab/MinerU)
|
|
54
56
|
[](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
|
|
55
57
|
[](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
|
|
56
|
-
|
|
58
|
+
|
|
59
|
+
[](https://arxiv.org/abs/2409.18839)
|
|
60
|
+
|
|
57
61
|
|
|
58
62
|
<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
|
|
59
63
|
|
|
@@ -76,6 +80,19 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
|
|
|
76
80
|
</div>
|
|
77
81
|
|
|
78
82
|
# Changelog
|
|
83
|
+
- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
|
|
84
|
+
- Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
|
|
85
|
+
- Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
|
|
86
|
+
- Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
|
|
87
|
+
- Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
|
|
88
|
+
- Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
|
|
89
|
+
- Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
|
|
90
|
+
- Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
|
|
91
|
+
- Integrated [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit):
|
|
92
|
+
- Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
|
|
93
|
+
- Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
|
|
94
|
+
- Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
|
|
95
|
+
- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
|
|
79
96
|
- 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
|
|
80
97
|
- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
|
|
81
98
|
- 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
|
|
@@ -103,6 +120,7 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
|
|
|
103
120
|
<ul>
|
|
104
121
|
<li><a href="#command-line">Command Line</a></li>
|
|
105
122
|
<li><a href="#api">API</a></li>
|
|
123
|
+
<li><a href="#deploy-derived-projects">Deploy Derived Projects</a></li>
|
|
106
124
|
<li><a href="#development-guide">Development Guide</a></li>
|
|
107
125
|
</ul>
|
|
108
126
|
</li>
|
|
@@ -134,15 +152,18 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
|
|
|
134
152
|
|
|
135
153
|
## Key Features
|
|
136
154
|
|
|
137
|
-
-
|
|
138
|
-
-
|
|
139
|
-
-
|
|
140
|
-
-
|
|
141
|
-
- Automatically
|
|
142
|
-
- Automatically
|
|
143
|
-
- Automatically
|
|
144
|
-
-
|
|
145
|
-
- Supports
|
|
155
|
+
- Remove headers, footers, footnotes, page numbers, etc., to ensure semantic coherence.
|
|
156
|
+
- Output text in human-readable order, suitable for single-column, multi-column, and complex layouts.
|
|
157
|
+
- Preserve the structure of the original document, including headings, paragraphs, lists, etc.
|
|
158
|
+
- Extract images, image descriptions, tables, table titles, and footnotes.
|
|
159
|
+
- Automatically recognize and convert formulas in the document to LaTeX format.
|
|
160
|
+
- Automatically recognize and convert tables in the document to LaTeX or HTML format.
|
|
161
|
+
- Automatically detect scanned PDFs and garbled PDFs and enable OCR functionality.
|
|
162
|
+
- OCR supports detection and recognition of 84 languages.
|
|
163
|
+
- Supports multiple output formats, such as multimodal and NLP Markdown, JSON sorted by reading order, and rich intermediate formats.
|
|
164
|
+
- Supports various visualization results, including layout visualization and span visualization, for efficient confirmation of output quality.
|
|
165
|
+
- Supports both CPU and GPU environments.
|
|
166
|
+
- Compatible with Windows, Linux, and Mac platforms.
|
|
146
167
|
|
|
147
168
|
## Quick Start
|
|
148
169
|
|
|
@@ -173,8 +194,8 @@ In non-mainline environments, due to the diversity of hardware and software conf
|
|
|
173
194
|
</tr>
|
|
174
195
|
<tr>
|
|
175
196
|
<td colspan="3">CPU</td>
|
|
176
|
-
<td>x86_64</td>
|
|
177
|
-
<td>x86_64</td>
|
|
197
|
+
<td>x86_64(unsupported ARM Linux)</td>
|
|
198
|
+
<td>x86_64(unsupported ARM Windows)</td>
|
|
178
199
|
<td>x86_64 / arm64</td>
|
|
179
200
|
</tr>
|
|
180
201
|
<tr>
|
|
@@ -183,7 +204,7 @@ In non-mainline environments, due to the diversity of hardware and software conf
|
|
|
183
204
|
</tr>
|
|
184
205
|
<tr>
|
|
185
206
|
<td colspan="3">Python Version</td>
|
|
186
|
-
<td colspan="3">3.10</td>
|
|
207
|
+
<td colspan="3">3.10(Please make sure to create a Python 3.10 virtual environment using conda)</td>
|
|
187
208
|
</tr>
|
|
188
209
|
<tr>
|
|
189
210
|
<td colspan="3">Nvidia Driver Version</td>
|
|
@@ -200,22 +221,24 @@ In non-mainline environments, due to the diversity of hardware and software conf
|
|
|
200
221
|
<tr>
|
|
201
222
|
<td rowspan="2">GPU Hardware Support List</td>
|
|
202
223
|
<td colspan="2">Minimum Requirement 8G+ VRAM</td>
|
|
203
|
-
<td colspan="2">3060ti/3070/
|
|
204
|
-
8G VRAM
|
|
224
|
+
<td colspan="2">3060ti/3070/4060<br>
|
|
225
|
+
8G VRAM enables layout, formula recognition acceleration and OCR acceleration</td>
|
|
205
226
|
<td rowspan="2">None</td>
|
|
206
227
|
</tr>
|
|
207
228
|
<tr>
|
|
208
|
-
<td colspan="2">Recommended Configuration
|
|
209
|
-
<td colspan="2">3090/3090ti/4070ti
|
|
210
|
-
|
|
211
|
-
24G or more can enable layout, formula recognition, OCR acceleration and table recognition simultaneously
|
|
229
|
+
<td colspan="2">Recommended Configuration 10G+ VRAM</td>
|
|
230
|
+
<td colspan="2">3080/3080ti/3090/3090ti/4070/4070ti/4070tisuper/4080/4090<br>
|
|
231
|
+
10G VRAM or more can enable layout, formula recognition, OCR acceleration and table recognition acceleration simultaneously
|
|
212
232
|
</td>
|
|
213
233
|
</tr>
|
|
214
234
|
</table>
|
|
215
235
|
|
|
216
236
|
### Online Demo
|
|
217
237
|
|
|
238
|
+
Stable Version (Stable version verified by QA):
|
|
218
239
|
[](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
|
|
240
|
+
|
|
241
|
+
Test Version (Synced with dev branch updates, testing new features):
|
|
219
242
|
[](https://huggingface.co/spaces/opendatalab/MinerU)
|
|
220
243
|
[](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
|
|
221
244
|
|
|
@@ -233,37 +256,32 @@ pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
|
|
|
233
256
|
|
|
234
257
|
Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for detailed instructions.
|
|
235
258
|
|
|
236
|
-
|
|
237
|
-
>
|
|
238
|
-
> Check if the model file sizes match the description on the webpage. If possible, use sha256 to verify the integrity of the files.
|
|
259
|
+
#### 3. Modify the Configuration File for Additional Configuration
|
|
239
260
|
|
|
240
|
-
|
|
261
|
+
After completing the [2. Download model weight files](#2-download-model-weight-files) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
|
|
262
|
+
You can find the `magic-pdf.json` file in your 【user directory】.
|
|
241
263
|
|
|
242
|
-
|
|
264
|
+
> The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
|
|
243
265
|
|
|
244
|
-
|
|
245
|
-
>
|
|
246
|
-
> The user directory for Windows is `C:\Users\YourUsername`, for Linux it is `/home/YourUsername`, and for macOS it is `/Users/YourUsername`.
|
|
266
|
+
You can modify certain configurations in this file to enable or disable features, such as table recognition:
|
|
247
267
|
|
|
248
|
-
```bash
|
|
249
|
-
cp magic-pdf.template.json ~/magic-pdf.json
|
|
250
|
-
```
|
|
251
|
-
|
|
252
|
-
Find the `magic-pdf.json` file in your user directory and configure the "models-dir" path to point to the directory where the model weight files were downloaded in [Step 2](#2-download-model-weight-files).
|
|
253
268
|
|
|
254
|
-
>
|
|
255
|
-
>
|
|
256
|
-
> On Windows, this path should include the drive letter and all backslashes (`\`) in the path should be replaced with forward slashes (`/`) to avoid syntax errors in the JSON file due to escape sequences.
|
|
257
|
-
>
|
|
258
|
-
> For example: If the models are stored in the "models" directory at the root of the D drive, the "model-dir" value should be `D:/models`.
|
|
269
|
+
> If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
|
|
259
270
|
|
|
260
271
|
```json
|
|
261
272
|
{
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
265
|
-
|
|
266
|
-
|
|
273
|
+
// other config
|
|
274
|
+
"layout-config": {
|
|
275
|
+
"model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
|
|
276
|
+
},
|
|
277
|
+
"formula-config": {
|
|
278
|
+
"mfd_model": "yolo_v8_mfd",
|
|
279
|
+
"mfr_model": "unimernet_small",
|
|
280
|
+
"enable": true // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
|
|
281
|
+
},
|
|
282
|
+
"table-config": {
|
|
283
|
+
"model": "tablemaster", // When using structEqTable, please change to "struct_eqtable".
|
|
284
|
+
"enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
|
|
267
285
|
"max_time": 400
|
|
268
286
|
}
|
|
269
287
|
}
|
|
@@ -301,13 +319,26 @@ Usage: magic-pdf [OPTIONS]
|
|
|
301
319
|
Options:
|
|
302
320
|
-v, --version display the version and exit
|
|
303
321
|
-p, --path PATH local pdf filepath or directory [required]
|
|
304
|
-
-o, --output-dir
|
|
305
|
-
-m, --method [ocr|txt|auto] the method for parsing pdf.
|
|
306
|
-
|
|
307
|
-
|
|
308
|
-
auto: automatically choose the
|
|
309
|
-
|
|
310
|
-
without method specified, auto will be used by
|
|
322
|
+
-o, --output-dir PATH output local directory [required]
|
|
323
|
+
-m, --method [ocr|txt|auto] the method for parsing pdf. ocr: using ocr
|
|
324
|
+
technique to extract information from pdf. txt:
|
|
325
|
+
suitable for the text-based pdf only and
|
|
326
|
+
outperform ocr. auto: automatically choose the
|
|
327
|
+
best method for parsing pdf from ocr and txt.
|
|
328
|
+
without method specified, auto will be used by
|
|
329
|
+
default.
|
|
330
|
+
-l, --lang TEXT Input the languages in the pdf (if known) to
|
|
331
|
+
improve OCR accuracy. Optional. You should
|
|
332
|
+
input "Abbreviation" with language form url: ht
|
|
333
|
+
tps://paddlepaddle.github.io/PaddleOCR/latest/en
|
|
334
|
+
/ppocr/blog/multi_languages.html#5-support-languages-
|
|
335
|
+
and-abbreviations
|
|
336
|
+
-d, --debug BOOLEAN Enables detailed debugging information during
|
|
337
|
+
the execution of the CLI commands.
|
|
338
|
+
-s, --start INTEGER The starting page for PDF parsing, beginning
|
|
339
|
+
from 0.
|
|
340
|
+
-e, --end INTEGER The ending page for PDF parsing, beginning from
|
|
341
|
+
0.
|
|
311
342
|
--help Show this message and exit.
|
|
312
343
|
|
|
313
344
|
|
|
@@ -324,11 +355,12 @@ The results will be saved in the `{some_output_dir}` directory. The output file
|
|
|
324
355
|
```text
|
|
325
356
|
├── some_pdf.md # markdown file
|
|
326
357
|
├── images # directory for storing images
|
|
327
|
-
├── some_pdf_layout.pdf # layout diagram
|
|
358
|
+
├── some_pdf_layout.pdf # layout diagram (Include layout reading order)
|
|
328
359
|
├── some_pdf_middle.json # MinerU intermediate processing result
|
|
329
360
|
├── some_pdf_model.json # model inference result
|
|
330
361
|
├── some_pdf_origin.pdf # original PDF file
|
|
331
|
-
|
|
362
|
+
├── some_pdf_spans.pdf # smallest granularity bbox position information diagram
|
|
363
|
+
└── some_pdf_content_list.json # Rich text JSON arranged in reading order
|
|
332
364
|
```
|
|
333
365
|
|
|
334
366
|
For more information about the output files, please refer to the [Output File Description](docs/output_file_en_us.md).
|
|
@@ -368,29 +400,38 @@ For detailed implementation, refer to:
|
|
|
368
400
|
- [demo.py Simplest Processing Method](demo/demo.py)
|
|
369
401
|
- [magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
|
|
370
402
|
|
|
403
|
+
### Deploy Derived Projects
|
|
404
|
+
|
|
405
|
+
Derived projects include secondary development projects based on MinerU by project developers and community developers,
|
|
406
|
+
such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
|
|
407
|
+
These projects may offer more features and a better user experience.
|
|
408
|
+
For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
|
|
409
|
+
|
|
410
|
+
|
|
371
411
|
### Development Guide
|
|
372
412
|
|
|
373
413
|
TODO
|
|
374
414
|
|
|
375
415
|
# TODO
|
|
376
416
|
|
|
377
|
-
-
|
|
378
|
-
-
|
|
379
|
-
-
|
|
380
|
-
-
|
|
381
|
-
- [
|
|
382
|
-
-
|
|
383
|
-
- [ ] Geometric shape recognition
|
|
417
|
+
- 🗹 Reading order based on the model
|
|
418
|
+
- 🗹 Recognition of `index` and `list` in the main text
|
|
419
|
+
- 🗹 Table recognition
|
|
420
|
+
- ☐ Code block recognition in the main text
|
|
421
|
+
- ☐ [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
|
|
422
|
+
- ☐ Geometric shape recognition
|
|
384
423
|
|
|
385
424
|
# Known Issues
|
|
386
425
|
|
|
387
|
-
- Reading order is
|
|
388
|
-
- Vertical text is not supported
|
|
389
|
-
-
|
|
390
|
-
-
|
|
391
|
-
-
|
|
392
|
-
-
|
|
393
|
-
|
|
426
|
+
- Reading order is determined by the model based on the spatial distribution of readable content, and may be out of order in some areas under extremely complex layouts.
|
|
427
|
+
- Vertical text is not supported.
|
|
428
|
+
- Tables of contents and lists are recognized through rules, and some uncommon list formats may not be recognized.
|
|
429
|
+
- Only one level of headings is supported; hierarchical headings are not currently supported.
|
|
430
|
+
- Code blocks are not yet supported in the layout model.
|
|
431
|
+
- Comic books, art albums, primary school textbooks, and exercises cannot be parsed well.
|
|
432
|
+
- Table recognition may result in row/column recognition errors in complex tables.
|
|
433
|
+
- OCR recognition may produce inaccurate characters in PDFs of lesser-known languages (e.g., diacritical marks in Latin script, easily confused characters in Arabic script).
|
|
434
|
+
- Some formulas may not render correctly in Markdown.
|
|
394
435
|
|
|
395
436
|
# FAQ
|
|
396
437
|
|
|
@@ -416,25 +457,29 @@ This project currently uses PyMuPDF to achieve advanced functionality. However,
|
|
|
416
457
|
- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
|
|
417
458
|
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
|
|
418
459
|
- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
|
|
460
|
+
- [layoutreader](https://github.com/ppaanngggg/layoutreader)
|
|
419
461
|
- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
|
|
420
462
|
- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
|
|
421
463
|
|
|
422
464
|
# Citation
|
|
423
465
|
|
|
424
466
|
```bibtex
|
|
467
|
+
@misc{wang2024mineruopensourcesolutionprecise,
|
|
468
|
+
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
|
|
469
|
+
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
|
|
470
|
+
year={2024},
|
|
471
|
+
eprint={2409.18839},
|
|
472
|
+
archivePrefix={arXiv},
|
|
473
|
+
primaryClass={cs.CV},
|
|
474
|
+
url={https://arxiv.org/abs/2409.18839},
|
|
475
|
+
}
|
|
476
|
+
|
|
425
477
|
@article{he2024opendatalab,
|
|
426
478
|
title={Opendatalab: Empowering general artificial intelligence with open datasets},
|
|
427
479
|
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
|
|
428
480
|
journal={arXiv preprint arXiv:2407.13773},
|
|
429
481
|
year={2024}
|
|
430
482
|
}
|
|
431
|
-
|
|
432
|
-
@misc{2024mineru,
|
|
433
|
-
title={MinerU: A One-stop, Open-source, High-quality Data Extraction Tool},
|
|
434
|
-
author={MinerU Contributors},
|
|
435
|
-
howpublished = {\url{https://github.com/opendatalab/MinerU}},
|
|
436
|
-
year={2024}
|
|
437
|
-
}
|
|
438
483
|
```
|
|
439
484
|
|
|
440
485
|
# Star History
|
|
@@ -1,11 +1,29 @@
|
|
|
1
1
|
magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
2
|
-
magic_pdf/pdf_parse_by_ocr.py,sha256=
|
|
3
|
-
magic_pdf/pdf_parse_by_txt.py,sha256=
|
|
2
|
+
magic_pdf/pdf_parse_by_ocr.py,sha256=E-AYHUXjzorFli0CEtmnAi09SI2STJ7FX58yjU0c9PI,810
|
|
3
|
+
magic_pdf/pdf_parse_by_txt.py,sha256=YeFYVAdfwF1CXOHq0LVE5131nqPHA14nt5t_sb-CMMk,709
|
|
4
4
|
magic_pdf/pdf_parse_union_core.py,sha256=AGIrP7ahc6Ycku0PxAlbjZhwqsdJ8iuRPIn-PFASKWY,11772
|
|
5
|
-
magic_pdf/
|
|
5
|
+
magic_pdf/pdf_parse_union_core_v2.py,sha256=18V8aYLz0gLQSMxGJDgUCWSltr15L8s8ClNqB17DNvw,23647
|
|
6
|
+
magic_pdf/user_api.py,sha256=gM-3RQYc6pMEsVvEPFXfWf5RBjAvHcUccugL6fXpP_U,3991
|
|
7
|
+
magic_pdf/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
8
|
+
magic_pdf/config/enums.py,sha256=CImYuw4sbKpq9zrj6zrrEvtdoGkjxDt8S8ByNVDpypU,89
|
|
9
|
+
magic_pdf/config/exceptions.py,sha256=87UX7gyUpj4HqjPcz2hLqdnYeImtDQAxOxj8oXZ_zkE,622
|
|
10
|
+
magic_pdf/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
11
|
+
magic_pdf/data/dataset.py,sha256=n8rGw1-wizABR8giSk_XWPCXzx3478u5DK2Z0wOCOeI,5089
|
|
12
|
+
magic_pdf/data/read_api.py,sha256=3fKLsEYAow5RwAmGFMMgvcCh0-_WEEHem2uewukjXOA,3570
|
|
13
|
+
magic_pdf/data/schemas.py,sha256=XSFNxyYbIWgU_Z4U0695elpGQP3J5dpq4Rlyr3S0O_s,595
|
|
14
|
+
magic_pdf/data/utils.py,sha256=dJZiqygwNier0UG5tbt5jAPjgwcnfsAN6-m-G1kVPLQ,917
|
|
15
|
+
magic_pdf/data/data_reader_writer/__init__.py,sha256=QtevUaeSivv9dQKi3Tomfn4Z0E4To0cB8qXTnglxaHc,705
|
|
16
|
+
magic_pdf/data/data_reader_writer/base.py,sha256=gUrHCMTHYBrWpqgHdIc-hN7HHwUC2ApK_VXrDUrnfdg,1320
|
|
17
|
+
magic_pdf/data/data_reader_writer/filebase.py,sha256=21RYy4m9MqJGqwd2HWICQJHM-PZXp7UYETCQQK390Kk,1988
|
|
18
|
+
magic_pdf/data/data_reader_writer/multi_bucket_s3.py,sha256=BY3faRfZTg27kfkaI4iXPjgFW_RecN0am9r9z2RuYgY,5582
|
|
19
|
+
magic_pdf/data/data_reader_writer/s3.py,sha256=4tT_hcb5I1m-qojNP2CAUKGOoWBH2ripKQmBa9_dAfg,2096
|
|
20
|
+
magic_pdf/data/io/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
21
|
+
magic_pdf/data/io/base.py,sha256=So3G_Kndunfs0f9nn3l9dRJG_7N09CX0JbFqYEvyaRI,1113
|
|
22
|
+
magic_pdf/data/io/http.py,sha256=XlKB0DNf4a_uUnfgcclvaaOtmE7lmddx0DnK8A-emAM,958
|
|
23
|
+
magic_pdf/data/io/s3.py,sha256=hyA7sbNriQy64xd_uyJ7acN_oneQ1Pdmoc7_xcvkue8,3606
|
|
6
24
|
magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
7
25
|
magic_pdf/dict2md/mkcontent.py,sha256=rWUY-2opd0jeowEUEVOV_uWcKum1Q7ng4nOoT6-ka_s,17459
|
|
8
|
-
magic_pdf/dict2md/ocr_mkcontent.py,sha256=
|
|
26
|
+
magic_pdf/dict2md/ocr_mkcontent.py,sha256=eMd3qOIh21cZgTl-LMLGh42uxDMpHU2nwE6iA6b_qrA,11915
|
|
9
27
|
magic_pdf/filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
10
28
|
magic_pdf/filter/pdf_classify_by_type.py,sha256=spmDO-f2ihAl1d6-EP-j271Yi50oyu6mw4X2kRd_m0s,42320
|
|
11
29
|
magic_pdf/filter/pdf_meta_scan.py,sha256=5R2XDiBZw0xd4ugbDxuyk6fztGlT5jFsGN85hLvo-hQ,17390
|
|
@@ -20,18 +38,19 @@ magic_pdf/layout/layout_det_utils.py,sha256=NCYBTvsrULE3Cue53aMD1MfXTmOL9Xy0nivl
|
|
|
20
38
|
magic_pdf/layout/layout_sort.py,sha256=jtacQVcxnuYAksvEqtS0DH-v6U8qyjX-jmyZgDJ-egA,37005
|
|
21
39
|
magic_pdf/layout/layout_spiler_recog.py,sha256=QjBSgB-a7J2yjUR1eaCs9ZD7URtiRnV6W934hpAeuC4,3067
|
|
22
40
|
magic_pdf/layout/mcol_sort.py,sha256=ADnLisBJBHXDKYChcf2lzTb_TC_vZ4q89_CSN8mwEJc,11331
|
|
23
|
-
magic_pdf/libs/Constants.py,sha256=
|
|
24
|
-
magic_pdf/libs/MakeContentConfig.py,sha256=
|
|
41
|
+
magic_pdf/libs/Constants.py,sha256=u9i-ivxxcGp7Hu_zvrLA1jdPcEnYhPb7wXOSUaOSwGQ,1140
|
|
42
|
+
magic_pdf/libs/MakeContentConfig.py,sha256=Do5VKNQp3gfUKyhrZStfzfBj7l-vbsYpsJFF1SsmEc0,248
|
|
25
43
|
magic_pdf/libs/ModelBlockTypeEnum.py,sha256=kalXPbo5ya6hKhhBHPGlHl1yjWOURoXZWQM3rVUyPsY,164
|
|
26
44
|
magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
27
|
-
magic_pdf/libs/boxbase.py,sha256=
|
|
45
|
+
magic_pdf/libs/boxbase.py,sha256=ELMHWolgWROxOAQDgwmL7VS5kveZp4ifvEzRmPul2Ws,16925
|
|
28
46
|
magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
|
|
47
|
+
magic_pdf/libs/clean_memory.py,sha256=BIOmEWuwR7c_p4OwTSW2muE3PRaGhmOplS-wTXt_EXk,211
|
|
29
48
|
magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
|
|
30
|
-
magic_pdf/libs/config_reader.py,sha256=
|
|
49
|
+
magic_pdf/libs/config_reader.py,sha256=0uMOTSZE2crvqdGj2j21tlwV0nNRZha44Y9X98gQ3AQ,4067
|
|
31
50
|
magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
|
|
32
51
|
magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
|
|
33
52
|
magic_pdf/libs/detect_language_from_model.py,sha256=Uln8F9qs8EJOw4EgI7KRlaU3lD_mK8KMTlADLFtz8fk,816
|
|
34
|
-
magic_pdf/libs/draw_bbox.py,sha256=
|
|
53
|
+
magic_pdf/libs/draw_bbox.py,sha256=J_RaG6sRkqNyUd75NiWbDk-3LIE8es-zNIbcwR9myvo,17196
|
|
35
54
|
magic_pdf/libs/drop_reason.py,sha256=IfjPSrPLMmVziqjOXPep7r_ioQKFRahDgbOW1SD-Tuw,2148
|
|
36
55
|
magic_pdf/libs/drop_tag.py,sha256=bZDg3bIVWvBT1Ec1icwj5WLOkt5-hI6eRYZ2tX9_a74,673
|
|
37
56
|
magic_pdf/libs/hash_utils.py,sha256=VEKK9WfFoZgrPfi8kfITjLpr8Ahufs8tXh9R1Y5lAL8,404
|
|
@@ -40,21 +59,21 @@ magic_pdf/libs/language.py,sha256=Hj5-lrGoNExxdHLbkcNG-c27U4AjJ9AZPdZblaNSehU,10
|
|
|
40
59
|
magic_pdf/libs/local_math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
|
|
41
60
|
magic_pdf/libs/markdown_utils.py,sha256=cLxLXjRhrNp_wCHvtglrGA_FVdrvfd1KULeTtj1p18w,944
|
|
42
61
|
magic_pdf/libs/nlp_utils.py,sha256=-X9W3-Ns5ZdDYFvyyEq6i6P2b5hCATaFEZeOjwNOH9M,6901
|
|
43
|
-
magic_pdf/libs/ocr_content_type.py,sha256=
|
|
62
|
+
magic_pdf/libs/ocr_content_type.py,sha256=e_7RBTdShaWvWhMO2SFou7GM521elMH_Jtn5usbHWdY,890
|
|
44
63
|
magic_pdf/libs/path_utils.py,sha256=Hykw_l5CU736b2egHV9P7B-qh3QNKO4nZSGCbsi0Z8E,1043
|
|
45
64
|
magic_pdf/libs/pdf_check.py,sha256=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2145
|
|
46
65
|
magic_pdf/libs/pdf_image_tools.py,sha256=CAd01giTKr_UJz1_QtDOARG9G9z69GFpzRZwcWSfLtE,1282
|
|
47
66
|
magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
|
|
48
67
|
magic_pdf/libs/textbase.py,sha256=SC1Frhz3Fb7V7n2SFRBsl7Bmg0JZdlvZskq0lfW1vIk,732
|
|
49
|
-
magic_pdf/libs/version.py,sha256=
|
|
68
|
+
magic_pdf/libs/version.py,sha256=H9NWRZb7NbeRRPLP_V1fARmLNXranorVM-OOY-8_2ug,22
|
|
50
69
|
magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
|
|
51
70
|
magic_pdf/model/__init__.py,sha256=1QcfMKET0xQhSaZMjNQHi_TjzSSDR6PI5mjkmaXHPe8,52
|
|
52
|
-
magic_pdf/model/doc_analyze_by_custom_model.py,sha256=
|
|
53
|
-
magic_pdf/model/magic_model.py,sha256=
|
|
71
|
+
magic_pdf/model/doc_analyze_by_custom_model.py,sha256=eYrtOIlFqw8O95ShoCTaAhLBHk7TXc5DGif93VikW4s,6977
|
|
72
|
+
magic_pdf/model/magic_model.py,sha256=RKJOruUGAV1lHcGqSlCDbkJn5kutb3fphDreOHASPQg,43505
|
|
54
73
|
magic_pdf/model/model_list.py,sha256=tJ9jtMB93HGx8Rmt8wmQSDFXZBUIPQrwaaYsep4luTM,183
|
|
55
|
-
magic_pdf/model/pdf_extract_kit.py,sha256=
|
|
56
|
-
magic_pdf/model/ppTableModel.py,sha256=
|
|
57
|
-
magic_pdf/model/pp_structure_v2.py,sha256=
|
|
74
|
+
magic_pdf/model/pdf_extract_kit.py,sha256=qlZANx8DErfSyaPHlOYNYW_Qp50dAEX_4jG8N3coDmM,21317
|
|
75
|
+
magic_pdf/model/ppTableModel.py,sha256=Qm5vy6v5aw2wwO5aZTyVr-r1sr3Pi9ManG86WZvfvEo,2697
|
|
76
|
+
magic_pdf/model/pp_structure_v2.py,sha256=BKPN7W4BjG0eWPAPjPEac1RMnb5eIzmAz4E4Rq-9b1U,3019
|
|
58
77
|
magic_pdf/model/pek_sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
59
78
|
magic_pdf/model/pek_sub_modules/post_process.py,sha256=HzRxV2sVR3Qo8XKYEHhT6tae-bYTb6dnAfGP6gfVNaM,1135
|
|
60
79
|
magic_pdf/model/pek_sub_modules/self_modify.py,sha256=NGUr8t4bXSeh38hwrfs6qxhf0IW-f3J96bnrg1xw8BA,14281
|
|
@@ -78,8 +97,10 @@ magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/configur
|
|
|
78
97
|
magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
|
|
79
98
|
magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
|
|
80
99
|
magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
|
|
81
|
-
magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py,sha256=
|
|
100
|
+
magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py,sha256=qtAkShYlXBrrkRWHvgAy3y9SEBtMRYVIvI3CASTuLHU,1069
|
|
82
101
|
magic_pdf/model/pek_sub_modules/structeqtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
102
|
+
magic_pdf/model/v3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
103
|
+
magic_pdf/model/v3/helpers.py,sha256=IVUFcNMDF3-kio-BIxjppHnWS3eHPqvvNihIw2fbIFM,4372
|
|
83
104
|
magic_pdf/para/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
84
105
|
magic_pdf/para/block_continuation_processor.py,sha256=IkReB5hirjm0OAirNzQQpnWe2f2bdP3Hug3Ef8qTRDA,22749
|
|
85
106
|
magic_pdf/para/block_termination_processor.py,sha256=YU3ZYqJy9e3OQmOuQYZrR6AUpmAlQ0mhj0PgZZPZ_fM,17957
|
|
@@ -91,13 +112,14 @@ magic_pdf/para/layout_match_processor.py,sha256=yr4FEO7GJ502udShqGRqIJQ_FQxoa0aG
|
|
|
91
112
|
magic_pdf/para/para_pipeline.py,sha256=zLaCHI9jLi1UPzh0lHP44mUjpKVTHS0gE_5YrkjVqEY,11796
|
|
92
113
|
magic_pdf/para/para_split.py,sha256=-UJM2jREW_2h3ZlJAU7dRD8bK3CMGKuhJrfgqv3Auvk,31310
|
|
93
114
|
magic_pdf/para/para_split_v2.py,sha256=ZIiLzpvVL364x1zcEG9IbT6ARJ-6JnWLIVrsDmf4w1M,36878
|
|
115
|
+
magic_pdf/para/para_split_v3.py,sha256=vHHswSAcTpXqnaEAbGEbt2g96YLh9eh839HdRNilDT8,13378
|
|
94
116
|
magic_pdf/para/raw_processor.py,sha256=mHxD9FrdOSXH7NqM41s55URyCyuyACvm9kKtowkIb3k,6317
|
|
95
117
|
magic_pdf/para/stats.py,sha256=-6Pf9Y8jkP1uJOYWiHUjw9Lb-Fb9GY7MHr_ok7x2GX0,9731
|
|
96
118
|
magic_pdf/para/title_processor.py,sha256=pYZv9vEkIjAtCz8jIUtl9AVUy_ib5SdAZmMVoZtsMRI,38593
|
|
97
|
-
magic_pdf/pipe/AbsPipe.py,sha256=
|
|
98
|
-
magic_pdf/pipe/OCRPipe.py,sha256=
|
|
99
|
-
magic_pdf/pipe/TXTPipe.py,sha256=
|
|
100
|
-
magic_pdf/pipe/UNIPipe.py,sha256=
|
|
119
|
+
magic_pdf/pipe/AbsPipe.py,sha256=jpJD-8S5K89bCxI4FY2_tMKGV1lghlbtmpOeJXqEhz0,4487
|
|
120
|
+
magic_pdf/pipe/OCRPipe.py,sha256=TswwfMkAYP-fpfsBoNIArtcCoNEqzCQCVWfwR4n8G-E,2159
|
|
121
|
+
magic_pdf/pipe/TXTPipe.py,sha256=zcsiOreOHJBtaeYgEc5yGKMSiNzBED8HcsD7NGu5RaY,2218
|
|
122
|
+
magic_pdf/pipe/UNIPipe.py,sha256=3ytYHoyTboHUGlRQpfyITiAP_mYXTOBjqy7wYHoUHpE,4944
|
|
101
123
|
magic_pdf/pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
102
124
|
magic_pdf/post_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
103
125
|
magic_pdf/post_proc/detect_para.py,sha256=5LX86ueHQGOV9CNimAxqZH4R3KTi78leum1de_Na0pw,126181
|
|
@@ -119,9 +141,9 @@ magic_pdf/pre_proc/equations_replace.py,sha256=fXj7ZV7F3YtkDYrAhE9g5tHk4_3pVUyLb
|
|
|
119
141
|
magic_pdf/pre_proc/fix_image.py,sha256=5MOfkXc8abfIp49g-68vll40wwTUZ5tcQ2gtsJuFmvs,11486
|
|
120
142
|
magic_pdf/pre_proc/fix_table.py,sha256=20sqJe27fAXcL7_C0qQ9mpsggmH37WuX-wPYWyRgACA,13227
|
|
121
143
|
magic_pdf/pre_proc/main_text_font.py,sha256=1gkjvPuBdKC4oVFkLvnRm2zghsLtVlfAEMKXouyVonM,1048
|
|
122
|
-
magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=
|
|
144
|
+
magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=omR2aOQNerKmKUF13CFP5-Z6Hv4GZztmsAQgLpHiugc,11341
|
|
123
145
|
magic_pdf/pre_proc/ocr_detect_layout.py,sha256=DW0_HXzmcbW22cXKIYFsyZNFh8mEjSHXIFVjXndJsvQ,5878
|
|
124
|
-
magic_pdf/pre_proc/ocr_dict_merge.py,sha256=
|
|
146
|
+
magic_pdf/pre_proc/ocr_dict_merge.py,sha256=KyXSW36lJ1PsK816J55vVQQtXTWODX1xG1_DvA7pOSo,14248
|
|
125
147
|
magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=jqBheXF8EuYCfS9tn6typr-aE57nfMoeBC36J5GjpbQ,11519
|
|
126
148
|
magic_pdf/pre_proc/pdf_pre_filter.py,sha256=FIMwe8Lei9LI2RmkqiaSyTHV5b7ViADbpyBwgVwZH-c,2687
|
|
127
149
|
magic_pdf/pre_proc/post_layout_split.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -133,8 +155,8 @@ magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=bJiegofPUeDyi--oZjfipQ5Q5RLm6
|
|
|
133
155
|
magic_pdf/pre_proc/solve_line_alien.py,sha256=aNoQptPcC38Sm1I2ABhgw8jeH_5kjsRHx3VYlFFtm1g,853
|
|
134
156
|
magic_pdf/pre_proc/statistics.py,sha256=_9jGlXq0iXd03UMxB92ZqCiu7cjNkG5vHvFlTF_9ytA,220
|
|
135
157
|
magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
|
|
136
|
-
magic_pdf/resources/model_config/model_configs.yaml,sha256=
|
|
137
|
-
magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=
|
|
158
|
+
magic_pdf/resources/model_config/model_configs.yaml,sha256=muwPuO6C8Z5oEStE-wWEt7vmkenmJiqTbkRfUfle_vU,257
|
|
159
|
+
magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=Jdaim2D2lAYrV9rhc1X5Sy2_IacGOrfysJhxEUgSElo,827
|
|
138
160
|
magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=9aNAEYgpHTAWpcUrDvuPG2y4V-Qw8QdcJefi96y8yDU,6109
|
|
139
161
|
magic_pdf/rw/AbsReaderWriter.py,sha256=2H5SDJfAAOX9kPfel06a8VRCHxD1Y8aPbWEkQDdn9JM,452
|
|
140
162
|
magic_pdf/rw/DiskReaderWriter.py,sha256=7ZAekH8V6xlBo_1WeSZ6sNwAj2WGPtjNl50zq1CoMDY,2614
|
|
@@ -143,12 +165,14 @@ magic_pdf/rw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
|
143
165
|
magic_pdf/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
144
166
|
magic_pdf/spark/spark_api.py,sha256=eSLXTjMYW5Ya41VMIApRVfji1ZxEZXdH9ZdsL6fy5Kw,1131
|
|
145
167
|
magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
146
|
-
magic_pdf/tools/cli.py,sha256=
|
|
168
|
+
magic_pdf/tools/cli.py,sha256=yl2E-DYxBN3XF7bWOBseYxptbmeE7tXWpwV-sp2aGIE,3140
|
|
147
169
|
magic_pdf/tools/cli_dev.py,sha256=3e5eyCQEt_EujXZu5fUAWr_W-YQQVqS9pB0Qgw7t1D8,4122
|
|
148
|
-
magic_pdf/tools/common.py,sha256=
|
|
149
|
-
magic_pdf
|
|
150
|
-
magic_pdf
|
|
151
|
-
magic_pdf-0.
|
|
152
|
-
magic_pdf-0.
|
|
153
|
-
magic_pdf-0.
|
|
154
|
-
magic_pdf-0.
|
|
170
|
+
magic_pdf/tools/common.py,sha256=2S8N60pcA6bFqAmdchoEmn22l9ntQxEfyaKpxfCKJ-Y,5465
|
|
171
|
+
magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
172
|
+
magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
|
|
173
|
+
magic_pdf-0.9.0.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
|
|
174
|
+
magic_pdf-0.9.0.dist-info/METADATA,sha256=DPanG2IP5v1TNR6Qyto-UqZ53IOA09lNCQpMyjguJ_k,39420
|
|
175
|
+
magic_pdf-0.9.0.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
|
|
176
|
+
magic_pdf-0.9.0.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
|
|
177
|
+
magic_pdf-0.9.0.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
|
|
178
|
+
magic_pdf-0.9.0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|