grobid-client-python 0.0.16__tar.gz → 0.0.17__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.
Files changed (42) hide show
  1. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/PKG-INFO +36 -36
  2. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/Readme.md +35 -35
  3. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client/grobid_client.py +1 -1
  4. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/PKG-INFO +36 -36
  5. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/pyproject.toml +1 -1
  6. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/.github/workflows/ci-build.yml +0 -0
  7. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/.github/workflows/ci-release.yml +0 -0
  8. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/.gitignore +0 -0
  9. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/LICENSE +0 -0
  10. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/MANIFEST.in +0 -0
  11. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/config.json +0 -0
  12. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/example.py +0 -0
  13. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client/__init__.py +0 -0
  14. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client/client.py +0 -0
  15. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/SOURCES.txt +0 -0
  16. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/dependency_links.txt +0 -0
  17. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/entry_points.txt +0 -0
  18. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/requires.txt +0 -0
  19. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/grobid_client_python.egg-info/top_level.txt +0 -0
  20. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/pytest.ini +0 -0
  21. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/requirements.txt +0 -0
  22. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/20180928112135.png +0 -0
  23. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/20180928112138.csv +0 -0
  24. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_out/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml +0 -0
  25. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_out/test_1/0f318087-b211-4ace-8ac9-3d9372a73c1c.tei.xml +0 -0
  26. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf +0 -0
  27. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml +0 -0
  28. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-1.txt +0 -0
  29. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-2.txt +0 -0
  30. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-3.txt +0 -0
  31. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-4.txt +0 -0
  32. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-5.txt +0 -0
  33. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-6.txt +0 -0
  34. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/resources/test_txt/reference-strings-7.txt +0 -0
  35. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/setup.cfg +0 -0
  36. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/__init__.py +0 -0
  37. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/conftest.py +0 -0
  38. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/run_tests.py +0 -0
  39. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/test_client.py +0 -0
  40. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/test_config.json +0 -0
  41. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/test_grobid_client.py +0 -0
  42. {grobid_client_python-0.0.16 → grobid_client_python-0.0.17}/tests/test_integration.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: grobid-client-python
3
- Version: 0.0.16
3
+ Version: 0.0.17
4
4
  Summary: Simple python client for GROBID REST services
5
5
  Author-email: Patrice Lopez <patrice.lopez@science-miner.com>
6
6
  Maintainer-email: Patrice Lopez <patrice.lopez@science-miner.com>, Luca Foppiano <lucanoro@duck.com>
@@ -254,7 +254,7 @@ A simple, efficient Python client for [GROBID](https://github.com/kermitt2/grobi
254
254
  - Local installation: [GROBID Documentation](http://grobid.readthedocs.io/)
255
255
  - Docker: `docker run -t --rm -p 8070:8070 lfoppiano/grobid:0.8.2`
256
256
  - Default server: `http://localhost:8070`
257
- - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply)
257
+ - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply), more details [here](https://grobid.readthedocs.io/en/latest/getting_started/#using-grobid-from-the-cloud).
258
258
 
259
259
  > [!IMPORTANT]
260
260
  > GROBID supports Windows only through Docker containers. See the [Docker documentation](https://grobid.readthedocs.io/en/latest/Grobid-docker/) for details.
@@ -314,39 +314,39 @@ grobid_client [OPTIONS] SERVICE
314
314
 
315
315
  #### Available Services
316
316
 
317
- | Service | Description | Input Format |
318
- |---------|-------------|--------------|
319
- | `processFulltextDocument` | Extract full document structure | PDF files |
320
- | `processHeaderDocument` | Extract document metadata | PDF files |
321
- | `processReferences` | Extract bibliographic references | PDF files |
322
- | `processCitationList` | Parse citation strings | Text files (one citation per line) |
323
- | `processCitationPatentST36` | Process patent citations | XML ST36 format |
324
- | `processCitationPatentPDF` | Process patent PDFs | PDF files |
317
+ | Service | Description | Input Format |
318
+ |-----------------------------|-----------------------------------|------------------------------------|
319
+ | `processFulltextDocument` | Extract full document structure | PDF files |
320
+ | `processHeaderDocument` | Extract document metadata | PDF files |
321
+ | `processReferences` | Extract bibliographic references | PDF files |
322
+ | `processCitationList` | Parse citation strings | Text files (one citation per line) |
323
+ | `processCitationPatentST36` | Process patent citations | XML ST36 format |
324
+ | `processCitationPatentPDF` | Process patent PDFs | PDF files |
325
325
 
326
326
  #### Common Options
327
327
 
328
- | Option | Description | Default |
329
- |--------|-------------|---------|
330
- | `--input` | Input directory path | Required |
331
- | `--output` | Output directory path | Same as input |
332
- | `--server` | GROBID server URL | `http://localhost:8070` |
333
- | `--n` | Concurrency level | 10 |
334
- | `--config` | Config file path | Optional |
335
- | `--force` | Overwrite existing files | False |
336
- | `--verbose` | Enable verbose logging | False |
328
+ | Option | Description | Default |
329
+ |-------------|--------------------------|-------------------------|
330
+ | `--input` | Input directory path | Required |
331
+ | `--output` | Output directory path | Same as input |
332
+ | `--server` | GROBID server URL | `http://localhost:8070` |
333
+ | `--n` | Concurrency level | 10 |
334
+ | `--config` | Config file path | Optional |
335
+ | `--force` | Overwrite existing files | False |
336
+ | `--verbose` | Enable verbose logging | False |
337
337
 
338
338
  #### Processing Options
339
339
 
340
- | Option | Description |
341
- |--------|-------------|
342
- | `--generateIDs` | Generate random XML IDs |
343
- | `--consolidate_header` | Consolidate header metadata |
344
- | `--consolidate_citations` | Consolidate bibliographic references |
345
- | `--include_raw_citations` | Include raw citation text |
346
- | `--include_raw_affiliations` | Include raw affiliation text |
347
- | `--teiCoordinates` | Add PDF coordinates to XML |
348
- | `--segmentSentences` | Segment sentences with coordinates |
349
- | `--flavor` | Processing flavor for fulltext extraction |
340
+ | Option | Description |
341
+ |------------------------------|-------------------------------------------|
342
+ | `--generateIDs` | Generate random XML IDs |
343
+ | `--consolidate_header` | Consolidate header metadata |
344
+ | `--consolidate_citations` | Consolidate bibliographic references |
345
+ | `--include_raw_citations` | Include raw citation text |
346
+ | `--include_raw_affiliations` | Include raw affiliation text |
347
+ | `--teiCoordinates` | Add PDF coordinates to XML |
348
+ | `--segmentSentences` | Segment sentences with coordinates |
349
+ | `--flavor` | Processing flavor for fulltext extraction |
350
350
 
351
351
  #### Examples
352
352
 
@@ -430,13 +430,13 @@ Configuration can be provided via a JSON file. When using the CLI, the `--server
430
430
 
431
431
  ### Configuration Parameters
432
432
 
433
- | Parameter | Description | Default |
434
- |-----------|-------------|---------|
435
- | `grobid_server` | GROBID server URL | `http://localhost:8070` |
436
- | `batch_size` | Thread pool size | 1000 |
437
- | `sleep_time` | Wait time when server is busy (seconds) | 5 |
438
- | `timeout` | Client-side timeout (seconds) | 60 |
439
- | `coordinates` | XML elements for coordinate extraction | See above |
433
+ | Parameter | Description | Default |
434
+ |-----------------|------------------------------------------------------------------------------------------------------------------|-------------------------|
435
+ | `grobid_server` | GROBID server URL | `http://localhost:8070` |
436
+ | `batch_size` | Thread pool size. **Tune carefully: a large batch size will result in the data being written less frequently** | 1000 |
437
+ | `sleep_time` | Wait time when server is busy (seconds) | 5 |
438
+ | `timeout` | Client-side timeout (seconds) | 180 |
439
+ | `coordinates` | XML elements for coordinate extraction | See above |
440
440
 
441
441
  > [!TIP]
442
442
  > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration is provided.
@@ -38,7 +38,7 @@ A simple, efficient Python client for [GROBID](https://github.com/kermitt2/grobi
38
38
  - Local installation: [GROBID Documentation](http://grobid.readthedocs.io/)
39
39
  - Docker: `docker run -t --rm -p 8070:8070 lfoppiano/grobid:0.8.2`
40
40
  - Default server: `http://localhost:8070`
41
- - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply)
41
+ - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply), more details [here](https://grobid.readthedocs.io/en/latest/getting_started/#using-grobid-from-the-cloud).
42
42
 
43
43
  > [!IMPORTANT]
44
44
  > GROBID supports Windows only through Docker containers. See the [Docker documentation](https://grobid.readthedocs.io/en/latest/Grobid-docker/) for details.
@@ -98,39 +98,39 @@ grobid_client [OPTIONS] SERVICE
98
98
 
99
99
  #### Available Services
100
100
 
101
- | Service | Description | Input Format |
102
- |---------|-------------|--------------|
103
- | `processFulltextDocument` | Extract full document structure | PDF files |
104
- | `processHeaderDocument` | Extract document metadata | PDF files |
105
- | `processReferences` | Extract bibliographic references | PDF files |
106
- | `processCitationList` | Parse citation strings | Text files (one citation per line) |
107
- | `processCitationPatentST36` | Process patent citations | XML ST36 format |
108
- | `processCitationPatentPDF` | Process patent PDFs | PDF files |
101
+ | Service | Description | Input Format |
102
+ |-----------------------------|-----------------------------------|------------------------------------|
103
+ | `processFulltextDocument` | Extract full document structure | PDF files |
104
+ | `processHeaderDocument` | Extract document metadata | PDF files |
105
+ | `processReferences` | Extract bibliographic references | PDF files |
106
+ | `processCitationList` | Parse citation strings | Text files (one citation per line) |
107
+ | `processCitationPatentST36` | Process patent citations | XML ST36 format |
108
+ | `processCitationPatentPDF` | Process patent PDFs | PDF files |
109
109
 
110
110
  #### Common Options
111
111
 
112
- | Option | Description | Default |
113
- |--------|-------------|---------|
114
- | `--input` | Input directory path | Required |
115
- | `--output` | Output directory path | Same as input |
116
- | `--server` | GROBID server URL | `http://localhost:8070` |
117
- | `--n` | Concurrency level | 10 |
118
- | `--config` | Config file path | Optional |
119
- | `--force` | Overwrite existing files | False |
120
- | `--verbose` | Enable verbose logging | False |
112
+ | Option | Description | Default |
113
+ |-------------|--------------------------|-------------------------|
114
+ | `--input` | Input directory path | Required |
115
+ | `--output` | Output directory path | Same as input |
116
+ | `--server` | GROBID server URL | `http://localhost:8070` |
117
+ | `--n` | Concurrency level | 10 |
118
+ | `--config` | Config file path | Optional |
119
+ | `--force` | Overwrite existing files | False |
120
+ | `--verbose` | Enable verbose logging | False |
121
121
 
122
122
  #### Processing Options
123
123
 
124
- | Option | Description |
125
- |--------|-------------|
126
- | `--generateIDs` | Generate random XML IDs |
127
- | `--consolidate_header` | Consolidate header metadata |
128
- | `--consolidate_citations` | Consolidate bibliographic references |
129
- | `--include_raw_citations` | Include raw citation text |
130
- | `--include_raw_affiliations` | Include raw affiliation text |
131
- | `--teiCoordinates` | Add PDF coordinates to XML |
132
- | `--segmentSentences` | Segment sentences with coordinates |
133
- | `--flavor` | Processing flavor for fulltext extraction |
124
+ | Option | Description |
125
+ |------------------------------|-------------------------------------------|
126
+ | `--generateIDs` | Generate random XML IDs |
127
+ | `--consolidate_header` | Consolidate header metadata |
128
+ | `--consolidate_citations` | Consolidate bibliographic references |
129
+ | `--include_raw_citations` | Include raw citation text |
130
+ | `--include_raw_affiliations` | Include raw affiliation text |
131
+ | `--teiCoordinates` | Add PDF coordinates to XML |
132
+ | `--segmentSentences` | Segment sentences with coordinates |
133
+ | `--flavor` | Processing flavor for fulltext extraction |
134
134
 
135
135
  #### Examples
136
136
 
@@ -214,13 +214,13 @@ Configuration can be provided via a JSON file. When using the CLI, the `--server
214
214
 
215
215
  ### Configuration Parameters
216
216
 
217
- | Parameter | Description | Default |
218
- |-----------|-------------|---------|
219
- | `grobid_server` | GROBID server URL | `http://localhost:8070` |
220
- | `batch_size` | Thread pool size | 1000 |
221
- | `sleep_time` | Wait time when server is busy (seconds) | 5 |
222
- | `timeout` | Client-side timeout (seconds) | 60 |
223
- | `coordinates` | XML elements for coordinate extraction | See above |
217
+ | Parameter | Description | Default |
218
+ |-----------------|------------------------------------------------------------------------------------------------------------------|-------------------------|
219
+ | `grobid_server` | GROBID server URL | `http://localhost:8070` |
220
+ | `batch_size` | Thread pool size. **Tune carefully: a large batch size will result in the data being written less frequently** | 1000 |
221
+ | `sleep_time` | Wait time when server is busy (seconds) | 5 |
222
+ | `timeout` | Client-side timeout (seconds) | 180 |
223
+ | `coordinates` | XML elements for coordinate extraction | See above |
224
224
 
225
225
  > [!TIP]
226
226
  > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration is provided.
@@ -41,7 +41,7 @@ class GrobidClient(ApiClient):
41
41
  # Default configuration values
42
42
  DEFAULT_CONFIG = {
43
43
  'grobid_server': 'http://localhost:8070',
44
- 'batch_size': 1000,
44
+ 'batch_size': 10,
45
45
  'sleep_time': 5,
46
46
  'timeout': 180,
47
47
  'coordinates': [
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: grobid-client-python
3
- Version: 0.0.16
3
+ Version: 0.0.17
4
4
  Summary: Simple python client for GROBID REST services
5
5
  Author-email: Patrice Lopez <patrice.lopez@science-miner.com>
6
6
  Maintainer-email: Patrice Lopez <patrice.lopez@science-miner.com>, Luca Foppiano <lucanoro@duck.com>
@@ -254,7 +254,7 @@ A simple, efficient Python client for [GROBID](https://github.com/kermitt2/grobi
254
254
  - Local installation: [GROBID Documentation](http://grobid.readthedocs.io/)
255
255
  - Docker: `docker run -t --rm -p 8070:8070 lfoppiano/grobid:0.8.2`
256
256
  - Default server: `http://localhost:8070`
257
- - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply)
257
+ - Online demo: https://lfoppiano-grobid.hf.space (usage limits apply), more details [here](https://grobid.readthedocs.io/en/latest/getting_started/#using-grobid-from-the-cloud).
258
258
 
259
259
  > [!IMPORTANT]
260
260
  > GROBID supports Windows only through Docker containers. See the [Docker documentation](https://grobid.readthedocs.io/en/latest/Grobid-docker/) for details.
@@ -314,39 +314,39 @@ grobid_client [OPTIONS] SERVICE
314
314
 
315
315
  #### Available Services
316
316
 
317
- | Service | Description | Input Format |
318
- |---------|-------------|--------------|
319
- | `processFulltextDocument` | Extract full document structure | PDF files |
320
- | `processHeaderDocument` | Extract document metadata | PDF files |
321
- | `processReferences` | Extract bibliographic references | PDF files |
322
- | `processCitationList` | Parse citation strings | Text files (one citation per line) |
323
- | `processCitationPatentST36` | Process patent citations | XML ST36 format |
324
- | `processCitationPatentPDF` | Process patent PDFs | PDF files |
317
+ | Service | Description | Input Format |
318
+ |-----------------------------|-----------------------------------|------------------------------------|
319
+ | `processFulltextDocument` | Extract full document structure | PDF files |
320
+ | `processHeaderDocument` | Extract document metadata | PDF files |
321
+ | `processReferences` | Extract bibliographic references | PDF files |
322
+ | `processCitationList` | Parse citation strings | Text files (one citation per line) |
323
+ | `processCitationPatentST36` | Process patent citations | XML ST36 format |
324
+ | `processCitationPatentPDF` | Process patent PDFs | PDF files |
325
325
 
326
326
  #### Common Options
327
327
 
328
- | Option | Description | Default |
329
- |--------|-------------|---------|
330
- | `--input` | Input directory path | Required |
331
- | `--output` | Output directory path | Same as input |
332
- | `--server` | GROBID server URL | `http://localhost:8070` |
333
- | `--n` | Concurrency level | 10 |
334
- | `--config` | Config file path | Optional |
335
- | `--force` | Overwrite existing files | False |
336
- | `--verbose` | Enable verbose logging | False |
328
+ | Option | Description | Default |
329
+ |-------------|--------------------------|-------------------------|
330
+ | `--input` | Input directory path | Required |
331
+ | `--output` | Output directory path | Same as input |
332
+ | `--server` | GROBID server URL | `http://localhost:8070` |
333
+ | `--n` | Concurrency level | 10 |
334
+ | `--config` | Config file path | Optional |
335
+ | `--force` | Overwrite existing files | False |
336
+ | `--verbose` | Enable verbose logging | False |
337
337
 
338
338
  #### Processing Options
339
339
 
340
- | Option | Description |
341
- |--------|-------------|
342
- | `--generateIDs` | Generate random XML IDs |
343
- | `--consolidate_header` | Consolidate header metadata |
344
- | `--consolidate_citations` | Consolidate bibliographic references |
345
- | `--include_raw_citations` | Include raw citation text |
346
- | `--include_raw_affiliations` | Include raw affiliation text |
347
- | `--teiCoordinates` | Add PDF coordinates to XML |
348
- | `--segmentSentences` | Segment sentences with coordinates |
349
- | `--flavor` | Processing flavor for fulltext extraction |
340
+ | Option | Description |
341
+ |------------------------------|-------------------------------------------|
342
+ | `--generateIDs` | Generate random XML IDs |
343
+ | `--consolidate_header` | Consolidate header metadata |
344
+ | `--consolidate_citations` | Consolidate bibliographic references |
345
+ | `--include_raw_citations` | Include raw citation text |
346
+ | `--include_raw_affiliations` | Include raw affiliation text |
347
+ | `--teiCoordinates` | Add PDF coordinates to XML |
348
+ | `--segmentSentences` | Segment sentences with coordinates |
349
+ | `--flavor` | Processing flavor for fulltext extraction |
350
350
 
351
351
  #### Examples
352
352
 
@@ -430,13 +430,13 @@ Configuration can be provided via a JSON file. When using the CLI, the `--server
430
430
 
431
431
  ### Configuration Parameters
432
432
 
433
- | Parameter | Description | Default |
434
- |-----------|-------------|---------|
435
- | `grobid_server` | GROBID server URL | `http://localhost:8070` |
436
- | `batch_size` | Thread pool size | 1000 |
437
- | `sleep_time` | Wait time when server is busy (seconds) | 5 |
438
- | `timeout` | Client-side timeout (seconds) | 60 |
439
- | `coordinates` | XML elements for coordinate extraction | See above |
433
+ | Parameter | Description | Default |
434
+ |-----------------|------------------------------------------------------------------------------------------------------------------|-------------------------|
435
+ | `grobid_server` | GROBID server URL | `http://localhost:8070` |
436
+ | `batch_size` | Thread pool size. **Tune carefully: a large batch size will result in the data being written less frequently** | 1000 |
437
+ | `sleep_time` | Wait time when server is busy (seconds) | 5 |
438
+ | `timeout` | Client-side timeout (seconds) | 180 |
439
+ | `coordinates` | XML elements for coordinate extraction | See above |
440
440
 
441
441
  > [!TIP]
442
442
  > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration is provided.
@@ -3,7 +3,7 @@ requires = ["setuptools", "setuptools-scm"]
3
3
  build-backend = "setuptools.build_meta"
4
4
 
5
5
  [tool.bumpversion]
6
- current_version = "0.0.16"
6
+ current_version = "0.0.17"
7
7
  commit = "true"
8
8
  tag = "true"
9
9
  tag_name = "v{new_version}"