grobid-client-python 0.0.12__tar.gz → 0.0.13__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.
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/.github/workflows/ci-build.yml +12 -4
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/PKG-INFO +11 -10
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/Readme.md +10 -9
- grobid_client_python-0.0.13/config.json +28 -0
- grobid_client_python-0.0.13/grobid_client/grobid_client.py +802 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/PKG-INFO +11 -10
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/SOURCES.txt +9 -1
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/pyproject.toml +1 -1
- grobid_client_python-0.0.13/pytest.ini +21 -0
- grobid_client_python-0.0.13/tests/__init__.py +2 -0
- grobid_client_python-0.0.13/tests/conftest.py +64 -0
- grobid_client_python-0.0.13/tests/run_tests.py +53 -0
- grobid_client_python-0.0.13/tests/test_client.py +225 -0
- grobid_client_python-0.0.13/tests/test_config.json +16 -0
- grobid_client_python-0.0.13/tests/test_grobid_client.py +441 -0
- grobid_client_python-0.0.13/tests/test_integration.py +346 -0
- grobid_client_python-0.0.12/config.json +0 -7
- grobid_client_python-0.0.12/grobid_client/grobid_client.py +0 -531
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/.github/workflows/ci-release.yml +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/.gitignore +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/LICENSE +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/MANIFEST.in +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/example.py +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client/__init__.py +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client/client.py +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/dependency_links.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/entry_points.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/requires.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/grobid_client_python.egg-info/top_level.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/requirements.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/20180928112135.png +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/20180928112138.csv +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_out/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_out/test_1/0f318087-b211-4ace-8ac9-3d9372a73c1c.tei.xml +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-1.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-2.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-3.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-4.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-5.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-6.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/resources/test_txt/reference-strings-7.txt +0 -0
- {grobid_client_python-0.0.12 → grobid_client_python-0.0.13}/setup.cfg +0 -0
|
@@ -26,7 +26,7 @@ jobs:
|
|
|
26
26
|
- name: Install dependencies
|
|
27
27
|
run: |
|
|
28
28
|
python -m pip install --upgrade pip
|
|
29
|
-
pip install --upgrade flake8 pytest pycodestyle pytest-cov
|
|
29
|
+
pip install --upgrade flake8 pytest pycodestyle pytest-cov pytest-mock
|
|
30
30
|
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
|
|
31
31
|
- name: Lint with flake8
|
|
32
32
|
run: |
|
|
@@ -34,6 +34,14 @@ jobs:
|
|
|
34
34
|
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
|
|
35
35
|
# exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
|
|
36
36
|
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
37
|
+
- name: Test with pytest
|
|
38
|
+
run: |
|
|
39
|
+
pytest tests/ -v --cov=grobid_client --cov-report=xml --cov-report=term-missing
|
|
40
|
+
- name: Upload coverage to Codecov
|
|
41
|
+
if: matrix.python-version == '3.11'
|
|
42
|
+
uses: codecov/codecov-action@v4
|
|
43
|
+
with:
|
|
44
|
+
file: ./coverage.xml
|
|
45
|
+
flags: unittests
|
|
46
|
+
name: codecov-umbrella
|
|
47
|
+
fail_ci_if_error: false
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: grobid-client-python
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.13
|
|
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>
|
|
@@ -218,15 +218,12 @@ Requires-Dist: requests
|
|
|
218
218
|
[](https://archive.softwareheritage.org/browse/origin/https://github.com/kermitt2/grobid_client_python/)
|
|
219
219
|
[](http://www.apache.org/licenses/LICENSE-2.0.html)
|
|
220
220
|
|
|
221
|
-
# Simple
|
|
221
|
+
# Simple Python client for GROBID REST services
|
|
222
222
|
|
|
223
223
|
This Python client can be used to process in an efficient concurrent manner a set of PDF in a given directory by the [GROBID](https://github.com/kermitt2/grobid) service. It includes a command line for processing PDF on a file system and write results in a given output directory and a library for import in other python scripts. The client can also process similarly a list of files with reference strings (one per line) and patents in XML ST36 formats.
|
|
224
224
|
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
Please be aware that, at the moment, [grobid does not support Windows](https://grobid.readthedocs.io/en/latest/Troubleshooting/#windows-related-issues).
|
|
228
|
-
If you are a Windows user, don't worry. You can still [run grobid
|
|
229
|
-
via Docker](https://grobid.readthedocs.io/en/latest/Grobid-docker/).
|
|
225
|
+
> [!IMPORTANT]
|
|
226
|
+
> Please be aware that, at the moment, Grobid supports windows only through Docker containers. See [here](https://grobid.readthedocs.io/en/latest/Grobid-docker/).
|
|
230
227
|
|
|
231
228
|
## Build and run
|
|
232
229
|
|
|
@@ -314,11 +311,12 @@ optional arguments:
|
|
|
314
311
|
with additional <s> elements
|
|
315
312
|
--verbose print information about processed files in the console
|
|
316
313
|
--flavor specifcy the flavor to be used. Current accepted
|
|
317
|
-
values: `article/light`, `article/light-ref`, `sdo/ietf
|
|
318
|
-
|
|
314
|
+
values: `article/light`, `article/light-ref`, `sdo/ietf`.
|
|
315
|
+
```
|
|
319
316
|
|
|
317
|
+
> [!TIP]
|
|
318
|
+
> Before using flavors, check [here](https://grobid.readthedocs.io/en/latest/Grobid-specialized-processes/#flavors).
|
|
320
319
|
|
|
321
|
-
```
|
|
322
320
|
|
|
323
321
|
Examples:
|
|
324
322
|
|
|
@@ -367,6 +365,9 @@ See also `example.py`.
|
|
|
367
365
|
|
|
368
366
|
## Configuration of the client
|
|
369
367
|
|
|
368
|
+
> [!TIP]
|
|
369
|
+
> from version 0.0.12 the `config.json` will be optional, by default the client will connect to the local server.
|
|
370
|
+
|
|
370
371
|
There are a few parameters that can be set with the `config.json` file.
|
|
371
372
|
|
|
372
373
|
- `grobid_server` indicates the URL of the GROBID server to be used by the client.
|
|
@@ -2,15 +2,12 @@
|
|
|
2
2
|
[](https://archive.softwareheritage.org/browse/origin/https://github.com/kermitt2/grobid_client_python/)
|
|
3
3
|
[](http://www.apache.org/licenses/LICENSE-2.0.html)
|
|
4
4
|
|
|
5
|
-
# Simple
|
|
5
|
+
# Simple Python client for GROBID REST services
|
|
6
6
|
|
|
7
7
|
This Python client can be used to process in an efficient concurrent manner a set of PDF in a given directory by the [GROBID](https://github.com/kermitt2/grobid) service. It includes a command line for processing PDF on a file system and write results in a given output directory and a library for import in other python scripts. The client can also process similarly a list of files with reference strings (one per line) and patents in XML ST36 formats.
|
|
8
8
|
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
Please be aware that, at the moment, [grobid does not support Windows](https://grobid.readthedocs.io/en/latest/Troubleshooting/#windows-related-issues).
|
|
12
|
-
If you are a Windows user, don't worry. You can still [run grobid
|
|
13
|
-
via Docker](https://grobid.readthedocs.io/en/latest/Grobid-docker/).
|
|
9
|
+
> [!IMPORTANT]
|
|
10
|
+
> Please be aware that, at the moment, Grobid supports windows only through Docker containers. See [here](https://grobid.readthedocs.io/en/latest/Grobid-docker/).
|
|
14
11
|
|
|
15
12
|
## Build and run
|
|
16
13
|
|
|
@@ -98,11 +95,12 @@ optional arguments:
|
|
|
98
95
|
with additional <s> elements
|
|
99
96
|
--verbose print information about processed files in the console
|
|
100
97
|
--flavor specifcy the flavor to be used. Current accepted
|
|
101
|
-
values: `article/light`, `article/light-ref`, `sdo/ietf
|
|
102
|
-
|
|
98
|
+
values: `article/light`, `article/light-ref`, `sdo/ietf`.
|
|
99
|
+
```
|
|
103
100
|
|
|
101
|
+
> [!TIP]
|
|
102
|
+
> Before using flavors, check [here](https://grobid.readthedocs.io/en/latest/Grobid-specialized-processes/#flavors).
|
|
104
103
|
|
|
105
|
-
```
|
|
106
104
|
|
|
107
105
|
Examples:
|
|
108
106
|
|
|
@@ -151,6 +149,9 @@ See also `example.py`.
|
|
|
151
149
|
|
|
152
150
|
## Configuration of the client
|
|
153
151
|
|
|
152
|
+
> [!TIP]
|
|
153
|
+
> from version 0.0.12 the `config.json` will be optional, by default the client will connect to the local server.
|
|
154
|
+
|
|
154
155
|
There are a few parameters that can be set with the `config.json` file.
|
|
155
156
|
|
|
156
157
|
- `grobid_server` indicates the URL of the GROBID server to be used by the client.
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
{
|
|
2
|
+
"grobid_server": "http://localhost:8070",
|
|
3
|
+
"batch_size": 1000,
|
|
4
|
+
"timeout": 120,
|
|
5
|
+
"sleep_time": 5,
|
|
6
|
+
"coordinates": [
|
|
7
|
+
"title",
|
|
8
|
+
"persName",
|
|
9
|
+
"affiliation",
|
|
10
|
+
"orgName",
|
|
11
|
+
"formula",
|
|
12
|
+
"figure",
|
|
13
|
+
"ref",
|
|
14
|
+
"biblStruct",
|
|
15
|
+
"head",
|
|
16
|
+
"p",
|
|
17
|
+
"s",
|
|
18
|
+
"note"
|
|
19
|
+
],
|
|
20
|
+
"logging": {
|
|
21
|
+
"level": "INFO",
|
|
22
|
+
"format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
|
|
23
|
+
"console": true,
|
|
24
|
+
"file": null,
|
|
25
|
+
"max_file_size": "10MB",
|
|
26
|
+
"backup_count": 3
|
|
27
|
+
}
|
|
28
|
+
}
|