semantify3 0.0.1__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.
- semantify3-0.0.1/.github/workflows/build.yml +37 -0
- semantify3-0.0.1/.github/workflows/upload-to-pypi.yml +27 -0
- semantify3-0.0.1/.gitignore +207 -0
- semantify3-0.0.1/LICENSE +201 -0
- semantify3-0.0.1/PKG-INFO +49 -0
- semantify3-0.0.1/README.md +16 -0
- semantify3-0.0.1/pyproject.toml +74 -0
- semantify3-0.0.1/scripts/blackisort +15 -0
- semantify3-0.0.1/scripts/doc +88 -0
- semantify3-0.0.1/scripts/install +4 -0
- semantify3-0.0.1/scripts/release +8 -0
- semantify3-0.0.1/scripts/test +132 -0
- semantify3-0.0.1/sem3/__init__.py +11 -0
- semantify3-0.0.1/sem3/extractor.py +169 -0
- semantify3-0.0.1/sem3/sem3_cmd.py +116 -0
- semantify3-0.0.1/sem3/version.py +38 -0
- semantify3-0.0.1/tests/__init__.py +0 -0
- semantify3-0.0.1/tests/test_extractor.py +45 -0
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
|
|
2
|
+
# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
|
|
3
|
+
|
|
4
|
+
name: Build
|
|
5
|
+
|
|
6
|
+
on:
|
|
7
|
+
push:
|
|
8
|
+
branches: [ main ]
|
|
9
|
+
pull_request:
|
|
10
|
+
branches: [ main ]
|
|
11
|
+
|
|
12
|
+
jobs:
|
|
13
|
+
build:
|
|
14
|
+
|
|
15
|
+
runs-on: ubuntu-latest
|
|
16
|
+
strategy:
|
|
17
|
+
matrix:
|
|
18
|
+
# os: [ubuntu-latest, macos-latest, windows-latest]
|
|
19
|
+
# python-version: [ '3.10', '3.11', '3.12', '3.13' ]
|
|
20
|
+
os: [ubuntu-latest]
|
|
21
|
+
python-version: [ '3.12']
|
|
22
|
+
|
|
23
|
+
steps:
|
|
24
|
+
- uses: actions/checkout@v4
|
|
25
|
+
- name: Set up Python ${{ matrix.python-version }}
|
|
26
|
+
uses: actions/setup-python@v5
|
|
27
|
+
with:
|
|
28
|
+
python-version: ${{ matrix.python-version }}
|
|
29
|
+
- name: Install pip
|
|
30
|
+
run: |
|
|
31
|
+
python -m pip install --upgrade pip
|
|
32
|
+
- name: Install dependencies
|
|
33
|
+
run: |
|
|
34
|
+
scripts/install
|
|
35
|
+
- name: Run tests
|
|
36
|
+
run: |
|
|
37
|
+
scripts/test
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
name: Upload Python Package
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
release:
|
|
5
|
+
types: [created]
|
|
6
|
+
|
|
7
|
+
jobs:
|
|
8
|
+
deploy:
|
|
9
|
+
runs-on: ubuntu-latest
|
|
10
|
+
permissions:
|
|
11
|
+
# IMPORTANT: this permission is mandatory for trusted publishing
|
|
12
|
+
id-token: write
|
|
13
|
+
steps:
|
|
14
|
+
- uses: actions/checkout@v4
|
|
15
|
+
- name: Set up Python
|
|
16
|
+
uses: actions/setup-python@v5
|
|
17
|
+
with:
|
|
18
|
+
python-version: '3.x'
|
|
19
|
+
- name: Install dependencies
|
|
20
|
+
run: |
|
|
21
|
+
python -m pip install --upgrade pip
|
|
22
|
+
pip install hatch
|
|
23
|
+
- name: Build and publish
|
|
24
|
+
run: |
|
|
25
|
+
hatch build
|
|
26
|
+
- name: Publish distribution to PyPI
|
|
27
|
+
uses: pypa/gh-action-pypi-publish@release/v1
|
|
@@ -0,0 +1,207 @@
|
|
|
1
|
+
# Byte-compiled / optimized / DLL files
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[codz]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# C extensions
|
|
7
|
+
*.so
|
|
8
|
+
|
|
9
|
+
# Distribution / packaging
|
|
10
|
+
.Python
|
|
11
|
+
build/
|
|
12
|
+
develop-eggs/
|
|
13
|
+
dist/
|
|
14
|
+
downloads/
|
|
15
|
+
eggs/
|
|
16
|
+
.eggs/
|
|
17
|
+
lib/
|
|
18
|
+
lib64/
|
|
19
|
+
parts/
|
|
20
|
+
sdist/
|
|
21
|
+
var/
|
|
22
|
+
wheels/
|
|
23
|
+
share/python-wheels/
|
|
24
|
+
*.egg-info/
|
|
25
|
+
.installed.cfg
|
|
26
|
+
*.egg
|
|
27
|
+
MANIFEST
|
|
28
|
+
|
|
29
|
+
# PyInstaller
|
|
30
|
+
# Usually these files are written by a python script from a template
|
|
31
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
32
|
+
*.manifest
|
|
33
|
+
*.spec
|
|
34
|
+
|
|
35
|
+
# Installer logs
|
|
36
|
+
pip-log.txt
|
|
37
|
+
pip-delete-this-directory.txt
|
|
38
|
+
|
|
39
|
+
# Unit test / coverage reports
|
|
40
|
+
htmlcov/
|
|
41
|
+
.tox/
|
|
42
|
+
.nox/
|
|
43
|
+
.coverage
|
|
44
|
+
.coverage.*
|
|
45
|
+
.cache
|
|
46
|
+
nosetests.xml
|
|
47
|
+
coverage.xml
|
|
48
|
+
*.cover
|
|
49
|
+
*.py.cover
|
|
50
|
+
.hypothesis/
|
|
51
|
+
.pytest_cache/
|
|
52
|
+
cover/
|
|
53
|
+
|
|
54
|
+
# Translations
|
|
55
|
+
*.mo
|
|
56
|
+
*.pot
|
|
57
|
+
|
|
58
|
+
# Django stuff:
|
|
59
|
+
*.log
|
|
60
|
+
local_settings.py
|
|
61
|
+
db.sqlite3
|
|
62
|
+
db.sqlite3-journal
|
|
63
|
+
|
|
64
|
+
# Flask stuff:
|
|
65
|
+
instance/
|
|
66
|
+
.webassets-cache
|
|
67
|
+
|
|
68
|
+
# Scrapy stuff:
|
|
69
|
+
.scrapy
|
|
70
|
+
|
|
71
|
+
# Sphinx documentation
|
|
72
|
+
docs/_build/
|
|
73
|
+
|
|
74
|
+
# PyBuilder
|
|
75
|
+
.pybuilder/
|
|
76
|
+
target/
|
|
77
|
+
|
|
78
|
+
# Jupyter Notebook
|
|
79
|
+
.ipynb_checkpoints
|
|
80
|
+
|
|
81
|
+
# IPython
|
|
82
|
+
profile_default/
|
|
83
|
+
ipython_config.py
|
|
84
|
+
|
|
85
|
+
# pyenv
|
|
86
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
87
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
88
|
+
# .python-version
|
|
89
|
+
|
|
90
|
+
# pipenv
|
|
91
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
92
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
93
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
94
|
+
# install all needed dependencies.
|
|
95
|
+
#Pipfile.lock
|
|
96
|
+
|
|
97
|
+
# UV
|
|
98
|
+
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
|
99
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
100
|
+
# commonly ignored for libraries.
|
|
101
|
+
#uv.lock
|
|
102
|
+
|
|
103
|
+
# poetry
|
|
104
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
105
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
106
|
+
# commonly ignored for libraries.
|
|
107
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
108
|
+
#poetry.lock
|
|
109
|
+
#poetry.toml
|
|
110
|
+
|
|
111
|
+
# pdm
|
|
112
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
113
|
+
# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
|
|
114
|
+
# https://pdm-project.org/en/latest/usage/project/#working-with-version-control
|
|
115
|
+
#pdm.lock
|
|
116
|
+
#pdm.toml
|
|
117
|
+
.pdm-python
|
|
118
|
+
.pdm-build/
|
|
119
|
+
|
|
120
|
+
# pixi
|
|
121
|
+
# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
|
|
122
|
+
#pixi.lock
|
|
123
|
+
# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
|
|
124
|
+
# in the .venv directory. It is recommended not to include this directory in version control.
|
|
125
|
+
.pixi
|
|
126
|
+
|
|
127
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
128
|
+
__pypackages__/
|
|
129
|
+
|
|
130
|
+
# Celery stuff
|
|
131
|
+
celerybeat-schedule
|
|
132
|
+
celerybeat.pid
|
|
133
|
+
|
|
134
|
+
# SageMath parsed files
|
|
135
|
+
*.sage.py
|
|
136
|
+
|
|
137
|
+
# Environments
|
|
138
|
+
.env
|
|
139
|
+
.envrc
|
|
140
|
+
.venv
|
|
141
|
+
env/
|
|
142
|
+
venv/
|
|
143
|
+
ENV/
|
|
144
|
+
env.bak/
|
|
145
|
+
venv.bak/
|
|
146
|
+
|
|
147
|
+
# Spyder project settings
|
|
148
|
+
.spyderproject
|
|
149
|
+
.spyproject
|
|
150
|
+
|
|
151
|
+
# Rope project settings
|
|
152
|
+
.ropeproject
|
|
153
|
+
|
|
154
|
+
# mkdocs documentation
|
|
155
|
+
/site
|
|
156
|
+
|
|
157
|
+
# mypy
|
|
158
|
+
.mypy_cache/
|
|
159
|
+
.dmypy.json
|
|
160
|
+
dmypy.json
|
|
161
|
+
|
|
162
|
+
# Pyre type checker
|
|
163
|
+
.pyre/
|
|
164
|
+
|
|
165
|
+
# pytype static type analyzer
|
|
166
|
+
.pytype/
|
|
167
|
+
|
|
168
|
+
# Cython debug symbols
|
|
169
|
+
cython_debug/
|
|
170
|
+
|
|
171
|
+
# PyCharm
|
|
172
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
173
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
174
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
175
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
176
|
+
#.idea/
|
|
177
|
+
|
|
178
|
+
# Abstra
|
|
179
|
+
# Abstra is an AI-powered process automation framework.
|
|
180
|
+
# Ignore directories containing user credentials, local state, and settings.
|
|
181
|
+
# Learn more at https://abstra.io/docs
|
|
182
|
+
.abstra/
|
|
183
|
+
|
|
184
|
+
# Visual Studio Code
|
|
185
|
+
# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
|
|
186
|
+
# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
|
|
187
|
+
# and can be added to the global gitignore or merged into this file. However, if you prefer,
|
|
188
|
+
# you could uncomment the following to ignore the entire vscode folder
|
|
189
|
+
# .vscode/
|
|
190
|
+
|
|
191
|
+
# Ruff stuff:
|
|
192
|
+
.ruff_cache/
|
|
193
|
+
|
|
194
|
+
# PyPI configuration file
|
|
195
|
+
.pypirc
|
|
196
|
+
|
|
197
|
+
# Cursor
|
|
198
|
+
# Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
|
|
199
|
+
# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
|
|
200
|
+
# refer to https://docs.cursor.com/context/ignore-files
|
|
201
|
+
.cursorignore
|
|
202
|
+
.cursorindexingignore
|
|
203
|
+
|
|
204
|
+
# Marimo
|
|
205
|
+
marimo/_static/
|
|
206
|
+
marimo/_lsp/
|
|
207
|
+
__marimo__/
|
semantify3-0.0.1/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: semantify3
|
|
3
|
+
Version: 0.0.1
|
|
4
|
+
Summary: semantify³ — Extract knowledge graph ready triples from human-readable annotations wherever possible — Syntax matters!
|
|
5
|
+
Project-URL: Home, https://github.com/WolfgangFahl/semantify3
|
|
6
|
+
Project-URL: Documentation, https://wiki.bitplan.com/index.php/semantify3
|
|
7
|
+
Project-URL: Source, https://github.com/WolfgangFahl/semantify3
|
|
8
|
+
Author-email: Wolfgang Fahl <wf@WolfgangFahl.com>
|
|
9
|
+
Maintainer-email: Wolfgang Fahl <wf@WolfgangFahl.com>
|
|
10
|
+
License: Apache-2.0
|
|
11
|
+
License-File: LICENSE
|
|
12
|
+
Keywords: RDF,SiDIF,YAML,knowledge-graph,ontology,semantic-web,triples
|
|
13
|
+
Classifier: Development Status :: 3 - Alpha
|
|
14
|
+
Classifier: Environment :: Console
|
|
15
|
+
Classifier: Intended Audience :: Developers
|
|
16
|
+
Classifier: Intended Audience :: Science/Research
|
|
17
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
18
|
+
Classifier: Operating System :: OS Independent
|
|
19
|
+
Classifier: Programming Language :: Python :: 3 :: Only
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
21
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
22
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
23
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
24
|
+
Classifier: Topic :: Scientific/Engineering :: Information Analysis
|
|
25
|
+
Classifier: Topic :: Text Processing :: Markup
|
|
26
|
+
Requires-Python: >=3.10
|
|
27
|
+
Requires-Dist: pybasemkit>=0.1.3
|
|
28
|
+
Requires-Dist: pyyaml>=6.0
|
|
29
|
+
Requires-Dist: rdflib>=7.0.0
|
|
30
|
+
Provides-Extra: test
|
|
31
|
+
Requires-Dist: green; extra == 'test'
|
|
32
|
+
Description-Content-Type: text/markdown
|
|
33
|
+
|
|
34
|
+
# semantify3
|
|
35
|
+
semantify³ - extract knowledge graph ready triples from human readable annotations whereever possible - Syntax matters!
|
|
36
|
+
|
|
37
|
+
| | |
|
|
38
|
+
| :--- | :--- |
|
|
39
|
+
| **PyPi** | [](https://pypi.python.org/pypi/semantify3/) [](https://www.apache.org/licenses/LICENSE-2.0) [](https://pypi.org/project/semantify3/) [](https://pypi.org/project/semantify3/) [](https://pypi.org/project/semantify3/) |
|
|
40
|
+
| **GitHub** | [](https://github.com/BITPlan/semantify3/actions/workflows/build.yml) [](https://github.com/BITPlan/semantify3/releases) [](https://github.com/BITPlan/semantify3/graphs/contributors) [](https://github.com/BITPlan/semantify3/commits/) [](https://github.com/BITPlan/semantify3/issues) [](https://github.com/BITPlan/semantify3/issues/?q=is%3Aissue+is%3Aclosed) |
|
|
41
|
+
| **Code** | [](https://github.com/psf/black) [](https://pycqa.github.io/isort/) |
|
|
42
|
+
| **Docs** | [](https://BITPlan.github.io/semantify3/) [](https://github.com/PyCQA/docformatter) [](https://google.github.io/styleguide/pyguide.html#s3.8-comments-and-docstrings) |
|
|
43
|
+
|
|
44
|
+
## Documentation
|
|
45
|
+
[Wiki](https://wiki.bitplan.com/index.php/semantify3)
|
|
46
|
+
|
|
47
|
+
### Authors
|
|
48
|
+
* [Tim Holzheim](https://www.semantic-mediawiki.org/wiki/Tim_Holzheim)
|
|
49
|
+
* [Wolfgang Fahl](http://www.bitplan.com/Wolfgang_Fahl)
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
# semantify3
|
|
2
|
+
semantify³ - extract knowledge graph ready triples from human readable annotations whereever possible - Syntax matters!
|
|
3
|
+
|
|
4
|
+
| | |
|
|
5
|
+
| :--- | :--- |
|
|
6
|
+
| **PyPi** | [](https://pypi.python.org/pypi/semantify3/) [](https://www.apache.org/licenses/LICENSE-2.0) [](https://pypi.org/project/semantify3/) [](https://pypi.org/project/semantify3/) [](https://pypi.org/project/semantify3/) |
|
|
7
|
+
| **GitHub** | [](https://github.com/BITPlan/semantify3/actions/workflows/build.yml) [](https://github.com/BITPlan/semantify3/releases) [](https://github.com/BITPlan/semantify3/graphs/contributors) [](https://github.com/BITPlan/semantify3/commits/) [](https://github.com/BITPlan/semantify3/issues) [](https://github.com/BITPlan/semantify3/issues/?q=is%3Aissue+is%3Aclosed) |
|
|
8
|
+
| **Code** | [](https://github.com/psf/black) [](https://pycqa.github.io/isort/) |
|
|
9
|
+
| **Docs** | [](https://BITPlan.github.io/semantify3/) [](https://github.com/PyCQA/docformatter) [](https://google.github.io/styleguide/pyguide.html#s3.8-comments-and-docstrings) |
|
|
10
|
+
|
|
11
|
+
## Documentation
|
|
12
|
+
[Wiki](https://wiki.bitplan.com/index.php/semantify3)
|
|
13
|
+
|
|
14
|
+
### Authors
|
|
15
|
+
* [Tim Holzheim](https://www.semantic-mediawiki.org/wiki/Tim_Holzheim)
|
|
16
|
+
* [Wolfgang Fahl](http://www.bitplan.com/Wolfgang_Fahl)
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
# see https://flit.pypa.io/en/latest/pyproject_toml.html
|
|
2
|
+
[build-system]
|
|
3
|
+
requires = ["hatchling"]
|
|
4
|
+
build-backend = "hatchling.build"
|
|
5
|
+
|
|
6
|
+
[project]
|
|
7
|
+
name = "semantify3"
|
|
8
|
+
description = "semantify³ — Extract knowledge graph ready triples from human-readable annotations wherever possible — Syntax matters!"
|
|
9
|
+
keywords = ["RDF", "YAML", "SiDIF", "triples", "knowledge-graph", "semantic-web", "ontology"]
|
|
10
|
+
|
|
11
|
+
authors = [
|
|
12
|
+
{name = "Wolfgang Fahl", email = "wf@WolfgangFahl.com"}
|
|
13
|
+
]
|
|
14
|
+
|
|
15
|
+
maintainers = [
|
|
16
|
+
{ name = "Wolfgang Fahl", email = "wf@WolfgangFahl.com" },
|
|
17
|
+
]
|
|
18
|
+
|
|
19
|
+
readme = "README.md"
|
|
20
|
+
license = {text = "Apache-2.0"}
|
|
21
|
+
dependencies = [
|
|
22
|
+
# https://pypi.org/project/pybasemkit/
|
|
23
|
+
# https://github.com/WolfgangFahl/pybasemkit
|
|
24
|
+
# Python base module kit: YAML/JSON I/O, structured logging, CLI tooling, shell execution, and remote pydevd debug support.
|
|
25
|
+
"pybasemkit>=0.1.3",
|
|
26
|
+
# https://pypi.org/project/rdflib/
|
|
27
|
+
# RDF library for Python - parsing, serializing, querying RDF
|
|
28
|
+
"rdflib>=7.0.0",
|
|
29
|
+
# https://pypi.org/project/PyYAML/
|
|
30
|
+
# YAML parser and emitter for Python
|
|
31
|
+
"PyYAML>=6.0",
|
|
32
|
+
]
|
|
33
|
+
|
|
34
|
+
requires-python = ">=3.10"
|
|
35
|
+
classifiers=[
|
|
36
|
+
"Development Status :: 3 - Alpha",
|
|
37
|
+
"Environment :: Console",
|
|
38
|
+
"Programming Language :: Python :: 3 :: Only",
|
|
39
|
+
"Programming Language :: Python :: 3.10",
|
|
40
|
+
"Programming Language :: Python :: 3.11",
|
|
41
|
+
"Programming Language :: Python :: 3.12",
|
|
42
|
+
"Programming Language :: Python :: 3.13",
|
|
43
|
+
"Operating System :: OS Independent",
|
|
44
|
+
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
45
|
+
"Topic :: Text Processing :: Markup",
|
|
46
|
+
"Intended Audience :: Developers",
|
|
47
|
+
"Intended Audience :: Science/Research",
|
|
48
|
+
"License :: OSI Approved :: Apache Software License"
|
|
49
|
+
]
|
|
50
|
+
dynamic = ["version"]
|
|
51
|
+
|
|
52
|
+
[tool.hatch.version]
|
|
53
|
+
path = "sem3/__init__.py"
|
|
54
|
+
|
|
55
|
+
[project.urls]
|
|
56
|
+
Home = "https://github.com/WolfgangFahl/semantify3"
|
|
57
|
+
Documentation = "https://wiki.bitplan.com/index.php/semantify3"
|
|
58
|
+
Source = "https://github.com/WolfgangFahl/semantify3"
|
|
59
|
+
|
|
60
|
+
[project.scripts]
|
|
61
|
+
sem3 = "sem3.sem3_cmd:main"
|
|
62
|
+
|
|
63
|
+
[project.optional-dependencies]
|
|
64
|
+
test = [
|
|
65
|
+
"green",
|
|
66
|
+
]
|
|
67
|
+
|
|
68
|
+
[tool.hatch.build.targets.wheel]
|
|
69
|
+
only-include = ["sem3"]
|
|
70
|
+
|
|
71
|
+
[tool.hatch.build.targets.wheel.sources]
|
|
72
|
+
"semantify3" = "sem3"
|
|
73
|
+
|
|
74
|
+
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
#!/bin/bash
|
|
2
|
+
# WF 2025-11-29
|
|
3
|
+
package=sem3
|
|
4
|
+
|
|
5
|
+
# Sort imports
|
|
6
|
+
isort tests/*.py
|
|
7
|
+
isort $package/*.py
|
|
8
|
+
|
|
9
|
+
# Format code
|
|
10
|
+
black tests/*.py
|
|
11
|
+
black $package/*.py
|
|
12
|
+
|
|
13
|
+
# Format docstrings
|
|
14
|
+
#docformatter --in-place tests/*.py
|
|
15
|
+
#docformatter --in-place $package/*.py
|
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
#!/bin/bash
|
|
2
|
+
# create docs for a configurable project
|
|
3
|
+
# WF 2024-07-30 - updated
|
|
4
|
+
|
|
5
|
+
# Extract project name from pyproject.toml
|
|
6
|
+
PROJECT_NAME=$(grep "\[project\]" pyproject.toml -A1 | grep name | cut -d '=' -f2 | tr -d ' "')
|
|
7
|
+
PACKAGE_NAME=$(grep "\[tool.hatch.build.targets.wheel.sources\]" pyproject.toml -A1 | tail -1 | cut -d '=' -f2 | tr -d ' "')
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
# Function to print usage information
|
|
11
|
+
print_usage() {
|
|
12
|
+
echo "Usage: $0 [OPTIONS]"
|
|
13
|
+
echo "Options:"
|
|
14
|
+
echo " -pr, --project NAME Set the project name (default: $PROJECT_NAME)"
|
|
15
|
+
echo " -pa, --package NAME Set the package name (default: $PACKAGE_NAME)"
|
|
16
|
+
echo " -d, --deploy Deploy the documentation after building"
|
|
17
|
+
echo " -h, --help Display this help message"
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
# Parse command line arguments
|
|
21
|
+
DEPLOY=false
|
|
22
|
+
while [[ "$#" -gt 0 ]]; do
|
|
23
|
+
case $1 in
|
|
24
|
+
-pr|--project) PROJECT_NAME="$2"; shift ;;
|
|
25
|
+
-pa|--package) PACKAGE_NAME="$2"; shift ;;
|
|
26
|
+
-d|--deploy) DEPLOY=true ;;
|
|
27
|
+
-h|--help) print_usage; exit 0 ;;
|
|
28
|
+
*) echo "Unknown parameter: $1"; print_usage; exit 1 ;;
|
|
29
|
+
esac
|
|
30
|
+
shift
|
|
31
|
+
done
|
|
32
|
+
|
|
33
|
+
# Ensure we're in the correct directory
|
|
34
|
+
if [[ ! -d "$PACKAGE_NAME" ]]; then
|
|
35
|
+
echo "Error: $PACKAGE_NAME package directory not found. Are you in the correct directory?"
|
|
36
|
+
exit 1
|
|
37
|
+
fi
|
|
38
|
+
|
|
39
|
+
# Check if mkdocs is installed
|
|
40
|
+
if ! command -v mkdocs &> /dev/null; then
|
|
41
|
+
pip install mkdocs mkdocs-material mkdocstrings[python]
|
|
42
|
+
fi
|
|
43
|
+
|
|
44
|
+
# Create or update mkdocs.yml
|
|
45
|
+
cat << EOF > mkdocs.yml
|
|
46
|
+
site_name: $PROJECT_NAME API Documentation
|
|
47
|
+
theme:
|
|
48
|
+
name: material
|
|
49
|
+
plugins:
|
|
50
|
+
- search
|
|
51
|
+
- mkdocstrings:
|
|
52
|
+
handlers:
|
|
53
|
+
python:
|
|
54
|
+
setup_commands:
|
|
55
|
+
- import sys
|
|
56
|
+
- import os
|
|
57
|
+
- sys.path.insert(0, os.path.abspath("."))
|
|
58
|
+
selection:
|
|
59
|
+
docstring_style: google
|
|
60
|
+
rendering:
|
|
61
|
+
show_source: true
|
|
62
|
+
nav:
|
|
63
|
+
- API: index.md
|
|
64
|
+
EOF
|
|
65
|
+
|
|
66
|
+
# Create or update index.md
|
|
67
|
+
index_md=docs/index.md
|
|
68
|
+
mkdir -p docs
|
|
69
|
+
cat << EOF > $index_md
|
|
70
|
+
# $PROJECT_NAME API Documentation
|
|
71
|
+
|
|
72
|
+
::: $PACKAGE_NAME
|
|
73
|
+
options:
|
|
74
|
+
show_submodules: true
|
|
75
|
+
EOF
|
|
76
|
+
|
|
77
|
+
# Ignore DeprecationWarnings during build
|
|
78
|
+
export PYTHONWARNINGS="ignore::DeprecationWarning"
|
|
79
|
+
|
|
80
|
+
# Build the documentation
|
|
81
|
+
mkdocs build --config-file ./mkdocs.yml
|
|
82
|
+
|
|
83
|
+
# Deploy if requested
|
|
84
|
+
if [ "$DEPLOY" = true ]; then
|
|
85
|
+
mkdocs gh-deploy --force --config-file ./mkdocs.yml
|
|
86
|
+
fi
|
|
87
|
+
|
|
88
|
+
echo "Documentation process completed for $PROJECT_NAME."
|
|
@@ -0,0 +1,132 @@
|
|
|
1
|
+
#!/bin/bash
|
|
2
|
+
# WF 2022-08-20
|
|
3
|
+
# WF 2024-08-03
|
|
4
|
+
|
|
5
|
+
#ansi colors
|
|
6
|
+
#http://www.csc.uvic.ca/~sae/seng265/fall04/tips/s265s047-tips/bash-using-colors.html
|
|
7
|
+
blue='\033[0;34m'
|
|
8
|
+
red='\033[0;31m'
|
|
9
|
+
green='\033[0;32m' # '\e[1;32m' is too bright for white bg.
|
|
10
|
+
endColor='\033[0m'
|
|
11
|
+
|
|
12
|
+
#
|
|
13
|
+
# a colored message
|
|
14
|
+
# params:
|
|
15
|
+
# 1: l_color - the color of the message
|
|
16
|
+
# 2: l_msg - the message to display
|
|
17
|
+
#
|
|
18
|
+
color_msg() {
|
|
19
|
+
local l_color="$1"
|
|
20
|
+
local l_msg="$2"
|
|
21
|
+
echo -e "${l_color}$l_msg${endColor}"
|
|
22
|
+
}
|
|
23
|
+
|
|
24
|
+
#
|
|
25
|
+
# error
|
|
26
|
+
#
|
|
27
|
+
# show the given error message on stderr and exit
|
|
28
|
+
#
|
|
29
|
+
# params:
|
|
30
|
+
# 1: l_msg - the error message to display
|
|
31
|
+
#
|
|
32
|
+
error() {
|
|
33
|
+
local l_msg="$1"
|
|
34
|
+
# use ansi red for error
|
|
35
|
+
color_msg $red "Error:" 1>&2
|
|
36
|
+
color_msg $red "\t$l_msg" 1>&2
|
|
37
|
+
exit 1
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
#
|
|
41
|
+
# show a negative message
|
|
42
|
+
#
|
|
43
|
+
negative() {
|
|
44
|
+
local l_msg="$1"
|
|
45
|
+
color_msg $red "❌:$l_msg"
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
#
|
|
49
|
+
# show a positive message
|
|
50
|
+
#
|
|
51
|
+
positive() {
|
|
52
|
+
local l_msg="$1"
|
|
53
|
+
color_msg $green "✅:$l_msg"
|
|
54
|
+
}
|
|
55
|
+
|
|
56
|
+
# show usage
|
|
57
|
+
#
|
|
58
|
+
usage() {
|
|
59
|
+
echo "$0 [-g|--green|-m|--module|-t|--tox|-h|--help]"
|
|
60
|
+
echo "-t |--tox: run tests with tox"
|
|
61
|
+
echo "-g |--green: run tests with green"
|
|
62
|
+
echo "-m |--module: run modulewise test"
|
|
63
|
+
echo "-h |--help: show this usage"
|
|
64
|
+
echo "default is running tests with unittest discover"
|
|
65
|
+
exit 1
|
|
66
|
+
}
|
|
67
|
+
|
|
68
|
+
#
|
|
69
|
+
# check and optional install the given package
|
|
70
|
+
#
|
|
71
|
+
check_package() {
|
|
72
|
+
local l_package="$1"
|
|
73
|
+
pip show $l_package > /dev/null
|
|
74
|
+
if [ $? -ne 0 ]
|
|
75
|
+
then
|
|
76
|
+
negative "$l_package"
|
|
77
|
+
color_msg $blue "installing $l_package"
|
|
78
|
+
pip install $l_package
|
|
79
|
+
else
|
|
80
|
+
positive "$l_package"
|
|
81
|
+
fi
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
#
|
|
85
|
+
# test module by module
|
|
86
|
+
#
|
|
87
|
+
modulewise_test() {
|
|
88
|
+
foundErrors=0
|
|
89
|
+
foundTests=0
|
|
90
|
+
for testmodule in tests/test*.py
|
|
91
|
+
do
|
|
92
|
+
echo "testing $testmodule ..."
|
|
93
|
+
# see https://github.com/CleanCut/green/issues/263
|
|
94
|
+
#green $testmodule -s1
|
|
95
|
+
python -m unittest $testmodule
|
|
96
|
+
exit_code=$?
|
|
97
|
+
foundErrors=$((foundErrors+exit_code))
|
|
98
|
+
foundTests=$((foundTests+1))
|
|
99
|
+
done
|
|
100
|
+
echo "$foundErrors/$foundTests module unit tests failed" 1>&2
|
|
101
|
+
if [[ $foundErrors -gt 0 ]]
|
|
102
|
+
then
|
|
103
|
+
exit 1
|
|
104
|
+
fi
|
|
105
|
+
}
|
|
106
|
+
|
|
107
|
+
export PYTHON_PATH="."
|
|
108
|
+
while [ "$1" != "" ]
|
|
109
|
+
do
|
|
110
|
+
option="$1"
|
|
111
|
+
case $option in
|
|
112
|
+
-h|--help)
|
|
113
|
+
usage
|
|
114
|
+
exit 0
|
|
115
|
+
;;
|
|
116
|
+
-g|--green)
|
|
117
|
+
check_package green
|
|
118
|
+
green tests -s 1
|
|
119
|
+
exit 0
|
|
120
|
+
;;
|
|
121
|
+
-m|--module)
|
|
122
|
+
modulewise_test
|
|
123
|
+
exit 0
|
|
124
|
+
;;
|
|
125
|
+
-t|--tox)
|
|
126
|
+
check_package tox
|
|
127
|
+
tox -e py
|
|
128
|
+
exit 0
|
|
129
|
+
;;
|
|
130
|
+
esac
|
|
131
|
+
done
|
|
132
|
+
python3 -m unittest discover
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
"""
|
|
2
|
+
semantify³ - Extract knowledge graph ready triples from human-readable annotations wherever possible.
|
|
3
|
+
|
|
4
|
+
Syntax matters!
|
|
5
|
+
|
|
6
|
+
Created: 2025-01-29
|
|
7
|
+
Authors: Wolfgang Fahl, Tim Holzheim
|
|
8
|
+
Repository: https://github.com/BITPlan/semantify3
|
|
9
|
+
"""
|
|
10
|
+
|
|
11
|
+
__version__ = "0.0.1"
|
|
@@ -0,0 +1,169 @@
|
|
|
1
|
+
"""Command-line interface for semantify³.
|
|
2
|
+
|
|
3
|
+
```yaml
|
|
4
|
+
# 🌐🕸
|
|
5
|
+
extractor:
|
|
6
|
+
isA: PythonModule
|
|
7
|
+
author: Wolfgang Fahl
|
|
8
|
+
createdAt: 2025-11-29
|
|
9
|
+
purpose: extraction of relevant markup snippets for semantify³.
|
|
10
|
+
```
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
import glob
|
|
14
|
+
import logging
|
|
15
|
+
import re
|
|
16
|
+
from dataclasses import dataclass
|
|
17
|
+
from typing import List, Optional
|
|
18
|
+
|
|
19
|
+
from basemkit.yamlable import lod_storable
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
@lod_storable
|
|
23
|
+
@dataclass
|
|
24
|
+
class Markup:
|
|
25
|
+
"""A single markup."""
|
|
26
|
+
|
|
27
|
+
lang: str
|
|
28
|
+
code: str
|
|
29
|
+
source: str
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
class Extractor:
|
|
33
|
+
"""Extract semantic annotation markup from files."""
|
|
34
|
+
|
|
35
|
+
def __init__(self, marker: str = "🌐🕸", debug: bool = False):
|
|
36
|
+
"""constructor."""
|
|
37
|
+
self.marker = marker
|
|
38
|
+
self.debug = debug
|
|
39
|
+
self.logger = logging.getLogger(__name__)
|
|
40
|
+
self.logger.setLevel(logging.DEBUG if debug else logging.INFO)
|
|
41
|
+
|
|
42
|
+
def log(self, msg: str):
|
|
43
|
+
if self.debug:
|
|
44
|
+
self.logger.debug(msg)
|
|
45
|
+
|
|
46
|
+
def extract_from_file(self, filepath: str) -> List[Markup]:
|
|
47
|
+
"""Extract markup snippets from a single file.
|
|
48
|
+
|
|
49
|
+
Args:
|
|
50
|
+
filepath: Path to the file to extract from.
|
|
51
|
+
|
|
52
|
+
Returns:
|
|
53
|
+
List[Markup]: List of extracted markup snippets.
|
|
54
|
+
"""
|
|
55
|
+
markups = []
|
|
56
|
+
try:
|
|
57
|
+
with open(filepath, "r", encoding="utf-8") as f:
|
|
58
|
+
content = f.read()
|
|
59
|
+
markups = self.extract_from_text(content, source_path=filepath)
|
|
60
|
+
except (IOError, UnicodeDecodeError) as e:
|
|
61
|
+
self.logger.warning(f"Error reading {filepath}: {e}")
|
|
62
|
+
markups = []
|
|
63
|
+
return markups
|
|
64
|
+
|
|
65
|
+
def extract_from_text(
|
|
66
|
+
self, text: str, source_path: Optional[str] = None
|
|
67
|
+
) -> List[Markup]:
|
|
68
|
+
"""Extract all semantic markup snippets from text.
|
|
69
|
+
|
|
70
|
+
Args:
|
|
71
|
+
text: The source text to extract from.
|
|
72
|
+
source_path: Optional file path for location tracking.
|
|
73
|
+
|
|
74
|
+
Returns:
|
|
75
|
+
List[Markup]: List of extracted markup snippets.
|
|
76
|
+
"""
|
|
77
|
+
markups = []
|
|
78
|
+
|
|
79
|
+
# Pattern to match code blocks with yaml or sidif
|
|
80
|
+
pattern = re.compile(
|
|
81
|
+
r"```(yaml|sidif)\s*\n" # Opening fence with language
|
|
82
|
+
r"(.*?)" # Content (non-greedy)
|
|
83
|
+
r"\n\s*```", # Closing fence
|
|
84
|
+
re.DOTALL,
|
|
85
|
+
)
|
|
86
|
+
|
|
87
|
+
for match in pattern.finditer(text):
|
|
88
|
+
lang = match.group(1)
|
|
89
|
+
raw_content = match.group(2)
|
|
90
|
+
|
|
91
|
+
# Find first non-empty line
|
|
92
|
+
lines = raw_content.split("\n")
|
|
93
|
+
first_content_idx = None
|
|
94
|
+
|
|
95
|
+
for idx, line in enumerate(lines):
|
|
96
|
+
if line.strip():
|
|
97
|
+
first_content_idx = idx
|
|
98
|
+
break
|
|
99
|
+
|
|
100
|
+
if first_content_idx is None:
|
|
101
|
+
continue
|
|
102
|
+
|
|
103
|
+
first_line = lines[first_content_idx].strip()
|
|
104
|
+
|
|
105
|
+
# Check for marker
|
|
106
|
+
if self.marker not in first_line:
|
|
107
|
+
continue
|
|
108
|
+
|
|
109
|
+
# Extract content after marker line
|
|
110
|
+
content_lines = lines[first_content_idx + 1 :]
|
|
111
|
+
code = "\n".join(content_lines).strip()
|
|
112
|
+
|
|
113
|
+
if not code:
|
|
114
|
+
continue
|
|
115
|
+
|
|
116
|
+
# Calculate source line (1-based)
|
|
117
|
+
line_num = text[: match.start()].count("\n") + 1
|
|
118
|
+
|
|
119
|
+
source = ""
|
|
120
|
+
if source_path:
|
|
121
|
+
source = f"{source_path}:{line_num}"
|
|
122
|
+
|
|
123
|
+
markup = Markup(lang=lang, code=code, source=source)
|
|
124
|
+
markups.append(markup)
|
|
125
|
+
|
|
126
|
+
if self.debug and len(markups) > 0:
|
|
127
|
+
self.log(f"Found {len(markups)} snippets in {source_path}")
|
|
128
|
+
|
|
129
|
+
return markups
|
|
130
|
+
|
|
131
|
+
def extract_from_glob(self, pattern: str) -> List[Markup]:
|
|
132
|
+
"""Extract markup snippets from files matching a glob pattern.
|
|
133
|
+
|
|
134
|
+
Args:
|
|
135
|
+
pattern: Glob pattern to match files (supports **).
|
|
136
|
+
|
|
137
|
+
Returns:
|
|
138
|
+
List[Markup]: All markup snippets from matching files.
|
|
139
|
+
"""
|
|
140
|
+
all_markups = []
|
|
141
|
+
|
|
142
|
+
files = glob.glob(pattern, recursive=True)
|
|
143
|
+
self.log(f"Glob pattern '{pattern}' found {len(files)} files")
|
|
144
|
+
|
|
145
|
+
for filepath in files:
|
|
146
|
+
markups = self.extract_from_file(filepath)
|
|
147
|
+
all_markups.extend(markups)
|
|
148
|
+
|
|
149
|
+
return all_markups
|
|
150
|
+
|
|
151
|
+
def extract_from_glob_list(self, patterns: List[str]) -> List[Markup]:
|
|
152
|
+
"""Extract markup snippets from files matching multiple glob patterns.
|
|
153
|
+
|
|
154
|
+
Args:
|
|
155
|
+
patterns: List of glob patterns to match files.
|
|
156
|
+
|
|
157
|
+
Returns:
|
|
158
|
+
List[Markup]: All markup snippets from matching files.
|
|
159
|
+
"""
|
|
160
|
+
all_markups = []
|
|
161
|
+
|
|
162
|
+
self.log(f"Processing {len(patterns)} glob patterns")
|
|
163
|
+
|
|
164
|
+
for pattern in patterns:
|
|
165
|
+
self.log(f"Checking pattern: {pattern}")
|
|
166
|
+
markups = self.extract_from_glob(pattern)
|
|
167
|
+
all_markups.extend(markups)
|
|
168
|
+
|
|
169
|
+
return all_markups
|
|
@@ -0,0 +1,116 @@
|
|
|
1
|
+
"""Command-line interface for semantify³.
|
|
2
|
+
|
|
3
|
+
```yaml
|
|
4
|
+
🌐🕸
|
|
5
|
+
sem3_cmd:
|
|
6
|
+
isA: PythonModule
|
|
7
|
+
author: Wolfgang Fahl
|
|
8
|
+
createdAt: 2025-11-29
|
|
9
|
+
purpose: Command-line interface for semantify³.
|
|
10
|
+
```
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
from argparse import ArgumentParser, Namespace
|
|
14
|
+
import argparse
|
|
15
|
+
import os
|
|
16
|
+
import sys
|
|
17
|
+
|
|
18
|
+
from basemkit.base_cmd import BaseCmd
|
|
19
|
+
from sem3.extractor import Extractor
|
|
20
|
+
from sem3.version import Version
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
class Semantify3Cmd(BaseCmd):
|
|
24
|
+
"""Command line interface for semantify³."""
|
|
25
|
+
|
|
26
|
+
def __init__(self):
|
|
27
|
+
"""Initialize the semantify³ command."""
|
|
28
|
+
super().__init__(version=Version, description=Version.description)
|
|
29
|
+
|
|
30
|
+
def get_arg_parser(self) -> ArgumentParser:
|
|
31
|
+
"""Create and configure the argument parser.
|
|
32
|
+
|
|
33
|
+
Returns:
|
|
34
|
+
ArgumentParser: The configured argument parser.
|
|
35
|
+
"""
|
|
36
|
+
parser = super().get_arg_parser()
|
|
37
|
+
parser.add_argument('files', type=argparse.FileType('r'), nargs='*')
|
|
38
|
+
|
|
39
|
+
parser.add_argument(
|
|
40
|
+
"-i",
|
|
41
|
+
"--input",
|
|
42
|
+
type=str,
|
|
43
|
+
help="Input file glob expression",
|
|
44
|
+
)
|
|
45
|
+
parser.add_argument(
|
|
46
|
+
"-o",
|
|
47
|
+
"--output",
|
|
48
|
+
type=str,
|
|
49
|
+
help="Output file path for triples",
|
|
50
|
+
)
|
|
51
|
+
parser.add_argument(
|
|
52
|
+
"--format",
|
|
53
|
+
type=str,
|
|
54
|
+
choices=[
|
|
55
|
+
"turtle",
|
|
56
|
+
"n3",
|
|
57
|
+
"ntriples",
|
|
58
|
+
"xml",
|
|
59
|
+
"json-ld",
|
|
60
|
+
"sidif",
|
|
61
|
+
"graphml", # Supported by Gremlin and Neo4j (via APOC)
|
|
62
|
+
"graphson", # Gremlin specific JSON
|
|
63
|
+
"cypher", # Neo4j Cypher CREATE statements
|
|
64
|
+
],
|
|
65
|
+
default="turtle",
|
|
66
|
+
help="Output serialization format (default: turtle)",
|
|
67
|
+
)
|
|
68
|
+
return parser
|
|
69
|
+
|
|
70
|
+
def handle_args(self, args: Namespace) -> bool:
|
|
71
|
+
"""Handle parsed arguments.
|
|
72
|
+
|
|
73
|
+
Args:
|
|
74
|
+
args: Parsed argument namespace.
|
|
75
|
+
|
|
76
|
+
Returns:
|
|
77
|
+
bool: True if handled, False otherwise.
|
|
78
|
+
"""
|
|
79
|
+
handled = super().handle_args(args)
|
|
80
|
+
if handled:
|
|
81
|
+
return True
|
|
82
|
+
|
|
83
|
+
if args.input or args.files:
|
|
84
|
+
extractor = Extractor(debug=self.debug)
|
|
85
|
+
markups = []
|
|
86
|
+
if args.input:
|
|
87
|
+
markups.extend(extractor.extract_from_glob(args.input))
|
|
88
|
+
if args.files:
|
|
89
|
+
for file_path in args.files:
|
|
90
|
+
markups.extend(extractor.extract_from_file(file_path))
|
|
91
|
+
if args.verbose:
|
|
92
|
+
print(f"Found {len(markups)} markups")
|
|
93
|
+
for i, markup in enumerate(markups):
|
|
94
|
+
print(f"{i+1}: {markup.lang} in {os.path.basename(markup.source)}")
|
|
95
|
+
print(markup.code)
|
|
96
|
+
print("-" * 20)
|
|
97
|
+
return True
|
|
98
|
+
|
|
99
|
+
return False
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
def main(argv=None) -> int:
|
|
103
|
+
"""Main entry point for semantify3 CLI.
|
|
104
|
+
|
|
105
|
+
Args:
|
|
106
|
+
argv: Command line arguments.
|
|
107
|
+
|
|
108
|
+
Returns:
|
|
109
|
+
int: Exit code.
|
|
110
|
+
"""
|
|
111
|
+
cmd = Semantify3Cmd()
|
|
112
|
+
return cmd.run(argv)
|
|
113
|
+
|
|
114
|
+
|
|
115
|
+
if __name__ == "__main__":
|
|
116
|
+
sys.exit(main())
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
"""Created on 2025-11-29.
|
|
2
|
+
|
|
3
|
+
@author: wf
|
|
4
|
+
"""
|
|
5
|
+
|
|
6
|
+
from basemkit.yamlable import lod_storable
|
|
7
|
+
|
|
8
|
+
import sem3
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
@lod_storable
|
|
12
|
+
class Version:
|
|
13
|
+
"""Version handling for semantify³."""
|
|
14
|
+
|
|
15
|
+
name = "semantify³"
|
|
16
|
+
version = sem3.__version__
|
|
17
|
+
date = "2025-11-29"
|
|
18
|
+
updated = "2025-11-29"
|
|
19
|
+
description = "Extract knowledge graph ready triples from human-readable annotations wherever possible — Syntax matters!"
|
|
20
|
+
|
|
21
|
+
authors = "Wolfgang Fahl, Tim Holzheim"
|
|
22
|
+
|
|
23
|
+
doc_url = "https://wiki.bitplan.com/index.php/semantify3"
|
|
24
|
+
chat_url = "https://github.com/BITPlan/semantify3/discussions"
|
|
25
|
+
cm_url = "https://github.com/BITPlan/semantify3"
|
|
26
|
+
|
|
27
|
+
license = """Copyright 2025 contributors. All rights reserved.
|
|
28
|
+
|
|
29
|
+
Licensed under the Apache License 2.0
|
|
30
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
31
|
+
|
|
32
|
+
Distributed on an "AS IS" basis without warranties
|
|
33
|
+
or conditions of any kind, either express or implied."""
|
|
34
|
+
|
|
35
|
+
longDescription = f"""{name} version {version}
|
|
36
|
+
{description}
|
|
37
|
+
|
|
38
|
+
Created by {authors} on {date} last updated {updated}"""
|
|
File without changes
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
"""
|
|
2
|
+
```sidif
|
|
3
|
+
# 🌐🕸
|
|
4
|
+
test_extractor isA PythonModule
|
|
5
|
+
"Wolfgang Fahl" is author of it
|
|
6
|
+
"2025-11-29" is createdAt of it
|
|
7
|
+
"Test main micro annotation snippet extraction" is purpose of it
|
|
8
|
+
```
|
|
9
|
+
"""
|
|
10
|
+
|
|
11
|
+
import os
|
|
12
|
+
|
|
13
|
+
from basemkit.basetest import Basetest
|
|
14
|
+
|
|
15
|
+
from sem3.extractor import Extractor
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
class Test_Extractor(Basetest):
|
|
19
|
+
"""Test the extractor."""
|
|
20
|
+
|
|
21
|
+
def setUp(self, debug=True, profile=True):
|
|
22
|
+
Basetest.setUp(self, debug=debug, profile=profile)
|
|
23
|
+
self.script_path = os.path.abspath(__file__)
|
|
24
|
+
self.project_root = os.path.dirname(os.path.dirname(self.script_path))
|
|
25
|
+
|
|
26
|
+
def test_extract_from_own_source(self):
|
|
27
|
+
"""Test that the extractor can find annotations in the project's own
|
|
28
|
+
source code."""
|
|
29
|
+
# recursive=True in glob() requires the "**" pattern to actually traverse directories
|
|
30
|
+
glob_patterns = [
|
|
31
|
+
os.path.join(self.project_root, "**", "*.py"),
|
|
32
|
+
]
|
|
33
|
+
|
|
34
|
+
extractor = Extractor(debug=self.debug)
|
|
35
|
+
markups = extractor.extract_from_glob_list(glob_patterns)
|
|
36
|
+
if self.debug:
|
|
37
|
+
print(f"Found {len(markups)} markups")
|
|
38
|
+
for i, markup in enumerate(markups):
|
|
39
|
+
print(f"{i+1}: {markup.lang} in {os.path.basename(markup.source)}")
|
|
40
|
+
print(markup.code)
|
|
41
|
+
print("-" * 20)
|
|
42
|
+
self.assertGreaterEqual(3, len(markups))
|
|
43
|
+
for markup in markups:
|
|
44
|
+
for field in ["isA", "author", "createdAt", "purpose"]:
|
|
45
|
+
self.assertTrue(field in markup.code)
|