maqayis 1.0.0__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.
- maqayis-1.0.0/.github/workflows/publish.yml +32 -0
- maqayis-1.0.0/CITATION.cff +25 -0
- maqayis-1.0.0/GOVERNANCE.md +32 -0
- maqayis-1.0.0/LICENSE +190 -0
- maqayis-1.0.0/NOTICE +24 -0
- maqayis-1.0.0/PKG-INFO +114 -0
- maqayis-1.0.0/README.md +89 -0
- maqayis-1.0.0/SECURITY.md +29 -0
- maqayis-1.0.0/logo.png +0 -0
- maqayis-1.0.0/pyproject.toml +37 -0
- maqayis-1.0.0/src/maqayis/__init__.py +6 -0
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
name: Publish to PyPI (maqayis)
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
release:
|
|
5
|
+
types: ["published"]
|
|
6
|
+
workflow_dispatch:
|
|
7
|
+
|
|
8
|
+
permissions:
|
|
9
|
+
contents: read
|
|
10
|
+
id-token: write
|
|
11
|
+
|
|
12
|
+
env:
|
|
13
|
+
TARKIB_OPENITI_ONLY: "1"
|
|
14
|
+
|
|
15
|
+
jobs:
|
|
16
|
+
publish:
|
|
17
|
+
runs-on: ubuntu-latest
|
|
18
|
+
steps:
|
|
19
|
+
- name: Checkout repository
|
|
20
|
+
uses: actions/checkout@v4
|
|
21
|
+
|
|
22
|
+
- name: Install uv
|
|
23
|
+
uses: astral-sh/setup-uv@v5
|
|
24
|
+
|
|
25
|
+
- name: Set up Python 3.12
|
|
26
|
+
run: uv python install 3.12
|
|
27
|
+
|
|
28
|
+
- name: Build wheel and sdist
|
|
29
|
+
run: uv build
|
|
30
|
+
|
|
31
|
+
- name: Publish package distributions to PyPI via OIDC Trusted Publisher
|
|
32
|
+
uses: pypa/gh-action-pypi-publish@release/v1
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
cff-version: 1.2.0
|
|
2
|
+
message: "If you use the Maqāyīs ecosystem, unified portal, atlases, or benchmarks in your research or software, please cite this work."
|
|
3
|
+
title: "Maqāyīs: Unified Open Ecosystem for Arabic Computational Philology, Sub-Lexical Algebra, and Zero-LLM NLP"
|
|
4
|
+
type: software
|
|
5
|
+
version: "1.0.0"
|
|
6
|
+
date-released: "2026-11-08"
|
|
7
|
+
license: "Apache-2.0"
|
|
8
|
+
url: "https://maqayis.org"
|
|
9
|
+
repository-code: "https://github.com/maqayis/maqayis"
|
|
10
|
+
authors:
|
|
11
|
+
- family-names: "Abdo"
|
|
12
|
+
given-names: "Salah"
|
|
13
|
+
email: "Salah.Abdo.Tech@gmail.com"
|
|
14
|
+
website: "https://maqayis.org"
|
|
15
|
+
abstract: >-
|
|
16
|
+
Umbrella open-source release architecture, unified bilingual web portal (maqayis.org),
|
|
17
|
+
and zero-cost edge observatory uniting Handasat al-Lisān al-ʿArabī (v2.0), Tarkīb (v2.0),
|
|
18
|
+
Tayf (v1.0), Dīwān al-Iṣṭilāḥ (v1.0), Misbār (v1.0), Arabic WordNet v4 (AWN4), and Manhaj.
|
|
19
|
+
keywords:
|
|
20
|
+
- "Arabic computational linguistics"
|
|
21
|
+
- "computational philology"
|
|
22
|
+
- "sub-lexical algebra"
|
|
23
|
+
- "Zero-LLM"
|
|
24
|
+
- "governed machine translation"
|
|
25
|
+
- "Maqayis"
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# Maqāyīs (`مَقاييس`) — Scientific & Open-Source Governance (`GOVERNANCE.md`)
|
|
2
|
+
|
|
3
|
+
## 1. Stewardship & Legal Grantee
|
|
4
|
+
|
|
5
|
+
**Maqāyīs (`مَقايīs`)** is founded and maintained by **Salah Abdo** (`<Salah.Abdo.Tech@gmail.com>`), Principal Investigator & Benevolent Architect. Institutional stewardship, open research trace grants, and trademark/domain continuity are held by **`"Salah Abdo and successor entity"`**.
|
|
6
|
+
|
|
7
|
+
- **Software Codebase:** Openly licensed under `Apache-2.0` (contributions follow standard Apache-2.0 Section 5 inbound=outbound terms; no separate CLA obstacle required for routine pull requests).
|
|
8
|
+
- **Book `v2.0`, Lexical Atlases & Public Curriculum:** Openly licensed under `CC BY 4.0`.
|
|
9
|
+
- **Community Research Telemetry:** Opt-in scrubbed records submitted to `POST /api/v1/traces` are granted under `CC0-1.0` / `Apache-2.0` to `"Salah Abdo and successor entity"` with permanent 1-click right-to-erasure (`DELETE /api/v1/traces/:anon_id`).
|
|
10
|
+
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
## 2. Scientific Terminology Governance (`Dīwān al-Iṣṭilāḥ` 6-Gate Protocol)
|
|
14
|
+
|
|
15
|
+
Every new scientific term proposal or classical witness challenge submitted via `POST /api/v1/diwan/propose` or GitHub Pull Request undergoes a two-stage verification protocol before promotion from `provisional` / `pending_review` to `confirmed`:
|
|
16
|
+
|
|
17
|
+
1. **Automated Deterministic Gate (`Tarkīb` + `Edge Observatory`):**
|
|
18
|
+
- **Gate 1 (`Σ₂₈` & Root Attestation):** Root must consist of 3 or 4 canonical Arabic radicals attested in classical pre-1205 AH lexica (or explicitly marked as one of the `83` gold safe *Muhmal* reservists / `taʿrīb` loan mechanisms).
|
|
19
|
+
- **Gate 2 (Biomechanical OCP & Template Well-Formedness):** Zero `C₁=C₂` onset gemination deadlocks, zero forbidden guttural/coronal OCP clashes, and well-formed Unicode *ḥarakāt*.
|
|
20
|
+
- **Gate 3 (Morphological Pattern Licensing):** Valid `B01–B31` morphological operator & Sībawayh `F07` (`infaʿala`) assimilation/blocking compliance.
|
|
21
|
+
- **Gate 4 (Exact Collision Freedom):** Zero injective collision with existing `Dīwān` concepts in the target domain.
|
|
22
|
+
- **Gate 5 (*Taṣḥīf* & *Rasm* Guardband):** Undotted *rasm* skeleton verified against confusable neighbor collisions.
|
|
23
|
+
- **Gate 6 (Discourse Folding `F ⊣ U`):** Explicit `U → F1 → F2` surface trajectory and 8-form paradigm where applicable.
|
|
24
|
+
- **Clean-Room Witness Rule:** `witness_citation` is capped at `<= 280` characters (bibliographic source ID + headword + classical *aṣl* pointer only — verbatim modern dictionary prose is strictly prohibited).
|
|
25
|
+
2. **Blind Human Calibration (`Misbār` Review Queue):**
|
|
26
|
+
- Passing proposals are ingested via `scripts/pull_maqayis_to_misbar.py` into blind RTL/LTR `Misbār` review queues before public listing on `GET /api/v1/diwan/proposals` and inclusion in `diwan_public.db`.
|
|
27
|
+
|
|
28
|
+
---
|
|
29
|
+
|
|
30
|
+
## 3. Open Benchmarks Verification Protocol
|
|
31
|
+
|
|
32
|
+
Submissions to `Maqāyīs Open Benchmarks` (`POST /api/v1/benchmarks/submit`) require a public `https://` code or paper repository URL so results across the 5 suites (`tayf_homonym_20`, `rasm_viterbi`, `tarkib_guard_200`, `governed_mt_folding`, `subroot_composition`) can be independently reproduced prior to promotion to `status = 'verified'`.
|
maqayis-1.0.0/LICENSE
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
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
|
+
Copyright 2026 Salah Abdo (Maqāyīs Organization — https://maqayis.org)
|
|
179
|
+
|
|
180
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
181
|
+
you may not use this file except in compliance with the License.
|
|
182
|
+
You may obtain a copy of the License at
|
|
183
|
+
|
|
184
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
185
|
+
|
|
186
|
+
Unless required by applicable law or agreed to in writing, software
|
|
187
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
188
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
189
|
+
See the License for the specific language governing permissions and
|
|
190
|
+
limitations under the License.
|
maqayis-1.0.0/NOTICE
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
Maqāyīs (مَقاييس) — Unified Arabic Computational Philology & Zero-LLM NLP Ecosystem
|
|
2
|
+
Copyright 2026 Salah Abdo and successor entity (https://maqayis.org | https://github.com/maqayis)
|
|
3
|
+
|
|
4
|
+
1. SOFTWARE LICENSE (Apache-2.0):
|
|
5
|
+
All software source code, Python packages (`tarkib`, `tayf`, `diwan`, `misbar`, `manhaj`),
|
|
6
|
+
the unified web portal application (`portal/`), and the Cloudflare Edge Observatory Worker
|
|
7
|
+
(`edge-worker/`) are licensed under the Apache License, Version 2.0.
|
|
8
|
+
|
|
9
|
+
2. BOOK, PUBLIC ATLASES & CURRICULUM LICENSE (CC BY 4.0):
|
|
10
|
+
- Handasat al-Lisān al-ʿArabī (هندسة اللسان العربي — v2.0) and its 10 companion monographs,
|
|
11
|
+
- The Al-Jadwal 28³ Periodic Root Atlas, Iqtirān 66-Atom Atlas, Dīwān al-Iṣṭilāḥ public ledger,
|
|
12
|
+
Arabic WordNet v4 (AWN4) static semantic neighborhood index, and Tayf retrieval arena bundle,
|
|
13
|
+
- The public Manhaj educational curriculum
|
|
14
|
+
are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0):
|
|
15
|
+
https://creativecommons.org/licenses/by/4.0/
|
|
16
|
+
|
|
17
|
+
3. CLASSICAL CORPUS & LEXICAL PROVENANCE:
|
|
18
|
+
Classical Arabic lexical statistics and root *uṣūl* summaries are derived cleanly from
|
|
19
|
+
open pre-modern classical texts in the Open Islamicate Texts Initiative (OpenITI) corpus,
|
|
20
|
+
including Ibn Fāris's *Maqāyīs al-Lugha* (d. 395 AH), al-Khalīl's *Kitāb al-ʿAyn* (d. 175 AH),
|
|
21
|
+
al-Jawharī's *al-Ṣiḥāḥ* (d. 393 AH), Ibn Manẓūr's *Lisān al-ʿArab* (d. 711 AH), and
|
|
22
|
+
al-Zabīdī's *Tāj al-ʿArūs* (d. 1205 AH).
|
|
23
|
+
Showcase scientific paper translations in `/static-api/papers/` translate open-access arXiv
|
|
24
|
+
preprints (Khattab & Zaharia 2020; Hu et al. 2021; Wang et al. 2024) with full author attribution.
|
maqayis-1.0.0/PKG-INFO
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
1
|
+
Metadata-Version: 2.5
|
|
2
|
+
Name: maqayis
|
|
3
|
+
Version: 1.0.0
|
|
4
|
+
Summary: Maqayis — Umbrella meta-package for Open Arabic Computational Philology, Sub-Lexical Algebra, Zero-LLM Retrieval, and Governed Scientific MT
|
|
5
|
+
Project-URL: Homepage, https://maqayis.org
|
|
6
|
+
Project-URL: Repository, https://github.com/maqayis/maqayis
|
|
7
|
+
Project-URL: Issues, https://github.com/maqayis/maqayis/issues
|
|
8
|
+
Author-email: Salah Abdo <Salah.Abdo.Tech@gmail.com>
|
|
9
|
+
License: Apache-2.0
|
|
10
|
+
License-File: LICENSE
|
|
11
|
+
License-File: NOTICE
|
|
12
|
+
Keywords: arabic,computational-philology,diwan,maqayis,misbar,nlp,sarfchat,tarkib,tayf
|
|
13
|
+
Classifier: Development Status :: 5 - Production/Stable
|
|
14
|
+
Classifier: Intended Audience :: Science/Research
|
|
15
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
16
|
+
Classifier: Natural Language :: Arabic
|
|
17
|
+
Classifier: Programming Language :: Python :: 3
|
|
18
|
+
Requires-Python: >=3.10
|
|
19
|
+
Requires-Dist: maqayis-diwan>=1.0.0
|
|
20
|
+
Requires-Dist: misbar>=1.0.0
|
|
21
|
+
Requires-Dist: sarfchat>=2.0.0
|
|
22
|
+
Requires-Dist: tarkib>=2.0.0
|
|
23
|
+
Requires-Dist: tayf>=1.0.0
|
|
24
|
+
Description-Content-Type: text/markdown
|
|
25
|
+
|
|
26
|
+
<div align="center">
|
|
27
|
+
<img src="logo.png" width="140" height="140" alt="Maqāyīs Emblem" />
|
|
28
|
+
</div>
|
|
29
|
+
|
|
30
|
+
# مَقاييس · Maqāyīs — Umbrella Specification, Unified Web Portal & Edge Observatory
|
|
31
|
+
|
|
32
|
+
[](https://maqayis.org)
|
|
33
|
+
[](LICENSE)
|
|
34
|
+
[](NOTICE)
|
|
35
|
+
|
|
36
|
+
**Maqāyīs (`مَقاييس`)** is the open-source umbrella repository and unified web portal (`https://maqayis.org`) integrating six interconnected pillars of Arabic computational philology, sub-lexical linear algebra, Zero-LLM geometric retrieval, governed scientific machine translation, and open bilingual pedagogy.
|
|
37
|
+
|
|
38
|
+
---
|
|
39
|
+
|
|
40
|
+
## 1. Ecosystem Architecture
|
|
41
|
+
|
|
42
|
+
```
|
|
43
|
+
https://maqayis.org (Cloudflare Pages · $0/mo)
|
|
44
|
+
┌──────────────────┬──────────────────┬──────────────────┬──────────────────┐
|
|
45
|
+
│ Book v2.0 & 10 │ Unified Lexicon │ Zero-LLM Browser │ Governed MT │
|
|
46
|
+
│ Monographs │ Al-Jadwal (28³) │ Tarkīb + Tayf │ X-Ray Reader + │
|
|
47
|
+
│ + 140 Concepts │ Iqtirān (66) │ 5-Law Switchboard│ Zero-Custody │
|
|
48
|
+
│ + 75 Claims │ Dīwān + AWN4 │ (<5 ms JS) │ BYOK Studio │
|
|
49
|
+
└────────┬─────────┴────────┬─────────┴────────┬─────────┴────────┬─────────┘
|
|
50
|
+
│ │ │ │
|
|
51
|
+
▼ ▼ ▼ ▼
|
|
52
|
+
┌───────────────────────────────────────────────────────────────────────────┐
|
|
53
|
+
│ Clean-Room Open-Source Packages & Datasets (github.com/maqayis/*) │
|
|
54
|
+
│ • maqayis/tarkib (v2.0.0) • maqayis/tayf (v1.0.0) │
|
|
55
|
+
│ • maqayis/diwan (v1.0.0) • maqayis/misbar (v1.0.0) • maqayis/manhaj │
|
|
56
|
+
└───────────────────────────────────────────────────────────────────────────┘
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
---
|
|
60
|
+
|
|
61
|
+
## 2. Quickstart Across Packages
|
|
62
|
+
|
|
63
|
+
### Python SDKs (`tarkib`, `tayf`, `misbar`, `diwan`)
|
|
64
|
+
|
|
65
|
+
```bash
|
|
66
|
+
# Sub-lexical root algebra, OCP phonotactics, rasm Viterbi & Iqtirān 66-atom engine
|
|
67
|
+
pip install tarkib
|
|
68
|
+
|
|
69
|
+
# Zero-LLM Grassmannian, Ontological & Metaphor-Aware Arabic RAG Arena
|
|
70
|
+
pip install tayf
|
|
71
|
+
|
|
72
|
+
# Deterministic workflow tracing & blind RTL/LTR review queues
|
|
73
|
+
pip install misbar
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
### Unified Web Portal (`portal/`)
|
|
77
|
+
|
|
78
|
+
Zero external npm bundler bloat is required — the portal uses native ES modules, modular CSS tokens, and static JSON shards:
|
|
79
|
+
|
|
80
|
+
```bash
|
|
81
|
+
# Assemble and validate portal/dist/ (checks HTML links, UTF-8 JSON & Cloudflare Pages quotas)
|
|
82
|
+
python3 portal/build_portal.py
|
|
83
|
+
|
|
84
|
+
# Serve locally on http://localhost:8788
|
|
85
|
+
python3 -m http.server 8788 --directory portal/dist
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
### Zero-Cost Edge Observatory (`edge-worker/`)
|
|
89
|
+
|
|
90
|
+
```bash
|
|
91
|
+
# Run full Node.js WinterCG test suite (in-memory SQLite D1 harness)
|
|
92
|
+
node --test edge-worker/tests/worker.test.mjs
|
|
93
|
+
```
|
|
94
|
+
|
|
95
|
+
---
|
|
96
|
+
|
|
97
|
+
## 3. Licensing & Clean-Room Provenance Matrix
|
|
98
|
+
|
|
99
|
+
| Asset Class | Scope | License |
|
|
100
|
+
| :--- | :--- | :--- |
|
|
101
|
+
| **Software & Runtime Code** | `tarkib`, `tayf`, `diwan`, `misbar`, `manhaj` runtimes, `portal/`, `edge-worker/`, `scripts/` | **Apache License 2.0** (`Apache-2.0`) |
|
|
102
|
+
| **Scholarly Book & Monographs** | *Handasat al-Lisān al-ʿArabī* (`v2.0`) & 10 companion monographs | **CC BY 4.0** |
|
|
103
|
+
| **Public Lexical-Geometric Atlases** | `Al-Jadwal` (`11,249` roots), `Iqtirān` (`66` operators), `Dīwān` (`diwan_public.db`), `AWN4` (`120,630` synsets), `Tayf` arena | **CC BY 4.0** |
|
|
104
|
+
| **Public Academy Curriculum** | `Manhaj` computational linguistics & mathematical foundations tracks | **CC BY 4.0** |
|
|
105
|
+
|
|
106
|
+
All lexical statistics and classical root *uṣūl* in Maqāyīs public releases are derived strictly from open pre-modern Arabic corpora (**OpenITI**, including Ibn Fāris's *Maqāyīs al-Lugha*, al-Khalīl's *Kitāb al-ʿAyn*, al-Jawharī's *al-Ṣiḥāḥ*, Ibn Manẓūr's *Lisān al-ʿArab*, and al-Zabīdī's *Tāj al-ʿArūs*) with zero verbatim copyrighted modern dictionary prose.
|
|
107
|
+
|
|
108
|
+
---
|
|
109
|
+
|
|
110
|
+
## 4. Citation & Stewardship
|
|
111
|
+
|
|
112
|
+
- **Author:** Salah Abdo (`<Salah.Abdo.Tech@gmail.com>`)
|
|
113
|
+
- **Governance & Security:** See [`GOVERNANCE.md`](GOVERNANCE.md) and [`SECURITY.md`](SECURITY.md).
|
|
114
|
+
- **Machine-Readable Citation:** See [`CITATION.cff`](CITATION.cff) or click **Cite / BibTeX** on [https://maqayis.org](https://maqayis.org).
|
maqayis-1.0.0/README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
<img src="logo.png" width="140" height="140" alt="Maqāyīs Emblem" />
|
|
3
|
+
</div>
|
|
4
|
+
|
|
5
|
+
# مَقاييس · Maqāyīs — Umbrella Specification, Unified Web Portal & Edge Observatory
|
|
6
|
+
|
|
7
|
+
[](https://maqayis.org)
|
|
8
|
+
[](LICENSE)
|
|
9
|
+
[](NOTICE)
|
|
10
|
+
|
|
11
|
+
**Maqāyīs (`مَقاييس`)** is the open-source umbrella repository and unified web portal (`https://maqayis.org`) integrating six interconnected pillars of Arabic computational philology, sub-lexical linear algebra, Zero-LLM geometric retrieval, governed scientific machine translation, and open bilingual pedagogy.
|
|
12
|
+
|
|
13
|
+
---
|
|
14
|
+
|
|
15
|
+
## 1. Ecosystem Architecture
|
|
16
|
+
|
|
17
|
+
```
|
|
18
|
+
https://maqayis.org (Cloudflare Pages · $0/mo)
|
|
19
|
+
┌──────────────────┬──────────────────┬──────────────────┬──────────────────┐
|
|
20
|
+
│ Book v2.0 & 10 │ Unified Lexicon │ Zero-LLM Browser │ Governed MT │
|
|
21
|
+
│ Monographs │ Al-Jadwal (28³) │ Tarkīb + Tayf │ X-Ray Reader + │
|
|
22
|
+
│ + 140 Concepts │ Iqtirān (66) │ 5-Law Switchboard│ Zero-Custody │
|
|
23
|
+
│ + 75 Claims │ Dīwān + AWN4 │ (<5 ms JS) │ BYOK Studio │
|
|
24
|
+
└────────┬─────────┴────────┬─────────┴────────┬─────────┴────────┬─────────┘
|
|
25
|
+
│ │ │ │
|
|
26
|
+
▼ ▼ ▼ ▼
|
|
27
|
+
┌───────────────────────────────────────────────────────────────────────────┐
|
|
28
|
+
│ Clean-Room Open-Source Packages & Datasets (github.com/maqayis/*) │
|
|
29
|
+
│ • maqayis/tarkib (v2.0.0) • maqayis/tayf (v1.0.0) │
|
|
30
|
+
│ • maqayis/diwan (v1.0.0) • maqayis/misbar (v1.0.0) • maqayis/manhaj │
|
|
31
|
+
└───────────────────────────────────────────────────────────────────────────┘
|
|
32
|
+
```
|
|
33
|
+
|
|
34
|
+
---
|
|
35
|
+
|
|
36
|
+
## 2. Quickstart Across Packages
|
|
37
|
+
|
|
38
|
+
### Python SDKs (`tarkib`, `tayf`, `misbar`, `diwan`)
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
# Sub-lexical root algebra, OCP phonotactics, rasm Viterbi & Iqtirān 66-atom engine
|
|
42
|
+
pip install tarkib
|
|
43
|
+
|
|
44
|
+
# Zero-LLM Grassmannian, Ontological & Metaphor-Aware Arabic RAG Arena
|
|
45
|
+
pip install tayf
|
|
46
|
+
|
|
47
|
+
# Deterministic workflow tracing & blind RTL/LTR review queues
|
|
48
|
+
pip install misbar
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
### Unified Web Portal (`portal/`)
|
|
52
|
+
|
|
53
|
+
Zero external npm bundler bloat is required — the portal uses native ES modules, modular CSS tokens, and static JSON shards:
|
|
54
|
+
|
|
55
|
+
```bash
|
|
56
|
+
# Assemble and validate portal/dist/ (checks HTML links, UTF-8 JSON & Cloudflare Pages quotas)
|
|
57
|
+
python3 portal/build_portal.py
|
|
58
|
+
|
|
59
|
+
# Serve locally on http://localhost:8788
|
|
60
|
+
python3 -m http.server 8788 --directory portal/dist
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
### Zero-Cost Edge Observatory (`edge-worker/`)
|
|
64
|
+
|
|
65
|
+
```bash
|
|
66
|
+
# Run full Node.js WinterCG test suite (in-memory SQLite D1 harness)
|
|
67
|
+
node --test edge-worker/tests/worker.test.mjs
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
---
|
|
71
|
+
|
|
72
|
+
## 3. Licensing & Clean-Room Provenance Matrix
|
|
73
|
+
|
|
74
|
+
| Asset Class | Scope | License |
|
|
75
|
+
| :--- | :--- | :--- |
|
|
76
|
+
| **Software & Runtime Code** | `tarkib`, `tayf`, `diwan`, `misbar`, `manhaj` runtimes, `portal/`, `edge-worker/`, `scripts/` | **Apache License 2.0** (`Apache-2.0`) |
|
|
77
|
+
| **Scholarly Book & Monographs** | *Handasat al-Lisān al-ʿArabī* (`v2.0`) & 10 companion monographs | **CC BY 4.0** |
|
|
78
|
+
| **Public Lexical-Geometric Atlases** | `Al-Jadwal` (`11,249` roots), `Iqtirān` (`66` operators), `Dīwān` (`diwan_public.db`), `AWN4` (`120,630` synsets), `Tayf` arena | **CC BY 4.0** |
|
|
79
|
+
| **Public Academy Curriculum** | `Manhaj` computational linguistics & mathematical foundations tracks | **CC BY 4.0** |
|
|
80
|
+
|
|
81
|
+
All lexical statistics and classical root *uṣūl* in Maqāyīs public releases are derived strictly from open pre-modern Arabic corpora (**OpenITI**, including Ibn Fāris's *Maqāyīs al-Lugha*, al-Khalīl's *Kitāb al-ʿAyn*, al-Jawharī's *al-Ṣiḥāḥ*, Ibn Manẓūr's *Lisān al-ʿArab*, and al-Zabīdī's *Tāj al-ʿArūs*) with zero verbatim copyrighted modern dictionary prose.
|
|
82
|
+
|
|
83
|
+
---
|
|
84
|
+
|
|
85
|
+
## 4. Citation & Stewardship
|
|
86
|
+
|
|
87
|
+
- **Author:** Salah Abdo (`<Salah.Abdo.Tech@gmail.com>`)
|
|
88
|
+
- **Governance & Security:** See [`GOVERNANCE.md`](GOVERNANCE.md) and [`SECURITY.md`](SECURITY.md).
|
|
89
|
+
- **Machine-Readable Citation:** See [`CITATION.cff`](CITATION.cff) or click **Cite / BibTeX** on [https://maqayis.org](https://maqayis.org).
|
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
# Security & Privacy Policy (`SECURITY.md`)
|
|
2
|
+
|
|
3
|
+
## 1. Supported Versions
|
|
4
|
+
|
|
5
|
+
| Component | Version | Security Updates |
|
|
6
|
+
| :--- | :---: | :---: |
|
|
7
|
+
| `maqayis.org` Unified Portal (`portal/`) | `1.0.x` | Supported |
|
|
8
|
+
| `maqayis-edge-observatory` (`edge-worker/`) | `1.0.x` | Supported |
|
|
9
|
+
| `tarkib` | `2.0.x` | Supported |
|
|
10
|
+
| `tayf` | `1.0.x` | Supported |
|
|
11
|
+
| `diwan` | `1.0.x` | Supported |
|
|
12
|
+
| `misbar` | `1.0.x` | Supported |
|
|
13
|
+
| `manhaj` | `1.0.x` | Supported |
|
|
14
|
+
|
|
15
|
+
## 2. Zero-LLM-Custody & Privacy-by-Design Guarantees
|
|
16
|
+
|
|
17
|
+
1. **Zero Server-Side API Key Custody (`BYOK`):**
|
|
18
|
+
- `maqayis.org` and `edge-worker` **never** accept, proxy, or store user LLM API keys (`/api/v1/ai/*` returns `501 ZERO_SERVER_LLM_CUSTODY`).
|
|
19
|
+
- Any optional user-supplied `BYOK` key in the Governed MT Studio is held strictly in browser `sessionStorage` for the duration of the active tab and transmitted directly from the user's browser to their chosen provider (or local `Ollama`).
|
|
20
|
+
2. **Default-OFF Telemetry & Aggressive PII Scrubbing:**
|
|
21
|
+
- `Misbār` research telemetry is **disabled (`OFF`) by default**.
|
|
22
|
+
- When explicitly enabled by the user, `edge-worker` enforces a hard `<= 64 KB` payload cap, never stores raw IP addresses (only ephemeral salted day-hashes for sliding-window rate limiting and coarse 2-letter `CF-IPCountry`), recursively scrubs API keys, Bearer tokens, emails, phone numbers, and local paths to `[REDACTED]`, and honors 1-click cryptographic erasure (`DELETE /api/v1/traces/:anon_id`).
|
|
23
|
+
|
|
24
|
+
## 3. Reporting a Vulnerability
|
|
25
|
+
|
|
26
|
+
Please **do not** open public GitHub issues for sensitive security or privacy vulnerabilities. Instead, report privately via email:
|
|
27
|
+
|
|
28
|
+
- **Security Contact:** `security@maqayis.org` / `Salah.Abdo.Tech@gmail.com`
|
|
29
|
+
- **Target Response SLA:** Initial acknowledgment within **48 hours**; verified remediation or mitigation patch within **7 days**.
|
maqayis-1.0.0/logo.png
ADDED
|
Binary file
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["hatchling>=1.24.0"]
|
|
3
|
+
build-backend = "hatchling.build"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "maqayis"
|
|
7
|
+
version = "1.0.0"
|
|
8
|
+
description = "Maqayis — Umbrella meta-package for Open Arabic Computational Philology, Sub-Lexical Algebra, Zero-LLM Retrieval, and Governed Scientific MT"
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
license = { text = "Apache-2.0" }
|
|
11
|
+
requires-python = ">=3.10"
|
|
12
|
+
authors = [
|
|
13
|
+
{ name = "Salah Abdo", email = "Salah.Abdo.Tech@gmail.com" },
|
|
14
|
+
]
|
|
15
|
+
keywords = ["arabic", "nlp", "computational-philology", "maqayis", "tarkib", "tayf", "diwan", "misbar", "sarfchat"]
|
|
16
|
+
classifiers = [
|
|
17
|
+
"Development Status :: 5 - Production/Stable",
|
|
18
|
+
"Intended Audience :: Science/Research",
|
|
19
|
+
"License :: OSI Approved :: Apache Software License",
|
|
20
|
+
"Natural Language :: Arabic",
|
|
21
|
+
"Programming Language :: Python :: 3",
|
|
22
|
+
]
|
|
23
|
+
dependencies = [
|
|
24
|
+
"tarkib>=2.0.0",
|
|
25
|
+
"tayf>=1.0.0",
|
|
26
|
+
"misbar>=1.0.0",
|
|
27
|
+
"maqayis-diwan>=1.0.0",
|
|
28
|
+
"sarfchat>=2.0.0",
|
|
29
|
+
]
|
|
30
|
+
|
|
31
|
+
[project.urls]
|
|
32
|
+
Homepage = "https://maqayis.org"
|
|
33
|
+
Repository = "https://github.com/maqayis/maqayis"
|
|
34
|
+
Issues = "https://github.com/maqayis/maqayis/issues"
|
|
35
|
+
|
|
36
|
+
[tool.hatch.build.targets.wheel]
|
|
37
|
+
packages = ["src/maqayis"]
|