tarkib 2.0.0__tar.gz

tarkib-2.0.0/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the Work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

tarkib-2.0.0/NOTICE

@@ -0,0 +1,15 @@
+Tarkīb (تركيب) v2.0.0 — Maqāyīs (مَقاييس) Open-Source Ecosystem
+Copyright 2026 Salah Abdo and successor entity
+
+Software & Source Code License:
+  Licensed under the Apache License, Version 2.0 (Apache-2.0).
+  You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
+
+Book, Research Monographs, & Public Linguistic Atlases (`book/`, `paper*/`, `papers_en/`, `data/`):
+  Licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
+  https://creativecommons.org/licenses/by/4.0/
+
+Clean-Room Classical Heritage Provenance:
+  Public `tarkib` (`TARKIB_OPENITI_ONLY=1`) derives strictly from pre-modern public-domain
+  classical Arabic lexicons (170–1205 AH via OpenITI witnesses with `#META#` editorial
+  headers stripped). See `DATA_PROVENANCE_BOM.md` and `sources/external/provenance.json`.

tarkib-2.0.0/PKG-INFO

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: tarkib
+Version: 2.0.0
+Summary: Computational Philology, Sub-Lexical Algebraic Semantics, Jadwal & Iqtiran Arabic NLP SDK (Maqayis)
+Author-email: Salah Abdo <Salah.Abdo.Tech@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://maqayis.org
+Project-URL: Repository, https://github.com/maqayis/tarkib
+Project-URL: Mirror, https://codeberg.org/maqayis/tarkib
+Project-URL: Documentation, https://maqayis.org
+Keywords: arabic,nlp,computational-philology,morphology,zero-llm,maqayis,tarkib
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: Arabic
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy>=1.24
+Requires-Dist: scipy>=1.10
+Requires-Dist: scikit-learn>=1.3
+Provides-Extra: hybrid
+Requires-Dist: torch>=2.1; extra == "hybrid"
+Requires-Dist: transformers>=4.40; extra == "hybrid"
+Requires-Dist: sentence-transformers>=2.6; extra == "hybrid"
+Dynamic: license-file
+
+# Tarkīb (`تركيب`) v2.0.0 — هندسة اللسان العربي وجبر المعجم التحت-جذري
+
+<div align="center">
+
+**Computational Philology, Sub-Lexical Algebraic Semantics, & Zero-LLM Arabic NLP Engine**  
+Part of the **Maqāyīs (`مَقاييس`)** Open-Source Ecosystem · [maqayis.org](https://maqayis.org) · [github.com/maqayis/tarkib](https://github.com/maqayis/tarkib)
+
+[![License: Apache-2.0](https://img.shields.io/badge/Code-Apache--2.0-blue.svg)](LICENSE)
+[![Data & Book: CC BY 4.0](https://img.shields.io/badge/Book%20%26%20Atlases-CC%20BY%204.0-teal.svg)](NOTICE)
+[![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-3776AB.svg)](pyproject.toml)
+[![Zero-LLM Ready](https://img.shields.io/badge/Mode-Zero--LLM%20%280%20Neural%20Params%29-success.svg)](DATA_PROVENANCE_BOM.md)
+
+</div>
+
+---
+
+## نظرة عامّة | Overview
+
+**`tarkib` (`تركيب` v2.0.0)** هو المحرّك الأساسي للفقه الحاسوبي وجبر الدلالة التحت-جذرية والصرف الريماني في منظومة **مَقاييس (`Maqāyīs`)** بقيادة المؤلّف **صلاح عبده (`Salah Abdo`)**. يعمل المحرّك في طوره الافتراضي **`mode="zero_llm"`** بصفر أوزان عصبية وباعتمادٍ نقيّ (`TARKIB_OPENITI_ONLY=1`) على خمسة معاجم تراثية عربية من المشاع العام تمتدّ عبر **1,035 سنة قمرية (`170–1205` هـ)**: *العين*، *الصحاح*، *مقاييس اللغة* لابن فارس، *لسان العرب*، و*تاج العروس*.
+
+**`tarkib` (`v2.0.0`)** is the core computational-philology and sub-lexical algebraic Arabic NLP SDK of the **Maqāyīs (`مَقاييس`)** ecosystem by **Salah Abdo**. In its default `mode="zero_llm"`, `TarkibEngine` executes with **zero neural parameters** over a 256-dimensional spectral manifold constructed strictly from five pre-modern public-domain classical Arabic lexicons (`170–1205 AH`), packaged cleanly inside the Python wheel so every API works out of the box with zero external database setup.
+
+---
+
+## التثبيت السريع | Installation
+
+```bash
+pip install tarkib
+# Or with uv:
+uv add tarkib
+```
+
+Optional neural hybrid manifold (`intfloat/multilingual-e5-large` + PyTorch adapter):
+
+```bash
+pip install "tarkib[hybrid]"
+```
+
+---
+
+## الاستخدام البرمجي الموحَّد (`v2.0.0` SDK) | Quickstart
+
+```python
+from tarkib import TarkibEngine
+
+engine = TarkibEngine(mode="zero_llm")
+
+# 1. Structural, kinematic, & Grassmannian Root X-Ray (`21,952` Sigma_28^3 cube)
+xray = engine.inspect_root("كتب")
+
+# 2. Zero-leakage Furūq near-synonym comparison
+furuq = engine.compare_furuq("سنة", "عام")
+
+# 3. Al-Jadwal Periodic Table of Arabic Roots (`11,249` roots across S0–S5 strata)
+jadwal = engine.inspect_jadwal("كتب")
+
+# 4. Iqtirān 66-Atom Morpho-Syntactic Phase-Coupling Algebra (`B01–B31 × R01–R35`)
+iqtiran_all = engine.inspect_iqtiran()
+iqtiran_fi = engine.inspect_iqtiran("في")
+
+# 5. Paleographic undotted rasm Viterbi restoration (0% post-1205 AH anachronism)
+rasm = engine.restore_rasm("ٮسم الله الرحمں الرحىم")
+
+# 6. Six-Gate CI/CD Terminology & Localization Governance QA (legal/financial/technical)
+qa = engine.terminology_qa("msgid \" Encryption\"\nmsgstr \"تعمية\"\n", fmt="po")
+```
+
+### Unified `TarkibEngine(mode="zero_llm")` Methods (`v2.0.0`)
+
+| Method | Subsystem | Description |
+| :--- | :--- | :--- |
+| `inspect_root(token_or_root)` | **Tarkīb · Bayān · Burhān** | Full Root X-Ray across `21,952` cells (`((C1*C2)*C3)`, Sībawayhian 13-feature kinematics, Grassmannian fibers) |
+| `inspect_jadwal(root)` | **Al-Jadwal (`الجدول`)** | Periodic Table lookup across `11,249` roots, `S0–S5` strata, `[C1C2_]` genera, and verified witnesses |
+| `inspect_iqtiran(particle=None)` | **Iqtirān (`اقتران`)** | Closed `66`-atom morpho-syntactic algebra (`31` `B` × `35` `R` = `1,085` cells, `Delta_12`, Laws `ن١١–ن١٦`) |
+| `compare_furuq(a, b, sentence=...)` | **Bayān (`بيان`)** | Zero-leakage contextual & intrinsic *Furūq* ranker (`rank_contextual_furuq`) |
+| `audit_tashif(text)` | **Ījāz (`إيجاز`)** | Shannon guardband anti-*taṣḥīf* & `OCR/ASR` repair (`audit_tashif_and_ocr`) |
+| `coin_term(concept_ar, ...)` | **Ījāz · Dīwān** | Six-gate scientific/technical/regulatory neologism coining (`coin_scientific_term`) |
+| `tokenize_text(text)` | **Mīzān (`ميزان`)** | Non-concatenative `(proclitic, root_3, pattern_id, enclitic)` tokenizer (`0.0%` root fragmentation) |
+| `fiber_rag(query, ...)` | **Burhān · Tayf** | Grassmannian fiber & metaphor-transport `T_majaz` retrieval (`search_fiber_rag`) |
+| `restore_rasm(text, ...)` | **Paleography** | Exact Viterbi undotted *rasm* decoder over `170–1205 AH` lexicons (`restore_undotted_rasm`) |
+| `audit_diachronic(text, ...)` | **Millennium Drift** | 5-epoch (`170→1205 AH`) semantic drift & anachronism detector (`audit_diachronic_anachronism`) |
+| `terminology_qa(content, ...)` | **CI/CD Governance** | 6-gate localization QA for legal, financial, regulatory, & software pipelines (`SARIF 2.1.0`) |
+
+---
+
+## الحصيلة القياسية المجمّدة (`data/*.json`) | Frozen Empirical Benchmarks
+
+All headline benchmarks are deterministically synchronized with `data/*.json` and verified by `pytest`:
+
+- **First-Principles Vocal-Tract OCP Hamiltonian (`ocp_physics_derivation.json`):** Zero-corpus biomechanical Hamiltonian achieves **`0.8451`** out-of-fold AUROC across `6,963` pan-classical roots vs. **`0.7960`** for the unigram consonant-frequency baseline.
+- **Grassmannian Fiber & Metaphor-Aware RAG (`fiber_rag_benchmark.json`):** Surgical `rigid_jamid_nominal` vs. `eventive_derived` isolation reaches **`53.03%`** `Precision@1` under strict `0%` non-root vocabulary overlap.
+- **Paleographic Rasm Viterbi Restorer (`rasm_restorer_benchmark.json`):** Contextual Viterbi lattice decoding achieves **`+13.64`** percentage-point accuracy gain over unigram baselines on minimal-pair *rasm* traps with `0.00%` modern lexical intrusion.
+- **Millennium Diachronic Anachronism Auditor (`diachronic_auditor_benchmark.json`):** Semantic calque detection achieves **`90.0%`** balanced accuracy with the classical calque atlas (`65.0%` fully unsupervised Leave-One-Root-Out graph coherence).
+- **Six-Gate CI/CD Terminology QA (`terminology_qa_benchmark.json`):** Achieves **`98.04%`** `F1` across all 6 governance gates and **`97.67%`** `F1` under objective-defects-only policy on software, financial, regulatory, and legal localization suites.
+
+---
+
+## الواجهات التنفيذية (`CLI` · `MCP` · `Web Studio`) | Interfaces
+
+```bash
+# Command-line interface
+tarkib inspect يستغفرون
+tarkib qa-gate path/to/translations.po --fail-under 85
+
+# Model Context Protocol (MCP) JSON-RPC 2.0 stdio server (11 tools)
+tarkib-mcp --mode zero_llm
+
+# Interactive RTL Web Studio
+tarkib-studio --port 8765
+```
+
+---
+
+## الترخيص ونسب المصادر | License & Provenance
+
+- **Code (`Apache-2.0`):** Licensed under the [Apache License, Version 2.0](LICENSE).
+- **Book & Public Linguistic Atlases (`CC BY 4.0`):** `book/`, `paper*/`, `papers_en/`, and `data/` are licensed under [Creative Commons Attribution 4.0 International (`CC BY 4.0`)](https://creativecommons.org/licenses/by/4.0/).
+- **Provenance BOM:** See [`DATA_PROVENANCE_BOM.md`](DATA_PROVENANCE_BOM.md) and [`NOTICE`](NOTICE).
+- **Copyright:** `Copyright 2026 Salah Abdo and successor entity`.

tarkib-2.0.0/README.md

@@ -0,0 +1,119 @@
+# Tarkīb (`تركيب`) v2.0.0 — هندسة اللسان العربي وجبر المعجم التحت-جذري
+
+<div align="center">
+
+**Computational Philology, Sub-Lexical Algebraic Semantics, & Zero-LLM Arabic NLP Engine**  
+Part of the **Maqāyīs (`مَقاييس`)** Open-Source Ecosystem · [maqayis.org](https://maqayis.org) · [github.com/maqayis/tarkib](https://github.com/maqayis/tarkib)
+
+[![License: Apache-2.0](https://img.shields.io/badge/Code-Apache--2.0-blue.svg)](LICENSE)
+[![Data & Book: CC BY 4.0](https://img.shields.io/badge/Book%20%26%20Atlases-CC%20BY%204.0-teal.svg)](NOTICE)
+[![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-3776AB.svg)](pyproject.toml)
+[![Zero-LLM Ready](https://img.shields.io/badge/Mode-Zero--LLM%20%280%20Neural%20Params%29-success.svg)](DATA_PROVENANCE_BOM.md)
+
+</div>
+
+---
+
+## نظرة عامّة | Overview
+
+**`tarkib` (`تركيب` v2.0.0)** هو المحرّك الأساسي للفقه الحاسوبي وجبر الدلالة التحت-جذرية والصرف الريماني في منظومة **مَقاييس (`Maqāyīs`)** بقيادة المؤلّف **صلاح عبده (`Salah Abdo`)**. يعمل المحرّك في طوره الافتراضي **`mode="zero_llm"`** بصفر أوزان عصبية وباعتمادٍ نقيّ (`TARKIB_OPENITI_ONLY=1`) على خمسة معاجم تراثية عربية من المشاع العام تمتدّ عبر **1,035 سنة قمرية (`170–1205` هـ)**: *العين*، *الصحاح*، *مقاييس اللغة* لابن فارس، *لسان العرب*، و*تاج العروس*.
+
+**`tarkib` (`v2.0.0`)** is the core computational-philology and sub-lexical algebraic Arabic NLP SDK of the **Maqāyīs (`مَقاييس`)** ecosystem by **Salah Abdo**. In its default `mode="zero_llm"`, `TarkibEngine` executes with **zero neural parameters** over a 256-dimensional spectral manifold constructed strictly from five pre-modern public-domain classical Arabic lexicons (`170–1205 AH`), packaged cleanly inside the Python wheel so every API works out of the box with zero external database setup.
+
+---
+
+## التثبيت السريع | Installation
+
+```bash
+pip install tarkib
+# Or with uv:
+uv add tarkib
+```
+
+Optional neural hybrid manifold (`intfloat/multilingual-e5-large` + PyTorch adapter):
+
+```bash
+pip install "tarkib[hybrid]"
+```
+
+---
+
+## الاستخدام البرمجي الموحَّد (`v2.0.0` SDK) | Quickstart
+
+```python
+from tarkib import TarkibEngine
+
+engine = TarkibEngine(mode="zero_llm")
+
+# 1. Structural, kinematic, & Grassmannian Root X-Ray (`21,952` Sigma_28^3 cube)
+xray = engine.inspect_root("كتب")
+
+# 2. Zero-leakage Furūq near-synonym comparison
+furuq = engine.compare_furuq("سنة", "عام")
+
+# 3. Al-Jadwal Periodic Table of Arabic Roots (`11,249` roots across S0–S5 strata)
+jadwal = engine.inspect_jadwal("كتب")
+
+# 4. Iqtirān 66-Atom Morpho-Syntactic Phase-Coupling Algebra (`B01–B31 × R01–R35`)
+iqtiran_all = engine.inspect_iqtiran()
+iqtiran_fi = engine.inspect_iqtiran("في")
+
+# 5. Paleographic undotted rasm Viterbi restoration (0% post-1205 AH anachronism)
+rasm = engine.restore_rasm("ٮسم الله الرحمں الرحىم")
+
+# 6. Six-Gate CI/CD Terminology & Localization Governance QA (legal/financial/technical)
+qa = engine.terminology_qa("msgid \" Encryption\"\nmsgstr \"تعمية\"\n", fmt="po")
+```
+
+### Unified `TarkibEngine(mode="zero_llm")` Methods (`v2.0.0`)
+
+| Method | Subsystem | Description |
+| :--- | :--- | :--- |
+| `inspect_root(token_or_root)` | **Tarkīb · Bayān · Burhān** | Full Root X-Ray across `21,952` cells (`((C1*C2)*C3)`, Sībawayhian 13-feature kinematics, Grassmannian fibers) |
+| `inspect_jadwal(root)` | **Al-Jadwal (`الجدول`)** | Periodic Table lookup across `11,249` roots, `S0–S5` strata, `[C1C2_]` genera, and verified witnesses |
+| `inspect_iqtiran(particle=None)` | **Iqtirān (`اقتران`)** | Closed `66`-atom morpho-syntactic algebra (`31` `B` × `35` `R` = `1,085` cells, `Delta_12`, Laws `ن١١–ن١٦`) |
+| `compare_furuq(a, b, sentence=...)` | **Bayān (`بيان`)** | Zero-leakage contextual & intrinsic *Furūq* ranker (`rank_contextual_furuq`) |
+| `audit_tashif(text)` | **Ījāz (`إيجاز`)** | Shannon guardband anti-*taṣḥīf* & `OCR/ASR` repair (`audit_tashif_and_ocr`) |
+| `coin_term(concept_ar, ...)` | **Ījāz · Dīwān** | Six-gate scientific/technical/regulatory neologism coining (`coin_scientific_term`) |
+| `tokenize_text(text)` | **Mīzān (`ميزان`)** | Non-concatenative `(proclitic, root_3, pattern_id, enclitic)` tokenizer (`0.0%` root fragmentation) |
+| `fiber_rag(query, ...)` | **Burhān · Tayf** | Grassmannian fiber & metaphor-transport `T_majaz` retrieval (`search_fiber_rag`) |
+| `restore_rasm(text, ...)` | **Paleography** | Exact Viterbi undotted *rasm* decoder over `170–1205 AH` lexicons (`restore_undotted_rasm`) |
+| `audit_diachronic(text, ...)` | **Millennium Drift** | 5-epoch (`170→1205 AH`) semantic drift & anachronism detector (`audit_diachronic_anachronism`) |
+| `terminology_qa(content, ...)` | **CI/CD Governance** | 6-gate localization QA for legal, financial, regulatory, & software pipelines (`SARIF 2.1.0`) |
+
+---
+
+## الحصيلة القياسية المجمّدة (`data/*.json`) | Frozen Empirical Benchmarks
+
+All headline benchmarks are deterministically synchronized with `data/*.json` and verified by `pytest`:
+
+- **First-Principles Vocal-Tract OCP Hamiltonian (`ocp_physics_derivation.json`):** Zero-corpus biomechanical Hamiltonian achieves **`0.8451`** out-of-fold AUROC across `6,963` pan-classical roots vs. **`0.7960`** for the unigram consonant-frequency baseline.
+- **Grassmannian Fiber & Metaphor-Aware RAG (`fiber_rag_benchmark.json`):** Surgical `rigid_jamid_nominal` vs. `eventive_derived` isolation reaches **`53.03%`** `Precision@1` under strict `0%` non-root vocabulary overlap.
+- **Paleographic Rasm Viterbi Restorer (`rasm_restorer_benchmark.json`):** Contextual Viterbi lattice decoding achieves **`+13.64`** percentage-point accuracy gain over unigram baselines on minimal-pair *rasm* traps with `0.00%` modern lexical intrusion.
+- **Millennium Diachronic Anachronism Auditor (`diachronic_auditor_benchmark.json`):** Semantic calque detection achieves **`90.0%`** balanced accuracy with the classical calque atlas (`65.0%` fully unsupervised Leave-One-Root-Out graph coherence).
+- **Six-Gate CI/CD Terminology QA (`terminology_qa_benchmark.json`):** Achieves **`98.04%`** `F1` across all 6 governance gates and **`97.67%`** `F1` under objective-defects-only policy on software, financial, regulatory, and legal localization suites.
+
+---
+
+## الواجهات التنفيذية (`CLI` · `MCP` · `Web Studio`) | Interfaces
+
+```bash
+# Command-line interface
+tarkib inspect يستغفرون
+tarkib qa-gate path/to/translations.po --fail-under 85
+
+# Model Context Protocol (MCP) JSON-RPC 2.0 stdio server (11 tools)
+tarkib-mcp --mode zero_llm
+
+# Interactive RTL Web Studio
+tarkib-studio --port 8765
+```
+
+---
+
+## الترخيص ونسب المصادر | License & Provenance
+
+- **Code (`Apache-2.0`):** Licensed under the [Apache License, Version 2.0](LICENSE).
+- **Book & Public Linguistic Atlases (`CC BY 4.0`):** `book/`, `paper*/`, `papers_en/`, and `data/` are licensed under [Creative Commons Attribution 4.0 International (`CC BY 4.0`)](https://creativecommons.org/licenses/by/4.0/).
+- **Provenance BOM:** See [`DATA_PROVENANCE_BOM.md`](DATA_PROVENANCE_BOM.md) and [`NOTICE`](NOTICE).
+- **Copyright:** `Copyright 2026 Salah Abdo and successor entity`.

tarkib-2.0.0/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tarkib"
+version = "2.0.0"
+description = "Computational Philology, Sub-Lexical Algebraic Semantics, Jadwal & Iqtiran Arabic NLP SDK (Maqayis)"
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "Apache-2.0"}
+authors = [
+  {name = "Salah Abdo", email = "Salah.Abdo.Tech@gmail.com"}
+]
+keywords = ["arabic", "nlp", "computational-philology", "morphology", "zero-llm", "maqayis", "tarkib"]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: Apache Software License",
+  "Natural Language :: Arabic",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Topic :: Text Processing :: Linguistic",
+]
+dependencies = [
+  "numpy>=1.24",
+  "scipy>=1.10",
+  "scikit-learn>=1.3",
+]
+
+[project.optional-dependencies]
+hybrid = [
+  "torch>=2.1",
+  "transformers>=4.40",
+  "sentence-transformers>=2.6",
+]
+
+[project.urls]
+Homepage = "https://maqayis.org"
+Repository = "https://github.com/maqayis/tarkib"
+Mirror = "https://codeberg.org/maqayis/tarkib"
+Documentation = "https://maqayis.org"
+
+[project.scripts]
+tarkib = "tarkib.cli:main"
+tarkib-mcp = "tarkib.mcp_server:main"
+tarkib-studio = "tarkib.studio:main"
+
+[tool.setuptools.packages.find]
+include = ["tarkib*"]
+
+[tool.setuptools.package-data]
+tarkib = [
+  "data/*.json",
+  "data/*.jsonl",
+  "data/cache/*.gz",
+  "data/cache/*.npz",
+]

tarkib-2.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

tarkib-2.0.0/tarkib/__init__.py

@@ -0,0 +1,10 @@
+"""tarkib (تركيب) v2.0.0 — Sub-Lexical Algebraic Arabic NLP & Computational Philology SDK."""
+
+from __future__ import annotations
+
+__version__ = "2.0.0"
+__author__ = "Salah Abdo"
+
+from tarkib.sdk import TarkibEngine, resolve_data_dir
+
+__all__ = ["TarkibEngine", "resolve_data_dir", "__author__", "__version__"]