pyaegean 0.1.0__tar.gz

pyaegean-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Ryan Pavlicek
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

pyaegean-0.1.0/NOTICE

@@ -0,0 +1,40 @@
+pyaegean
+Copyright 2026 Ryan Pavlicek
+
+This product includes software developed by Ryan Pavlicek, licensed under the
+Apache License, Version 2.0.
+
+================================================================================
+Third-party data and attributions
+================================================================================
+
+Linear A corpus (bundled text JSON: src/aegean/data/bundled/lineara/)
+  Derived from the GORILA edition — Godart, L. & Olivier, J.-P. (1976–1985),
+  "Recueil des inscriptions en linéaire A" (Études Crétoises) — via the
+  open dataset at https://github.com/mwenge/lineara.xyz.
+  Used as a scholarly reference corpus. Transliterations and structured
+  metadata only; no facsimile imagery is bundled or redistributed.
+
+Linear A facsimile / photographic imagery (fetched on demand, NOT redistributed)
+  © École Française d'Athènes and respective rights holders. Downloaded by the
+  user on demand from the linearaworkbench repository for academic reference;
+  never re-hosted by this package.
+
+Ancient Greek Dependency Treebank — AGDT v2.1 (fetched on demand, NOT redistributed)
+  Perseus Ancient Greek Dependency Treebank, v2.1
+  (https://github.com/PerseusDL/treebank_data), licensed CC BY-SA 3.0. Downloaded
+  by the user on demand via aegean.greek.use_treebank(); pyaegean builds a derived
+  lemma/morphology lexicon in the local cache and neither bundles nor re-hosts the
+  treebank itself. Attribute the AGDT in academic work that relies on it.
+
+Planned (future versions; included here for forward attribution):
+  - DAMOS — Database of Mycenaean at Oslo (Linear B).
+  - LiBER — Linear B Electronic Resources.
+  - PROIEL treebanks (Ancient Greek) — CC BY-NC-SA.
+  - First1KGreek / Open Greek and Latin — CC BY.
+  - Morpheus morphological data; LSJ lexicon (per applicable license).
+  Each will be attributed and license-gated as it is integrated.
+
+The structured-data layer of this package is licensed Apache-2.0; underlying
+scholarly editions and imagery remain under their respective rights. Cite the
+original editions in academic work (see Corpus.provenance.cite()).

pyaegean-0.1.0/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: pyaegean
+Version: 0.1.0
+Summary: A specialist Python toolkit for Ancient Greek — alphabetic Greek and the Aegean syllabic scripts (Linear A/B).
+Author: Ryan Pavlicek
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/ryanpavlicek/pyaegean
+Project-URL: Source, https://github.com/ryanpavlicek/pyaegean
+Project-URL: Documentation, https://github.com/ryanpavlicek/pyaegean/wiki
+Project-URL: Issues, https://github.com/ryanpavlicek/pyaegean/issues
+Project-URL: Changelog, https://github.com/ryanpavlicek/pyaegean/blob/main/CHANGELOG.md
+Keywords: ancient greek,linear a,linear b,mycenaean,aegean,epigraphy,philology,corpus,bronze age,syllabary
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: pandas>=2.0
+Requires-Dist: scipy>=1.10
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.39; extra == "anthropic"
+Provides-Extra: openai
+Requires-Dist: openai>=1.30; extra == "openai"
+Provides-Extra: gemini
+Requires-Dist: google-genai>=0.3; extra == "gemini"
+Provides-Extra: grok
+Requires-Dist: openai>=1.30; extra == "grok"
+Provides-Extra: ai
+Requires-Dist: anthropic>=0.39; extra == "ai"
+Requires-Dist: openai>=1.30; extra == "ai"
+Requires-Dist: google-genai>=0.3; extra == "ai"
+Provides-Extra: epidoc
+Requires-Dist: lxml>=5.0; extra == "epidoc"
+Provides-Extra: geo
+Requires-Dist: geopandas>=0.14; extra == "geo"
+Requires-Dist: shapely>=2.0; extra == "geo"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: hypothesis; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Requires-Dist: nbmake; extra == "dev"
+Requires-Dist: ipykernel; extra == "dev"
+Provides-Extra: all
+Requires-Dist: pyaegean[ai,epidoc,geo]; extra == "all"
+Dynamic: license-file
+
+# pyaegean
+
+**A specialist Python toolkit for Ancient Greek** — alphabetic Greek *and* the
+Aegean syllabic scripts (Linear A / Linear B). pyaegean focuses narrowly and
+deeply on Greek and the Aegean world: a script-agnostic corpus data layer, the
+analytical methods from the Linear A Research Workbench, translation, and a
+pluggable multi-provider AI layer. The excellent [CLTK](https://cltk.org) already
+serves many ancient languages broadly; pyaegean is intentionally narrower, and
+uses CLTK as a friendly benchmark to measure its Greek coverage against.
+
+> **Status: v0.1 (alpha).** Script-agnostic core + Linear A fully implemented;
+> the Greek NLP track and the AI layer are landing across v0.1–v0.2. See the
+> roadmap. Analytical output on the undeciphered Linear A material is
+> **exploratory** — see the methodology/limitations.
+
+## Install
+
+```bash
+pip install pyaegean            # core + Linear A + Greek
+pip install "pyaegean[ai]"      # + Anthropic / OpenAI / Grok / Gemini clients
+pip install "pyaegean[all]"     # everything
+```
+
+> **Not on PyPI yet.** Until the first release, install from source instead:
+> `pip install git+https://github.com/ryanpavlicek/pyaegean`
+
+> **New to Python, or not a programmer?** You're exactly who this tool is for.
+> The **[Getting Started guide](https://github.com/ryanpavlicek/pyaegean/wiki/Getting-Started)**
+> walks you from "I have nothing installed" to your first result — no prior coding
+> assumed.
+
+## Quick start
+
+Prefer to learn by doing? Run the guided tour in your browser — nothing to install:
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ryanpavlicek/pyaegean/blob/main/notebooks/getting-started.ipynb)
+
+```python
+import aegean
+
+corpus = aegean.load("lineara")          # 1,721 inscriptions, bundled, offline
+print(len(corpus))                       # 1721
+
+ht = corpus.filter(site="Haghia Triada") # filter by metadata (full site name)
+df = corpus.to_dataframe(level="word")   # pandas-native, one row per word
+
+from aegean.analysis import balance_check, word_matches_sign_pattern
+checks = balance_check(corpus.get("HT13"))          # KU-RO accounting reconciliation
+hits = [w for w, _ in corpus.word_frequencies()
+        if word_matches_sign_pattern(w, "KU-*-RO")] # wildcard sign search
+```
+
+And a taste of the Greek pipeline:
+
+```python
+from aegean import greek
+
+greek.betacode_to_unicode("mh=nin")     # 'μῆνιν'   (type Greek in plain ASCII)
+greek.syllabify("ἄνθρωπος")             # ['ἄν', 'θρω', 'πος']
+greek.scan_hexameter("ἄνδρα μοι ἔννεπε, Μοῦσα, πολύτροπον, ὃς μάλα πολλὰ").pattern
+# '—⏑⏑|—⏑⏑|—⏑⏑|—⏑⏑|—⏑⏑|—×'             (Odyssey 1.1)
+[str(a) for a in greek.analyze("λόγον")][:2]
+# ['λόγος [NOUN acc sg masc]', 'λόγος [NOUN acc sg fem]']
+```
+
+The full Linear A facsimile mirror (3,368 images, ~116 MB) is **not** bundled;
+fetch it on demand: `aegean.data.fetch("lineara-images")` (downloaded from the
+workbench repo, sha256-verified, cached locally — never re-hosted).
+
+## What's here (v0.1)
+
+- **`aegean.core`** — script-agnostic model: `Corpus`, `Document`, `Token`,
+  `Sign`, `SignInventory`, `Numeral`, the `Script` plugin registry, provenance.
+- **`aegean.scripts.lineara`** — Linear A: bundled corpus + 84-sign inventory +
+  sign→sound map + transliteration.
+- **`aegean.analysis`** — ported from the workbench: accounting reconciliation,
+  wildcard sign-pattern search, weighted phonetic distance + alignment,
+  morphology clustering, collocation statistics, a compound-query engine, and
+  heuristic tablet-structure classification (all with golden-fixture parity).
+- **`aegean.greek`** — the Greek NLP track: Unicode/Beta Code normalization,
+  word/sentence tokenization, syllabification, accent and prosody analysis,
+  metrical scansion (dactylic hexameter + elegiac pentameter), reconstructed IPA,
+  POS tagging, a rule-based morphological analyzer (with an optional
+  Perseus-treebank–backed lexicon for attested, accented lemmas), and baseline
+  lemmatization. `aegean.load("greek")` loads a small bundled sample corpus (Archaic→Koine).
+- **`aegean.data`** — bundled-data access + download-to-cache for large assets.
+- **`aegean.ai`** (v0.2) — multi-provider AI layer: a provider-agnostic
+  `LLMClient` (Anthropic default, plus OpenAI, xAI Grok, Gemini — SDKs optional),
+  response caching, corpus grounding, and capabilities (translate, gloss,
+  decipherment hypotheses, NLP-assist, ask/summarize). Every generative result is
+  labeled **exploratory** with provenance. `aegean.translate` is the hybrid
+  lexicon+LLM front end.
+
+## Documentation
+
+Full documentation lives in the **[project wiki](https://github.com/ryanpavlicek/pyaegean/wiki)**:
+
+- **[Getting Started](https://github.com/ryanpavlicek/pyaegean/wiki/Getting-Started)** — for newcomers to Python
+- **[Example notebook](notebooks/getting-started.ipynb)** — a runnable guided tour ([open in Colab](https://colab.research.google.com/github/ryanpavlicek/pyaegean/blob/main/notebooks/getting-started.ipynb))
+- **[Tutorial](https://github.com/ryanpavlicek/pyaegean/wiki/Tutorial)** — two guided, end-to-end research walkthroughs
+- **[Linear A](https://github.com/ryanpavlicek/pyaegean/wiki/Linear-A)** · **[Analysis](https://github.com/ryanpavlicek/pyaegean/wiki/Analysis)** · **[Greek NLP](https://github.com/ryanpavlicek/pyaegean/wiki/Greek-NLP)** · **[AI Layer](https://github.com/ryanpavlicek/pyaegean/wiki/AI-Layer)** — reference per domain
+- **[Data & Provenance](https://github.com/ryanpavlicek/pyaegean/wiki/Data-and-Provenance)** · **[FAQ](https://github.com/ryanpavlicek/pyaegean/wiki/FAQ)**
+
+## Roadmap
+
+v0.1 core + Linear A (+ Greek start) → v0.2 AI layer (multi-provider) +
+translation → v0.3 deep Greek NLP (benchmarked against CLTK) → v0.4 Linear B
+(DAMOS/LiBER) → v0.5 Cypriot/Cypro-Minoan → v1.0 stable.
+
+## License
+
+Apache-2.0. Corpus data is GORILA (Godart & Olivier 1976–1985) via
+mwenge/lineara.xyz; facsimile imagery © École Française d'Athènes (referenced,
+not redistributed). See `NOTICE`.

pyaegean-0.1.0/README.md

@@ -0,0 +1,113 @@
+# pyaegean
+
+**A specialist Python toolkit for Ancient Greek** — alphabetic Greek *and* the
+Aegean syllabic scripts (Linear A / Linear B). pyaegean focuses narrowly and
+deeply on Greek and the Aegean world: a script-agnostic corpus data layer, the
+analytical methods from the Linear A Research Workbench, translation, and a
+pluggable multi-provider AI layer. The excellent [CLTK](https://cltk.org) already
+serves many ancient languages broadly; pyaegean is intentionally narrower, and
+uses CLTK as a friendly benchmark to measure its Greek coverage against.
+
+> **Status: v0.1 (alpha).** Script-agnostic core + Linear A fully implemented;
+> the Greek NLP track and the AI layer are landing across v0.1–v0.2. See the
+> roadmap. Analytical output on the undeciphered Linear A material is
+> **exploratory** — see the methodology/limitations.
+
+## Install
+
+```bash
+pip install pyaegean            # core + Linear A + Greek
+pip install "pyaegean[ai]"      # + Anthropic / OpenAI / Grok / Gemini clients
+pip install "pyaegean[all]"     # everything
+```
+
+> **Not on PyPI yet.** Until the first release, install from source instead:
+> `pip install git+https://github.com/ryanpavlicek/pyaegean`
+
+> **New to Python, or not a programmer?** You're exactly who this tool is for.
+> The **[Getting Started guide](https://github.com/ryanpavlicek/pyaegean/wiki/Getting-Started)**
+> walks you from "I have nothing installed" to your first result — no prior coding
+> assumed.
+
+## Quick start
+
+Prefer to learn by doing? Run the guided tour in your browser — nothing to install:
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ryanpavlicek/pyaegean/blob/main/notebooks/getting-started.ipynb)
+
+```python
+import aegean
+
+corpus = aegean.load("lineara")          # 1,721 inscriptions, bundled, offline
+print(len(corpus))                       # 1721
+
+ht = corpus.filter(site="Haghia Triada") # filter by metadata (full site name)
+df = corpus.to_dataframe(level="word")   # pandas-native, one row per word
+
+from aegean.analysis import balance_check, word_matches_sign_pattern
+checks = balance_check(corpus.get("HT13"))          # KU-RO accounting reconciliation
+hits = [w for w, _ in corpus.word_frequencies()
+        if word_matches_sign_pattern(w, "KU-*-RO")] # wildcard sign search
+```
+
+And a taste of the Greek pipeline:
+
+```python
+from aegean import greek
+
+greek.betacode_to_unicode("mh=nin")     # 'μῆνιν'   (type Greek in plain ASCII)
+greek.syllabify("ἄνθρωπος")             # ['ἄν', 'θρω', 'πος']
+greek.scan_hexameter("ἄνδρα μοι ἔννεπε, Μοῦσα, πολύτροπον, ὃς μάλα πολλὰ").pattern
+# '—⏑⏑|—⏑⏑|—⏑⏑|—⏑⏑|—⏑⏑|—×'             (Odyssey 1.1)
+[str(a) for a in greek.analyze("λόγον")][:2]
+# ['λόγος [NOUN acc sg masc]', 'λόγος [NOUN acc sg fem]']
+```
+
+The full Linear A facsimile mirror (3,368 images, ~116 MB) is **not** bundled;
+fetch it on demand: `aegean.data.fetch("lineara-images")` (downloaded from the
+workbench repo, sha256-verified, cached locally — never re-hosted).
+
+## What's here (v0.1)
+
+- **`aegean.core`** — script-agnostic model: `Corpus`, `Document`, `Token`,
+  `Sign`, `SignInventory`, `Numeral`, the `Script` plugin registry, provenance.
+- **`aegean.scripts.lineara`** — Linear A: bundled corpus + 84-sign inventory +
+  sign→sound map + transliteration.
+- **`aegean.analysis`** — ported from the workbench: accounting reconciliation,
+  wildcard sign-pattern search, weighted phonetic distance + alignment,
+  morphology clustering, collocation statistics, a compound-query engine, and
+  heuristic tablet-structure classification (all with golden-fixture parity).
+- **`aegean.greek`** — the Greek NLP track: Unicode/Beta Code normalization,
+  word/sentence tokenization, syllabification, accent and prosody analysis,
+  metrical scansion (dactylic hexameter + elegiac pentameter), reconstructed IPA,
+  POS tagging, a rule-based morphological analyzer (with an optional
+  Perseus-treebank–backed lexicon for attested, accented lemmas), and baseline
+  lemmatization. `aegean.load("greek")` loads a small bundled sample corpus (Archaic→Koine).
+- **`aegean.data`** — bundled-data access + download-to-cache for large assets.
+- **`aegean.ai`** (v0.2) — multi-provider AI layer: a provider-agnostic
+  `LLMClient` (Anthropic default, plus OpenAI, xAI Grok, Gemini — SDKs optional),
+  response caching, corpus grounding, and capabilities (translate, gloss,
+  decipherment hypotheses, NLP-assist, ask/summarize). Every generative result is
+  labeled **exploratory** with provenance. `aegean.translate` is the hybrid
+  lexicon+LLM front end.
+
+## Documentation
+
+Full documentation lives in the **[project wiki](https://github.com/ryanpavlicek/pyaegean/wiki)**:
+
+- **[Getting Started](https://github.com/ryanpavlicek/pyaegean/wiki/Getting-Started)** — for newcomers to Python
+- **[Example notebook](notebooks/getting-started.ipynb)** — a runnable guided tour ([open in Colab](https://colab.research.google.com/github/ryanpavlicek/pyaegean/blob/main/notebooks/getting-started.ipynb))
+- **[Tutorial](https://github.com/ryanpavlicek/pyaegean/wiki/Tutorial)** — two guided, end-to-end research walkthroughs
+- **[Linear A](https://github.com/ryanpavlicek/pyaegean/wiki/Linear-A)** · **[Analysis](https://github.com/ryanpavlicek/pyaegean/wiki/Analysis)** · **[Greek NLP](https://github.com/ryanpavlicek/pyaegean/wiki/Greek-NLP)** · **[AI Layer](https://github.com/ryanpavlicek/pyaegean/wiki/AI-Layer)** — reference per domain
+- **[Data & Provenance](https://github.com/ryanpavlicek/pyaegean/wiki/Data-and-Provenance)** · **[FAQ](https://github.com/ryanpavlicek/pyaegean/wiki/FAQ)**
+
+## Roadmap
+
+v0.1 core + Linear A (+ Greek start) → v0.2 AI layer (multi-provider) +
+translation → v0.3 deep Greek NLP (benchmarked against CLTK) → v0.4 Linear B
+(DAMOS/LiBER) → v0.5 Cypriot/Cypro-Minoan → v1.0 stable.
+
+## License
+
+Apache-2.0. Corpus data is GORILA (Godart & Olivier 1976–1985) via
+mwenge/lineara.xyz; facsimile imagery © École Française d'Athènes (referenced,
+not redistributed). See `NOTICE`.

pyaegean-0.1.0/pyproject.toml

@@ -0,0 +1,72 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyaegean"
+version = "0.1.0"
+description = "A specialist Python toolkit for Ancient Greek — alphabetic Greek and the Aegean syllabic scripts (Linear A/B)."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Ryan Pavlicek" }]
+keywords = [
+  "ancient greek", "linear a", "linear b", "mycenaean", "aegean",
+  "epigraphy", "philology", "corpus", "bronze age", "syllabary",
+]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3 :: Only",
+  "Topic :: Text Processing :: Linguistic",
+  "Typing :: Typed",
+]
+# Core stays import-light: numpy/pandas/scipy are imported lazily, only inside
+# DataFrame interop and the collocation statistics. `import aegean` stays instant.
+dependencies = ["pandas>=2.0", "scipy>=1.10"]
+
+[project.optional-dependencies]
+anthropic = ["anthropic>=0.39"]
+openai = ["openai>=1.30"]
+gemini = ["google-genai>=0.3"]
+grok = ["openai>=1.30"]            # xAI Grok is OpenAI-API-compatible
+ai = ["anthropic>=0.39", "openai>=1.30", "google-genai>=0.3"]
+epidoc = ["lxml>=5.0"]
+geo = ["geopandas>=0.14", "shapely>=2.0"]
+dev = ["pytest>=8", "pytest-cov", "hypothesis", "mypy", "ruff", "build", "twine", "nbmake", "ipykernel"]
+all = ["pyaegean[ai,epidoc,geo]"]
+
+[project.urls]
+Homepage = "https://github.com/ryanpavlicek/pyaegean"
+Source = "https://github.com/ryanpavlicek/pyaegean"
+Documentation = "https://github.com/ryanpavlicek/pyaegean/wiki"
+Issues = "https://github.com/ryanpavlicek/pyaegean/issues"
+Changelog = "https://github.com/ryanpavlicek/pyaegean/blob/main/CHANGELOG.md"
+
+[tool.setuptools]
+package-dir = { "" = "src" }
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+aegean = ["py.typed", "data/bundled/**/*.json"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"
+
+[tool.ruff]
+line-length = 100
+src = ["src", "tests"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+files = ["src/aegean"]
+warn_unused_ignores = false   # pandas/numpy are lazy-imported; ignores vary by env
+
+[[tool.mypy.overrides]]
+module = ["pandas.*", "numpy.*", "scipy.*", "anthropic.*", "openai.*", "google.*"]
+ignore_missing_imports = true

pyaegean-0.1.0/setup.cfg

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

pyaegean-0.1.0/src/aegean/__init__.py

@@ -0,0 +1,42 @@
+"""pyaegean — a specialist Python toolkit for Ancient Greek and the Aegean
+syllabic scripts (Linear A/B).
+
+v0.1: a script-agnostic corpus data layer with Linear A fully implemented (the
+analytical core ported from the Linear A Workbench) and the Greek track begun.
+"""
+
+from __future__ import annotations
+
+from importlib.metadata import PackageNotFoundError, version as _pkg_version
+
+from . import ai  # noqa: F401 — multi-provider AI layer (SDKs lazy/optional)
+from . import analysis  # noqa: F401
+from . import greek  # noqa: F401 — Greek NLP pipeline
+from . import scripts  # noqa: F401 — registers built-in scripts (Linear A, Greek)
+from . import translate  # noqa: F401 — hybrid lexicon+LLM translation
+from .core.corpus import Corpus
+from .core.script import get_script, register, registered_scripts
+
+try:
+    __version__ = _pkg_version("pyaegean")
+except PackageNotFoundError:  # pragma: no cover - running from a source tree, uninstalled
+    __version__ = "0.0.0+unknown"
+
+
+def load(script_id: str) -> Corpus:
+    """Load a bundled corpus, e.g. ``aegean.load("lineara")``."""
+    return Corpus.load(script_id)
+
+
+__all__ = [
+    "Corpus",
+    "load",
+    "get_script",
+    "register",
+    "registered_scripts",
+    "analysis",
+    "greek",
+    "ai",
+    "translate",
+    "__version__",
+]