kotobacore 0.1.11__tar.gz

kotobacore-0.1.11/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 KotobaCore Project
+
+   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.

kotobacore-0.1.11/PKG-INFO

@@ -0,0 +1,261 @@
+Metadata-Version: 2.4
+Name: kotobacore
+Version: 0.1.11
+Summary: Japanese semantic understanding engine for LLM, RAG, SNS analysis, and AI agents
+Author: KotobaCore Project
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/ekiyo55/kotobacore
+Project-URL: Repository, https://github.com/ekiyo55/kotobacore
+Project-URL: Issues, https://github.com/ekiyo55/kotobacore/issues
+Project-URL: Demo, https://kotobacore.mooma.style/
+Keywords: japanese,nlp,tokenizer,semantic,rag,llm,emotion-analysis,karuizawa
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+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 :: Text Processing :: Linguistic
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: typer>=0.12.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0.0; extra == "dev"
+Requires-Dist: ruff>=0.5.0; extra == "dev"
+Requires-Dist: mypy>=1.10.0; extra == "dev"
+Provides-Extra: ui
+Requires-Dist: streamlit>=1.36.0; extra == "ui"
+Dynamic: license-file
+
+# KotobaCore
+
+[![CI](https://github.com/ekiyo55/kotobacore/actions/workflows/ci.yml/badge.svg)](https://github.com/ekiyo55/kotobacore/actions/workflows/ci.yml)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/)
+
+[English](README_en.md) | **日本語**
+
+日本語テキストの意味を構造化データに変換するセマンティックエンジン。  
+LLM前処理・RAG・SNS解析・AIエージェント入力に使えます。
+
+---
+
+## 何ができるか
+
+```python
+from kotobacore import Analyzer
+
+result = Analyzer().analyze("クラウドAPIの課金高すぎてしぬw")
+```
+
+```
+chunks   : ["クラウドAPI", "課金高すぎ", "しぬw"]
+emotion  : anger / negative  (Plutchik: anger+disgust)
+intent   : pricing_complaint
+keywords : ["クラウドAPI", "課金"]
+```
+
+単なるトークナイザーではなく、**感情・意図・RAGキーワードまで一括で返す**のが特徴です。
+
+---
+
+## パイプライン
+
+```
+入力テキスト
+  └─ 正規化 (NFKC / SNS表現保持)
+       └─ トークナイズ (外部依存ゼロの内蔵トークナイザー)
+            └─ セマンティックチャンク生成
+                 ├─ 感情検出 + Plutchik 8軸マッピング
+                 ├─ 意図分類
+                 └─ RAGキーワード抽出
+```
+
+---
+
+## 感情モデル — Plutchik の感情の輪
+
+KotobaCore は心理学者 Robert Plutchik が提唱した **8基本感情モデル** をベースにしています。  
+怒り・恐れ・喜び・悲しみ・信頼・嫌悪・驚き・期待の8軸で感情を分類し、  
+テキストの感情を `primary / polarity / plutchik_axes` として構造化して返します。
+
+| Plutchik 軸 | KotobaCore カテゴリ | 例 |
+|---|---|---|
+| joy | joy / moved / admiration | 嬉しい, 感動した, 誇らしい |
+| anger | anger / refusal | ムカつく, 無理, 許せない |
+| sadness | sadness / anxiety | 悲しい, 不安, 心配 |
+| surprise | surprise / exaggeration | まじか, やばい, しぬw |
+| anticipation | anticipation / desire | 楽しみ, したい, 欲しい |
+| trust | admiration | 尊い, 信頼, 神対応 |
+| fear | anxiety | 怖い, 恐怖, ゾッとした |
+| disgust | refusal | 最悪, 気持ち悪い, 無理 |
+
+---
+
+## 内蔵辞書
+
+KotobaCore の判定は機械学習モデルではなく、**同梱の人手メンテナンス辞書（プレーンな CSV）** に基づきます。
+モデルのダウンロードや学習は不要で、CSV を編集するだけで語彙・ルールを追加・調整できます（`resources/dict/`）。
+
+| 辞書ファイル | 件数 | 役割 | 主な列 |
+|---|---:|---|---|
+| `entity.csv` | 701 | 固有表現（人名・ブランド・組織・地名・作品・サービス等）。`aliases` 列で別名表記も認識 | surface, type, normalized, aliases, priority, keep_as_unit |
+| `emotion.csv` | 507 | 感情語。11 カテゴリ（joy / sadness / admiration / refusal / moved / anger / anxiety / exaggeration / anticipation / irritation / agreement）を Plutchik 8 軸へマップ | surface, base_emotion, polarity, intensity, keep_as_unit |
+| `slang.csv` | 203 | SNS・ネットスラング（草 / しぬw / ワロタ 等） | surface, normalized, meaning, emotion, category, intensity, keep_as_unit |
+| `stopwords.csv` | 113 | チャンク・キーワードから除外する助詞・副詞・接続詞 | surface, category |
+| `normalization.csv` | 21 | 表記ゆれ正規化（(株) → 株式会社 等） | source, target, type |
+| `intent_rules.csv` | 9 | 意図分類ルール（pricing_complaint / support_request / positive_feedback / negative_feedback / agreement / admiration / desire / question / request） | intent, pattern, score, priority |
+| `emotion_examples.csv` | 17 | 例文ベース感情マッチ（surface 一致しない文の確信度を補強）の手書きシード | surface, base_emotion, plutchik_emotion, polarity, intensity, example |
+| `Japanese-SNS-Emotion-Examples-v1.txt` | 546 語 / 約 2,746 例文 | SNS 感情例文集（喜び・悲しみ・怒り・恐れ・驚き等）。例文ベースの Jaccard 類似度マッチに使用 | word, emotion, intensity, context, examples, emojis |
+
+`entity.csv` の内訳は人名 230 / ブランド 140 / 組織 132 / 地名 89 / 作品 59 / サービス 39 ほか。
+
+`Japanese-SNS-Emotion-Examples-v1.txt` も `resources/dict/` に同梱され、デフォルトで読み込まれます（外部辞書なしでも例文マッチが効きます）。
+各行の `examples`（「、」区切りの複数例文）が展開され、入力文との bigram Jaccard 類似度で感情の confidence を補強します。
+
+### 任意の外部辞書（NRC、非同梱）
+
+唯一の **非同梱** 辞書が **NRC Emotion Intensity Lexicon**（約 9,800 語 / 8 Plutchik 感情の強度辞書）です。
+`dic/`（環境変数 `KOTOBACORE_DIC_DIR` で指定）に置くと、内部辞書に無い感情語を **検出語彙として追加** します
+（内部辞書 `lex_weight=1.0` に対し外部は `0.5` の低めの重みで、文学的・稀少語を補完）。**無くても内蔵辞書だけで動作します。**
+
+感情の confidence は `lex_weight × 0.5 + ex_sim × 0.3 + intensity × 0.2` で算出され、
+NRC は第1項（検出語彙）、同梱の SNS 例文は第2項（類似度）に効きます。
+
+#### NRC 辞書の入手方法
+
+> **⚠️ ライセンス注意**: NRC Emotion Intensity Lexicon は **再配布が禁止** されているため本リポジトリには含まれません。
+> 各自で公式ページから入手してください。**非商用の研究用途は無償**ですが、**商用利用には NRC の商用ライセンスが別途必要** です。
+> 利用時は下記の引用と帰属表示が求められます。必ず[公式ページの利用規約](https://saifmohammad.com/WebPages/AffectIntensity.htm)をご自身で確認してください。
+
+1. 公式ページ **NRC Emotion/Affect Intensity Lexicon** から辞書を入手します（多言語自動翻訳版に日本語が含まれます）。
+   - https://saifmohammad.com/WebPages/AffectIntensity.htm
+2. 日本語訳データを次の **タブ区切り (TSV) 4 列** 形式に整え、`dic/` に配置します。
+   ```
+   English Word<TAB>Emotion<TAB>Emotion-Intensity-Score<TAB>Japanese Word
+   ```
+   - ファイル名: `dic/Japanese-NRC-Emotion-Intensity-Lexicon-v1.txt`
+   - `Emotion` は 8 軸（anger / anticipation / disgust / fear / joy / sadness / surprise / trust）
+3. `dic/` の場所は次の順で探索されます: 環境変数 `KOTOBACORE_DIC_DIR` → `<project>/dic` → `<project>/../dic`。
+
+**引用（必須）**:
+
+```bibtex
+@inproceedings{LREC18-AIL,
+  author    = {Mohammad, Saif M.},
+  title     = {Word Affect Intensities},
+  booktitle = {Proceedings of the 11th Edition of the Language Resources
+               and Evaluation Conference (LREC-2018)},
+  year      = {2018},
+  address   = {Miyazaki, Japan}
+}
+```
+
+**帰属表示の例**: "This product makes use of the NRC Emotion Intensity Lexicon, created by Saif M. Mohammad at the National Research Council Canada."
+
+```python
+from kotobacore.dictionary import load_user_bundle
+bundle = load_user_bundle()   # 内蔵 seed + 同梱 SNS 例文 + (あれば) dic/ の NRC を統合
+```
+
+---
+
+## インストール
+
+```bash
+git clone https://github.com/ekiyo55/kotobacore.git
+cd kotobacore
+python -m venv .venv
+source .venv/bin/activate   # Windows: .venv\Scripts\activate
+pip install -e .[dev,ui]
+```
+
+---
+
+## Python API
+
+```python
+from kotobacore import Analyzer
+
+result = Analyzer().analyze("クラウドAPIの課金高すぎてしぬw")
+print(result.to_json())
+```
+
+## 出力 JSON 構造
+
+```json
+{
+  "chunks": [
+    {"id": 0, "text": "クラウドAPI", "type": "service",      "score": 0.96},
+    {"id": 1, "text": "課金高すぎ",  "type": "complaint",    "score": 0.88},
+    {"id": 2, "text": "しぬw",       "type": "slang_emotion","score": 0.88}
+  ],
+  "emotion": {
+    "primary": "anger",
+    "polarity": "negative",
+    "intensity": 0.82,
+    "plutchik_axes": ["anger", "disgust"]
+  },
+  "intent": {"label": "pricing_complaint", "score": 0.85},
+  "rag": {
+    "keywords": ["クラウドAPI", "課金"],
+    "search_query": "クラウドAPI 課金",
+    "summary_hint": "pricing complaint about cloud API"
+  }
+}
+```
+
+---
+
+## CLI
+
+```bash
+kotobacore analyze "今日のランチが絶品だった" --pretty
+kotobacore tokenize "東京都に行った"
+kotobacore version
+```
+
+---
+
+## Demo UI
+
+```bash
+streamlit run tools/demo_ui/streamlit_app.py
+# → http://localhost:8501
+```
+
+公開デモ: https://kotobacore.mooma.style/
+
+---
+
+## 他ライブラリとの比較
+
+| ライブラリ | トークナイズ | 感情解析 | 意図分類 | RAGキーワード | 外部依存 |
+|---|:---:|:---:|:---:|:---:|---|
+| MeCab / SudachiPy | ✅ | ❌ | ❌ | ❌ | C++/辞書 |
+| GiNZA (spaCy) | ✅ | ❌ | ❌ | ❌ | spaCy モデル |
+| oseti / asari | ❌ | ポジ/ネガのみ | ❌ | ❌ | 辞書/ML |
+| BERT系 (transformers) | ✅ | ✅ | △ | ❌ | モデル数GB |
+| **KotobaCore** | ✅ | **Plutchik 8軸** | **✅** | **✅** | **ゼロ** |
+
+KotobaCoreが埋めているのは「感情・意図・RAGキーワードを一つのパイプラインで構造化JSON化する」領域です。
+
+---
+
+## ステータス
+
+v0.1.11 pre-alpha。5000例文の品質評価で 感情正確度 95.2% / 極性正確度 96.1% / 意図正確度 68.1%、処理エラー 0件。
+処理速度はサーバー実機で 1文あたり平均 3.77ms（p99 21.83ms、外部依存ゼロ）。149 テスト全 PASS。
+
+---
+
+## ライセンス
+
+Apache License 2.0