From 0a4fc9ba990710cfc480720af35210fded2a578c Mon Sep 17 00:00:00 2001
From: CoprDistGit <infra@openeuler.org>
Date: Mon, 10 Apr 2023 21:46:45 +0000
Subject: automatic import of python-konoha

---
 .gitignore         |   1 +
 python-konoha.spec | 652 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 sources            |   1 +
 3 files changed, 654 insertions(+)
 create mode 100644 python-konoha.spec
 create mode 100644 sources

diff --git a/.gitignore b/.gitignore
index e69de29..5cb5b72 100644
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1 @@
+/konoha-5.4.0.tar.gz
diff --git a/python-konoha.spec b/python-konoha.spec
new file mode 100644
index 0000000..fd2eab9
--- /dev/null
+++ b/python-konoha.spec
@@ -0,0 +1,652 @@
+%global _empty_manifest_terminate_build 0
+Name:		python-konoha
+Version:	5.4.0
+Release:	1
+Summary:	A tiny sentence/word tokenizer for Japanese text written in Python
+License:	MIT
+URL:		https://pypi.org/project/konoha/
+Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/f3/f1/a83f55d8e7e824d483bccce3902335d130b572b5a17bde8b282acd13d504/konoha-5.4.0.tar.gz
+BuildArch:	noarch
+
+Requires:	python3-importlib-metadata
+Requires:	python3-overrides
+Requires:	python3-janome
+Requires:	python3-natto-py
+Requires:	python3-kytea
+Requires:	python3-sentencepiece
+Requires:	python3-sudachipy
+Requires:	python3-boto3
+Requires:	python3-fastapi
+Requires:	python3-uvicorn
+Requires:	python3-sudachidict-core
+Requires:	python3-sphinx
+Requires:	python3-pydata-sphinx-theme
+Requires:	python3-nagisa
+Requires:	python3-rich
+Requires:	python3-requests
+
+%description
+# 🌿 Konoha: Simple wrapper of Japanese Tokenizers
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/himkt/konoha/blob/main/example/Konoha_Example.ipynb)
+<p align="center"><img src="https://user-images.githubusercontent.com/5164000/120913279-e7d62380-c6d0-11eb-8d17-6571277cdf27.gif" width="95%"></p>
+
+[![GitHub stars](https://img.shields.io/github/stars/himkt/konoha?style=social)](https://github.com/himkt/konoha/stargazers)
+
+[![Downloads](https://pepy.tech/badge/konoha)](https://pepy.tech/project/konoha)
+[![Downloads](https://pepy.tech/badge/konoha/month)](https://pepy.tech/project/konoha/month)
+[![Downloads](https://pepy.tech/badge/konoha/week)](https://pepy.tech/project/konoha/week)
+
+[![Build Status](https://github.com/himkt/konoha/workflows/Python%20package/badge.svg?style=flat-square)](https://github.com/himkt/konoha/actions)
+[![Documentation Status](https://readthedocs.org/projects/konoha/badge/?version=latest)](https://konoha.readthedocs.io/en/latest/?badge=latest)
+![Python](https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8-blue?logo=python)
+[![PyPI](https://img.shields.io/pypi/v/konoha.svg)](https://pypi.python.org/pypi/konoha)
+[![GitHub Issues](https://img.shields.io/github/issues/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+[![GitHub Pull Requests](https://img.shields.io/github/issues-pr/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+
+`Konoha` is a Python library for providing easy-to-use integrated interface of various Japanese tokenizers,
+which enables you to switch a tokenizer and boost your pre-processing.
+
+## Supported tokenizers
+
+<a href="https://github.com/buruzaemon/natto-py"><img src="https://img.shields.io/badge/MeCab-natto--py-ff69b4"></a>
+<a href="https://github.com/chezou/Mykytea-python"><img src="https://img.shields.io/badge/KyTea-Mykytea--python-ff69b4"></a>
+<a href="https://github.com/mocobeta/janome"><img src="https://img.shields.io/badge/Janome-janome-ff69b4"></a>
+<a href="https://github.com/WorksApplications/SudachiPy"><img src="https://img.shields.io/badge/Sudachi-sudachipy-ff69b4"></a>
+<a href="https://github.com/google/sentencepiece"><img src="https://img.shields.io/badge/Sentencepiece-sentencepiece-ff69b4"></a>
+<a href="https://github.com/taishi-i/nagisa"><img src="https://img.shields.io/badge/nagisa-nagisa-ff69b4"></a>
+
+Also, `konoha` provides rule-based tokenizers (whitespace, character) and a rule-based sentence splitter.
+
+
+## Quick Start with Docker
+
+Simply run followings on your computer:
+
+```bash
+docker run --rm -p 8000:8000 -t himkt/konoha  # from DockerHub
+```
+
+Or you can build image on your machine:
+
+```bash
+git clone https://github.com/himkt/konoha  # download konoha
+cd konoha && docker-compose up --build  # build and launch container
+```
+
+Tokenization is done by posting a json object to `localhost:8000/api/v1/tokenize`.
+You can also batch tokenize by passing `texts: ["１つ目の入力", "２つ目の入力"]` to `localhost:8000/api/v1/batch_tokenize`.
+
+(API documentation is available on `localhost:8000/redoc`, you can check it using your web browser)
+
+Send a request using `curl` on your terminal.
+Note that a path to an endpoint is changed in v4.6.4.
+Please check our release note (https://github.com/himkt/konoha/releases/tag/v4.6.4).
+
+```json
+$ curl localhost:8000/api/v1/tokenize -X POST -H "Content-Type: application/json" \
+    -d '{"tokenizer": "mecab", "text": "これはペンです"}'
+
+{
+  "tokens": [
+    [
+      {
+        "surface": "これ",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "は",
+        "part_of_speech": "助詞"
+      },
+      {
+        "surface": "ペン",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "です",
+        "part_of_speech": "助動詞"
+      }
+    ]
+  ]
+}
+```
+
+
+## Installation
+
+
+I recommend you to install konoha by `pip install 'konoha[all]'`.
+
+- Install konoha with a specific tokenizer: `pip install 'konoha[(tokenizer_name)]`.
+- Install konoha with a specific tokenizer and remote file support: `pip install 'konoha[(tokenizer_name),remote]'`
+
+If you want to install konoha with a tokenizer, please install konoha with a specific tokenizer
+(e.g. `konoha[mecab]`, `konoha[sudachi]`, ...etc) or install tokenizers individually.
+
+
+## Example
+
+### Word level tokenization
+
+```python
+from konoha import WordTokenizer
+
+sentence = '自然言語処理を勉強しています'
+
+tokenizer = WordTokenizer('MeCab')
+print(tokenizer.tokenize(sentence))
+# => [自然, 言語, 処理, を, 勉強, し, て, い, ます]
+
+tokenizer = WordTokenizer('Sentencepiece', model_path="data/model.spm")
+print(tokenizer.tokenize(sentence))
+# => [▁, 自然, 言語, 処理, を, 勉強, し, ています]
+```
+
+For more detail, please see the `example/` directory.
+
+### Remote files
+
+Konoha supports dictionary and model on cloud storage (currently supports Amazon S3).
+It requires installing konoha with the `remote` option, see [Installation](#installation).
+
+```python
+# download user dictionary from S3
+word_tokenizer = WordTokenizer("mecab", user_dictionary_path="s3://abc/xxx.dic")
+print(word_tokenizer.tokenize(sentence))
+
+# download system dictionary from S3
+word_tokenizer = WordTokenizer("mecab", system_dictionary_path="s3://abc/yyy")
+print(word_tokenizer.tokenize(sentence))
+
+# download model file from S3
+word_tokenizer = WordTokenizer("sentencepiece", model_path="s3://abc/zzz.model")
+print(word_tokenizer.tokenize(sentence))
+```
+
+### Sentence level tokenization
+
+```python
+from konoha import SentenceTokenizer
+
+sentence = "私は猫だ。名前なんてものはない。だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer()
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，「かわいい。それで十分だろう」。']
+```
+
+You can change symbols for a sentence splitter and bracket expression.
+
+1. sentence splitter
+
+```python
+sentence = "私は猫だ。名前なんてものはない．だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer(period="．")
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。名前なんてものはない．', 'だが，「かわいい。それで十分だろう」。']
+```
+
+2. bracket expression
+
+```python
+sentence = "私は猫だ。名前なんてものはない。だが，『かわいい。それで十分だろう』。"
+
+tokenizer = SentenceTokenizer(
+    patterns=SentenceTokenizer.PATTERNS + [re.compile(r"『.*?』")],
+)
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，『かわいい。それで十分だろう』。']
+```
+
+
+## Test
+
+```
+python -m pytest
+```
+
+## Article
+
+- [トークナイザをいい感じに切り替えるライブラリ konoha を作った](https://qiita.com/klis/items/bb9ffa4d9c886af0f531)
+- [日本語解析ツール Konoha に AllenNLP 連携機能を実装した](https://qiita.com/klis/items/f1d29cb431d1bf879898)
+
+## Acknowledgement
+
+Sentencepiece model used in test is provided by @yoheikikuta. Thanks!
+
+
+%package -n python3-konoha
+Summary:	A tiny sentence/word tokenizer for Japanese text written in Python
+Provides:	python-konoha
+BuildRequires:	python3-devel
+BuildRequires:	python3-setuptools
+BuildRequires:	python3-pip
+%description -n python3-konoha
+# 🌿 Konoha: Simple wrapper of Japanese Tokenizers
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/himkt/konoha/blob/main/example/Konoha_Example.ipynb)
+<p align="center"><img src="https://user-images.githubusercontent.com/5164000/120913279-e7d62380-c6d0-11eb-8d17-6571277cdf27.gif" width="95%"></p>
+
+[![GitHub stars](https://img.shields.io/github/stars/himkt/konoha?style=social)](https://github.com/himkt/konoha/stargazers)
+
+[![Downloads](https://pepy.tech/badge/konoha)](https://pepy.tech/project/konoha)
+[![Downloads](https://pepy.tech/badge/konoha/month)](https://pepy.tech/project/konoha/month)
+[![Downloads](https://pepy.tech/badge/konoha/week)](https://pepy.tech/project/konoha/week)
+
+[![Build Status](https://github.com/himkt/konoha/workflows/Python%20package/badge.svg?style=flat-square)](https://github.com/himkt/konoha/actions)
+[![Documentation Status](https://readthedocs.org/projects/konoha/badge/?version=latest)](https://konoha.readthedocs.io/en/latest/?badge=latest)
+![Python](https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8-blue?logo=python)
+[![PyPI](https://img.shields.io/pypi/v/konoha.svg)](https://pypi.python.org/pypi/konoha)
+[![GitHub Issues](https://img.shields.io/github/issues/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+[![GitHub Pull Requests](https://img.shields.io/github/issues-pr/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+
+`Konoha` is a Python library for providing easy-to-use integrated interface of various Japanese tokenizers,
+which enables you to switch a tokenizer and boost your pre-processing.
+
+## Supported tokenizers
+
+<a href="https://github.com/buruzaemon/natto-py"><img src="https://img.shields.io/badge/MeCab-natto--py-ff69b4"></a>
+<a href="https://github.com/chezou/Mykytea-python"><img src="https://img.shields.io/badge/KyTea-Mykytea--python-ff69b4"></a>
+<a href="https://github.com/mocobeta/janome"><img src="https://img.shields.io/badge/Janome-janome-ff69b4"></a>
+<a href="https://github.com/WorksApplications/SudachiPy"><img src="https://img.shields.io/badge/Sudachi-sudachipy-ff69b4"></a>
+<a href="https://github.com/google/sentencepiece"><img src="https://img.shields.io/badge/Sentencepiece-sentencepiece-ff69b4"></a>
+<a href="https://github.com/taishi-i/nagisa"><img src="https://img.shields.io/badge/nagisa-nagisa-ff69b4"></a>
+
+Also, `konoha` provides rule-based tokenizers (whitespace, character) and a rule-based sentence splitter.
+
+
+## Quick Start with Docker
+
+Simply run followings on your computer:
+
+```bash
+docker run --rm -p 8000:8000 -t himkt/konoha  # from DockerHub
+```
+
+Or you can build image on your machine:
+
+```bash
+git clone https://github.com/himkt/konoha  # download konoha
+cd konoha && docker-compose up --build  # build and launch container
+```
+
+Tokenization is done by posting a json object to `localhost:8000/api/v1/tokenize`.
+You can also batch tokenize by passing `texts: ["１つ目の入力", "２つ目の入力"]` to `localhost:8000/api/v1/batch_tokenize`.
+
+(API documentation is available on `localhost:8000/redoc`, you can check it using your web browser)
+
+Send a request using `curl` on your terminal.
+Note that a path to an endpoint is changed in v4.6.4.
+Please check our release note (https://github.com/himkt/konoha/releases/tag/v4.6.4).
+
+```json
+$ curl localhost:8000/api/v1/tokenize -X POST -H "Content-Type: application/json" \
+    -d '{"tokenizer": "mecab", "text": "これはペンです"}'
+
+{
+  "tokens": [
+    [
+      {
+        "surface": "これ",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "は",
+        "part_of_speech": "助詞"
+      },
+      {
+        "surface": "ペン",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "です",
+        "part_of_speech": "助動詞"
+      }
+    ]
+  ]
+}
+```
+
+
+## Installation
+
+
+I recommend you to install konoha by `pip install 'konoha[all]'`.
+
+- Install konoha with a specific tokenizer: `pip install 'konoha[(tokenizer_name)]`.
+- Install konoha with a specific tokenizer and remote file support: `pip install 'konoha[(tokenizer_name),remote]'`
+
+If you want to install konoha with a tokenizer, please install konoha with a specific tokenizer
+(e.g. `konoha[mecab]`, `konoha[sudachi]`, ...etc) or install tokenizers individually.
+
+
+## Example
+
+### Word level tokenization
+
+```python
+from konoha import WordTokenizer
+
+sentence = '自然言語処理を勉強しています'
+
+tokenizer = WordTokenizer('MeCab')
+print(tokenizer.tokenize(sentence))
+# => [自然, 言語, 処理, を, 勉強, し, て, い, ます]
+
+tokenizer = WordTokenizer('Sentencepiece', model_path="data/model.spm")
+print(tokenizer.tokenize(sentence))
+# => [▁, 自然, 言語, 処理, を, 勉強, し, ています]
+```
+
+For more detail, please see the `example/` directory.
+
+### Remote files
+
+Konoha supports dictionary and model on cloud storage (currently supports Amazon S3).
+It requires installing konoha with the `remote` option, see [Installation](#installation).
+
+```python
+# download user dictionary from S3
+word_tokenizer = WordTokenizer("mecab", user_dictionary_path="s3://abc/xxx.dic")
+print(word_tokenizer.tokenize(sentence))
+
+# download system dictionary from S3
+word_tokenizer = WordTokenizer("mecab", system_dictionary_path="s3://abc/yyy")
+print(word_tokenizer.tokenize(sentence))
+
+# download model file from S3
+word_tokenizer = WordTokenizer("sentencepiece", model_path="s3://abc/zzz.model")
+print(word_tokenizer.tokenize(sentence))
+```
+
+### Sentence level tokenization
+
+```python
+from konoha import SentenceTokenizer
+
+sentence = "私は猫だ。名前なんてものはない。だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer()
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，「かわいい。それで十分だろう」。']
+```
+
+You can change symbols for a sentence splitter and bracket expression.
+
+1. sentence splitter
+
+```python
+sentence = "私は猫だ。名前なんてものはない．だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer(period="．")
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。名前なんてものはない．', 'だが，「かわいい。それで十分だろう」。']
+```
+
+2. bracket expression
+
+```python
+sentence = "私は猫だ。名前なんてものはない。だが，『かわいい。それで十分だろう』。"
+
+tokenizer = SentenceTokenizer(
+    patterns=SentenceTokenizer.PATTERNS + [re.compile(r"『.*?』")],
+)
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，『かわいい。それで十分だろう』。']
+```
+
+
+## Test
+
+```
+python -m pytest
+```
+
+## Article
+
+- [トークナイザをいい感じに切り替えるライブラリ konoha を作った](https://qiita.com/klis/items/bb9ffa4d9c886af0f531)
+- [日本語解析ツール Konoha に AllenNLP 連携機能を実装した](https://qiita.com/klis/items/f1d29cb431d1bf879898)
+
+## Acknowledgement
+
+Sentencepiece model used in test is provided by @yoheikikuta. Thanks!
+
+
+%package help
+Summary:	Development documents and examples for konoha
+Provides:	python3-konoha-doc
+%description help
+# 🌿 Konoha: Simple wrapper of Japanese Tokenizers
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/himkt/konoha/blob/main/example/Konoha_Example.ipynb)
+<p align="center"><img src="https://user-images.githubusercontent.com/5164000/120913279-e7d62380-c6d0-11eb-8d17-6571277cdf27.gif" width="95%"></p>
+
+[![GitHub stars](https://img.shields.io/github/stars/himkt/konoha?style=social)](https://github.com/himkt/konoha/stargazers)
+
+[![Downloads](https://pepy.tech/badge/konoha)](https://pepy.tech/project/konoha)
+[![Downloads](https://pepy.tech/badge/konoha/month)](https://pepy.tech/project/konoha/month)
+[![Downloads](https://pepy.tech/badge/konoha/week)](https://pepy.tech/project/konoha/week)
+
+[![Build Status](https://github.com/himkt/konoha/workflows/Python%20package/badge.svg?style=flat-square)](https://github.com/himkt/konoha/actions)
+[![Documentation Status](https://readthedocs.org/projects/konoha/badge/?version=latest)](https://konoha.readthedocs.io/en/latest/?badge=latest)
+![Python](https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8-blue?logo=python)
+[![PyPI](https://img.shields.io/pypi/v/konoha.svg)](https://pypi.python.org/pypi/konoha)
+[![GitHub Issues](https://img.shields.io/github/issues/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+[![GitHub Pull Requests](https://img.shields.io/github/issues-pr/himkt/konoha.svg?cacheSeconds=60&color=yellow)](https://github.com/himkt/konoha/issues)
+
+`Konoha` is a Python library for providing easy-to-use integrated interface of various Japanese tokenizers,
+which enables you to switch a tokenizer and boost your pre-processing.
+
+## Supported tokenizers
+
+<a href="https://github.com/buruzaemon/natto-py"><img src="https://img.shields.io/badge/MeCab-natto--py-ff69b4"></a>
+<a href="https://github.com/chezou/Mykytea-python"><img src="https://img.shields.io/badge/KyTea-Mykytea--python-ff69b4"></a>
+<a href="https://github.com/mocobeta/janome"><img src="https://img.shields.io/badge/Janome-janome-ff69b4"></a>
+<a href="https://github.com/WorksApplications/SudachiPy"><img src="https://img.shields.io/badge/Sudachi-sudachipy-ff69b4"></a>
+<a href="https://github.com/google/sentencepiece"><img src="https://img.shields.io/badge/Sentencepiece-sentencepiece-ff69b4"></a>
+<a href="https://github.com/taishi-i/nagisa"><img src="https://img.shields.io/badge/nagisa-nagisa-ff69b4"></a>
+
+Also, `konoha` provides rule-based tokenizers (whitespace, character) and a rule-based sentence splitter.
+
+
+## Quick Start with Docker
+
+Simply run followings on your computer:
+
+```bash
+docker run --rm -p 8000:8000 -t himkt/konoha  # from DockerHub
+```
+
+Or you can build image on your machine:
+
+```bash
+git clone https://github.com/himkt/konoha  # download konoha
+cd konoha && docker-compose up --build  # build and launch container
+```
+
+Tokenization is done by posting a json object to `localhost:8000/api/v1/tokenize`.
+You can also batch tokenize by passing `texts: ["１つ目の入力", "２つ目の入力"]` to `localhost:8000/api/v1/batch_tokenize`.
+
+(API documentation is available on `localhost:8000/redoc`, you can check it using your web browser)
+
+Send a request using `curl` on your terminal.
+Note that a path to an endpoint is changed in v4.6.4.
+Please check our release note (https://github.com/himkt/konoha/releases/tag/v4.6.4).
+
+```json
+$ curl localhost:8000/api/v1/tokenize -X POST -H "Content-Type: application/json" \
+    -d '{"tokenizer": "mecab", "text": "これはペンです"}'
+
+{
+  "tokens": [
+    [
+      {
+        "surface": "これ",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "は",
+        "part_of_speech": "助詞"
+      },
+      {
+        "surface": "ペン",
+        "part_of_speech": "名詞"
+      },
+      {
+        "surface": "です",
+        "part_of_speech": "助動詞"
+      }
+    ]
+  ]
+}
+```
+
+
+## Installation
+
+
+I recommend you to install konoha by `pip install 'konoha[all]'`.
+
+- Install konoha with a specific tokenizer: `pip install 'konoha[(tokenizer_name)]`.
+- Install konoha with a specific tokenizer and remote file support: `pip install 'konoha[(tokenizer_name),remote]'`
+
+If you want to install konoha with a tokenizer, please install konoha with a specific tokenizer
+(e.g. `konoha[mecab]`, `konoha[sudachi]`, ...etc) or install tokenizers individually.
+
+
+## Example
+
+### Word level tokenization
+
+```python
+from konoha import WordTokenizer
+
+sentence = '自然言語処理を勉強しています'
+
+tokenizer = WordTokenizer('MeCab')
+print(tokenizer.tokenize(sentence))
+# => [自然, 言語, 処理, を, 勉強, し, て, い, ます]
+
+tokenizer = WordTokenizer('Sentencepiece', model_path="data/model.spm")
+print(tokenizer.tokenize(sentence))
+# => [▁, 自然, 言語, 処理, を, 勉強, し, ています]
+```
+
+For more detail, please see the `example/` directory.
+
+### Remote files
+
+Konoha supports dictionary and model on cloud storage (currently supports Amazon S3).
+It requires installing konoha with the `remote` option, see [Installation](#installation).
+
+```python
+# download user dictionary from S3
+word_tokenizer = WordTokenizer("mecab", user_dictionary_path="s3://abc/xxx.dic")
+print(word_tokenizer.tokenize(sentence))
+
+# download system dictionary from S3
+word_tokenizer = WordTokenizer("mecab", system_dictionary_path="s3://abc/yyy")
+print(word_tokenizer.tokenize(sentence))
+
+# download model file from S3
+word_tokenizer = WordTokenizer("sentencepiece", model_path="s3://abc/zzz.model")
+print(word_tokenizer.tokenize(sentence))
+```
+
+### Sentence level tokenization
+
+```python
+from konoha import SentenceTokenizer
+
+sentence = "私は猫だ。名前なんてものはない。だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer()
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，「かわいい。それで十分だろう」。']
+```
+
+You can change symbols for a sentence splitter and bracket expression.
+
+1. sentence splitter
+
+```python
+sentence = "私は猫だ。名前なんてものはない．だが，「かわいい。それで十分だろう」。"
+
+tokenizer = SentenceTokenizer(period="．")
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。名前なんてものはない．', 'だが，「かわいい。それで十分だろう」。']
+```
+
+2. bracket expression
+
+```python
+sentence = "私は猫だ。名前なんてものはない。だが，『かわいい。それで十分だろう』。"
+
+tokenizer = SentenceTokenizer(
+    patterns=SentenceTokenizer.PATTERNS + [re.compile(r"『.*?』")],
+)
+print(tokenizer.tokenize(sentence))
+# => ['私は猫だ。', '名前なんてものはない。', 'だが，『かわいい。それで十分だろう』。']
+```
+
+
+## Test
+
+```
+python -m pytest
+```
+
+## Article
+
+- [トークナイザをいい感じに切り替えるライブラリ konoha を作った](https://qiita.com/klis/items/bb9ffa4d9c886af0f531)
+- [日本語解析ツール Konoha に AllenNLP 連携機能を実装した](https://qiita.com/klis/items/f1d29cb431d1bf879898)
+
+## Acknowledgement
+
+Sentencepiece model used in test is provided by @yoheikikuta. Thanks!
+
+
+%prep
+%autosetup -n konoha-5.4.0
+
+%build
+%py3_build
+
+%install
+%py3_install
+install -d -m755 %{buildroot}/%{_pkgdocdir}
+if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
+if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
+if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
+if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
+pushd %{buildroot}
+if [ -d usr/lib ]; then
+	find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
+fi
+if [ -d usr/lib64 ]; then
+	find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
+fi
+if [ -d usr/bin ]; then
+	find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
+fi
+if [ -d usr/sbin ]; then
+	find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
+fi
+touch doclist.lst
+if [ -d usr/share/man ]; then
+	find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
+fi
+popd
+mv %{buildroot}/filelist.lst .
+mv %{buildroot}/doclist.lst .
+
+%files -n python3-konoha -f filelist.lst
+%dir %{python3_sitelib}/*
+
+%files help -f doclist.lst
+%{_docdir}/*
+
+%changelog
+* Mon Apr 10 2023 Python_Bot <Python_Bot@openeuler.org> - 5.4.0-1
+- Package Spec generated
diff --git a/sources b/sources
new file mode 100644
index 0000000..fd6ee56
--- /dev/null
+++ b/sources
@@ -0,0 +1 @@
+4babab57ca6539800f5b959e6a0793d7  konoha-5.4.0.tar.gz
-- 
cgit v1.2.3