ubuntu(docker)安装 python3 和 Mecab 并添加自定义词典

原创已于 2025-06-20 11:24:03 修改 · 189 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#ubuntu #docker #linux #mecab #日文分词

于 2025-06-20 11:22:21 首次发布

1. create ubuntu docker container

docker pull ubuntu:22.04

cd /opt
mkdir dockerfiles
chmod -R 777 /opt/dockerfiles
cd /opt/dockerfiles
vi test-ubuntu-ja

FROM ubuntu:22.04
RUN apt-get update
RUN apt-get install language-pack-ja -y
RUN update-locale LANG=ja_JP.UTF-8
RUN locale-gen ja_JP.UTF-8
RUN ln -s /usr/lib/locale/ja_JP.UTF-8 /var/lib/locales/ja_JP.UTF-8
RUN echo 'export LC_ALL=ja_JP.UTF-8' > /etc/profile
RUN . /etc/profile

:wq


# create docker image
docker build -t test-ubuntu-ja -f test-ubuntu-ja .

docker images  # 查看新构建的镜像是否出现在列表中

# create docker container
sudo docker run --name split-keyword-ubuntu -h "split-keyword-ubuntu" --privileged -d -v /opt/pia-api-dl-folder:/opt -v /mnt:/mnt  --ulimit memlock=-1 -td test-ubuntu-ja /bin/bash

2. install python3 (docker内)

docker exec -it split-keyword-ubuntu bash
apt update
apt upgrade -y
apt install python3 python3-pip python3-venv -y
python3 --version

3. install MeCab & 辞書ipadic2.7.0

# install gcc
apt install build-essential gawk

# confirm
gcc --version

#install MeCab
cd /opt/mecab-fan/
git clone https://github.com/taku910/mecab.git
cd mecab/mecab
./configure --prefix=/usr/local --sysconfdir=/usr/local/etc
make
make install

ldconfig


# install  辞書ipadic2.7.0
wget http://downloads.sourceforge.net/mecab/mecab-ipadic-2.7.0-20070801.tar.gz
tar xvfz mecab-ipadic-2.7.0-20070801.tar.gz
cd mecab-ipadic-2.7.0-20070801
./configure --with-charset=utf8
make
make install

ldconfig


# 测试 MeCab 命令行
echo "飯テロの脱衣所" | mecab

4. MeCab自定義単語追加

4.1 创建自定义词典文件

cd /opt
mkdir mecab-user-dict
cd mecab-user-dict
apt install vim
vi userdic.csv


飯テロ,0,0,-500,名詞
脱衣所,0,0,-500,名詞

:wq


4.2: 编译用户词典
cd /usr/local/lib/mecab/dic
mkdir userdic
cd userdic



# 编译用户词典
/usr/local/libexec/mecab/mecab-dict-index \
-d /usr/local/lib/mecab/dic/ipadic \
-u /usr/local/lib/mecab/dic/userdic/userdic.dic \
-f utf-8 \
-t utf-8 \
/opt/mecab-user-dict/userdic.csv


4.3 编辑mecab配置文件，追加自定义词典
find / -name mecabrc
vi /usr/local/etc/mecabrc

userdic = /usr/local/lib/mecab/dic/userdic/userdic.dic
:wq


# 测试
echo "飯テロの脱衣所" | mecab

5. 安装 Python3 的 MeCab 绑定

git clone https://github.com/SamuraiT/mecab-python3.git
cd mecab-python3


pip3 install --upgrade pip setuptools setuptools_scm
apt install git build-essential python3-dev
export SETUPTOOLS_SCM_PRETEND_VERSION=1.0.0
pip3 install .



# 测试 Python 绑定
python3 /opt/mecab-fan/split_sentence.py "飯テロの脱衣所"

6. split_sentence.py 代码

'''
Date: 2022-06-17 12:29:21
LastEditTime: 2022-06-17 12:29:22
FilePath: /opt/mecab-fan/split_sentence.py
Description: 这是默认设置,请设置`customMade`, 打开koroFileHeader查看配置 进行设置: https://github.com/OBKoro1/koro1FileHeader/wiki/%E9%85%8D%E7%BD%AE
'''
#!/usr/bin/python

import sys
import MeCab

def split_sentence(sentence):

	result = ""
	splitStr = ","
	# mecab = MeCab.Tagger ("-Owakati")
	mecab = MeCab.Tagger ("-Ochasen")
	m = mecab.parse ('')
	m = mecab.parseToNode (sentence)

	while m:
		arr = m.feature.split(',')
		clazz = arr[0]
		if clazz != u'BOS/EOS':
			result = result + m.surface + splitStr
		m = m.next
	print(result)

# if __name__ == '__main__':
# 	if len(sys.argv) <= 1:
# 		exit(0)
	
split_sentence(sys.argv[1])