debian~:$ python -V
Python 3.9.2
debian~:$ sudo apt install -y swig
debian~:$ mkdir -p ~/tmp/app
debian~:$ cd tmp/app
debian~:$ git clone https://github.com/taku910/mecab.git
debian~:$ cd mecab/mecab
debian~:$ ./configure --with-charset=utf8
debian~:$ make -j4 && make check
debian~:$ sudo make install
debian~:$ mecab -v
mecab: error while loading shared libraries: libmecab.so.2: cannot open shared object file: No such file or directory
debian~:$ ls /usr/local/lib/libmecab.so.2
/usr/local/lib/libmecab.so.2
debian~:$ mecab-config --libs-only-L | sudo tee /etc/ld.so.conf.d/mecab.conf
/usr/local/lib
debian~:$ sudo ldconfig
debian~:$ mecab -v
mecab of 0.996
debian~:$ cd ../mecab-ipadic
debian~:$ wget 'https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7MWVlSDBCSXZMTXM' -O mecab-ipadic-2.7.0-20070801.tar.gz
debian~:$ tar zxvf mecab-ipadic-2.7.0-20070801.tar.gz
debian~:$ cd mecab-ipadic-2.7.0-20070801
debian~:$ ./configure --with-charset=utf8
debian~:$ make
debian~:$ sudo make install
debian~:$ mecab
もももすももももものうち
もも 名詞,一般,*,*,*,*,もも,モモ,モモ
も 助詞,係助詞,*,*,*,*,も,モ,モ
すもも 名詞,一般,*,*,*,*,すもも,スモモ,スモモ
も 助詞,係助詞,*,*,*,*,も,モ,モ
もも 名詞,一般,*,*,*,*,もも,モモ,モモ
の 助詞,連体化,*,*,*,*,の,ノ,ノ
うち 名詞,非自立,副詞可能,*,*,*,うち,ウチ,ウチ
EOS
[Ctrl]+[C]
debian~:$ mkdir -p ~/tmp/app/mecab/mecab-ipadic-neologd
debian~:$ cd ~/tmp/app/mecab/mecab-ipadic-neologd
debian~:$ git clone --depth 1 https://github.com/neologd/mecab-ipadic-neologd.git
debian~:$ ./bin/install-mecab-ipadic-neologd -n
...
[install-mecab-ipadic-NEologd] : OK. Let's install mecab-ipadic-NEologd.
[install-mecab-ipadic-NEologd] : Start..
[install-mecab-ipadic-NEologd] : /usr/local/lib/mecab/dic isn't current user's directory
[install-mecab-ipadic-NEologd] : Sudo make install to /usr/local/lib/mecab/dic/mecab-ipadic-neologd
[sudo] xxx のパスワード:
...
[install-mecab-ipadic-NEologd] : Install completed.
[install-mecab-ipadic-NEologd] : When you use MeCab, you can set '/usr/local/lib/mecab/dic/mecab-ipadic-neologd' as a value of '-d' option of MeCab.
[install-mecab-ipadic-NEologd] : Usage of mecab-ipadic-NEologd is here.
Usage:
debian~:$ mecab -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd ...
[install-mecab-ipadic-NEologd] : Finish..
[install-mecab-ipadic-NEologd] : Finish..
...
debian~:$ echo `mecab-config --dicdir`"/mecab-ipadic-neologd"
/usr/local/lib/mecab/dic/mecab-ipadic-neologd
debian~:$ ./bin/install-mecab-ipadic-neologd -h
...
debian~:$ mecab -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd
もももすももももものうち
もも 名詞,一般,*,*,*,*,もも,モモ,モモ
も 助詞,係助詞,*,*,*,*,も,モ,モ
すももももも 名詞,固有名詞,一般,*,*,*,すももももも,スモモモモモ,スモモモモモ
の 助詞,連体化,*,*,*,*,の,ノ,ノ
うち 名詞,非自立,副詞可能,*,*,*,うち,ウチ,ウチ
EOS
[Ctrl]+[C]
debian~:$ mecab -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd -Oyomi
JPOP再生して
JPOPサイセイシテ
[Ctrl]+[C]
debian~:$ mecab -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd -Owakati
JPOP再生して
JPOP 再生 し て
[Ctrl]+[C]
debian~:$ mecab -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd -Odump
JPOP再生して
0 BOS BOS/EOS,*,*,*,*,*,*,*,* 0 0 0 0 0 0 2 1 0.000000 0.000000 0.000000 0
7 JPOP 名詞,固有名詞,組織,*,*,*,* 0 4 1292 1292 45 5 1 1 0.000000 0.000000 0.000000 12857
26 再生 名詞,サ変接続,*,*,*,*,再生,サイセイ,サイセイ 4 10 1283 1283 36 2 0 1 0.000000 0.000000 0.000000 16850
40 し 動詞,自立,*,*,サ変・スル,連用形,する,シ,シ 10 13 610 610 31 6 0 1 0.000000 0.000000 0.000000 20218
47 て 助詞,接続助詞,*,*,*,*,て,テ,テ 13 16 307 307 18 6 0 1 0.000000 0.000000 0.000000 18725
49 EOS BOS/EOS,*,*,*,*,*,*,*,* 16 16 0 0 0 0 3 1 0.000000 0.000000 0.000000 18769
[Ctrl]+[C]
debian~:$ pip3 install mecab-python3
...
debian~:$ python
Python 3.9.2 (default, Feb 28 2021, 17:03:44)
[GCC 10.2.1 20210110] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import MeCab
>>>
[Ctrl]+[D]
debian~:$ cd ~/work
debian~:$ vi test.py
#!/usr/bin/env python3
import MeCab
tagger = MeCab.Tagger("-d /usr/local/lib/mecab/dic/mecab-ipadic-neologd -Odump")
text = "JPOP再生して"
dump = tagger.parse(text)
print(dump)
debian~:$ python test.py
0 BOS BOS/EOS,*,*,*,*,*,*,*,* 0 0 0 0 0 0 2 1 0.000000 0.000000 0.000000 0
7 JPOP 名詞,固有名詞,組織,*,*,*,* 0 4 1292 1292 45 5 1 1 0.000000 0.000000 0.000000 12857
26 再生 名詞,サ変接続,*,*,*,*,再生,サイセイ,サイセイ 4 10 1283 1283 36 2 0 1 0.000000 0.000000 0.000000 16850
40 し 動詞,自立,*,*,サ変・スル,連用形,する,シ,シ 10 13 610 610 31 6 0 1 0.000000 0.000000 0.000000 20218
47 て 助詞,接続助詞,*,*,*,*,て,テ,テ 13 16 307 307 18 6 0 1 0.000000 0.000000 0.000000 18725
49 EOS BOS/EOS,*,*,*,*,*,*,*,* 16 16 0 0 0 0 3 1 0.000000 0.000000 0.000000 18769
[Ctrl]+[C]
debian~:$