File size: 1,963 Bytes
914ca91
 
f9ed5bd
82bab6c
914ca91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7fcb78b
 
 
 
914ca91
 
82bab6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
914ca91
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
import os

os.system('git clone --depth 1 https://github.com/neologd/mecab-ipadic-neologd.git && cd mecab-ipadic-neologd && ./bin/install-mecab-ipadic-neologd -n -y -u -p $PWD')
os.system('git clone --depth 1 https://github.com/neologd/mecab-unidic-neologd.git && cd mecab-unidic-neologd && ./bin/install-mecab-unidic-neologd -n -y -u -p $PWD')

import streamlit as st

import MeCab

st.set_page_config(page_title="NEologd demo")
st.title('NEologd demo')


"""
Input the text you'd like to analyze. See the [NEologd][] docs for more details.
[NEologd]: https://github.com/neologd
"""

text = st.text_area("input", "麩菓子は、麩を主材料とした日本の菓子。")

def make_row(word):
    ff = word.feature.split(",")
    return dict(surface=word.surface, kana=ff[7], lemma=ff[6], 
            pos1=ff[0], pos2=ff[1], pos3=ff[2], pos4=ff[3])

"""
### [mecab-ipadic-NEologd : Neologism dictionary for MeCab](https://github.com/neologd/mecab-ipadic-neologd)
"""

data = []

tagger = MeCab.Tagger('-r /etc/mecabrc -Ochasen -d /home/user/app/mecab-ipadic-neologd')
node = tagger.parseToNode(text)
while node:
    if node.feature.startswith('BOS/EOS'):
        pass
    else:
        data.append(make_row(node))
    node = node.next

st.table(data)

"""
### [mecab-unidic-NEologd : Neologism dictionary for unidic-mecab](https://github.com/neologd/mecab-unidic-neologd)
"""

data = []

tagger = MeCab.Tagger('-r /etc/mecabrc -Ochasen -d /home/user/app/mecab-unidic-neologd')
node = tagger.parseToNode(text)
while node:
    if node.feature.startswith('BOS/EOS'):
        pass
    else:
        data.append(make_row(node))
    node = node.next

st.table(data)

"""
### [MeCab](https://taku910.github.io/mecab/)
"""

data = []

tagger = MeCab.Tagger('-r /etc/mecabrc -Ochasen')
node = tagger.parseToNode(text)
while node:
    if node.feature.startswith('BOS/EOS'):
        pass
    else:
        data.append(make_row(node))
    node = node.next

st.table(data)