summaryrefslogtreecommitdiff
path: root/python-udkundoku.spec
blob: f581dcaf1c0abff2053dcd622003b160fe281b15 (plain)
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
%global _empty_manifest_terminate_build 0
Name:		python-udkundoku
Version:	2.2.7
Release:	1
Summary:	Classical Chinese to Modern Japanese Translator
License:	MIT
URL:		https://github.com/KoichiYasuoka/UD-Kundoku
Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/5e/66/3278ca52a669eebb26add6a8f21320c2545d86f08353ffcbcba23e166bd9/udkundoku-2.2.7.tar.gz
BuildArch:	noarch


%description
[![Current PyPI packages](https://badge.fury.io/py/udkundoku.svg)](https://pypi.org/project/udkundoku/)

# UD-Kundoku

Classical Chinese to Modern Japanese Translator, working on [Universal Dependencies](https://universaldependencies.org/format.html).

## Basic usage

```py
>>> import udkundoku
>>> lzh=udkundoku.load()
>>> s=lzh("不入虎穴不得虎子")
>>> t=udkundoku.translate(s)
>>> print(t)
# text = 虎の穴に入らずして虎の子を得ず
1	虎	虎	NOUN	n,名詞,主体,動物	_	3	nmod	_	Gloss=tiger|SpaceAfter=No
2	の	_	ADP	_	_	1	case	_	SpaceAfter=No
3	穴	穴	NOUN	n,名詞,固定物,地形	Case=Loc	5	obj	_	Gloss=cave|SpaceAfter=No
4	に	_	ADP	_	_	3	case	_	SpaceAfter=No
5	入ら	入	VERB	v,動詞,行為,移動	_	0	root	_	Gloss=enter|SpaceAfter=No
6	ずして	不	AUX	v,副詞,否定,無界	Polarity=Neg	5	advmod	_	Gloss=not|SpaceAfter=No
7	虎	虎	NOUN	n,名詞,主体,動物	_	9	nmod	_	Gloss=tiger|SpaceAfter=No
8	の	_	ADP	_	_	7	case	_	SpaceAfter=No
9	子	子	NOUN	n,名詞,人,関係	_	11	obj	_	Gloss=child|SpaceAfter=No
10	を	_	ADP	_	_	9	case	_	SpaceAfter=No
11	得	得	VERB	v,動詞,行為,得失	_	5	parataxis	_	Gloss=get|SpaceAfter=No
12	ず	不	AUX	v,副詞,否定,無界	Polarity=Neg	11	advmod	_	Gloss=not|SpaceAfter=No

>>> print(t.sentence())
虎の穴に入らずして虎の子を得ず

>>> print(s.to_tree())
不 <════╗   advmod
入 ═══╗═╝═╗ root
虎 <╗ ║   ║ nmod
穴 ═╝<╝   ║ obj
不 <════╗ ║ advmod
得 ═══╗═╝<╝ parataxis
虎 <╗ ║     nmod
子 ═╝<╝     obj

>>> print(t.to_tree())
虎 ═╗<╗     nmod(体言による連体修飾語)
の <╝ ║     case(格表示)
穴 ═╗═╝<╗   obj(目的語)
に <╝   ║   case(格表示)
入 ═╗═══╝═╗ root(親)
ら  ║     ║
ず <╝     ║ advmod(連用修飾語)
し        ║
て        ║
虎 ═╗<╗   ║ nmod(体言による連体修飾語)
の <╝ ║   ║ case(格表示)
子 ═╗═╝<╗ ║ obj(目的語)
を <╝   ║ ║ case(格表示)
得 ═╗═══╝<╝ parataxis(隣接表現)
ず <╝       advmod(連用修飾語)
```

`udkundoku.load()` is an alias for `udkanbun.load()` of [UD-Kanbun](https://github.com/KoichiYasuoka/UD-Kanbun/). `udkundoku.translate()` is a transcriptive converter from Classical Chinese (under Universal Dependencies of UD-Kanbun) into Modern Japanese (under Universal Dependencies of [UniDic2UD](https://github.com/KoichiYasuoka/UniDic2UD/)). `udkundoku.reorder()` is called to rearrange Classical Chinese into Japanese word-order inside `udkundoku.translate()`. `to_tree()` and `to_svg()` are borrowed from those of UD-Kanbun.

You can simply use `udkundoku` on the command line:
```sh
echo 不入虎穴不得虎子 | udkundoku -j
```

## HTTP-server usage

```sh
python -m udkundoku.server 5000
```
Try to connect `http://127.0.0.1:5000` with your local browser. Input a Classical Chinese sentence there and push 解析-button (at least) three times.

![不入虎穴不得虎子](https://raw.githubusercontent.com/KoichiYasuoka/UD-Kundoku/master/example.png)

## Installation for Linux

Tar-ball is available for Linux, and is installed by default when you use `pip`:
```sh
pip install udkundoku
```
[旧仮名口語UniDic](https://clrd.ninjal.ac.jp/unidic/download_all.html#unidic_qkana) is automatically downloaded for UniDic2UD.

## Installation for Cygwin

Make sure to get `gcc-g++` `python37-pip` `python37-devel` packages, and then:
```sh
pip3.7 install udkundoku
```
Use `python3.7` command in [Cygwin](https://www.cygwin.com/install.html) instead of `python`.

## Installation for Jupyter Notebook (Google Colaboratory)

```py
!pip install udkundoku
```

Try [notebook](https://colab.research.google.com/github/KoichiYasuoka/UD-Kundoku/blob/master/udkundoku.ipynb) for Google Colaboratory.

## Author

Koichi Yasuoka (安岡孝一)

## References

* 安岡孝一: [漢文の依存文法解析にもとづく自動訓読システム](http://hdl.handle.net/2433/259315), 日本漢字学会第3回研究大会予稿集(2020年11月), pp.60-73.
* 安岡孝一: [漢文の依存文法解析と返り点の関係について](http://hdl.handle.net/2433/235609), 日本漢字学会第1回研究大会予稿集(2018年12月), pp.33-48.

%package -n python3-udkundoku
Summary:	Classical Chinese to Modern Japanese Translator
Provides:	python-udkundoku
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-udkundoku
[![Current PyPI packages](https://badge.fury.io/py/udkundoku.svg)](https://pypi.org/project/udkundoku/)

# UD-Kundoku

Classical Chinese to Modern Japanese Translator, working on [Universal Dependencies](https://universaldependencies.org/format.html).

## Basic usage

```py
>>> import udkundoku
>>> lzh=udkundoku.load()
>>> s=lzh("不入虎穴不得虎子")
>>> t=udkundoku.translate(s)
>>> print(t)
# text = 虎の穴に入らずして虎の子を得ず
1	虎	虎	NOUN	n,名詞,主体,動物	_	3	nmod	_	Gloss=tiger|SpaceAfter=No
2	の	_	ADP	_	_	1	case	_	SpaceAfter=No
3	穴	穴	NOUN	n,名詞,固定物,地形	Case=Loc	5	obj	_	Gloss=cave|SpaceAfter=No
4	に	_	ADP	_	_	3	case	_	SpaceAfter=No
5	入ら	入	VERB	v,動詞,行為,移動	_	0	root	_	Gloss=enter|SpaceAfter=No
6	ずして	不	AUX	v,副詞,否定,無界	Polarity=Neg	5	advmod	_	Gloss=not|SpaceAfter=No
7	虎	虎	NOUN	n,名詞,主体,動物	_	9	nmod	_	Gloss=tiger|SpaceAfter=No
8	の	_	ADP	_	_	7	case	_	SpaceAfter=No
9	子	子	NOUN	n,名詞,人,関係	_	11	obj	_	Gloss=child|SpaceAfter=No
10	を	_	ADP	_	_	9	case	_	SpaceAfter=No
11	得	得	VERB	v,動詞,行為,得失	_	5	parataxis	_	Gloss=get|SpaceAfter=No
12	ず	不	AUX	v,副詞,否定,無界	Polarity=Neg	11	advmod	_	Gloss=not|SpaceAfter=No

>>> print(t.sentence())
虎の穴に入らずして虎の子を得ず

>>> print(s.to_tree())
不 <════╗   advmod
入 ═══╗═╝═╗ root
虎 <╗ ║   ║ nmod
穴 ═╝<╝   ║ obj
不 <════╗ ║ advmod
得 ═══╗═╝<╝ parataxis
虎 <╗ ║     nmod
子 ═╝<╝     obj

>>> print(t.to_tree())
虎 ═╗<╗     nmod(体言による連体修飾語)
の <╝ ║     case(格表示)
穴 ═╗═╝<╗   obj(目的語)
に <╝   ║   case(格表示)
入 ═╗═══╝═╗ root(親)
ら  ║     ║
ず <╝     ║ advmod(連用修飾語)
し        ║
て        ║
虎 ═╗<╗   ║ nmod(体言による連体修飾語)
の <╝ ║   ║ case(格表示)
子 ═╗═╝<╗ ║ obj(目的語)
を <╝   ║ ║ case(格表示)
得 ═╗═══╝<╝ parataxis(隣接表現)
ず <╝       advmod(連用修飾語)
```

`udkundoku.load()` is an alias for `udkanbun.load()` of [UD-Kanbun](https://github.com/KoichiYasuoka/UD-Kanbun/). `udkundoku.translate()` is a transcriptive converter from Classical Chinese (under Universal Dependencies of UD-Kanbun) into Modern Japanese (under Universal Dependencies of [UniDic2UD](https://github.com/KoichiYasuoka/UniDic2UD/)). `udkundoku.reorder()` is called to rearrange Classical Chinese into Japanese word-order inside `udkundoku.translate()`. `to_tree()` and `to_svg()` are borrowed from those of UD-Kanbun.

You can simply use `udkundoku` on the command line:
```sh
echo 不入虎穴不得虎子 | udkundoku -j
```

## HTTP-server usage

```sh
python -m udkundoku.server 5000
```
Try to connect `http://127.0.0.1:5000` with your local browser. Input a Classical Chinese sentence there and push 解析-button (at least) three times.

![不入虎穴不得虎子](https://raw.githubusercontent.com/KoichiYasuoka/UD-Kundoku/master/example.png)

## Installation for Linux

Tar-ball is available for Linux, and is installed by default when you use `pip`:
```sh
pip install udkundoku
```
[旧仮名口語UniDic](https://clrd.ninjal.ac.jp/unidic/download_all.html#unidic_qkana) is automatically downloaded for UniDic2UD.

## Installation for Cygwin

Make sure to get `gcc-g++` `python37-pip` `python37-devel` packages, and then:
```sh
pip3.7 install udkundoku
```
Use `python3.7` command in [Cygwin](https://www.cygwin.com/install.html) instead of `python`.

## Installation for Jupyter Notebook (Google Colaboratory)

```py
!pip install udkundoku
```

Try [notebook](https://colab.research.google.com/github/KoichiYasuoka/UD-Kundoku/blob/master/udkundoku.ipynb) for Google Colaboratory.

## Author

Koichi Yasuoka (安岡孝一)

## References

* 安岡孝一: [漢文の依存文法解析にもとづく自動訓読システム](http://hdl.handle.net/2433/259315), 日本漢字学会第3回研究大会予稿集(2020年11月), pp.60-73.
* 安岡孝一: [漢文の依存文法解析と返り点の関係について](http://hdl.handle.net/2433/235609), 日本漢字学会第1回研究大会予稿集(2018年12月), pp.33-48.

%package help
Summary:	Development documents and examples for udkundoku
Provides:	python3-udkundoku-doc
%description help
[![Current PyPI packages](https://badge.fury.io/py/udkundoku.svg)](https://pypi.org/project/udkundoku/)

# UD-Kundoku

Classical Chinese to Modern Japanese Translator, working on [Universal Dependencies](https://universaldependencies.org/format.html).

## Basic usage

```py
>>> import udkundoku
>>> lzh=udkundoku.load()
>>> s=lzh("不入虎穴不得虎子")
>>> t=udkundoku.translate(s)
>>> print(t)
# text = 虎の穴に入らずして虎の子を得ず
1	虎	虎	NOUN	n,名詞,主体,動物	_	3	nmod	_	Gloss=tiger|SpaceAfter=No
2	の	_	ADP	_	_	1	case	_	SpaceAfter=No
3	穴	穴	NOUN	n,名詞,固定物,地形	Case=Loc	5	obj	_	Gloss=cave|SpaceAfter=No
4	に	_	ADP	_	_	3	case	_	SpaceAfter=No
5	入ら	入	VERB	v,動詞,行為,移動	_	0	root	_	Gloss=enter|SpaceAfter=No
6	ずして	不	AUX	v,副詞,否定,無界	Polarity=Neg	5	advmod	_	Gloss=not|SpaceAfter=No
7	虎	虎	NOUN	n,名詞,主体,動物	_	9	nmod	_	Gloss=tiger|SpaceAfter=No
8	の	_	ADP	_	_	7	case	_	SpaceAfter=No
9	子	子	NOUN	n,名詞,人,関係	_	11	obj	_	Gloss=child|SpaceAfter=No
10	を	_	ADP	_	_	9	case	_	SpaceAfter=No
11	得	得	VERB	v,動詞,行為,得失	_	5	parataxis	_	Gloss=get|SpaceAfter=No
12	ず	不	AUX	v,副詞,否定,無界	Polarity=Neg	11	advmod	_	Gloss=not|SpaceAfter=No

>>> print(t.sentence())
虎の穴に入らずして虎の子を得ず

>>> print(s.to_tree())
不 <════╗   advmod
入 ═══╗═╝═╗ root
虎 <╗ ║   ║ nmod
穴 ═╝<╝   ║ obj
不 <════╗ ║ advmod
得 ═══╗═╝<╝ parataxis
虎 <╗ ║     nmod
子 ═╝<╝     obj

>>> print(t.to_tree())
虎 ═╗<╗     nmod(体言による連体修飾語)
の <╝ ║     case(格表示)
穴 ═╗═╝<╗   obj(目的語)
に <╝   ║   case(格表示)
入 ═╗═══╝═╗ root(親)
ら  ║     ║
ず <╝     ║ advmod(連用修飾語)
し        ║
て        ║
虎 ═╗<╗   ║ nmod(体言による連体修飾語)
の <╝ ║   ║ case(格表示)
子 ═╗═╝<╗ ║ obj(目的語)
を <╝   ║ ║ case(格表示)
得 ═╗═══╝<╝ parataxis(隣接表現)
ず <╝       advmod(連用修飾語)
```

`udkundoku.load()` is an alias for `udkanbun.load()` of [UD-Kanbun](https://github.com/KoichiYasuoka/UD-Kanbun/). `udkundoku.translate()` is a transcriptive converter from Classical Chinese (under Universal Dependencies of UD-Kanbun) into Modern Japanese (under Universal Dependencies of [UniDic2UD](https://github.com/KoichiYasuoka/UniDic2UD/)). `udkundoku.reorder()` is called to rearrange Classical Chinese into Japanese word-order inside `udkundoku.translate()`. `to_tree()` and `to_svg()` are borrowed from those of UD-Kanbun.

You can simply use `udkundoku` on the command line:
```sh
echo 不入虎穴不得虎子 | udkundoku -j
```

## HTTP-server usage

```sh
python -m udkundoku.server 5000
```
Try to connect `http://127.0.0.1:5000` with your local browser. Input a Classical Chinese sentence there and push 解析-button (at least) three times.

![不入虎穴不得虎子](https://raw.githubusercontent.com/KoichiYasuoka/UD-Kundoku/master/example.png)

## Installation for Linux

Tar-ball is available for Linux, and is installed by default when you use `pip`:
```sh
pip install udkundoku
```
[旧仮名口語UniDic](https://clrd.ninjal.ac.jp/unidic/download_all.html#unidic_qkana) is automatically downloaded for UniDic2UD.

## Installation for Cygwin

Make sure to get `gcc-g++` `python37-pip` `python37-devel` packages, and then:
```sh
pip3.7 install udkundoku
```
Use `python3.7` command in [Cygwin](https://www.cygwin.com/install.html) instead of `python`.

## Installation for Jupyter Notebook (Google Colaboratory)

```py
!pip install udkundoku
```

Try [notebook](https://colab.research.google.com/github/KoichiYasuoka/UD-Kundoku/blob/master/udkundoku.ipynb) for Google Colaboratory.

## Author

Koichi Yasuoka (安岡孝一)

## References

* 安岡孝一: [漢文の依存文法解析にもとづく自動訓読システム](http://hdl.handle.net/2433/259315), 日本漢字学会第3回研究大会予稿集(2020年11月), pp.60-73.
* 安岡孝一: [漢文の依存文法解析と返り点の関係について](http://hdl.handle.net/2433/235609), 日本漢字学会第1回研究大会予稿集(2018年12月), pp.33-48.

%prep
%autosetup -n udkundoku-2.2.7

%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-udkundoku -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 2.2.7-1
- Package Spec generated