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
|
%global _empty_manifest_terminate_build 0
Name: python-spacymoji
Version: 3.0.1
Release: 1
Summary: spaCy pipeline component for adding emoji meta data to Doc, Token and Span objects
License: MIT
URL: https://github.com/explosion/spacymoji
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/2d/69/91125a437c48a2c5d40ff89a7adc659dcc4e371223f83540bf1ae990ffd3/spacymoji-3.0.1.tar.gz
BuildArch: noarch
Requires: python3-spacy
Requires: python3-emoji
%description
# spacymoji: emoji for spaCy
[spaCy](https://spacy.io) extension and pipeline component
for adding emoji meta data to `Doc` objects. Detects emoji consisting of one
or more unicode characters, and can optionally merge multi-char emoji (combined
pictures, emoji with skin tone modifiers) into one token. Human-readable emoji
descriptions are added as a custom attribute, and an optional lookup table can
be provided for your own descriptions. The extension sets the custom `Doc`,
`Token` and `Span` attributes `._.is_emoji`, `._.emoji_desc`, `._.has_emoji` and `._.emoji`. You can read more about custom pipeline components and extension attributes [here](https://spacy.io/usage/processing-pipelines).
Emoji are matched using spaCy's [`PhraseMatcher`](https://spacy.io/api/phrasematcher), and looked up in the data
table provided by the [`emoji` package](https://github.com/carpedm20/emoji).
[](https://dev.azure.com/explosion-ai/public/_build?definitionId=22)
[](https://github.com/explosion/spacymoji/releases)
[](https://pypi.org/project/spacymoji/)
# ⏳ Installation
`spacymoji` requires `spacy` v3.0.0 or higher. For spaCy v2.x, instally `spacymoji==2.0.0`.
```bash
pip install spacymoji
```
# ☝️ Usage
Import the component and add it anywhere in your pipeline using the string
name of the `"emoji"` component factory:
```python
import spacy
nlp = spacy.load("en_core_web_sm")
nlp.add_pipe("emoji", first=True)
doc = nlp("This is a test 😻 👍🏿")
assert doc._.has_emoji is True
assert doc[2:5]._.has_emoji is True
assert doc[0]._.is_emoji is False
assert doc[4]._.is_emoji is True
assert doc[5]._.emoji_desc == "thumbs up dark skin tone"
assert len(doc._.emoji) == 2
assert doc._.emoji[1] == ("👍🏿", 5, "thumbs up dark skin tone")
```
`spacymoji` only cares about the token text, so you can use it on a blank
`Language` instance (it should work for all
[available languages](https://spacy.io/usage/models#languages)!), or in
a pipeline with a loaded pipeline. If your pipeline
includes a tagger, parser and entity recognizer, make sure to add the emoji
component as `first=True`, so the spans are merged right after tokenization,
and _before_ the document is parsed. If your text contains a lot of emoji, this
might even give you a nice boost in parser accuracy.
## Available attributes
The extension sets attributes on the `Doc`, `Span` and `Token`. You can
change the attribute names (and other parameters of the Emoji component) by passing
them via the `config` parameter in the `nlp.add_pipe(...)` method. For more details
on custom components and attributes, see the
[processing pipelines documentation](https://spacy.io/usage/processing-pipelines#custom-components).
| Attribute | Type | Description |
| -------------------- | -------------------------- | ------------------------------------------------------------- |
| `Token._.is_emoji` | bool | Whether the token is an emoji. |
| `Token._.emoji_desc` | str | A human-readable description of the emoji. |
| `Doc._.has_emoji` | bool | Whether the document contains emoji. |
| `Doc._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the document's emoji. |
| `Span._.has_emoji` | bool | Whether the span contains emoji. |
| `Span._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the span's emoji. |
## Settings
You can configure the `emoji` factory by setting any of the following parameters in
the `config` dictionary:
| Setting | Type | Description |
| ------------- | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| `attrs` | Tuple[str, str, str, str] | Attributes to set on the `._` property. Defaults to `('has_emoji', 'is_emoji', 'emoji_desc', 'emoji')`. |
| `pattern_id` | str | ID of match pattern, defaults to `'EMOJI'`. Can be changed to avoid ID conflicts. |
| `merge_spans` | bool | Merge spans containing multi-character emoji, defaults to `True`. Will only merge combined emoji resulting in one icon, not sequences. |
| `lookup` | Dict[str, str] | Optional lookup table that maps emoji strings to custom descriptions, e.g. translations or other annotations. |
```python
emoji_config = {"attrs": ("has_e", "is_e", "e_desc", "e"), lookup={"👨🎤": "David Bowie"})
nlp.add_pipe(emoji, first=True, config=emoji_config)
doc = nlp("We can be 👨🎤 heroes")
assert doc[3]._.is_e
assert doc[3]._.e_desc == "David Bowie"
```
If you're training a pipeline, you can define the component config in your [`config.cfg`](https://spacy.io/usage/training):
```ini
[nlp]
pipeline = ["emoji", "ner"]
# ...
[components.emoji]
factory = "emoji"
merge_spans = false
```
%package -n python3-spacymoji
Summary: spaCy pipeline component for adding emoji meta data to Doc, Token and Span objects
Provides: python-spacymoji
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-spacymoji
# spacymoji: emoji for spaCy
[spaCy](https://spacy.io) extension and pipeline component
for adding emoji meta data to `Doc` objects. Detects emoji consisting of one
or more unicode characters, and can optionally merge multi-char emoji (combined
pictures, emoji with skin tone modifiers) into one token. Human-readable emoji
descriptions are added as a custom attribute, and an optional lookup table can
be provided for your own descriptions. The extension sets the custom `Doc`,
`Token` and `Span` attributes `._.is_emoji`, `._.emoji_desc`, `._.has_emoji` and `._.emoji`. You can read more about custom pipeline components and extension attributes [here](https://spacy.io/usage/processing-pipelines).
Emoji are matched using spaCy's [`PhraseMatcher`](https://spacy.io/api/phrasematcher), and looked up in the data
table provided by the [`emoji` package](https://github.com/carpedm20/emoji).
[](https://dev.azure.com/explosion-ai/public/_build?definitionId=22)
[](https://github.com/explosion/spacymoji/releases)
[](https://pypi.org/project/spacymoji/)
# ⏳ Installation
`spacymoji` requires `spacy` v3.0.0 or higher. For spaCy v2.x, instally `spacymoji==2.0.0`.
```bash
pip install spacymoji
```
# ☝️ Usage
Import the component and add it anywhere in your pipeline using the string
name of the `"emoji"` component factory:
```python
import spacy
nlp = spacy.load("en_core_web_sm")
nlp.add_pipe("emoji", first=True)
doc = nlp("This is a test 😻 👍🏿")
assert doc._.has_emoji is True
assert doc[2:5]._.has_emoji is True
assert doc[0]._.is_emoji is False
assert doc[4]._.is_emoji is True
assert doc[5]._.emoji_desc == "thumbs up dark skin tone"
assert len(doc._.emoji) == 2
assert doc._.emoji[1] == ("👍🏿", 5, "thumbs up dark skin tone")
```
`spacymoji` only cares about the token text, so you can use it on a blank
`Language` instance (it should work for all
[available languages](https://spacy.io/usage/models#languages)!), or in
a pipeline with a loaded pipeline. If your pipeline
includes a tagger, parser and entity recognizer, make sure to add the emoji
component as `first=True`, so the spans are merged right after tokenization,
and _before_ the document is parsed. If your text contains a lot of emoji, this
might even give you a nice boost in parser accuracy.
## Available attributes
The extension sets attributes on the `Doc`, `Span` and `Token`. You can
change the attribute names (and other parameters of the Emoji component) by passing
them via the `config` parameter in the `nlp.add_pipe(...)` method. For more details
on custom components and attributes, see the
[processing pipelines documentation](https://spacy.io/usage/processing-pipelines#custom-components).
| Attribute | Type | Description |
| -------------------- | -------------------------- | ------------------------------------------------------------- |
| `Token._.is_emoji` | bool | Whether the token is an emoji. |
| `Token._.emoji_desc` | str | A human-readable description of the emoji. |
| `Doc._.has_emoji` | bool | Whether the document contains emoji. |
| `Doc._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the document's emoji. |
| `Span._.has_emoji` | bool | Whether the span contains emoji. |
| `Span._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the span's emoji. |
## Settings
You can configure the `emoji` factory by setting any of the following parameters in
the `config` dictionary:
| Setting | Type | Description |
| ------------- | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| `attrs` | Tuple[str, str, str, str] | Attributes to set on the `._` property. Defaults to `('has_emoji', 'is_emoji', 'emoji_desc', 'emoji')`. |
| `pattern_id` | str | ID of match pattern, defaults to `'EMOJI'`. Can be changed to avoid ID conflicts. |
| `merge_spans` | bool | Merge spans containing multi-character emoji, defaults to `True`. Will only merge combined emoji resulting in one icon, not sequences. |
| `lookup` | Dict[str, str] | Optional lookup table that maps emoji strings to custom descriptions, e.g. translations or other annotations. |
```python
emoji_config = {"attrs": ("has_e", "is_e", "e_desc", "e"), lookup={"👨🎤": "David Bowie"})
nlp.add_pipe(emoji, first=True, config=emoji_config)
doc = nlp("We can be 👨🎤 heroes")
assert doc[3]._.is_e
assert doc[3]._.e_desc == "David Bowie"
```
If you're training a pipeline, you can define the component config in your [`config.cfg`](https://spacy.io/usage/training):
```ini
[nlp]
pipeline = ["emoji", "ner"]
# ...
[components.emoji]
factory = "emoji"
merge_spans = false
```
%package help
Summary: Development documents and examples for spacymoji
Provides: python3-spacymoji-doc
%description help
# spacymoji: emoji for spaCy
[spaCy](https://spacy.io) extension and pipeline component
for adding emoji meta data to `Doc` objects. Detects emoji consisting of one
or more unicode characters, and can optionally merge multi-char emoji (combined
pictures, emoji with skin tone modifiers) into one token. Human-readable emoji
descriptions are added as a custom attribute, and an optional lookup table can
be provided for your own descriptions. The extension sets the custom `Doc`,
`Token` and `Span` attributes `._.is_emoji`, `._.emoji_desc`, `._.has_emoji` and `._.emoji`. You can read more about custom pipeline components and extension attributes [here](https://spacy.io/usage/processing-pipelines).
Emoji are matched using spaCy's [`PhraseMatcher`](https://spacy.io/api/phrasematcher), and looked up in the data
table provided by the [`emoji` package](https://github.com/carpedm20/emoji).
[](https://dev.azure.com/explosion-ai/public/_build?definitionId=22)
[](https://github.com/explosion/spacymoji/releases)
[](https://pypi.org/project/spacymoji/)
# ⏳ Installation
`spacymoji` requires `spacy` v3.0.0 or higher. For spaCy v2.x, instally `spacymoji==2.0.0`.
```bash
pip install spacymoji
```
# ☝️ Usage
Import the component and add it anywhere in your pipeline using the string
name of the `"emoji"` component factory:
```python
import spacy
nlp = spacy.load("en_core_web_sm")
nlp.add_pipe("emoji", first=True)
doc = nlp("This is a test 😻 👍🏿")
assert doc._.has_emoji is True
assert doc[2:5]._.has_emoji is True
assert doc[0]._.is_emoji is False
assert doc[4]._.is_emoji is True
assert doc[5]._.emoji_desc == "thumbs up dark skin tone"
assert len(doc._.emoji) == 2
assert doc._.emoji[1] == ("👍🏿", 5, "thumbs up dark skin tone")
```
`spacymoji` only cares about the token text, so you can use it on a blank
`Language` instance (it should work for all
[available languages](https://spacy.io/usage/models#languages)!), or in
a pipeline with a loaded pipeline. If your pipeline
includes a tagger, parser and entity recognizer, make sure to add the emoji
component as `first=True`, so the spans are merged right after tokenization,
and _before_ the document is parsed. If your text contains a lot of emoji, this
might even give you a nice boost in parser accuracy.
## Available attributes
The extension sets attributes on the `Doc`, `Span` and `Token`. You can
change the attribute names (and other parameters of the Emoji component) by passing
them via the `config` parameter in the `nlp.add_pipe(...)` method. For more details
on custom components and attributes, see the
[processing pipelines documentation](https://spacy.io/usage/processing-pipelines#custom-components).
| Attribute | Type | Description |
| -------------------- | -------------------------- | ------------------------------------------------------------- |
| `Token._.is_emoji` | bool | Whether the token is an emoji. |
| `Token._.emoji_desc` | str | A human-readable description of the emoji. |
| `Doc._.has_emoji` | bool | Whether the document contains emoji. |
| `Doc._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the document's emoji. |
| `Span._.has_emoji` | bool | Whether the span contains emoji. |
| `Span._.emoji` | List[Tuple[str, int, str]] | `(emoji, index, description)` tuples of the span's emoji. |
## Settings
You can configure the `emoji` factory by setting any of the following parameters in
the `config` dictionary:
| Setting | Type | Description |
| ------------- | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| `attrs` | Tuple[str, str, str, str] | Attributes to set on the `._` property. Defaults to `('has_emoji', 'is_emoji', 'emoji_desc', 'emoji')`. |
| `pattern_id` | str | ID of match pattern, defaults to `'EMOJI'`. Can be changed to avoid ID conflicts. |
| `merge_spans` | bool | Merge spans containing multi-character emoji, defaults to `True`. Will only merge combined emoji resulting in one icon, not sequences. |
| `lookup` | Dict[str, str] | Optional lookup table that maps emoji strings to custom descriptions, e.g. translations or other annotations. |
```python
emoji_config = {"attrs": ("has_e", "is_e", "e_desc", "e"), lookup={"👨🎤": "David Bowie"})
nlp.add_pipe(emoji, first=True, config=emoji_config)
doc = nlp("We can be 👨🎤 heroes")
assert doc[3]._.is_e
assert doc[3]._.e_desc == "David Bowie"
```
If you're training a pipeline, you can define the component config in your [`config.cfg`](https://spacy.io/usage/training):
```ini
[nlp]
pipeline = ["emoji", "ner"]
# ...
[components.emoji]
factory = "emoji"
merge_spans = false
```
%prep
%autosetup -n spacymoji-3.0.1
%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-spacymoji -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 3.0.1-1
- Package Spec generated
|
