explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-07 13:44:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix docs and format file

Browse Source
This commit is contained in:
thomashacker 2022-11-14 11:08:06 +01:00
parent acb0d1685f
commit bc72e0e94c
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tests/doc/test_doc_api.py
View File

@ -380,9 +380,7 @@ def test_doc_api_serialize(en_tokenizer, text):
assert [t.text for t in tokens] == [t.text for t in new_tokens] assert [t.text for t in tokens] == [t.text for t in new_tokens]
assert [t.orth for t in tokens] == [t.orth for t in new_tokens] assert [t.orth for t in tokens] == [t.orth for t in new_tokens]
new_tokens = Doc(tokens.vocab).from_bytes( new_tokens = Doc(tokens.vocab).from_bytes(tokens.to_bytes())
tokens.to_bytes()
)
assert tokens.text == new_tokens.text assert tokens.text == new_tokens.text
assert [t.text for t in tokens] == [t.text for t in new_tokens] assert [t.text for t in tokens] == [t.text for t in new_tokens]
assert [t.orth for t in tokens] == [t.orth for t in new_tokens] assert [t.orth for t in tokens] == [t.orth for t in new_tokens]
@ -991,10 +989,11 @@ def test_doc_spans_setdefault(en_tokenizer):
doc.spans.setdefault("key3", default=SpanGroup(doc, spans=[doc[0:1], doc[1:2]])) doc.spans.setdefault("key3", default=SpanGroup(doc, spans=[doc[0:1], doc[1:2]]))
assert len(doc.spans["key3"]) == 2 assert len(doc.spans["key3"]) == 2
def test_doc_sentiment_from_bytes_v3_to_v4(): def test_doc_sentiment_from_bytes_v3_to_v4():
"""Test if a doc with sentiment attribute created in v3.x works with '.from_bytes' in v4.x without throwing errors. The sentiment attribute was removed in v4""" """Test if a doc with sentiment attribute created in v3.x works with '.from_bytes' in v4.x without throwing errors. The sentiment attribute was removed in v4"""
doc_bytes = b'\x89\xa4text\xa5happy\xaaarray_head\x9fGQACKOLMN\xcd\x01\xc4\xcd\x01\xc6I\xcd\x01\xc5JP\xaaarray_body\x85\xc4\x02nd\xc3\xc4\x04type\xa3<u8\xc4\x04kind\xc4\x00\xc4\x05shape\x92\x01\x0f\xc4\x04data\xc4x\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x9a\xd3\x17\xca\xf0b\x03\xa4\x9a\xd3\x17\xca\xf0b\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\xa9sentiment\xcb?\xf0\x00\x00\x00\x00\x00\x00\xa6tensor\x85\xc4\x02nd\xc3\xc4\x04type\xa3<f4\xc4\x04kind\xc4\x00\xc4\x05shape\x91\x00\xc4\x04data\xc4\x00\xa4cats\x80\xa5spans\xc4\x01\x90\xa7strings\x92\xa0\xa5happy\xb2has_unknown_spaces\xc2' doc_bytes = b"\x89\xa4text\xa5happy\xaaarray_head\x9fGQACKOLMN\xcd\x01\xc4\xcd\x01\xc6I\xcd\x01\xc5JP\xaaarray_body\x85\xc4\x02nd\xc3\xc4\x04type\xa3<u8\xc4\x04kind\xc4\x00\xc4\x05shape\x92\x01\x0f\xc4\x04data\xc4x\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x9a\xd3\x17\xca\xf0b\x03\xa4\x9a\xd3\x17\xca\xf0b\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\xa9sentiment\xcb?\xf0\x00\x00\x00\x00\x00\x00\xa6tensor\x85\xc4\x02nd\xc3\xc4\x04type\xa3<f4\xc4\x04kind\xc4\x00\xc4\x05shape\x91\x00\xc4\x04data\xc4\x00\xa4cats\x80\xa5spans\xc4\x01\x90\xa7strings\x92\xa0\xa5happy\xb2has_unknown_spaces\xc2"
doc = Doc(Vocab()).from_bytes(doc_bytes) doc = Doc(Vocab()).from_bytes(doc_bytes)
assert doc.text == "happy" assert doc.text == "happy"
with pytest.raises(AttributeError): with pytest.raises(AttributeError):
doc.sentiment == 1.0 doc.sentiment == 1.0

3
website/docs/usage/rule-based-matching.md
View File

@ -776,6 +776,7 @@ whitespace, making them easy to match as well.
### {executable="true"} ### {executable="true"}
from spacy.lang.en import English from spacy.lang.en import English
from spacy.matcher import Matcher from spacy.matcher import Matcher
from spacy.tokens import Doc
Doc.set_extension("sentiment", default=0.0) Doc.set_extension("sentiment", default=0.0)
@ -825,7 +826,7 @@ the emoji span will make it available as `span._.emoji_desc`.
```python ```python
from emojipedia import Emojipedia # Installation: pip install emojipedia from emojipedia import Emojipedia # Installation: pip install emojipedia
from spacy.tokens import Span # Get the global Span object from spacy.tokens import Doc, Span # Get the global Doc and Span object
Span.set_extension("emoji_desc", default=None) # Register the custom attribute Span.set_extension("emoji_desc", default=None) # Register the custom attribute
Doc.set_extension("sentiment", default=0.0) Doc.set_extension("sentiment", default=0.0)