explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add to tests

Browse Source
This commit is contained in:
Adriane Boyd 2023-03-17 11:17:41 +01:00
parent befff3ebf8
commit bf4005eb5e
2 changed files with 16 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tests/serialize/test_serialize_doc.py
View File

@ -213,6 +213,13 @@ def test_serialize_doc_exclude(en_vocab):
def test_serialize_doc_span_groups(en_vocab): def test_serialize_doc_span_groups(en_vocab):
doc = Doc(en_vocab, words=["hello", "world", "!"]) doc = Doc(en_vocab, words=["hello", "world", "!"])
doc.spans["content"] = [doc[0:2]] span = doc[0:2]
span.label_ = "test_serialize_doc_span_groups_label"
span.id_ = "test_serialize_doc_span_groups_id"
span.kb_id_ = "test_serialize_doc_span_groups_kb_id"
doc.spans["content"] = [span]
new_doc = Doc(en_vocab).from_bytes(doc.to_bytes()) new_doc = Doc(en_vocab).from_bytes(doc.to_bytes())
assert len(new_doc.spans["content"]) == 1 assert len(new_doc.spans["content"]) == 1
assert new_doc.spans["content"][0].label_ == "test_serialize_doc_span_groups_label"
assert new_doc.spans["content"][0].id_ == "test_serialize_doc_span_groups_id"
assert new_doc.spans["content"][0].kb_id_ == "test_serialize_doc_span_groups_kb_id"

9
spacy/tests/serialize/test_serialize_docbin.py
View File

@ -49,7 +49,11 @@ def test_serialize_doc_bin():
nlp = English() nlp = English()
for doc in nlp.pipe(texts): for doc in nlp.pipe(texts):
doc.cats = cats doc.cats = cats
doc.spans["start"] = [doc[0:2]] span = doc[0:2]
span.label_ = "UNUSUAL_SPAN_LABEL"
span.id_ = "UNUSUAL_SPAN_ID"
span.kb_id_ = "UNUSUAL_SPAN_KB_ID"
doc.spans["start"] = [span]
doc[0].norm_ = "UNUSUAL_TOKEN_NORM" doc[0].norm_ = "UNUSUAL_TOKEN_NORM"
doc[0].ent_id_ = "UNUSUAL_TOKEN_ENT_ID" doc[0].ent_id_ = "UNUSUAL_TOKEN_ENT_ID"
doc_bin.add(doc) doc_bin.add(doc)
@ -63,6 +67,9 @@ def test_serialize_doc_bin():
assert doc.text == texts[i] assert doc.text == texts[i]
assert doc.cats == cats assert doc.cats == cats
assert len(doc.spans) == 1 assert len(doc.spans) == 1
assert doc.spans["start"][0].label_ == "UNUSUAL_SPAN_LABEL"
assert doc.spans["start"][0].id_ == "UNUSUAL_SPAN_ID"
assert doc.spans["start"][0].kb_id_ == "UNUSUAL_SPAN_KB_ID"
assert doc[0].norm_ == "UNUSUAL_TOKEN_NORM" assert doc[0].norm_ == "UNUSUAL_TOKEN_NORM"
assert doc[0].ent_id_ == "UNUSUAL_TOKEN_ENT_ID" assert doc[0].ent_id_ == "UNUSUAL_TOKEN_ENT_ID"