def doc():
nlp = English() # make sure we get a new vocab every time
# fmt: off
words = ["Sarah", "'s", "sister", "flew", "to", "Silicon", "Valley", "via", "London", "."]
tags = ["NNP", "POS", "NN", "VBD", "IN", "NNP", "NNP", "IN", "NNP", "."]
pos = ["PROPN", "PART", "NOUN", "VERB", "ADP", "PROPN", "PROPN", "ADP", "PROPN", "PUNCT"]
morphs = ["NounType=prop|Number=sing", "Poss=yes", "Number=sing", "Tense=past|VerbForm=fin",
"", "NounType=prop|Number=sing", "NounType=prop|Number=sing", "",
"NounType=prop|Number=sing", "PunctType=peri"]
# head of '.' is intentionally nonprojective for testing
heads = [2, 0, 3, 3, 3, 6, 4, 3, 7, 5]
deps = ["poss", "case", "nsubj", "ROOT", "prep", "compound", "pobj", "prep", "pobj", "punct"]
lemmas = ["Sarah", "'s", "sister", "fly", "to", "Silicon", "Valley", "via", "London", "."]
ents = ["O"] * len(words)
ents[0] = "B-PERSON"
ents[1] = "I-PERSON"
ents[5] = "B-LOC"
ents[6] = "I-LOC"
ents[8] = "B-GPE"
cats = {"TRAVEL": 1.0, "BAKING": 0.0}
# fmt: on
doc = Doc(
nlp.vocab,
words=words,
tags=tags,
pos=pos,
morphs=morphs,
heads=heads,
deps=deps,
lemmas=lemmas,
ents=ents,
)
doc.cats = cats
return doc
def doc(nlp):
# fmt: off
words = ["Sarah", "'s", "sister", "flew", "to", "Silicon", "Valley", "via", "London", "."]
tags = ["NNP", "POS", "NN", "VBD", "IN", "NNP", "NNP", "IN", "NNP", "."]
pos = ["PROPN", "PART", "NOUN", "VERB", "ADP", "PROPN", "PROPN", "ADP", "PROPN", "PUNCT"]
ents = ["B-PERSON", "I-PERSON", "O", "O", "O", "B-LOC", "I-LOC", "O", "B-GPE", "O"]
cats = {"TRAVEL": 1.0, "BAKING": 0.0}
# fmt: on
doc = Doc(nlp.vocab, words=words, tags=tags, pos=pos, ents=ents)
doc.cats = cats
return doc
def test_serialize_doc_roundtrip_bytes(en_vocab):
doc = Doc(en_vocab, words=["hello", "world"])
doc.cats = {"A": 0.5}
doc_b = doc.to_bytes()
new_doc = Doc(en_vocab).from_bytes(doc_b)
assert new_doc.to_bytes() == doc_b