def test_serialize_doc_roundtrip_disk(en_vocab):
doc = Doc(en_vocab, words=["hello", "world"])
with make_tempdir() as d:
file_path = d / "doc"
doc.to_disk(file_path)
doc_d = Doc(en_vocab).from_disk(file_path)
assert doc.to_bytes() == doc_d.to_bytes()
def test_serialize_doc_roundtrip_disk(en_vocab):
doc = Doc(en_vocab, words=["hello", "world"])
with make_tempdir() as d:
file_path = d / "doc"
doc.to_disk(file_path)
doc_d = Doc(en_vocab).from_disk(file_path)
assert doc.to_bytes() == doc_d.to_bytes()
def Serialization():
print("\nThe outcomes of Serialization are:")
try:
text = open("/home/wangdi498/SpaCy/diary2.txt", 'r').read(
) # 'r'会按编码格式进行解析，read()返回的是str；'rb'：会按二进制进行解析，read()返回的是bytes。
print("\nInfo: The Serialization file can be read.\n")
except FileNotFoundError:
print("\nError! The Serialization file cannot be read!\n")
sys.exit(0) # os._exit()会直接将python程序终止，之后的所有代码都不会继续执行。
except:
print("\nError! The .txt file must be UTF-8 encoded format!\n")
doc = nlp(text)
doc.to_disk("/home/wangdi498/SpaCy/diary1.bin")
from spacy.tokens import Doc
from spacy.vocab import Vocab
doc = Doc(Vocab()).from_disk("/home/wangdi498/SpaCy/diary1.bin")
print("The texts are:\n{}".format(doc))
from spacy.tokens import Span
doc = nlp(text)
print("\nThe 1st round of Save and Load is:")
for ent in doc.ents:
print("\t{}\t\t{}\t{}\t{}\t{}\t{}".format(
ent.text, ent.start_char, ent.end_char, ent.label_,
doc[doc.ents.index(ent)].ent_iob_,
doc[doc.ents.index(ent)].ent_type_))
assert len(
doc.ents) != 0, "\nError! This document cannot be empty!" # 防止Doc为空。
augment = [Span(doc, 0, 2, label=doc.vocab.strings[u'EVENT'])]
doc.ents = list(doc.ents) + augment
doc.to_disk("/home/wangdi498/SpaCy/diary2.bin")
print("\nThe 2nd round of Save and Load is:")
for ent in doc.ents:
print("\t{}\t\t{}\t{}\t{}\t{}\t{}".format(
ent.text, ent.start_char, ent.end_char, ent.label_,
doc[doc.ents.index(ent)].ent_iob_,
doc[doc.ents.index(ent)].ent_type_))
paragraph = Doc(Vocab()).from_disk("/home/wangdi498/SpaCy/diary2.bin")
assert len(paragraph.ents
) != 0, "\nError! This document cannot be empty!" # 防止Doc为空。
print("\nThe 3rd round of Save and Load is:")
for ent in paragraph.ents:
print("\t{}\t\t{}\t{}\t{}\t{}\t{}".format(
ent.text, ent.start_char, ent.end_char, ent.label_,
doc[doc.ents.index(ent)].ent_iob_,
doc[doc.ents.index(ent)].ent_type_))
assert [(ent.text, ent.label_) for ent in paragraph.ents] != [
(u'2018年9月27日', u'EVENT')
], "\nHere! The entity '%s' has matched the specified one." % ent.text
def test_tensorwrapper(tmp_path: Path):
doc = Doc(Vocab(), words=["This", "is", "a", "test"])
doc.user_data["tensor"] = TensorWrapper(torch.zeros((2, 2)), 1)
doc.to_disk(tmp_path / "doc.bin")
spacy.load(tmp_path / "doc.bin")