explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5473 from explosion/fix/travis-tests

Browse Source 
Fix Python 2.7 compat
This commit is contained in:
Matthew Honnibal 2020-05-21 15:56:16 +02:00 committed by GitHub
commit 1f572ce89b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 11 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
spacy/lang/zh/__init__.py
View File

@ -169,21 +169,16 @@ class ChineseTokenizer(DummyTokenizer):
return util.to_bytes(serializers, []) return util.to_bytes(serializers, [])
def from_bytes(self, data, **kwargs): def from_bytes(self, data, **kwargs):
pkuseg_features_b = b"" pkuseg_data = {"features_b": b"", "weights_b": b"", "processors_data": None}
pkuseg_weights_b = b""
pkuseg_processors_data = None
def deserialize_pkuseg_features(b): def deserialize_pkuseg_features(b):
nonlocal pkuseg_features_b pkuseg_data["features_b"] = b
pkuseg_features_b = b
def deserialize_pkuseg_weights(b): def deserialize_pkuseg_weights(b):
nonlocal pkuseg_weights_b pkuseg_data["weights_b"] = b
pkuseg_weights_b = b
def deserialize_pkuseg_processors(b): def deserialize_pkuseg_processors(b):
nonlocal pkuseg_processors_data pkuseg_data["processors_data"] = srsly.msgpack_loads(b)
pkuseg_processors_data = srsly.msgpack_loads(b)
deserializers = OrderedDict( deserializers = OrderedDict(
( (
@ -195,13 +190,13 @@ class ChineseTokenizer(DummyTokenizer):
) )
util.from_bytes(data, deserializers, []) util.from_bytes(data, deserializers, [])
if pkuseg_features_b and pkuseg_weights_b: if pkuseg_data["features_b"] and pkuseg_data["weights_b"]:
with tempfile.TemporaryDirectory() as tempdir: with tempfile.TemporaryDirectory() as tempdir:
tempdir = Path(tempdir) tempdir = Path(tempdir)
with open(tempdir / "features.pkl", "wb") as fileh: with open(tempdir / "features.pkl", "wb") as fileh:
fileh.write(pkuseg_features_b) fileh.write(pkuseg_data["features_b"])
with open(tempdir / "weights.npz", "wb") as fileh: with open(tempdir / "weights.npz", "wb") as fileh:
fileh.write(pkuseg_weights_b) fileh.write(pkuseg_data["weights_b"])
try: try:
import pkuseg import pkuseg
except ImportError: except ImportError:
@ -210,13 +205,9 @@ class ChineseTokenizer(DummyTokenizer):
+ _PKUSEG_INSTALL_MSG + _PKUSEG_INSTALL_MSG
) )
self.pkuseg_seg = pkuseg.pkuseg(str(tempdir)) self.pkuseg_seg = pkuseg.pkuseg(str(tempdir))
if pkuseg_processors_data: if pkuseg_data["processors_data"]:
( processors_data = pkuseg_data["processors_data"]
user_dict, (user_dict, do_process, common_words, other_words) = processors_data
do_process,
common_words,
other_words,
) = pkuseg_processors_data
self.pkuseg_seg.preprocesser = pkuseg.Preprocesser(user_dict) self.pkuseg_seg.preprocesser = pkuseg.Preprocesser(user_dict)
self.pkuseg_seg.postprocesser.do_process = do_process self.pkuseg_seg.postprocesser.do_process = do_process
self.pkuseg_seg.postprocesser.common_words = set(common_words) self.pkuseg_seg.postprocesser.common_words = set(common_words)

1
spacy/tests/lang/hy/test_text.py
View File

@ -1,3 +1,4 @@
# coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
import pytest import pytest