From e28de12cbdeb932de0ec4fff901a3bc469bb90c3 Mon Sep 17 00:00:00 2001
From: Claudiu-Vlad Ursache <claudiu.vlad.ursache@gmail.com>
Date: Tue, 13 Feb 2018 20:44:33 +0100
Subject: [PATCH] Ensure files opened in `from_disk` are closed

Fixes [issue 1706](https://github.com/explosion/spaCy/issues/1706).
---
 spacy/language.py                             |  2 +-
 spacy/pipeline.pyx                            |  6 ++--
 spacy/syntax/nn_parser.pyx                    |  2 +-
 .../serialize/test_serialize_language.py      | 28 +++++++++++++++++++
 spacy/vectors.pyx                             |  3 +-
 5 files changed, 36 insertions(+), 5 deletions(-)
 create mode 100644 spacy/tests/serialize/test_serialize_language.py

diff --git a/spacy/language.py b/spacy/language.py
index a2b945c49..a61b6b09f 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -624,7 +624,7 @@ class Language(object):
         deserializers = OrderedDict((
             ('vocab', lambda p: self.vocab.from_disk(p)),
             ('tokenizer', lambda p: self.tokenizer.from_disk(p, vocab=False)),
-            ('meta.json', lambda p: self.meta.update(ujson.load(p.open('r'))))
+            ('meta.json', lambda p: self.meta.update(util.read_json(p)))
         ))
         for name, proc in self.pipeline:
             if name in disable:
diff --git a/spacy/pipeline.pyx b/spacy/pipeline.pyx
index c5f8065de..dae21941e 100644
--- a/spacy/pipeline.pyx
+++ b/spacy/pipeline.pyx
@@ -214,7 +214,8 @@ class Pipe(object):
 
 def _load_cfg(path):
     if path.exists():
-        return ujson.load(path.open())
+        with path.open() as file_:
+            return ujson.load(file_)
     else:
         return {}
 
@@ -580,7 +581,8 @@ class Tagger(Pipe):
         def load_model(p):
             if self.model is True:
                 self.model = self.Model(self.vocab.morphology.n_tags, **self.cfg)
-            self.model.from_bytes(p.open('rb').read())
+            with p.open('rb') as file_:
+                self.model.from_bytes(file_.read())
 
         def load_tag_map(p):
             with p.open('rb') as file_:
diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx
index fa91c697e..f192e3b96 100644
--- a/spacy/syntax/nn_parser.pyx
+++ b/spacy/syntax/nn_parser.pyx
@@ -887,7 +887,7 @@ cdef class Parser:
         deserializers = {
             'vocab': lambda p: self.vocab.from_disk(p),
             'moves': lambda p: self.moves.from_disk(p, strings=False),
-            'cfg': lambda p: self.cfg.update(ujson.load(p.open())),
+            'cfg': lambda p: self.cfg.update(util.read_json(p)),
             'model': lambda p: None
         }
         util.from_disk(path, deserializers, exclude)
diff --git a/spacy/tests/serialize/test_serialize_language.py b/spacy/tests/serialize/test_serialize_language.py
new file mode 100644
index 000000000..1fcf8ef18
--- /dev/null
+++ b/spacy/tests/serialize/test_serialize_language.py
@@ -0,0 +1,28 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from ..util import make_tempdir
+from ...language import Language
+
+import pytest
+
+
+@pytest.fixture
+def meta_data():
+    return {
+        'name': 'name-in-fixture',
+        'version': 'version-in-fixture',
+        'description': 'description-in-fixture',
+        'author': 'author-in-fixture',
+        'email': 'email-in-fixture',
+        'url': 'url-in-fixture',
+        'license': 'license-in-fixture',
+    }
+
+
+def test_serialize_language_meta_disk(meta_data):
+    language = Language(meta=meta_data)
+    with make_tempdir() as d:
+        language.to_disk(d)
+        new_language = Language().from_disk(d)
+    assert new_language.meta == language.meta
diff --git a/spacy/vectors.pyx b/spacy/vectors.pyx
index 079f6fc84..7daebabe6 100644
--- a/spacy/vectors.pyx
+++ b/spacy/vectors.pyx
@@ -347,7 +347,8 @@ cdef class Vectors:
         """
         def load_key2row(path):
             if path.exists():
-                self.key2row = msgpack.load(path.open('rb'))
+                with path.open('rb') as file_:
+                    self.key2row = msgpack.load(file_)
             for key, row in self.key2row.items():
                 if row in self._unset:
                     self._unset.remove(row)