Fix json imports and use ujson

spacy/gold.pyx

@@ -145,7 +145,7 @@ def read_json_file(loc, docs_filter=None):
             yield from read_json_file(loc / filename)
     else:
         with io.open(loc, 'r', encoding='utf8') as file_:
-            docs = json.load(file_)
+            docs = ujson.load(file_)
         for doc in docs:
             if docs_filter is not None and not docs_filter(doc):
                 continue

spacy/matcher.pyx

@@ -3,6 +3,8 @@
 # coding: utf8
 from __future__ import unicode_literals
 
+import ujson
+
 from .typedefs cimport attr_t
 from .typedefs cimport hash_t
 from .attrs cimport attr_id_t
@@ -53,12 +55,6 @@ from .attrs import FLAG36 as L9_ENT
 from .attrs import FLAG35 as L10_ENT
 
 
-try:
-    import ujson as json
-except ImportError:
-    import json
-
-
 cpdef enum quantifier_t:
     _META
     ONE
@@ -194,7 +190,7 @@ cdef class Matcher:
         """
         if (path / 'gazetteer.json').exists():
             with (path / 'gazetteer.json').open('r', encoding='utf8') as file_:
-                patterns = json.load(file_)
+                patterns = ujson.load(file_)
         else:
             patterns = {}
         return cls(vocab, patterns)

spacy/tagger.pyx

@@ -1,7 +1,7 @@
-import json
 # coding: utf8
 from __future__ import unicode_literals
 
+import ujson
 from collections import defaultdict
 
 from cymem.cymem cimport Pool
@@ -131,7 +131,7 @@ cdef class Tagger:
         path = util.ensure_path(path)
         if (path / 'templates.json').exists():
             with (path / 'templates.json').open('r', encoding='utf8') as file_:
-                templates = json.load(file_)
+                templates = ujson.load(file_)
         elif require:
             raise IOError(
                 "Required file %s/templates.json not found when loading Tagger" % str(path))

spacy/tokenizer.pyx

@@ -2,16 +2,10 @@
 # coding: utf8
 from __future__ import unicode_literals
 
+import ujson
 
 from cython.operator cimport dereference as deref
 from cython.operator cimport preincrement as preinc
-
-try:
-    import ujson as json
-except ImportError:
-    import json
-
-
 from cymem.cymem cimport Pool
 from preshed.maps cimport PreshMap
 
@@ -52,7 +46,7 @@ cdef class Tokenizer:
         path = util.ensure_path(path)
         if rules is None:
             with (path / 'tokenizer' / 'specials.json').open('r', encoding='utf8') as file_:
-                rules = json.load(file_)
+                rules = ujson.load(file_)
         if prefix_search in (None, True):
             with (path / 'tokenizer' / 'prefix.txt').open() as file_:
                 entries = file_.read().split('\n')

spacy/util.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals, print_function
 
 import io
-import json
+import ujson
 import re
 from pathlib import Path
 import sys
@@ -117,7 +117,7 @@ def parse_package_meta(package_path, package, require=True):
     location = package_path / package / 'meta.json'
     if location.is_file():
         with io.open(location, encoding='utf8') as f:
-            meta = json.load(f)
+            meta = ujson.load(f)
             return meta
     elif require:
         raise IOError("Could not read meta.json from %s" % location)

spacy/vocab.pyx

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 import bz2
-import ujson as json
+import ujson
 import re
 
 from libc.string cimport memset
@@ -69,7 +69,7 @@ cdef class Vocab:
                 "Install vectors after loading.")
         if tag_map is True and (path / 'vocab' / 'tag_map.json').exists():
             with (path / 'vocab' / 'tag_map.json').open('r', encoding='utf8') as file_:
-                tag_map = json.load(file_)
+                tag_map = ujson.load(file_)
         elif tag_map is True:
             tag_map = None
         if lex_attr_getters is not None \
@@ -82,12 +82,12 @@ cdef class Vocab:
             lemmatizer = Lemmatizer.load(path)
         if serializer_freqs is True and (path / 'vocab' / 'serializer.json').exists():
             with (path / 'vocab' / 'serializer.json').open('r', encoding='utf8') as file_:
-                serializer_freqs = json.load(file_)
+                serializer_freqs = ujson.load(file_)
         else:
             serializer_freqs = None
 
         with (path / 'vocab' / 'strings.json').open('r', encoding='utf8') as file_:
-            strings_list = json.load(file_)
+            strings_list = ujson.load(file_)
         cdef Vocab self = cls(lex_attr_getters=lex_attr_getters, tag_map=tag_map,
                               lemmatizer=lemmatizer, serializer_freqs=serializer_freqs,
                               strings=strings_list)