Merge pull request #2152 from explosion/feature/tidy-up-dependencies

💫 Tidy up dependencies

examples/pipeline/custom_component_countries_api.py

@@ -9,6 +9,7 @@ coordinates. Can be extended with more details from the API.
 * Custom pipeline components: https://spacy.io//usage/processing-pipelines#custom-components
 
 Compatible with: spaCy v2.0.0+
+Prerequisites: pip install requests
 """
 from __future__ import unicode_literals, print_function
 

requirements.txt

@@ -8,9 +8,6 @@ murmurhash>=0.28,<0.29
 plac<1.0.0,>=0.9.6
 ujson>=1.35
 dill>=0.2,<0.3
-requests>=2.13.0,<3.0.0
 regex==2017.4.5
 pytest>=3.0.6,<4.0.0
 mock>=2.0.0,<3.0.0
-msgpack-python==0.5.4
-msgpack-numpy==0.4.1

setup.py

@@ -194,10 +194,7 @@ def setup_package():
                 'pathlib',
                 'ujson>=1.35',
                 'dill>=0.2,<0.3',
-                'requests>=2.13.0,<3.0.0',
+                'regex==2017.4.5'],
-                'regex==2017.4.5',
-                'msgpack-python==0.5.4',
-                'msgpack-numpy==0.4.1'],
             classifiers=[
                 'Development Status :: 5 - Production/Stable',
                 'Environment :: Console',

spacy/cli/download.py

@@ -2,13 +2,14 @@
 from __future__ import unicode_literals
 
 import plac
-import requests
 import os
 import subprocess
 import sys
+import ujson
 
 from .link import link
 from ..util import prints, get_package_path
+from ..compat import url_read, HTTPError
 from .. import about
 
 
@@ -56,13 +57,14 @@ def download(model, direct=False):
 
 
 def get_json(url, desc):
-    r = requests.get(url)
+    try:
-    if r.status_code != 200:
+        data = url_read(url)
+    except HTTPError as e:
         msg = ("Couldn't fetch %s. Please find a model for your spaCy "
                "installation (v%s), and download it manually.")
         prints(msg % (desc, about.__version__), about.__docs_models__,
-               title="Server error (%d)" % r.status_code, exits=1)
+               title="Server error (%d: %s)" % (e.code, e.reason), exits=1)
-    return r.json()
+    return ujson.loads(data)
 
 
 def get_compatibility():

spacy/cli/validate.py

@@ -1,12 +1,12 @@
 # coding: utf8
 from __future__ import unicode_literals, print_function
 
-import requests
 import pkg_resources
 from pathlib import Path
 import sys
+import ujson
 
-from ..compat import path2str, locale_escape
+from ..compat import path2str, locale_escape, url_read, HTTPError
 from ..util import prints, get_data_path, read_json
 from .. import about
 
@@ -15,11 +15,12 @@ def validate():
     """Validate that the currently installed version of spaCy is compatible
     with the installed models. Should be run after `pip install -U spacy`.
     """
-    r = requests.get(about.__compatibility__)
+    try:
-    if r.status_code != 200:
+        data = url_read(about.__compatibility__)
+    except HTTPError as e:
         prints("Couldn't fetch compatibility table.",
-               title="Server error (%d)" % r.status_code, exits=1)
+               title="Server error (%d: %s)" % (e.code, e.reason), exits=1)
-    compat = r.json()['spacy']
+    compat = ujson.loads(data)['spacy']
     current_compat = compat.get(about.__version__)
     if not current_compat:
         prints(about.__compatibility__, exits=1,

spacy/compat.py

@@ -33,6 +33,16 @@ try:
 except ImportError:
     from thinc.neural.optimizers import Adam as Optimizer
 
+try:
+    import urllib.request
+except ImportError:
+    import urllib2 as urllib
+
+try:
+    from urllib.error import HTTPError
+except ImportError:
+    from urllib2 import HTTPError
+
 pickle = pickle
 copy_reg = copy_reg
 CudaStream = CudaStream
@@ -56,6 +66,7 @@ if is_python2:
     input_ = raw_input  # noqa: F821
     json_dumps = lambda data: ujson.dumps(data, indent=2, escape_forward_slashes=False).decode('utf8')
     path2str = lambda path: str(path).decode('utf8')
+    url_open = urllib.urlopen
 
 elif is_python3:
     bytes_ = bytes
@@ -64,6 +75,16 @@ elif is_python3:
     input_ = input
     json_dumps = lambda data: ujson.dumps(data, indent=2, escape_forward_slashes=False)
     path2str = lambda path: str(path)
+    url_open = urllib.request.urlopen
+
+
+def url_read(url):
+    file_ = url_open(url)
+    code = file_.getcode()
+    if code != 200:
+        raise HTTPError(url, code, "Cannot GET url", [], file_)
+    data = file_.read()
+    return data
 
 
 def b_to_str(b_str):

spacy/pipeline.pyx

@@ -8,7 +8,9 @@ cimport numpy as np
 import cytoolz
 from collections import OrderedDict
 import ujson
-import msgpack
+
+from .util import msgpack
+from .util import msgpack_numpy
 
 from thinc.api import chain
 from thinc.v2v import Affine, SELU, Softmax

spacy/util.py

@@ -23,9 +23,10 @@ from .symbols import ORTH
 from .compat import cupy, CudaStream, path2str, basestring_, input_, unicode_
 from .compat import import_file
 
-import msgpack
+# Import these directly from Thinc, so that we're sure we always have the
-import msgpack_numpy
+# same version.
-msgpack_numpy.patch()
+from thinc.neural._classes.model import msgpack
+from thinc.neural._classes.model import msgpack_numpy
 
 
 LANGUAGES = {}

spacy/vectors.pyx

@@ -4,9 +4,10 @@ from __future__ import unicode_literals
 import functools
 import numpy
 from collections import OrderedDict
-import msgpack
+
-import msgpack_numpy
+from .util import msgpack
-msgpack_numpy.patch()
+from .util import msgpack_numpy
+
 cimport numpy as np
 from thinc.neural.util import get_array_module
 from thinc.neural._classes.model import Model