Remove support for Python 2 (huggingface#233)

* remove support for python <= 3.6

* removing python2-compat future imports and utf8 declarations

* version bump to 4.1.0

* formatting with black for uniformity

* remove u strings, add f strings

* more u strings to remove

* remove 2.7 from Travis CI

.travis.yml

@@ -2,8 +2,8 @@ group: travis_latest
 language: python
 cache: pip
 python:
-    - 2.7
     - 3.6
+    - 3.8
     #- nightly
     #- pypy
     #- pypy3

bin/cythonize.py

@@ -25,7 +25,6 @@
 
 Note: this script does not check any of the dependent C++ libraries.
 """
-from __future__ import print_function
 
 import os
 import sys
@@ -35,41 +34,49 @@
 import argparse
 
 
-HASH_FILE = 'cythonize.json'
+HASH_FILE = "cythonize.json"
 
 
 def process_pyx(fromfile, tofile):
-    print('Processing %s' % fromfile)
+    print("Processing %s" % fromfile)
     try:
         from Cython.Compiler.Version import version as cython_version
         from distutils.version import LooseVersion
-        if LooseVersion(cython_version) < LooseVersion('0.19'):
-            raise Exception('Require Cython >= 0.19')
+
+        if LooseVersion(cython_version) < LooseVersion("0.19"):
+            raise Exception("Require Cython >= 0.19")
 
     except ImportError:
         pass
 
-    flags = ['--fast-fail']
-    if tofile.endswith('.cpp'):
-        flags += ['--cplus']
+    flags = ["--fast-fail"]
+    if tofile.endswith(".cpp"):
+        flags += ["--cplus"]
 
     try:
         try:
-            r = subprocess.call(['cython'] + flags + ['-o', tofile, fromfile],
-                                env=os.environ) # See Issue #791
+            r = subprocess.call(
+                ["cython"] + flags + ["-o", tofile, fromfile], env=os.environ
+            )  # See Issue #791
             if r != 0:
-                raise Exception('Cython failed')
+                raise Exception("Cython failed")
         except OSError:
             # There are ways of installing Cython that don't result in a cython
             # executable on the path, see gh-2397.
-            r = subprocess.call([sys.executable, '-c',
-                                'import sys; from Cython.Compiler.Main import '
-                                'setuptools_main as main; sys.exit(main())'] + flags +
-                                ['-o', tofile, fromfile])
+            r = subprocess.call(
+                [
+                    sys.executable,
+                    "-c",
+                    "import sys; from Cython.Compiler.Main import "
+                    "setuptools_main as main; sys.exit(main())",
+                ]
+                + flags
+                + ["-o", tofile, fromfile]
+            )
             if r != 0:
-                raise Exception('Cython failed')
+                raise Exception("Cython failed")
     except OSError:
-        raise OSError('Cython needs to be installed')
+        raise OSError("Cython needs to be installed")
 
 
 def preserve_cwd(path, func, *args):
@@ -89,12 +96,12 @@ def load_hashes(filename):
 
 
 def save_hashes(hash_db, filename):
-    with open(filename, 'w') as f:
+    with open(filename, "w") as f:
         f.write(json.dumps(hash_db))
 
 
 def get_hash(path):
-    return hashlib.md5(open(path, 'rb').read()).hexdigest()
+    return hashlib.md5(open(path, "rb").read()).hexdigest()
 
 
 def hash_changed(base, path, db):
@@ -109,25 +116,27 @@ def hash_add(base, path, db):
 
 def process(base, filename, db):
     root, ext = os.path.splitext(filename)
-    if ext in ['.pyx', '.cpp']:
-        if hash_changed(base, filename, db) or not os.path.isfile(os.path.join(base, root + '.cpp')):
-            preserve_cwd(base, process_pyx, root + '.pyx', root + '.cpp')
-            hash_add(base, root + '.cpp', db)
-            hash_add(base, root + '.pyx', db)
+    if ext in [".pyx", ".cpp"]:
+        if hash_changed(base, filename, db) or not os.path.isfile(
+            os.path.join(base, root + ".cpp")
+        ):
+            preserve_cwd(base, process_pyx, root + ".pyx", root + ".cpp")
+            hash_add(base, root + ".cpp", db)
+            hash_add(base, root + ".pyx", db)
 
 
 def check_changes(root, db):
     res = False
     new_db = {}
 
-    setup_filename = 'setup.py'
-    hash_add('.', setup_filename, new_db)
-    if hash_changed('.', setup_filename, db):
+    setup_filename = "setup.py"
+    hash_add(".", setup_filename, new_db)
+    if hash_changed(".", setup_filename, db):
         res = True
 
     for base, _, files in os.walk(root):
         for filename in files:
-            if filename.endswith('.pxd'):
+            if filename.endswith(".pxd"):
                 hash_add(base, filename, new_db)
                 if hash_changed(base, filename, db):
                     res = True
@@ -150,8 +159,10 @@ def run(root):
         save_hashes(db, HASH_FILE)
 
 
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser(description='Cythonize pyx files into C++ files as needed')
-    parser.add_argument('root', help='root directory')
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Cythonize pyx files into C++ files as needed"
+    )
+    parser.add_argument("root", help="root directory")
     args = parser.parse_args()
     run(args.root)

examples/server.py

@@ -1,26 +1,21 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 """Coreference resolution server example.
 A simple server serving the coreference system.
 """
-from __future__ import unicode_literals
-from __future__ import print_function
 
 import json
 from wsgiref.simple_server import make_server
 import falcon
 import spacy
 import neuralcoref
 
-try:
-    unicode_ = unicode  # Python 2
-except NameError:
-    unicode_ = str      # Python 3
+# Python 3
+unicode_ = str
 
 
 class AllResource(object):
     def __init__(self):
-        self.nlp = spacy.load('en')
+        self.nlp = spacy.load("en")
         neuralcoref.add_to_pipe(self.nlp)
         print("Server loaded")
         self.response = None
@@ -35,28 +30,34 @@ def on_get(self, req, resp):
             text = unicode_(text)
             doc = self.nlp(text)
             if doc._.has_coref:
-                mentions = [{'start':    mention.start_char,
-                             'end':      mention.end_char,
-                             'text':     mention.text,
-                             'resolved': cluster.main.text
-                            }
-                            for cluster in doc._.coref_clusters
-                            for mention in cluster.mentions]
-                clusters = list(list(span.text for span in cluster)
-                                for cluster in doc._.coref_clusters)
+                mentions = [
+                    {
+                        "start": mention.start_char,
+                        "end": mention.end_char,
+                        "text": mention.text,
+                        "resolved": cluster.main.text,
+                    }
+                    for cluster in doc._.coref_clusters
+                    for mention in cluster.mentions
+                ]
+                clusters = list(
+                    list(span.text for span in cluster)
+                    for cluster in doc._.coref_clusters
+                )
                 resolved = doc._.coref_resolved
-                self.response['mentions'] = mentions
-                self.response['clusters'] = clusters
-                self.response['resolved'] = resolved
+                self.response["mentions"] = mentions
+                self.response["clusters"] = clusters
+                self.response["resolved"] = resolved
 
         resp.body = json.dumps(self.response)
-        resp.content_type = 'application/json'
-        resp.append_header('Access-Control-Allow-Origin', "*")
+        resp.content_type = "application/json"
+        resp.append_header("Access-Control-Allow-Origin", "*")
         resp.status = falcon.HTTP_200
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     RESSOURCE = AllResource()
     APP = falcon.API()
-    APP.add_route('/', RESSOURCE)
-    HTTPD = make_server('0.0.0.0', 8000, APP)
+    APP.add_route("/", RESSOURCE)
+    HTTPD = make_server("0.0.0.0", 8000, APP)
     HTTPD.serve_forever()

neuralcoref/__init__.py

@@ -1,38 +1,44 @@
-# coding: utf8
-from __future__ import unicode_literals, absolute_import
-
 import os
-import shutil
 import tarfile
-import tempfile
 import logging
 
 # Filter Cython warnings that would force everybody to re-compile from source (like https://github.com/numpy/numpy/pull/432).
 import warnings
+
 warnings.filterwarnings("ignore", message="spacy.strings.StringStore size changed")
 
 from neuralcoref.neuralcoref import NeuralCoref
-from neuralcoref.file_utils import NEURALCOREF_MODEL_URL, NEURALCOREF_MODEL_PATH, NEURALCOREF_CACHE, cached_path
+from neuralcoref.file_utils import (
+    NEURALCOREF_MODEL_URL,
+    NEURALCOREF_MODEL_PATH,
+    NEURALCOREF_CACHE,
+    cached_path,
+)
 
-__all__ = ['NeuralCoref', 'add_to_pipe']
-__version__ = "4.0.0"
+__all__ = ["NeuralCoref", "add_to_pipe"]
+__version__ = "4.1.0"
 
 logger = logging.getLogger(__name__)
 
-if os.path.exists(NEURALCOREF_MODEL_PATH) and os.path.exists(os.path.join(NEURALCOREF_MODEL_PATH, "cfg")):
-    logger.info("Loading model from {}".format(NEURALCOREF_MODEL_PATH))
+if os.path.exists(NEURALCOREF_MODEL_PATH) and os.path.exists(
+    os.path.join(NEURALCOREF_MODEL_PATH, "cfg")
+):
+    logger.info(f"Loading model from {NEURALCOREF_MODEL_PATH}")
     local_model = cached_path(NEURALCOREF_MODEL_PATH)
 else:
     if not os.path.exists(NEURALCOREF_MODEL_PATH):
         os.makedirs(NEURALCOREF_MODEL_PATH)
-    logger.info("Getting model from {} or cache".format(NEURALCOREF_MODEL_URL))
+    logger.info(f"Getting model from {NEURALCOREF_MODEL_URL} or cache")
     downloaded_model = cached_path(NEURALCOREF_MODEL_URL)
 
-    logger.info("extracting archive file {} to dir {}".format(downloaded_model, NEURALCOREF_MODEL_PATH))
-    with tarfile.open(downloaded_model, 'r:gz') as archive:
+    logger.info(
+        f"extracting archive file {downloaded_model} to dir {NEURALCOREF_MODEL_PATH}"
+    )
+    with tarfile.open(downloaded_model, "r:gz") as archive:
         archive.extractall(NEURALCOREF_CACHE)
 
+
 def add_to_pipe(nlp, **kwargs):
     coref = NeuralCoref(nlp.vocab, **kwargs)
-    nlp.add_pipe(coref, name='neuralcoref')
+    nlp.add_pipe(coref, name="neuralcoref")
     return nlp