caught more codecs.open -> io.open

bin/init_model.py

@@ -20,7 +20,7 @@ from pathlib import Path
 
 from shutil import copyfile
 from shutil import copytree
-import codecs
+import io
 
 from spacy.en import get_lex_props
 from spacy.vocab import Vocab
@@ -41,7 +41,7 @@ def setup_tokenizer(lang_data_dir, tok_dir):
 
 def _read_clusters(loc):
     clusters = {}
-    for line in codecs.open(str(loc), 'r', 'utf8'):
+    for line in io.open(str(loc), 'r', encoding='utf8'):
         try:
             cluster, word, freq = line.split()
         except ValueError:
@@ -65,7 +65,7 @@ def _read_clusters(loc):
 
 def _read_probs(loc):
     probs = {}
-    for i, line in enumerate(codecs.open(str(loc), 'r', 'utf8')):
+    for i, line in enumerate(io.open(str(loc), 'r', encoding='utf8')):
         prob, word = line.split()
         prob = float(prob)
         probs[word] = prob

bin/ner_tag.py

@@ -1,11 +1,11 @@
-import codecs
+import io
 import plac
 
 from spacy.en import English
 
 
 def main(text_loc):
-    with codecs.open(text_loc, 'r', 'utf8') as file_:
+    with io.open(text_loc, 'r', encoding='utf8') as file_:
         text = file_.read()
     NLU = English()
     for paragraph in text.split('\n\n'):

bin/prepare_treebank.py

@@ -27,7 +27,7 @@ import json
 from os import path
 import os
 import re
-import codecs
+import io
 from collections import defaultdict
 
 from spacy.munge import read_ptb
@@ -122,7 +122,7 @@ def read_file(*pieces):
     if not path.exists(loc):
         return None
     else:
-        return codecs.open(loc, 'r', 'utf8').read().strip()
+        return io.open(loc, 'r', encoding='utf8').read().strip()
 
 
 def get_file_names(section_dir, subsection):

spacy/en/lemmatizer.py

@@ -1,6 +1,6 @@
 from __future__ import unicode_literals
 from os import path
-import codecs
+import io
 
 
 NOUN_RULES = (
@@ -85,7 +85,7 @@ def lemmatize(string, index, exceptions, rules):
 
 def read_index(loc):
     index = set()
-    for line in codecs.open(loc, 'r', 'utf8'):
+    for line in io.open(loc, 'r', encoding='utf8'):
         if line.startswith(' '):
             continue
         pieces = line.split()
@@ -97,7 +97,7 @@ def read_index(loc):
 
 def read_exc(loc):
     exceptions = {}
-    for line in codecs.open(loc, 'r', 'utf8'):
+    for line in io.open(loc, 'r', encoding='utf8'):
         if line.startswith(' '):
             continue
         pieces = line.split()

spacy/gold.pyx

@@ -1,5 +1,5 @@
 import numpy
-import codecs
+import io
 import json
 import ujson
 import random

spacy/strings.pyx

@@ -1,4 +1,4 @@
-import codecs
+import io
 
 from libc.string cimport memcpy
 from murmurhash.mrmr cimport hash64
@@ -112,11 +112,11 @@ cdef class StringStore:
             string = &self.strings[i]
             py_string = string.chars[:string.length]
             strings.append(py_string.decode('utf8'))
-        with codecs.open(loc, 'w', 'utf8') as file_:
+        with io.open(loc, 'w', encoding='utf8') as file_:
             file_.write(SEPARATOR.join(strings))
 
     def load(self, loc):
-        with codecs.open(loc, 'r', 'utf8') as file_:
+        with io.open(loc, 'r', encoding='utf8') as file_:
             strings = file_.read().split(SEPARATOR)
         cdef unicode string
         cdef bytes byte_string

spacy/vocab.pyx

@@ -4,7 +4,7 @@ from libc.stdint cimport int32_t
 
 import bz2
 from os import path
-import codecs
+import io
 import math
 
 from .lexeme cimport EMPTY_LEXEME

tests/test_parse_navigate.py

@@ -1,6 +1,6 @@
 from __future__ import unicode_literals
 from os import path
-import codecs
+import io
 
 from spacy.en import English
 
@@ -9,7 +9,7 @@ import pytest
 
 @pytest.fixture
 def sun_text():
-    with codecs.open(path.join(path.dirname(__file__), 'sun.txt'), 'r', 'utf8') as file_:
+    with io.open(path.join(path.dirname(__file__), 'sun.txt'), 'r', encoding='utf8') as file_:
         text = file_.read()
     return text