fix encoding issue on windows

yannvgn · Nov 1, 2019 · 75d134d · 75d134d
1 parent c79c33c
commit 75d134d
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 10 deletions.
diff --git a/laserembeddings/__main__.py b/laserembeddings/__main__.py
@@ -22,18 +22,18 @@ def print_usage():
 
 
 def download_file(url, dest):
-    print(f'⏳   Downloading {url}...', end='')
+    print(f'⏳   Downloading {url}...'.encode('utf8'), end='')
     sys.stdout.flush()
     urllib.request.urlretrieve(url, dest)
     print(f'\r✅   Downloaded {url}    ')
 
 
 def extract_tar(tar, output_dir):
-    print(f'⏳   Extracting archive...', end='')
+    print(f'⏳   Extracting archive...'.encode('utf8'), end='')
     sys.stdout.flush()
     with tarfile.open(tar) as t:
         t.extractall(output_dir)
-    print(f'\r✅   Extracted archive    ')
+    print(f'\r✅   Extracted archive    '.encode('utf8'))
 
 
 def download_models(output_dir):
@@ -49,7 +49,7 @@ def download_models(output_dir):
         os.path.join(output_dir, 'bilstm.93langs.2018-12-26.pt'))
 
     print('')
-    print("✨ You\'re all set!")
+    print("✨ You\'re all set!".encode('utf8'))
 
 
 def download_and_extract_test_data(output_dir):
@@ -64,7 +64,7 @@ def download_and_extract_test_data(output_dir):
                 output_dir)
 
     print('')
-    print("✨ Ready to test all that!")
+    print("✨ Ready to test all that!".encode('utf8'))
 
 
 def main():
@@ -93,7 +93,7 @@ def main():
         if os.path.basename(repository_root) != 'laserembeddings':
             print(
                 "❌  Looks like you're not running laserembeddings from its source code"
-            )
+                .encode('utf8'))
             print(
                 "     → please checkout https://github.com/yannvgn/laserembedings.git"
             )

diff --git a/laserembeddings/laser.py b/laserembeddings/laser.py
@@ -58,19 +58,19 @@ def __init__(self,
             if not os.path.isfile(self.DEFAULT_BPE_CODES_FILE):
                 raise FileNotFoundError(
                     '93langs.fcodes is missing, run "python -m laserembeddings download-models" to fix that 🔧'
-                )
+                    .encode('utf8'))
             bpe_codes = self.DEFAULT_BPE_CODES_FILE
         if bpe_vocab is None:
             if not os.path.isfile(self.DEFAULT_BPE_VOCAB_FILE):
                 raise FileNotFoundError(
                     '93langs.fvocab is missing, run "python -m laserembeddings download-models" to fix that 🔧'
-                )
+                    .encode('utf8'))
             bpe_vocab = self.DEFAULT_BPE_VOCAB_FILE
         if encoder is None:
             if not os.path.isfile(self.DEFAULT_ENCODER_FILE):
                 raise FileNotFoundError(
                     'bilstm.93langs.2018-12-26.pt is missing, run "python -m laserembeddings download-models" to fix that 🔧'
-                )
+                    .encode('utf8'))
             encoder = self.DEFAULT_ENCODER_FILE
 
         self.tokenizer_options = tokenizer_options

diff --git a/tests/test_laser.py b/tests/test_laser.py
@@ -27,7 +27,7 @@ def test_similarity(test_data):
     if not test_data:
         raise FileNotFoundError(
             'laserembeddings-test-data.npz is missing, run "python -m laserembeddings download-test-data" to fix that 🔧'
-        )
+            .encode('utf8'))
 
     report = os.path.join(os.path.dirname(os.path.realpath(__file__)),
                           'report', 'comparison-with-LASER.md')