Merge branch 'master' into ja-support

.travis.yml

@@ -1,16 +1,57 @@
-dist: xenial
 language: python
-python:
-  - "3.6"
-  - "3.7"
-before_install:
-  - pip install poetry
+jobs:
+  include:
+    - name: "Python 3.7 on Xenial Linux"
+      python: 3.7
+      before_install:
+        - python -m pip install --upgrade pip
+        - pip3 install poetry
+        - pip3 install torch==1.3.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
+    - name: "Python 3.6 on Xenial Linux"
+      python: 3.6
+      before_install:
+        - python -m pip install --upgrade pip
+        - pip3 install poetry
+        - pip3 install torch==1.3.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
+    - name: "Python 3.7 on macOS"
+      os: osx
+      osx_image: xcode11.2
+      language: shell
+      before_install:
+        - python3 -m pip install --upgrade pip
+        - pip3 install poetry
+        - pip3 install virtualenv
+        - virtualenv .env
+        - source .env/bin/activate
+        - pip3 install torch
+    - name: "Python 3.7 on Windows"
+      os: windows
+      language: shell
+      before_install:
+        - choco install python --version 3.7.0
+        - python -m pip install --upgrade pip
+        - pip3 install poetry
+        - poetry config settings.virtualenvs.create false
+        - pip3 install torch==1.3.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
+      env: PATH=/c/Python37:/c/Python37/Scripts:$PATH
+    - name: "Python 3.7 on Xenial Linux (wheel installation)"
+      python: 3.7
+      before_install:
+        - python -m pip install --upgrade pip
+        - pip3 install poetry
+        - pip3 install torch==1.3.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
+      install:
+        - poetry build
+        - pip3 install dist/laserembeddings-*.whl
+        - python -m laserembeddings download-models
+      script:
+        - python -c 'from laserembeddings import Laser; laser = Laser(); laser.embed_sentences(["test"], lang="en")'
+
 install:
-  - if [[ `python --version` =~ 'Python 3.6' ]]; then pip install https://download.pytorch.org/whl/cpu/torch-1.1.0-cp36-cp36m-linux_x86_64.whl; fi
-  - if [[ `python --version` =~ 'Python 3.7' ]]; then pip install https://download.pytorch.org/whl/cpu/torch-1.1.0-cp37-cp37m-linux_x86_64.whl; fi
   - poetry remove torch -n # fix: latest torch wheel (1.1.0.post2) not available for linux
   - poetry install -n
-  - python -m laserembeddings download-models
+  - python3 -m laserembeddings download-models || python -m laserembeddings download-models
+
 script:
   - poetry run pylint laserembeddings
   - poetry run pytest

laserembeddings/__main__.py

@@ -3,37 +3,53 @@
 import urllib.request
 import tarfile
 
+IS_WIN = os.name == 'nt'
+
+
+def non_win_string(s):
+    return s if not IS_WIN else ''
+
+
+CONSOLE_CLEAR = non_win_string('\033[0;0m')
+CONSOLE_BOLD = non_win_string('\033[0;1m')
+CONSOLE_WAIT = non_win_string('⏳')
+CONSOLE_DONE = non_win_string('✅')
+CONSOLE_STARS = non_win_string('✨')
+CONSOLE_ERROR = non_win_string('❌')
+
 
 def print_usage():
     print('Usage:')
     print('')
     print(
-        '\033[0;1mpython -m laserembeddings download-models [OUTPUT_DIRECTORY]\033[0;0m'
+        f'{CONSOLE_BOLD}python -m laserembeddings download-models [OUTPUT_DIRECTORY]{CONSOLE_CLEAR}'
     )
     print(
         '   Downloads LASER model files. If OUTPUT_DIRECTORY is omitted,'
         '\n'
-        '   the models will be placed into the \033[0;1mdata\033[0;0m directory of the module'
+        f'   the models will be placed into the {CONSOLE_BOLD}data{CONSOLE_CLEAR} directory of the module'
     )
     print('')
-    print('\033[0;1mpython -m laserembeddings download-test-data\033[0;0m')
+    print(
+        f'{CONSOLE_BOLD}python -m laserembeddings download-test-data{CONSOLE_CLEAR}'
+    )
     print('   downloads data needed to run the tests')
     print('')
 
 
 def download_file(url, dest):
-    print(f'⏳   Downloading {url}...', end='')
+    print(f'{CONSOLE_WAIT}   Downloading {url}...', end='')
     sys.stdout.flush()
     urllib.request.urlretrieve(url, dest)
-    print(f'\r✅   Downloaded {url}    ')
+    print(f'\r{CONSOLE_DONE}   Downloaded {url}    ')
 
 
 def extract_tar(tar, output_dir):
-    print(f'⏳   Extracting archive...', end='')
+    print(f'{CONSOLE_WAIT}   Extracting archive...', end='')
     sys.stdout.flush()
     with tarfile.open(tar) as t:
         t.extractall(output_dir)
-    print(f'\r✅   Extracted archive    ')
+    print(f'\r{CONSOLE_DONE}   Extracted archive    ')
 
 
 def download_models(output_dir):
@@ -49,7 +65,7 @@ def download_models(output_dir):
         os.path.join(output_dir, 'bilstm.93langs.2018-12-26.pt'))
 
     print('')
-    print("✨ You\'re all set!")
+    print(f'{CONSOLE_STARS} You\'re all set!')
 
 
 def download_and_extract_test_data(output_dir):
@@ -64,7 +80,7 @@ def download_and_extract_test_data(output_dir):
                 output_dir)
 
     print('')
-    print("✨ Ready to test all that!")
+    print(f'{CONSOLE_STARS} Ready to test all that!')
 
 
 def main():
@@ -92,7 +108,7 @@ def main():
 
         if os.path.basename(repository_root) != 'laserembeddings':
             print(
-                "❌  Looks like you're not running laserembeddings from its source code"
+                f"{CONSOLE_ERROR}  Looks like you're not running laserembeddings from its source code"
             )
             print(
                 "     → please checkout https://github.com/yannvgn/laserembedings.git"

laserembeddings/laser.py

@@ -57,19 +57,19 @@ def __init__(self,
         if bpe_codes is None:
             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 🔧'
+                    '93langs.fcodes is missing, run "python -m laserembeddings download-models" to fix that'
                 )
             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 🔧'
+                    '93langs.fvocab is missing, run "python -m laserembeddings download-models" to fix that'
                 )
             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 🔧'
+                    'bilstm.93langs.2018-12-26.pt is missing, run "python -m laserembeddings download-models" to fix that'
                 )
             encoder = self.DEFAULT_ENCODER_FILE
 

tests/test_laser.py

@@ -26,7 +26,7 @@ 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 🔧'
+            'laserembeddings-test-data.npz is missing, run "python -m laserembeddings download-test-data" to fix that'
         )
 
     report = os.path.join(os.path.dirname(os.path.realpath(__file__)),