mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-10-30 23:47:31 +03:00 
			
		
		
		
	Merge pull request #148 from maxirmx/master
Utf8 encoding for lemma_rules.json
This commit is contained in:
		
						commit
						3be94be0c0
					
				|  | @ -8,16 +8,24 @@ environment: | |||
|   matrix: | ||||
| 
 | ||||
|     # Python 2.7.10 is the latest version and is not pre-installed. | ||||
| 
 | ||||
|     - PYTHON: "C:\\Python27.10-x64" | ||||
|       PYTHON_VERSION: "2.7.10" | ||||
|       PYTHON_ARCH: "64" | ||||
| 
 | ||||
|     - PYTHON: "C:\\Python27.10-x32" | ||||
|       PYTHON_VERSION: "2.7.10" | ||||
|       PYTHON_ARCH: "32" | ||||
| 
 | ||||
|     # The lastest Python 3.4. | ||||
|     - PYTHON: "C:\\Python34-x64"  | ||||
|       PYTHON_VERSION: "3.4.x" # currently 3.4.3  | ||||
|       PYTHON_ARCH: "64"  | ||||
| 
 | ||||
|     #- PYTHON: "C:\\Python34-x32"  | ||||
|     #  PYTHON_VERSION: "3.4.x" # currently 3.4.3  | ||||
|     #  PYTHON_ARCH: "32"  | ||||
| 
 | ||||
| 
 | ||||
| install: | ||||
|   # Install Python (from the official .msi of http://python.org) and pip when | ||||
|   # not already installed. | ||||
|  | @ -31,6 +39,7 @@ install: | |||
| 
 | ||||
|   # Filesystem root | ||||
|   #- ps: "ls \"C:/\"" | ||||
|   #- SET | ||||
| 
 | ||||
|   # Installed SDKs | ||||
|   #- ps: "ls \"C:/Program Files/Microsoft SDKs/Windows\"" | ||||
|  |  | |||
|  | @ -1,3 +1,6 @@ | |||
| 
 | ||||
| <img src="https://ci.appveyor.com/api/projects/status/aoe3dtkep36rdaqf?svg=true" /> | ||||
| 
 | ||||
| spaCy: Industrial-strength NLP | ||||
| ============================== | ||||
| 
 | ||||
|  | @ -49,3 +52,6 @@ Difficult to support: | |||
| 
 | ||||
| * PyPy 2.7 | ||||
| * PyPy 3.4 | ||||
| 
 | ||||
| 
 | ||||
| 
 | ||||
|  |  | |||
|  | @ -19,7 +19,7 @@ class Lemmatizer(object): | |||
|             index[pos] = read_index(path.join(data_dir, 'wordnet', 'index.%s' % pos)) | ||||
|             exc[pos] = read_exc(path.join(data_dir, 'wordnet', '%s.exc' % pos)) | ||||
|         if path.exists(path.join(data_dir, 'vocab', 'lemma_rules.json')): | ||||
|             rules = json.load(open(path.join(data_dir, 'vocab', 'lemma_rules.json'))) | ||||
|             rules = json.load(codecs.open(path.join(data_dir, 'vocab', 'lemma_rules.json'), encoding='utf_8')) | ||||
|         else: | ||||
|             rules = {} | ||||
|         return cls(index, exc, rules) | ||||
|  |  | |||
		Loading…
	
		Reference in New Issue
	
	Block a user