Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix infixes in spanish and portuguese

This commit is contained in:
Matthew Honnibal 2016-11-02 20:43:12 +01:00
parent 3d4bd96e8a
commit 41a4766c1c
2 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/es/language_data.py
View File

@ -114,7 +114,10 @@ _
'''.strip().split('\n')
TOKENIZER_INFIXES = tuple()
TOKENIZER_INFIXES = (r'''\.\.\.+ (?<=[a-z])\.(?=[A-Z]) (?<=[a-zA-Z])-(?=[a-zA-z]) '''
r'''(?<=[a-zA-Z])--(?=[a-zA-z]) (?<=[0-9])-(?=[0-9]) '''
r'''(?<=[A-Za-z]),(?=[A-Za-z])''').split()
TOKENIZER_EXCEPTIONS = {

5
spacy/pt/language_data.py
View File

@ -114,7 +114,10 @@ _
'''.strip().split('\n')
TOKENIZER_INFIXES = tuple()
TOKENIZER_INFIXES = (r'''\.\.\.+ (?<=[a-z])\.(?=[A-Z]) (?<=[a-zA-Z])-(?=[a-zA-z]) '''
r'''(?<=[a-zA-Z])--(?=[a-zA-z]) (?<=[0-9])-(?=[0-9]) '''
r'''(?<=[A-Za-z]),(?=[A-Za-z])''').split()
TOKENIZER_EXCEPTIONS = {