Skip to content

N
nltk
Commit 9a20cfb5 by Steven Bird
Options

Merge pull request #844 from ducki13/new_reader 

nkjp reader
parents 6ac8a59c 0550d27f
Showing with 4 additions and 1 deletions
nltk/corpus/__init__.py
...@@ -147,6 +147,8 @@ movie_reviews = LazyCorpusLoader( ...@@ -147,6 +147,8 @@ movie_reviews = LazyCorpusLoader(
encoding='ascii') encoding='ascii')
names = LazyCorpusLoader( names = LazyCorpusLoader(
'names', WordListCorpusReader, r'(?!\.).*\.txt', encoding='ascii') 'names', WordListCorpusReader, r'(?!\.).*\.txt', encoding='ascii')
nkjp = LazyCorpusLoader(
'nkjp', NKJPCorpusReader, r'', encoding='utf8')
nps_chat = LazyCorpusLoader( nps_chat = LazyCorpusLoader(
'nps_chat', NPSChatCorpusReader, r'(?!README|\.).*\.xml', tagset='wsj') 'nps_chat', NPSChatCorpusReader, r'(?!README|\.).*\.xml', tagset='wsj')
pl196x = LazyCorpusLoader( pl196x = LazyCorpusLoader(
......
nltk/corpus/reader/__init__.py
...@@ -127,5 +127,6 @@ __all__ = [ ...@@ -127,5 +127,6 @@ __all__ = [
'CHILDESCorpusReader', 'AlignedCorpusReader', 'CHILDESCorpusReader', 'AlignedCorpusReader',
'TimitTaggedCorpusReader', 'LinThesaurusCorpusReader', 'TimitTaggedCorpusReader', 'LinThesaurusCorpusReader',
'SemcorCorpusReader', 'FramenetCorpusReader', 'UdhrCorpusReader', 'SemcorCorpusReader', 'FramenetCorpusReader', 'UdhrCorpusReader',
'BNCCorpusReader', 'SentiWordNetCorpusReader', 'SentiSynset' 'BNCCorpusReader', 'SentiWordNetCorpusReader', 'SentiSynset',
'NKJPCorpusReader'
] ]
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment