explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-27 10:26:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix data_dir=None argument to English class

Browse Source
This commit is contained in:
Matthew Honnibal 2015-01-21 18:27:31 +11:00
parent ef49b8c179
commit f2a229136c
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/en/__init__.py
View File

@ -20,7 +20,7 @@ def get_lex_props(string):
'flags': get_flags(string), 'flags': get_flags(string),
'length': len(string), 'length': len(string),
'sic': string, 'sic': string,
'norm1': string, 'norm1': string.lower(),
'norm2': string, 'norm2': string,
'shape': orth.word_shape(string), 'shape': orth.word_shape(string),
'prefix': string[0], 'prefix': string[0],
@ -75,10 +75,12 @@ class English(object):
else: else:
tok_data_dir = path.join(data_dir, 'tokenizer') tok_data_dir = path.join(data_dir, 'tokenizer')
tok_rules, prefix_re, suffix_re, infix_re = read_lang_data(tok_data_dir) tok_rules, prefix_re, suffix_re, infix_re = read_lang_data(tok_data_dir)
self.tokenizer = Tokenizer(self.vocab, tok_rules, re.compile(prefix_re), prefix_re = re.compile(prefix_re)
re.compile(suffix_re), re.compile(infix_re), suffix_re = re.compile(suffix_re)
infix_re = re.compile(infix_re)
self.tokenizer = Tokenizer(self.vocab, tok_rules, prefix_re,
suffix_re, infix_re,
POS_TAGS, tag_names) POS_TAGS, tag_names)
self.strings = self.vocab.strings
self._tagger = None self._tagger = None
self._parser = None self._parser = None