def __init__(self,
lang='nl',
tokens_glue=None,
tokens_aligner=fTokensAligner(
fTokensAligner.fRegexpTokenFinder())):
assert tokens_aligner
Tokenizer.__init__(self, lang)
self.text_parse_re = re.compile('([^/\s]+/[A-Z0]+)', re.U)
self.tokens_aligner = tokens_aligner
self.glue = tokens_glue
def __init__(self, lang = 'nl'):
Tokenizer.__init__(self, lang)
self.memory, self.tags_map = "-mx512M", {}
self.class_loader = self.ner_instance = None
# test wheher tokenizer has been started under Jython
try:
from java.lang import Class
self.class_loader = Class.forName("gravity.common.CustomClassLoader")(self.java_classpath())
except: pass
def __init__(self, lang="nl"):
Tokenizer.__init__(self, lang)
def __init__(self, lang='nl'):
Tokenizer.__init__(self, lang)
def __init__(self, lang='nl', tokens_glue = None, tokens_aligner =fTokensAligner(fTokensAligner.fRegexpTokenFinder())):
assert tokens_aligner
Tokenizer.__init__(self, lang)
self.text_parse_re = re.compile('([^/\s]+/[A-Z0]+)', re.U)
self.tokens_aligner = tokens_aligner
self.glue = tokens_glue
def __init__(self, lang='nl'):
Tokenizer.__init__(self, lang)
