def __init__(self, id, label, edges=None, **metas):
# double heritage
whitelist.WhitelistFile.__init__(self)
PyTextMiner.__init__(self, {}, id, label, edges, **metas)
### same database as tinasoft, but temp
self.storage = self._get_storage()
### cache for corpus
self.corpus = {}
def __init__(self,
id,
content=None,
edges=None,
**metas):
if content is None:
content = id
PyTextMiner.__init__(self, content, id, id, edges, **metas)
def __init__(
self,
content,
id,
label,
edges=None,
**metas
):
PyTextMiner.__init__(self, content, id, label, edges, **metas)
if 'keyword' not in self.edges:
self.edges['keyword']={}
def __init__(self, tokenlist, id=None, label=None, edges=None, postag=None, **metas):
"""
initiate the object
normalize must be local value for pickling reasons
"""
# normlist is the normalized list of tokens
normalized_tokens = [NGram.normalize(word) for word in tokenlist]
# prepares postag
if postag is not None:
metas["postag"] = postag
else:
metas["postag"] = ["?"]
# default emtpy edges
if edges is None:
edges = { 'label': {}, 'postag' : {} }
PyTextMiner.__init__(self, normalized_tokens, id, label, edges, **metas)
# updates majors forms before returning instance
self.addForm(normalized_tokens, metas["postag"], 1)
def __init__(self, name, edges=None, **metas):
# list of corpus id
content = []
if edges is not None and 'Corpus' in edges:
content = edges['Corpus'].keys()
PyTextMiner.__init__(self, content, name, name, edges=edges, **metas)
def __init__(self, id, label, edges=None, **metas):
PyTextMiner.__init__(self, {}, id, label, edges, **metas)
### same database as tinasoft, but temp
self.storage = self._get_storage()
### cache for corpus
self.corpus = {}