def getDocumentTokens(self, doc):
"""
Returns a dict of all terms in the document
"""
full_text=doc.getFullDocumentText(True,False)
full_text=full_text.lower()
tokens=tokenizeText(full_text)
# remove many stopwords. hack!
tokens=[token for token in tokens
if token not in local_stopwords_list]
counts=getDictOfTokenCounts(tokens)
return counts
def textFormatting(self, text, glob):
"""
Text formatting function to be passed to JsonDoc.prettyPrintDocumentHTML()
Args:
text: text of sentence
glob: globals dictionary
"""
res=[]
text=text.strip(".")
tokens=tokenizeText(text)
for token in tokens:
token_dict=self.term_info.get(token.lower(),
{"token_id":0, "references":[]})
references=" ".join(token_dict["references"])
classes=str(token_dict["token_id"]) + " " + references
res.append('<span term_id="%s" class="%s">%s</span>' %
(str(token_dict["token_id"]),classes,token))
result=" ".join(res).strip()
return result.strip(".")
