def loadPaperParagraph(self, p, newDocument, parent_id):
"""
Creates a paragraph in newDocument, splits the text into sentences,
creates a sentence object for each
"""
if p.parent.name == "td":
# This is not a content paragraph, but the content of a table cell
return None
par_text=p.renderContents(encoding=None)
if re.match(r"(<i>)?proceedings\s+of\s+the\s+.*",par_text,flags=re.IGNORECASE):
# This is not a content paragraph, we throw it away
return None
newPar=newDocument.addParagraph(parent_id)
try:
sentences=sentenceSplit(par_text)
except:
print("UNICODE ERROR!",par_text)
sentences=[par_text]
for s in sentences:
self.loadPaperSentence(s,newDocument,newPar["id"])
return newPar
def loadJATSParagraph(self, p,newDocument, parent):
"""
Creates a paragraph in newDocument, splits the text into sentences,
creates a sentence object for each
"""
newPar=newDocument.addParagraph(parent)
par_text=p.renderContents(encoding=None)
sentences=sentenceSplit(par_text)
for s in sentences:
self.loadJATSSentence(s, newDocument, newPar["id"], parent)
return newPar
