private void setCategories(Article article, ParsedPage page) { final ArrayList<Link> categories = new ArrayList<Link>(10); for (final de.tudarmstadt.ukp.wikipedia.parser.Link c : page.getCategories()) { categories.add(new Link(c.getTarget(), c.getText(), c.getPos().getStart(), c.getPos().getEnd(), Link.Type.CATEGORY)); } article.setCategories(categories); }
private void parseCategory(RawPage xml, ParsedPage pp){ // handle categories for (Link cat : pp.getCategories()){ Title destTitle = new Title(cat.getTarget(), lang); // TODO: ensure title is a category ParsedCategory pc = new ParsedCategory(); pc.location = new ParsedLocation(xml, -1, -1, cat.getSrcSpan().getStart()); pc.category = destTitle; visitCategory(pc); } // handle ILLs parseIlls(xml, pp); }
for (Link cat : pp.getCategories()){ String linkText = cat.getText(); if (linkText.contains(Pattern.quote("|"))){