/**
* Retrieve all pages it is embedded in of a list of pages.
*
* @param wikipedia Wikipedia.
* @param pageList List of pages.
* @param namespaces List of name spaces to look into.
* @param limit Flag indicating if the number of results should be limited.
* @throws APIException
*/
@SuppressWarnings("unchecked")
public List<Page> retrieveAllEmbeddedIn(
EnumWikipedia wikipedia, List<Page> pageList,
List<Integer> namespaces,
boolean limit) throws APIException {
if ((pageList == null) || (pageList.size() == 0)) {
return null;
}
final API api = APIFactory.getAPI();
for (final Page page : pageList) {
addTask(new EmbeddedInCallable(wikipedia, this, api, page, namespaces, limit));
}
List<Page> resultList = new ArrayList<Page>();
while (hasRemainingTask() && !shouldStop()) {
Object result = getNextResult();
if (result instanceof List<?>) {
List<Page> pageResult = (List<Page>) result;
for (Page page : pageResult) {
resultList.add(page);
}
}
}
Collections.sort(resultList);
Iterator<Page> itPage = resultList.iterator();
Page previousPage = null;
while (itPage.hasNext()) {
Page page = itPage.next();
if ((previousPage != null) &&
(Page.areSameTitle(previousPage.getTitle(), page.getTitle()))) {
itPage.remove();
} else {
previousPage = page;
}
}
return resultList;
}
/**
* Update redirect and missing information of a list of pages.
*
* @param root Root element.
* @param pages List of pages.
* @throws JDOMException
*/
public void updateRedirect(Element root, Collection<Page> pages) throws JDOMException {
// Retrieving redirects
XPath xpaRedirects = XPath.newInstance("/api/query/redirects/r");
List listRedirects = xpaRedirects.selectNodes(root);
XPath xpaFrom = XPath.newInstance("./@from");
XPath xpaTo = XPath.newInstance("./@to");
// Retrieving pages
XPath xpaPages = XPath.newInstance("/api/query/pages");
Element listPages = (Element) xpaPages.selectSingleNode(root);
XPath xpaPageId = XPath.newInstance("./@pageid");
XPath xpaNamespace = XPath.newInstance("./@ns");
XPath xpaTitle = XPath.newInstance("./@title");
// Retrieving normalization information
Map<String, String> normalization = new HashMap<String, String>();
retrieveNormalization(root, normalization);
// Analyzing redirects
Iterator itRedirect = listRedirects.iterator();
while (itRedirect.hasNext()) {
Element currentRedirect = (Element) itRedirect.next();
String fromPage = xpaFrom.valueOf(currentRedirect);
String toPage = xpaTo.valueOf(currentRedirect);
for (Page p : pages) {
// Find if the redirect is already taken into account
boolean exists = false;
Iterator<Page> itPage = p.getRedirectIteratorWithPage();
while (itPage.hasNext()) {
Page tmp = itPage.next();
String title = getNormalizedTitle(tmp.getTitle(), normalization);
if (Page.areSameTitle(title, toPage)) {
exists = true;
}
}
// Add the redirect if needed
itPage = p.getRedirectIteratorWithPage();
while (itPage.hasNext()) {
Page tmp = itPage.next();
String title = getNormalizedTitle(tmp.getTitle(), normalization);
if (!exists && Page.areSameTitle(title, fromPage)) {
XPath xpaPage = createXPath("page", "title", toPage);
List listTo = xpaPage.selectNodes(listPages);
if (!listTo.isEmpty()) {
Element to = (Element) listTo.get(0);
Page pageTo =
DataManager.getPage(p.getWikipedia(), xpaTitle.valueOf(to), null, null, null);
pageTo.setNamespace(xpaNamespace.valueOf(to));
pageTo.setPageId(xpaPageId.valueOf(to));
p.addRedirect(pageTo);
}
}
}
}
}
// Analyzing missing pages
for (Page p : pages) {
Iterator<Page> itPage = p.getRedirectIteratorWithPage();
while (itPage.hasNext()) {
Page tmp = itPage.next();
String title = getNormalizedTitle(tmp.getTitle(), normalization);
XPath xpaPage = createXPath("page", "title", title);
Element page = (Element) xpaPage.selectSingleNode(listPages);
if (page != null) {
List pageId = xpaPageId.selectNodes(page);
if ((pageId != null) && (!pageId.isEmpty())) {
tmp.setExisting(Boolean.TRUE);
} else {
Attribute attrMissing = page.getAttribute("missing");
if (attrMissing != null) {
tmp.setExisting(Boolean.FALSE);
}
}
}
}
}
}
