/** For debugging. */
public static void main(String[] args) throws Exception {
final String usage = "NutchBean query";
if (args.length == 0) {
System.err.println(usage);
System.exit(-1);
}
final Configuration conf = NutchConfiguration.create();
final NutchBean bean = new NutchBean(conf);
try {
final Query query = Query.parse(args[0], conf);
final Hits hits = bean.search(query, 10);
System.out.println("Total hits: " + hits.getTotal());
final int length = (int) Math.min(hits.getTotal(), 10);
final Hit[] show = hits.getHits(0, length);
final HitDetails[] details = bean.getDetails(show);
final Summary[] summaries = bean.getSummary(details, query);
for (int i = 0; i < hits.getLength(); i++) {
System.out.println(" " + i + " " + details[i] + "\n" + summaries[i]);
}
} catch (Throwable t) {
LOG.error("Exception occured while executing search: " + t, t);
System.exit(1);
}
System.exit(0);
}
/** appends a sorted list of hits to an existing set of hits. */
public void appendSingleHits(SingleHit[] hits, String prefix, int chrom) throws IOException {
if (hits.length == 0) {
return;
}
int s = getPositionsBuffer().limit() - 1;
SingleHit last =
new SingleHit(
chrom,
getPositionsBuffer().get(s),
getWeightsBuffer().get(s),
Hits.getStrandOne(getLASBuffer().get(s)),
Hits.getLengthOne(getLASBuffer().get(s)));
if (hits[0].compareTo(last) > 0) {
append(hits, prefix, chrom);
} else {
merge(hits, prefix, chrom);
}
}
private void merge(SingleHit[] hits, String prefix, int chrom) throws IOException {
String postmp = getPositionsFname(prefix, chrom) + ".tmp";
String weightstmp = getWeightsFname(prefix, chrom) + ".tmp";
String lastmp = getLaSFname(prefix, chrom) + ".tmp";
RandomAccessFile positionsRAF = new RandomAccessFile(postmp, "rw");
RandomAccessFile weightsRAF = new RandomAccessFile(weightstmp, "rw");
RandomAccessFile lasRAF = new RandomAccessFile(lastmp, "rw");
int newsize = getPositionsBuffer().limit() + hits.length;
IntBP posfile =
new IntBP(positionsRAF.getChannel().map(FileChannel.MapMode.READ_WRITE, 0, newsize * 4));
FloatBP weightfile =
new FloatBP(weightsRAF.getChannel().map(FileChannel.MapMode.READ_WRITE, 0, newsize * 4));
IntBP lasfile =
new IntBP(lasRAF.getChannel().map(FileChannel.MapMode.READ_WRITE, 0, newsize * 4));
int oldp = 0;
int newp = 0;
int pos = 0;
IntBP oldpositions = getPositionsBuffer();
FloatBP oldweights = getWeightsBuffer();
IntBP oldlas = getLASBuffer();
while (oldp < oldpositions.limit() || newp < hits.length) {
while (newp < hits.length
&& (oldp == oldpositions.limit() || hits[newp].pos <= oldpositions.get(oldp))) {
posfile.put(pos, hits[newp].pos);
weightfile.put(pos, hits[newp].weight);
lasfile.put(pos, Hits.makeLAS(hits[newp].length, hits[newp].strand));
newp++;
pos++;
}
while (oldp < oldpositions.limit()
&& (newp == hits.length || oldpositions.get(oldp) <= hits[newp].pos)) {
posfile.put(pos, oldpositions.get(oldp));
weightfile.put(pos, oldweights.get(oldp));
lasfile.put(pos, oldlas.get(oldp));
oldp++;
pos++;
}
// System.err.println(String.format("%d %d %d", pos, newp, oldp));
}
posfile = null;
weightfile = null;
lasfile = null;
oldpositions = null;
oldweights = null;
oldlas = null;
positionsRAF.close();
weightsRAF.close();
lasRAF.close();
/* ideally this part with the renames would atomic... */
(new File(postmp)).renameTo(new File(getPositionsFname(prefix, chrom)));
(new File(weightstmp)).renameTo(new File(getWeightsFname(prefix, chrom)));
(new File(lastmp)).renameTo(new File(getLaSFname(prefix, chrom)));
}
/**
* Search for pages matching a query, eliminating excessive hits with matching values for a named
* field. Hits after the first <code>maxHitsPerDup</code> are removed from results. The remaining
* hits have {@link Hit#moreFromDupExcluded()} set.
*
* <p>If maxHitsPerDup is zero then all hits are returned.
*
* @param query query
* @param numHits number of requested hits
* @param maxHitsPerDup the maximum hits returned with matching values, or zero
* @param dedupField field name to check for duplicates
* @param sortField Field to sort on (or null if no sorting).
* @param reverse True if we are to reverse sort by <code>sortField</code>.
* @return Hits the matching hits
* @throws IOException
*/
public Hits search(
Query query,
int numHits,
int maxHitsPerDup,
String dedupField,
String sortField,
boolean reverse)
throws IOException {
if (maxHitsPerDup <= 0) // disable dup checking
return search(query, numHits, dedupField, sortField, reverse);
final float rawHitsFactor = this.conf.getFloat("searcher.hostgrouping.rawhits.factor", 2.0f);
int numHitsRaw = (int) (numHits * rawHitsFactor);
if (LOG.isInfoEnabled()) {
LOG.info("searching for " + numHitsRaw + " raw hits");
}
Hits hits = searchBean.search(query, numHitsRaw, dedupField, sortField, reverse);
final long total = hits.getTotal();
final Map<String, DupHits> dupToHits = new HashMap<String, DupHits>();
final List<Hit> resultList = new ArrayList<Hit>();
final Set<Hit> seen = new HashSet<Hit>();
final List<String> excludedValues = new ArrayList<String>();
boolean totalIsExact = true;
for (int rawHitNum = 0; rawHitNum < hits.getTotal(); rawHitNum++) {
// get the next raw hit
if (rawHitNum >= hits.getLength()) {
// optimize query by prohibiting more matches on some excluded values
final Query optQuery = (Query) query.clone();
for (int i = 0; i < excludedValues.size(); i++) {
if (i == MAX_PROHIBITED_TERMS) break;
optQuery.addProhibitedTerm(excludedValues.get(i), dedupField);
}
numHitsRaw = (int) (numHitsRaw * rawHitsFactor);
if (LOG.isInfoEnabled()) {
LOG.info("re-searching for " + numHitsRaw + " raw hits, query: " + optQuery);
}
hits = searchBean.search(optQuery, numHitsRaw, dedupField, sortField, reverse);
if (LOG.isInfoEnabled()) {
LOG.info("found " + hits.getTotal() + " raw hits");
}
rawHitNum = -1;
continue;
}
final Hit hit = hits.getHit(rawHitNum);
if (seen.contains(hit)) continue;
seen.add(hit);
// get dup hits for its value
final String value = hit.getDedupValue();
DupHits dupHits = dupToHits.get(value);
if (dupHits == null) dupToHits.put(value, dupHits = new DupHits());
// does this hit exceed maxHitsPerDup?
if (dupHits.size() == maxHitsPerDup) { // yes -- ignore the hit
if (!dupHits.maxSizeExceeded) {
// mark prior hits with moreFromDupExcluded
for (int i = 0; i < dupHits.size(); i++) {
dupHits.get(i).setMoreFromDupExcluded(true);
}
dupHits.maxSizeExceeded = true;
excludedValues.add(value); // exclude dup
}
totalIsExact = false;
} else { // no -- collect the hit
resultList.add(hit);
dupHits.add(hit);
// are we done?
// we need to find one more than asked for, so that we can tell if
// there are more hits to be shown
if (resultList.size() > numHits) break;
}
}
final Hits results = new Hits(total, resultList.toArray(new Hit[resultList.size()]));
results.setTotalIsExact(totalIsExact);
return results;
}
public static void main(String args[]) throws IOException, ParseException {
Hits hits = new Hits();
hits.computeHits();
}
