private static <T> void updateBlockMap(Map<Block, T> blockmap, Block oldblock, Block newblock)
throws IOException {
if (blockmap.containsKey(oldblock)) {
T value = blockmap.remove(oldblock);
blockmap.put(newblock, value);
}
}
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
countMap.put(new Text(key), new IntWritable(sum));
}
public static <K extends Text, V extends IntWritable> Map<K, V> sortByValues(Map<K, V> map) {
List<Map.Entry<K, V>> entries = new LinkedList<Map.Entry<K, V>>(map.entrySet());
Collections.sort(
entries,
new Comparator<Map.Entry<K, V>>() {
public int compare(Map.Entry<K, V> o1, Map.Entry<K, V> o2) {
return o2.getValue().compareTo(o1.getValue());
}
});
Map<K, V> sortedMap = new LinkedHashMap<K, V>();
for (Map.Entry<K, V> entry : entries) {
sortedMap.put(entry.getKey(), entry.getValue());
}
return sortedMap;
}
/**
* 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 void map(
WritableComparable<?> key,
Text value,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
String url = value.toString(); // value is line of text
if (url != null && url.trim().startsWith("#")) {
/* Ignore line that start with # */
return;
}
// if tabs : metadata that could be stored
// must be name=value and separated by \t
float customScore = -1f;
int customInterval = interval;
int fixedInterval = -1;
Map<String, String> metadata = new TreeMap<String, String>();
if (url.indexOf("\t") != -1) {
String[] splits = url.split("\t");
url = splits[0];
for (int s = 1; s < splits.length; s++) {
// find separation between name and value
int indexEquals = splits[s].indexOf("=");
if (indexEquals == -1) {
// skip anything without a =
continue;
}
String metaname = splits[s].substring(0, indexEquals);
String metavalue = splits[s].substring(indexEquals + 1);
if (metaname.equals(nutchScoreMDName)) {
try {
customScore = Float.parseFloat(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFetchIntervalMDName)) {
try {
customInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFixedFetchIntervalMDName)) {
try {
fixedInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else metadata.put(metaname, metavalue);
}
}
try {
url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);
url = filters.filter(url); // filter the url
} catch (Exception e) {
if (LOG.isWarnEnabled()) {
LOG.warn("Skipping " + url + ":" + e);
}
url = null;
}
if (url == null) {
reporter.getCounter("injector", "urls_filtered").increment(1);
} else { // if it passes
value.set(url); // collect it
CrawlDatum datum = new CrawlDatum();
datum.setStatus(CrawlDatum.STATUS_INJECTED);
// Is interval custom? Then set as meta data
if (fixedInterval > -1) {
// Set writable using float. Flaot is used by AdaptiveFetchSchedule
datum
.getMetaData()
.put(Nutch.WRITABLE_FIXED_INTERVAL_KEY, new FloatWritable(fixedInterval));
datum.setFetchInterval(fixedInterval);
} else {
datum.setFetchInterval(customInterval);
}
datum.setFetchTime(curTime);
// now add the metadata
Iterator<String> keysIter = metadata.keySet().iterator();
while (keysIter.hasNext()) {
String keymd = keysIter.next();
String valuemd = metadata.get(keymd);
datum.getMetaData().put(new Text(keymd), new Text(valuemd));
}
if (customScore != -1) datum.setScore(customScore);
else datum.setScore(scoreInjected);
try {
scfilters.injectedScore(value, datum);
} catch (ScoringFilterException e) {
if (LOG.isWarnEnabled()) {
LOG.warn(
"Cannot filter injected score for url "
+ url
+ ", using default ("
+ e.getMessage()
+ ")");
}
}
reporter.getCounter("injector", "urls_injected").increment(1);
output.collect(value, datum);
}
}