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);
}
}
public void reduce(
Text key,
Iterator<CrawlDatum> values,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
boolean oldSet = false;
boolean injectedSet = false;
while (values.hasNext()) {
CrawlDatum val = values.next();
if (val.getStatus() == CrawlDatum.STATUS_INJECTED) {
injected.set(val);
injected.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
injectedSet = true;
} else {
old.set(val);
oldSet = true;
}
}
CrawlDatum res = null;
/**
* Whether to overwrite, ignore or update existing records
*
* @see https://issues.apache.org/jira/browse/NUTCH-1405
*/
// Injected record already exists and overwrite but not update
if (injectedSet && oldSet && overwrite) {
res = injected;
if (update) {
LOG.info(key.toString() + " overwritten with injected record but update was specified.");
}
}
// Injected record already exists and update but not overwrite
if (injectedSet && oldSet && update && !overwrite) {
res = old;
old.putAllMetaData(injected);
old.setScore(injected.getScore() != scoreInjected ? injected.getScore() : old.getScore());
old.setFetchInterval(
injected.getFetchInterval() != interval
? injected.getFetchInterval()
: old.getFetchInterval());
}
// Old default behaviour
if (injectedSet && !oldSet) {
res = injected;
} else {
res = old;
}
output.collect(key, res);
}
