// specify input and out keys
public void map(
LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
String line = value.toString(); // define new variable to be string
ArrayList<Integer> range = new ArrayList<Integer>();
for (int i = 2000; i <= 2010; i++) {
range.add(i);
}
// String[] inputs = line.split(",(?=([^\"]*\"[^\"]*\")*[^\"]*$)");
String[] inputs = line.split(",");
try {
int year = Integer.parseInt(inputs[165]);
if (range.contains(year)) {
String dur = inputs[3];
String artist_name = inputs[2];
String song_title = inputs[1];
String final_input = artist_name + ',' + dur + ',' + song_title;
Final_Value.set(final_input);
output.collect(Final_Value, dummy);
}
} catch (NumberFormatException e) {
// do nothing
}
}
public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
/* Finds a full sentence and sets it as the value.
* If the sentence is shorter than the full line, the rest is stored to use later.
*/
public synchronized boolean next(LongWritable key, Text value) throws IOException {
Text line = new Text();
boolean getMore = true;
boolean retrieved = false;
String result = leftovers;
leftovers = "";
value.clear();
while (getMore) {
retrieved = recordReader.next(key, line);
if (retrieved) {
String lineValue = line.toString();
// here, we assume sentences run until the period.
int endOfSentence = lineValue.indexOf('.');
if (endOfSentence == -1) {
result += " " + lineValue;
} else {
result += " " + lineValue.substring(0, endOfSentence + 1);
leftovers = lineValue.substring(endOfSentence + 1);
getMore = false;
}
} else {
getMore = false;
value.set(result);
return false;
}
}
value.set(result);
return true;
}
/** Implements the map-method of the Mapper-interface */
@Override
public void map(
LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
String token = tokenizer.nextToken();
if (token.length() > 3) {
word.set(token);
output.collect(word, one);
}
}
}
/*
* Finds a full file and sets it as the value.
*/
public synchronized boolean next(LongWritable key, Text value) throws IOException {
Text line = new Text();
boolean retrieved = true;
String result = "";
value.clear();
while (retrieved) {
retrieved = recordReader.next(key, line);
if (line.toString().length() > 0) {
String lineValue = line.toString();
result += lineValue + "\n";
}
}
value.set(result);
return true;
}
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);
}
}
