public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String cur_file =
((FileSplit) context.getInputSplit()).getPath().getParent().getParent().getName();
String train_file = context.getConfiguration().get("train_file");
if (cur_file.equals(train_file)) {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
myKey.set(word);
myVal.set(f_id);
context.write(myKey, myVal);
} else {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
StringBuilder builder = new StringBuilder(dlt);
while (st.hasMoreTokens()) {
String filename = st.nextToken();
String tf_idf = st.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myKey.set(word);
myVal.set(builder.toString());
context.write(myKey, myVal);
}
}
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String file = value.toString();
String[] lines = file.split("\n");
for (String line : lines) {
if (line.contains("<author>") && line.contains("</author>")) {
String author = line.substring(8, line.indexOf("</a"));
word.set(author);
context.write(word, one);
} else if (line.contains("<author>")) {
String author = line.substring(8);
word.set(author);
context.write(word, one);
}
}
}
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
String[] pair = new String[2];
int count = 0;
for (Text txt : values) {
pair[count] = txt.toString();
count++;
}
// word exists in training
if (count == 2) {
StringTokenizer st_one, st_two;
if (pair[0].contains(dlt)) {
st_one = new StringTokenizer(pair[1]);
st_two = new StringTokenizer(pair[0]);
} else {
st_one = new StringTokenizer(pair[0]);
st_two = new StringTokenizer(pair[1]);
}
// outputting the data
String f_id = st_one.nextToken();
StringBuilder builder = new StringBuilder(dlt);
builder.append(f_id);
builder.append(dlt);
while (st_two.hasMoreTokens()) {
String filename = st_two.nextToken();
String tf_idf = st_two.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myVal.set(builder.toString());
context.write(key, myVal);
}
}
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);
}
}