public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
boolean filtered = true;
String keypair = key.toString();
String[] keys = keypair.split(" ");
if (keys.length == 1) {
filtered = false;
} else {
if (keys[0].equals("*") || keys[1].equals("*")) {
filtered = false;
}
}
if (!filtered) {
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
return;
}
for (IntWritable val : values) {
if (val.get() == -1) {
filtered = false;
continue;
}
sum += val.get();
}
// filter non-needed events
if (filtered) return;
context.write(key, new IntWritable(sum));
}
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,
org.apache.hadoop.mapreduce.Reducer<Text, Text, Text, InvertedListWritable>.Context context)
throws IOException, InterruptedException {
InvertedListWritable invertedList = new InvertedListWritable();
for (Text k : values) {
StringTokenizer itr = new StringTokenizer(k.toString());
url = "";
abs = "";
if (itr.hasMoreTokens()) url = itr.nextToken();
while (itr.hasMoreTokens()) {
abs += itr.nextToken() + " ";
}
dr = new ListURL(url, abs);
invertedList.paddingValueKey(dr);
}
invertedList.quickSortNodeKey();
context.write(key, invertedList);
}
@Override
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int movieId = Integer.parseInt(tokenizer.nextToken());
while (tokenizer.hasMoreTokens()) {
String word = tokenizer.nextToken();
context.write(new Text("1"), new IntWritable(1));
}
}
public void map(
Text key,
Text val,
org.apache.hadoop.mapreduce.Mapper<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
int i = 0, n = 0, j = 0, lj = 0, hj = 0;
String tem = "";
initStopWordsMap(); // initialize the stop list
String line = val.toString();
StringTokenizer itr =
new StringTokenizer(line.toLowerCase(), tokenDelimiter); // set delimiter
n = itr.countTokens();
cache = new String[n];
for (i = 0; i < n; i++) {
cache[i] = new String(""); // initialize the cache
}
i = 0;
while (itr.hasMoreTokens()) {
cache[i] = itr.nextToken(); // padding the cache with the words of the content
i++;
}
for (i = 0; i < n; i++) {
keyWord = cache[i];
keyWord = keyWord.trim();
if (!hmStopWord.containsKey(keyWord)) {
lj = i - 10;
hj = i + 10;
if (lj < 0) lj = 0;
if (hj > n) hj = n;
tem = " ";
for (j = lj; j < hj; j++) tem += cache[j] + " ";
location = new Text();
location.set(key.toString() + tem);
context.write(new Text(keyWord), location);
}
}
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
splitposition = line.indexOf("\t");
labels = line.substring(0, splitposition);
content = line.substring(splitposition + 1, line.length());
if (content.length() <= 5) {
word.set(labels);
int counter = Integer.parseInt(content);
context.write(word, new IntWritable(counter));
return;
}
labeltokens = labels.split(",");
contenttokens = tokenizeDoc(content);
for (String label : labelspace) {
for (String token : contenttokens) {
// filter token, denotes the needed events;
word.set(label + " " + token);
context.write(word, new IntWritable(-1));
}
}
}
