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<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);
}
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);
}
}
}