public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String strId = "";
String strBody = "";
// Parse the xml and read data (page id and article body)
// Using XOM library
Builder builder = new Builder();
try {
Document doc = builder.build(value.toString(), null);
Nodes nodeId = doc.query("//eecs485_article_id");
strId = nodeId.get(0).getChild(0).getValue();
Nodes nodeBody = doc.query("//eecs485_article_body");
strBody = nodeBody.get(0).getChild(0).getValue();
} catch (ParsingException ex) {
System.out.println("Not well-formed.");
System.out.println(ex.getMessage());
} catch (IOException ex) {
System.out.println("io exception");
}
// Tokenize document body
Pattern pattern = Pattern.compile("\\w+");
Matcher matcher = pattern.matcher(strBody);
while (matcher.find()) {
// Write the parsed token
// key = term, docid value = 1
context.write(new Text(matcher.group() + "," + strId), one);
}
}
public void reduce(Text key, Iterable<LongWritable> values, Context context)
throws IOException, InterruptedException {
// function starts here
int sum = 0;
for (LongWritable value : values) {
sum += value.get();
}
context.write(key, new LongWritable(sum));
}
