private static int[] parseJobSetup(Path jobFile) {
int[] result = new int[2];
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder db = dbf.newDocumentBuilder();
Document doc = db.parse(jobFile.toString());
Element configElement = doc.getDocumentElement();
NodeList nodes = configElement.getElementsByTagName("property");
if (nodes != null && nodes.getLength() > 0) {
for (int i = 0; i < nodes.getLength(); i++) {
Element property = (Element) nodes.item(i);
String elName = xmlGetSingleValue(property, "name");
if (elName == "example.count") {
result[0] = Integer.parseInt(xmlGetSingleValue(property, "value"));
} else if (elName == "batch.size") {
result[1] = Integer.parseInt(xmlGetSingleValue(property, "value"));
}
}
}
} catch (ParserConfigurationException pce) {
System.err.println(
"Caught exception while parsing the cached file '"
+ jobFile
+ "' : "
+ StringUtils.stringifyException(pce));
return null;
} catch (SAXException se) {
System.err.println(
"Caught exception while parsing the cached file '"
+ jobFile
+ "' : "
+ StringUtils.stringifyException(se));
return null;
} catch (IOException ioe) {
System.err.println(
"Caught exception while parsing the cached file '"
+ jobFile
+ "' : "
+ StringUtils.stringifyException(ioe));
return null;
}
return result;
}
public int run(String[] args) throws Exception {
if (args.length < 2) {
System.err.println("Usage: Injector <crawldb> <url_dir>");
return -1;
}
try {
inject(new Path(args[0]), new Path(args[1]));
return 0;
} catch (Exception e) {
LOG.error("Injector: " + StringUtils.stringifyException(e));
return -1;
}
}
public void configure(Configuration conf) {
if (conf.getBoolean("minibatch.job.setup", false)) {
Path[] jobSetupFiles = new Path[0];
try {
jobSetupFiles = DistributedCache.getLocalCacheFiles(conf);
} catch (IOException ioe) {
System.err.println(
"Caught exception while getting cached files: "
+ StringUtils.stringifyException(ioe));
}
for (Path jobSetup : jobSetupFiles) {
parseJobSetup(jobSetup);
}
}
}