public static Map<String, String> parseParams(String serializedString) throws IOException {
Configuration conf = new Configuration();
conf.set(
"io.serializations",
"org.apache.hadoop.io.serializer.JavaSerialization,"
+ "org.apache.hadoop.io.serializer.WritableSerialization");
Map<String, String> params = Maps.newHashMap();
DefaultStringifier<Map<String, String>> mapStringifier =
new DefaultStringifier<Map<String, String>>(conf, GenericsUtil.getClass(params));
return mapStringifier.fromString(serializedString);
}
/**
* Run the job
*
* @param input the input pathname String
* @param output the output pathname String
* @param catFile the file containing the Wikipedia categories
* @param exactMatchOnly if true, then the Wikipedia category must match exactly instead of simply
* containing the category string
*/
public static void runJob(
String input,
String output,
String catFile,
boolean exactMatchOnly,
Class<? extends Analyzer> analyzerClass)
throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
conf.set("key.value.separator.in.input.line", " ");
conf.set("xmlinput.start", "<page>");
conf.set("xmlinput.end", "</page>");
conf.setBoolean("exact.match.only", exactMatchOnly);
conf.set("analyzer.class", analyzerClass.getName());
conf.set(
"io.serializations",
"org.apache.hadoop.io.serializer.JavaSerialization,"
+ "org.apache.hadoop.io.serializer.WritableSerialization");
// Dont ever forget this. People should keep track of how hadoop conf
// parameters can make or break a piece of code
Set<String> categories = Sets.newHashSet();
for (String line : new FileLineIterable(new File(catFile))) {
categories.add(line.trim().toLowerCase(Locale.ENGLISH));
}
Stringifier<Set<String>> setStringifier =
new DefaultStringifier<Set<String>>(conf, GenericsUtil.getClass(categories));
String categoriesStr = setStringifier.toString(categories);
conf.set("wikipedia.categories", categoriesStr);
Job job = new Job(conf);
log.info("Input: {} Out: {} Categories: {}", input, output, catFile);
job.setJarByClass(WikipediaDatasetCreatorDriver.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(WikipediaDatasetCreatorMapper.class);
// TODO: job.setNumMapTasks(100);
job.setInputFormatClass(XmlInputFormat.class);
job.setReducerClass(WikipediaDatasetCreatorReducer.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(input));
Path outPath = new Path(output);
FileOutputFormat.setOutputPath(job, outPath);
HadoopUtil.delete(conf, outPath);
boolean succeeded = job.waitForCompletion(true);
if (!succeeded) {
throw new IllegalStateException("Job failed!");
}
}
/**
* Run the job
*
* @param input the input pathname String
* @param output the output pathname String
* @param catFile the file containing the Wikipedia categories
* @param exactMatchOnly if true, then the Wikipedia category must match exactly instead of simply
* containing the category string
* @param all if true select all categories
* @throws ClassNotFoundException
* @throws InterruptedException
*/
public static void runJob(
String input, String output, String catFile, boolean exactMatchOnly, boolean all)
throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
conf.set("xmlinput.start", "<page>");
conf.set("xmlinput.end", "</page>");
conf.setBoolean("exact.match.only", exactMatchOnly);
conf.setBoolean("all.files", all);
conf.set(
"io.serializations",
"org.apache.hadoop.io.serializer.JavaSerialization,"
+ "org.apache.hadoop.io.serializer.WritableSerialization");
Job job = new Job(conf);
if (WikipediaToSequenceFile.log.isInfoEnabled()) {
log.info(
"Input: " + input + " Out: " + output + " Categories: " + catFile + " All Files: " + all);
}
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path(input));
Path outPath = new Path(output);
FileOutputFormat.setOutputPath(job, outPath);
job.setMapperClass(WikipediaMapper.class);
job.setInputFormatClass(XmlInputFormat.class);
job.setReducerClass(Reducer.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setJarByClass(WikipediaToSequenceFile.class);
/*
* conf.set("mapred.compress.map.output", "true"); conf.set("mapred.map.output.compression.type",
* "BLOCK"); conf.set("mapred.output.compress", "true"); conf.set("mapred.output.compression.type",
* "BLOCK"); conf.set("mapred.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
*/
HadoopUtil.overwriteOutput(outPath);
Set<String> categories = new HashSet<String>();
if (catFile.length() > 0) {
for (String line : new FileLineIterable(new File(catFile))) {
categories.add(line.trim().toLowerCase(Locale.ENGLISH));
}
}
DefaultStringifier<Set<String>> setStringifier =
new DefaultStringifier<Set<String>>(conf, GenericsUtil.getClass(categories));
String categoriesStr = setStringifier.toString(categories);
conf.set("wikipedia.categories", categoriesStr);
job.waitForCompletion(true);
}
@Override
public String toString() {
Configuration conf = new Configuration();
conf.set(
"io.serializations",
"org.apache.hadoop.io.serializer.JavaSerialization,"
+ "org.apache.hadoop.io.serializer.WritableSerialization");
DefaultStringifier<Map<String, String>> mapStringifier =
new DefaultStringifier<Map<String, String>>(conf, GenericsUtil.getClass(params));
try {
return mapStringifier.toString(params);
} catch (IOException e) {
log.info("Encountered IOException while deserializing returning empty string", e);
return "";
}
}
