public void reduce(
BytesWritable key,
Iterator<IntWritable> values,
OutputCollector<BytesWritable, IntWritable> output,
Reporter reporter)
throws IOException {
int ones = 0;
int twos = 0;
while (values.hasNext()) {
IntWritable count = values.next();
if (count.equals(sortInput)) {
++ones;
} else if (count.equals(sortOutput)) {
++twos;
} else {
throw new IOException(
"Invalid 'value' of " + count.get() + " for (key,value): " + key.toString());
}
}
// Check to ensure there are equal no. of ones and twos
if (ones != twos) {
throw new IOException(
"Illegal ('one', 'two'): ("
+ ones
+ ", "
+ twos
+ ") for (key, value): "
+ key.toString());
}
}
public void reduce(
Text key,
Iterator<CrawlDatum> values,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
boolean oldSet = false;
boolean injectedSet = false;
while (values.hasNext()) {
CrawlDatum val = values.next();
if (val.getStatus() == CrawlDatum.STATUS_INJECTED) {
injected.set(val);
injected.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
injectedSet = true;
} else {
old.set(val);
oldSet = true;
}
}
CrawlDatum res = null;
/**
* Whether to overwrite, ignore or update existing records
*
* @see https://issues.apache.org/jira/browse/NUTCH-1405
*/
// Injected record already exists and overwrite but not update
if (injectedSet && oldSet && overwrite) {
res = injected;
if (update) {
LOG.info(key.toString() + " overwritten with injected record but update was specified.");
}
}
// Injected record already exists and update but not overwrite
if (injectedSet && oldSet && update && !overwrite) {
res = old;
old.putAllMetaData(injected);
old.setScore(injected.getScore() != scoreInjected ? injected.getScore() : old.getScore());
old.setFetchInterval(
injected.getFetchInterval() != interval
? injected.getFetchInterval()
: old.getFetchInterval());
}
// Old default behaviour
if (injectedSet && !oldSet) {
res = injected;
} else {
res = old;
}
output.collect(key, res);
}
public void reduce(
Text key,
Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output,
Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
public void reduce(
Text key,
Iterator<IntWritable> value,
OutputCollector<Text, IntWritable> output,
Reporter reporter)
throws IOException {
// TODO Auto-generated method stub
int maxAvg = 30;
int val = Integer.MIN_VALUE;
while (value.hasNext()) {
if ((val = value.next().get()) > maxAvg) {
output.collect(key, new IntWritable(val));
}
}
}
public void reduce(
DoubleWritable key,
Iterator<DoubleWritable> values,
OutputCollector<DoubleWritable, Text> output,
Reporter reporter)
throws IOException {
output.collect(key, new Text(values.next().toString() + " - "));
}
@Override
public void reduce(
IntWritable key,
Iterator<DoubleWritable> values,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
output.collect(key, values.next());
}
public void reduce(
IntWritable key,
Iterator<RecordStatsWritable> values,
OutputCollector<IntWritable, RecordStatsWritable> output,
Reporter reporter)
throws IOException {
long bytes = 0;
long records = 0;
int xor = 0;
while (values.hasNext()) {
RecordStatsWritable stats = values.next();
bytes += stats.getBytes();
records += stats.getRecords();
xor ^= stats.getChecksum();
}
output.collect(key, new RecordStatsWritable(bytes, records, xor));
}
public void reduce(
IntWritable key,
Iterator<Text> values,
OutputCollector<IntWritable, Text> output,
Reporter reporter)
throws IOException {
HashMap<String, Integer> countries_map = new HashMap<String, Integer>();
ArrayList<Integer> counties = new ArrayList<>();
String cp = new String();
while (values.hasNext()) {
cp = values.next().toString();
if (countries_map.containsKey(cp)) {
countries_map.put(cp, countries_map.get(cp) + 1);
} else {
countries_map.put(cp, 1);
}
}
for (java.util.Map.Entry<String, Integer> entry : countries_map.entrySet()) {
counties.add(entry.getValue());
}
output.collect(
key,
new Text(
""
+ countries_map.entrySet().size()
+ " "
+ Collections.min(counties)
+ " "
+ median(counties)
+ " "
+ Collections.max(counties)
+ " "
+ mean(counties)
+ " "
+ standard_deviation(counties)));
}
/**
* Initialize DFSCopyFileMapper specific job-configuration.
*
* @param conf : The dfs/mapred configuration.
* @param jobConf : The handle to the jobConf object to be initialized.
* @param args Arguments
*/
private static void setup(Configuration conf, JobConf jobConf, final Arguments args)
throws IOException {
jobConf.set(DST_DIR_LABEL, args.dst.toUri().toString());
// set boolean values
final boolean update = args.flags.contains(Options.UPDATE);
final boolean overwrite = !update && args.flags.contains(Options.OVERWRITE);
jobConf.setBoolean(Options.UPDATE.propertyname, update);
jobConf.setBoolean(Options.OVERWRITE.propertyname, overwrite);
jobConf.setBoolean(
Options.IGNORE_READ_FAILURES.propertyname,
args.flags.contains(Options.IGNORE_READ_FAILURES));
jobConf.setBoolean(
Options.PRESERVE_STATUS.propertyname, args.flags.contains(Options.PRESERVE_STATUS));
final String randomId = getRandomId();
JobClient jClient = new JobClient(jobConf);
Path jobDirectory = new Path(jClient.getSystemDir(), NAME + "_" + randomId);
jobConf.set(JOB_DIR_LABEL, jobDirectory.toString());
FileSystem dstfs = args.dst.getFileSystem(conf);
boolean dstExists = dstfs.exists(args.dst);
boolean dstIsDir = false;
if (dstExists) {
dstIsDir = dstfs.getFileStatus(args.dst).isDir();
}
// default logPath
Path logPath = args.log;
if (logPath == null) {
String filename = "_distcp_logs_" + randomId;
if (!dstExists || !dstIsDir) {
Path parent = args.dst.getParent();
if (!dstfs.exists(parent)) {
dstfs.mkdirs(parent);
}
logPath = new Path(parent, filename);
} else {
logPath = new Path(args.dst, filename);
}
}
FileOutputFormat.setOutputPath(jobConf, logPath);
// create src list, dst list
FileSystem jobfs = jobDirectory.getFileSystem(jobConf);
Path srcfilelist = new Path(jobDirectory, "_distcp_src_files");
jobConf.set(SRC_LIST_LABEL, srcfilelist.toString());
SequenceFile.Writer src_writer =
SequenceFile.createWriter(
jobfs,
jobConf,
srcfilelist,
LongWritable.class,
FilePair.class,
SequenceFile.CompressionType.NONE);
Path dstfilelist = new Path(jobDirectory, "_distcp_dst_files");
SequenceFile.Writer dst_writer =
SequenceFile.createWriter(
jobfs, jobConf, dstfilelist, Text.class, Text.class, SequenceFile.CompressionType.NONE);
Path dstdirlist = new Path(jobDirectory, "_distcp_dst_dirs");
jobConf.set(DST_DIR_LIST_LABEL, dstdirlist.toString());
SequenceFile.Writer dir_writer =
SequenceFile.createWriter(
jobfs,
jobConf,
dstdirlist,
Text.class,
FilePair.class,
SequenceFile.CompressionType.NONE);
// handle the case where the destination directory doesn't exist
// and we've only a single src directory OR we're updating/overwriting
// the contents of the destination directory.
final boolean special = (args.srcs.size() == 1 && !dstExists) || update || overwrite;
int srcCount = 0, cnsyncf = 0, dirsyn = 0;
long fileCount = 0L, byteCount = 0L, cbsyncs = 0L;
try {
for (Iterator<Path> srcItr = args.srcs.iterator(); srcItr.hasNext(); ) {
final Path src = srcItr.next();
FileSystem srcfs = src.getFileSystem(conf);
FileStatus srcfilestat = srcfs.getFileStatus(src);
Path root = special && srcfilestat.isDir() ? src : src.getParent();
if (srcfilestat.isDir()) {
++srcCount;
}
Stack<FileStatus> pathstack = new Stack<FileStatus>();
for (pathstack.push(srcfilestat); !pathstack.empty(); ) {
FileStatus cur = pathstack.pop();
FileStatus[] children = srcfs.listStatus(cur.getPath());
for (int i = 0; i < children.length; i++) {
boolean skipfile = false;
final FileStatus child = children[i];
final String dst = makeRelative(root, child.getPath());
++srcCount;
if (child.isDir()) {
pathstack.push(child);
} else {
// skip file if the src and the dst files are the same.
skipfile = update && sameFile(srcfs, child, dstfs, new Path(args.dst, dst));
// skip file if it exceed file limit or size limit
skipfile |=
fileCount == args.filelimit || byteCount + child.getLen() > args.sizelimit;
if (!skipfile) {
++fileCount;
byteCount += child.getLen();
if (LOG.isTraceEnabled()) {
LOG.trace("adding file " + child.getPath());
}
++cnsyncf;
cbsyncs += child.getLen();
if (cnsyncf > SYNC_FILE_MAX || cbsyncs > BYTES_PER_MAP) {
src_writer.sync();
dst_writer.sync();
cnsyncf = 0;
cbsyncs = 0L;
}
}
}
if (!skipfile) {
src_writer.append(
new LongWritable(child.isDir() ? 0 : child.getLen()), new FilePair(child, dst));
}
dst_writer.append(new Text(dst), new Text(child.getPath().toString()));
}
if (cur.isDir()) {
String dst = makeRelative(root, cur.getPath());
dir_writer.append(new Text(dst), new FilePair(cur, dst));
if (++dirsyn > SYNC_FILE_MAX) {
dirsyn = 0;
dir_writer.sync();
}
}
}
}
} finally {
checkAndClose(src_writer);
checkAndClose(dst_writer);
checkAndClose(dir_writer);
}
FileStatus dststatus = null;
try {
dststatus = dstfs.getFileStatus(args.dst);
} catch (FileNotFoundException fnfe) {
LOG.info(args.dst + " does not exist.");
}
// create dest path dir if copying > 1 file
if (dststatus == null) {
if (srcCount > 1 && !dstfs.mkdirs(args.dst)) {
throw new IOException("Failed to create" + args.dst);
}
}
final Path sorted = new Path(jobDirectory, "_distcp_sorted");
checkDuplication(jobfs, dstfilelist, sorted, conf);
if (dststatus != null && args.flags.contains(Options.DELETE)) {
deleteNonexisting(dstfs, dststatus, sorted, jobfs, jobDirectory, jobConf, conf);
}
Path tmpDir =
new Path(
(dstExists && !dstIsDir) || (!dstExists && srcCount == 1)
? args.dst.getParent()
: args.dst,
"_distcp_tmp_" + randomId);
jobConf.set(TMP_DIR_LABEL, tmpDir.toUri().toString());
LOG.info("srcCount=" + srcCount);
jobConf.setInt(SRC_COUNT_LABEL, srcCount);
jobConf.setLong(TOTAL_SIZE_LABEL, byteCount);
setMapCount(byteCount, jobConf);
}
@Override
public void reduce(
IntWritable key,
Iterator<ClusterWritable> values,
OutputCollector<IntWritable, Text> output,
Reporter reporter)
throws IOException {
float sumSimilarity = 0.0f;
int numMovies = 0;
float avgSimilarity = 0.0f;
float similarity = 0.0f;
int s = 0;
int count;
float diff = 0.0f;
float minDiff = 1.0f;
int candidate = 0;
String data = new String("");
String shortline = new String("");
ArrayList<String> arrl = new ArrayList<String>();
ArrayList<Float> simArrl = new ArrayList<Float>();
String oneElm = new String();
int indexShort, index2;
Text val = new Text();
while (values.hasNext()) {
ClusterWritable cr = (ClusterWritable) values.next();
similarity = cr.similarity;
simArrl.addAll(cr.similarities);
for (int i = 0; i < cr.movies.size(); i++) {
oneElm = cr.movies.get(i);
indexShort =
oneElm.indexOf(
",",
1000); // to avoid memory error caused by long arrays; it will results less
// accurate
if (indexShort == -1) {
shortline = new String(oneElm);
} else {
shortline = new String(oneElm.substring(0, indexShort));
}
arrl.add(shortline);
output.collect(key, new Text(oneElm));
}
numMovies += cr.movies.size();
sumSimilarity += similarity;
}
if (numMovies > 0) {
avgSimilarity = sumSimilarity / (float) numMovies;
}
diff = 0.0f;
minDiff = 1.0f;
for (s = 0; s < numMovies; s++) {
diff = (float) Math.abs(avgSimilarity - simArrl.get(s));
if (diff < minDiff) {
minDiff = diff;
candidate = s;
}
}
data = arrl.get(candidate);
index2 = data.indexOf(":");
String movieStr = data.substring(0, index2);
String reviews = data.substring(index2 + 1);
StringTokenizer token = new StringTokenizer(reviews, ",");
count = 0;
while (token.hasMoreTokens()) {
token.nextToken();
count++;
}
System.out.println(
"The key = "
+ key.toString()
+ " has members = "
+ numMovies
+ " simil = "
+ simArrl.get(candidate));
val = new Text(simArrl.get(candidate) + " " + movieStr + " " + count + " " + reviews);
output.collect(key, val);
reporter.incrCounter(Counter.VALUES, 1);
}
public void reduce(
Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
List<String[]> _temp = new ArrayList<String[]>();
int count = 0;
while (values.hasNext()) {
Text _out = values.next();
String[] tokens = StringUtils.splitPreserveAllTokens(_out.toString(), TAB);
_temp.add(tokens);
if (count++ > 100000) break;
}
if (count > 10000) {
Set<String> ipSet = new HashSet<String>();
for (int posI = 0; posI < _temp.size(); posI++) {
String[] array = _temp.get(posI);
if (array == null) continue;
String mid = array[2];
String ip = array[3];
ipSet.add(ip);
}
output.collect(
key, Utils.mergeKey(String.valueOf(ipSet.size()), StringUtils.join(ipSet, '|')));
return;
}
/**
* ·Ö×éËã·¨ FOREACH ALL_DATA IF IN INDEX THEN UPDATE INDEX AND INSERT DATA ELSE FOREACH SUB_DATA
* MAKE INDEX AND SET FIND'S DATA AS NULL
*/
// List<List<String[]>> dataList = new ArrayList<List<String[]>>();
List<StringBuffer> indexList = new ArrayList<StringBuffer>();
Set<String> ipSet = new HashSet<String>();
boolean muliHost = false;
for (int posI = 0; posI < _temp.size(); posI++) {
String[] array = _temp.get(posI);
if (array == null) continue;
String mid = array[2];
String ip = array[3];
ipSet.add(ip);
boolean hasIndex = false;
for (int i = 0; i < indexList.size(); i++) {
StringBuffer index = indexList.get(i);
if (index.indexOf("|" + mid + "|") >= 0 || index.indexOf("|" + ip + "|") >= 0) {
if (index.indexOf("|" + mid + "|") < 0) {
index.append('|').append(mid).append('|');
}
if (index.indexOf("|" + ip + "|") < 0) {
index.append('|').append(ip).append('|');
}
// dataList.get(i).add(array);
hasIndex = true;
break;
}
}
if (!hasIndex) {
StringBuffer index = new StringBuffer("|" + mid + "|" + ip + "|");
// List<String[]> _tmp = new ArrayList<String[]>();
// _tmp.add(array);
for (int k = posI + 1; k < _temp.size(); k++) {
String[] _newArray = _temp.get(k);
if (_newArray == null) {
continue;
}
String _mid = _newArray[2];
String _ip = _newArray[3];
if (index.indexOf("|" + _mid + "|") >= 0 || index.indexOf("|" + _ip + "|") >= 0) {
if (index.indexOf("|" + _mid + "|") < 0) {
index.append('|').append(_mid).append('|');
}
if (index.indexOf("|" + _ip + "|") < 0) {
index.append('|').append(_ip).append('|');
}
// _tmp.add(_newArray);
_temp.set(k, null);
}
}
indexList.add(index);
// dataList.add(_tmp);
}
}
// for(String[] _array : _temp){
// output.collect(key,Utils.mergeKey(_array[1],_array[2],_array[3],_array[4]));
// }
StringBuffer allIndex = new StringBuffer();
for (StringBuffer index : indexList) {
allIndex.append(index).append(';');
}
if (allIndex.length() > 0) {
allIndex.deleteCharAt(allIndex.length() - 1);
}
output.collect(
key, Utils.mergeKey(String.valueOf(indexList.size()), StringUtils.join(ipSet, '|')));
}
public void reduce(
BlockIDWritable key,
Iterator<PairWritable> values,
OutputCollector<BlockIDWritable, PairWritable> output,
Reporter reporter)
throws IOException {
// Vector<Star> starV = new Vector<Star>();
int buketsizeX = 0;
int buketsizeY = 0;
double bwidth = maxAlphas[key.zoneNum]; // ra ,x
double bheight = theta; // dec ,y
/* add 10 more in each dimension to make sure there is no overflow. */
Vector<Star>[][] arrstarV =
new Vector[((int) (zoneHeight / bheight)) + 10]
[((int) (blockWidth / bwidth)) + 10]; // create bucket vector[Y][X]
int num = 0;
while (values.hasNext()) {
num++;
Star s = values.next().get(0);
// participant
double posx = (s.ra - blockRanges[key.raNum][0]) / bwidth;
int x = (int) posx + 1; // shit by 1 in case star comes from other block
double posy = (s.dec - zoneRanges[key.zoneNum][0]) / bheight;
int y = (int) posy + 1;
// set bucket size as max
if (buketsizeX < x) buketsizeX = x;
if (buketsizeY < y) buketsizeY = y;
// create according bucket
if (arrstarV[y][x] == null)
// TODO avaoid creating vectors here.
arrstarV[y][x] = new Vector<Star>();
// put star into bucket
arrstarV[y][x].add(s);
}
// start reducer
int i, j, row, col;
// for each bucket
for (row = 0; row <= buketsizeY; row++) {
for (col = 0; col <= buketsizeX; col++) {
// starV.clear();
// construct a new vector to do compare
// TODO we need to avoid searching objects in the border.
if (arrstarV[row][col] != null) {
// old method to generate output
for (i = 0; i < arrstarV[row][col].size(); i++) {
for (j = i + 1; j < arrstarV[row][col].size(); j++) {
Star star1 = arrstarV[row][col].get(i);
Star star2 = arrstarV[row][col].get(j);
// what is this margin about
if (star1.margin && star2.margin) continue;
double dist = star1.x * star2.x + star1.y * star2.y + star1.z * star2.z;
if (dist > costheta) {
p.set(star1, star2, dist);
output.collect(key, p);
p.set(star2, star1, dist);
output.collect(key, p);
// num += 2;
}
}
} // end for i,j
} // end if
else {
continue;
}
// 4 more neighbors
// right upper arrstarV[row-1][col+1] vs arrstarV[row][col]
if (row != 0 && arrstarV[row - 1][col + 1] != null) {
search(arrstarV[row][col], arrstarV[row - 1][col + 1], key, output);
}
// right arrstarV[row][col+1] vs arrstarV[row][col]
if (arrstarV[row][col + 1] != null) {
search(arrstarV[row][col], arrstarV[row][col + 1], key, output);
}
// right lower
if (arrstarV[row + 1][col + 1] != null) {
search(arrstarV[row][col], arrstarV[row + 1][col + 1], key, output);
}
// lower
if (arrstarV[row + 1][col] != null) {
search(arrstarV[row][col], arrstarV[row + 1][col], key, output);
} // end if
} // end colum
} // end row
}
public void map(
WritableComparable<?> key,
Text value,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
String url = value.toString(); // value is line of text
if (url != null && url.trim().startsWith("#")) {
/* Ignore line that start with # */
return;
}
// if tabs : metadata that could be stored
// must be name=value and separated by \t
float customScore = -1f;
int customInterval = interval;
int fixedInterval = -1;
Map<String, String> metadata = new TreeMap<String, String>();
if (url.indexOf("\t") != -1) {
String[] splits = url.split("\t");
url = splits[0];
for (int s = 1; s < splits.length; s++) {
// find separation between name and value
int indexEquals = splits[s].indexOf("=");
if (indexEquals == -1) {
// skip anything without a =
continue;
}
String metaname = splits[s].substring(0, indexEquals);
String metavalue = splits[s].substring(indexEquals + 1);
if (metaname.equals(nutchScoreMDName)) {
try {
customScore = Float.parseFloat(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFetchIntervalMDName)) {
try {
customInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFixedFetchIntervalMDName)) {
try {
fixedInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else metadata.put(metaname, metavalue);
}
}
try {
url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);
url = filters.filter(url); // filter the url
} catch (Exception e) {
if (LOG.isWarnEnabled()) {
LOG.warn("Skipping " + url + ":" + e);
}
url = null;
}
if (url == null) {
reporter.getCounter("injector", "urls_filtered").increment(1);
} else { // if it passes
value.set(url); // collect it
CrawlDatum datum = new CrawlDatum();
datum.setStatus(CrawlDatum.STATUS_INJECTED);
// Is interval custom? Then set as meta data
if (fixedInterval > -1) {
// Set writable using float. Flaot is used by AdaptiveFetchSchedule
datum
.getMetaData()
.put(Nutch.WRITABLE_FIXED_INTERVAL_KEY, new FloatWritable(fixedInterval));
datum.setFetchInterval(fixedInterval);
} else {
datum.setFetchInterval(customInterval);
}
datum.setFetchTime(curTime);
// now add the metadata
Iterator<String> keysIter = metadata.keySet().iterator();
while (keysIter.hasNext()) {
String keymd = keysIter.next();
String valuemd = metadata.get(keymd);
datum.getMetaData().put(new Text(keymd), new Text(valuemd));
}
if (customScore != -1) datum.setScore(customScore);
else datum.setScore(scoreInjected);
try {
scfilters.injectedScore(value, datum);
} catch (ScoringFilterException e) {
if (LOG.isWarnEnabled()) {
LOG.warn(
"Cannot filter injected score for url "
+ url
+ ", using default ("
+ e.getMessage()
+ ")");
}
}
reporter.getCounter("injector", "urls_injected").increment(1);
output.collect(value, datum);
}
}
