public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String cur_file =
((FileSplit) context.getInputSplit()).getPath().getParent().getParent().getName();
String train_file = context.getConfiguration().get("train_file");
if (cur_file.equals(train_file)) {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
myKey.set(word);
myVal.set(f_id);
context.write(myKey, myVal);
} else {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
StringBuilder builder = new StringBuilder(dlt);
while (st.hasMoreTokens()) {
String filename = st.nextToken();
String tf_idf = st.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myKey.set(word);
myVal.set(builder.toString());
context.write(myKey, myVal);
}
}
/** Check whether the file list have duplication. */
private static void checkDuplication(FileSystem fs, Path file, Path sorted, Configuration conf)
throws IOException {
SequenceFile.Reader in = null;
try {
SequenceFile.Sorter sorter =
new SequenceFile.Sorter(fs, new Text.Comparator(), Text.class, Text.class, conf);
sorter.sort(file, sorted);
in = new SequenceFile.Reader(fs, sorted, conf);
Text prevdst = null, curdst = new Text();
Text prevsrc = null, cursrc = new Text();
for (; in.next(curdst, cursrc); ) {
if (prevdst != null && curdst.equals(prevdst)) {
throw new DuplicationException(
"Invalid input, there are duplicated files in the sources: "
+ prevsrc
+ ", "
+ cursrc);
}
prevdst = curdst;
curdst = new Text();
prevsrc = cursrc;
cursrc = new Text();
}
} finally {
checkAndClose(in);
}
}
@Test
public void get() throws Exception {
// vv MapFileSeekTest
Text value = new Text();
reader.get(new IntWritable(496), value);
assertThat(value.toString(), is("One, two, buckle my shoe"));
// ^^ MapFileSeekTest
}
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String file = value.toString();
String[] lines = file.split("\n");
for (String line : lines) {
if (line.contains("<author>") && line.contains("</author>")) {
String author = line.substring(8, line.indexOf("</a"));
word.set(author);
context.write(word, one);
} else if (line.contains("<author>")) {
String author = line.substring(8);
word.set(author);
context.write(word, one);
}
}
}
public void reduce(IntWritable key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
System.out.println(PREFIX + "Collecting all the matched results");
for (Text val : values) {
String[] tmp =
val.toString()
.split("\\|"); // The \\ here is very important. Cannot use "|" since split()
// need a regex(regular expression), and the vertical bar is
// special character.
System.out.println("filename:" + tmp[0] + " ratio:" + tmp[1]);
String filename = tmp[0];
double ratio = Double.valueOf(tmp[1]);
// Key:filename Value:ratio
context.write(new Text(filename), new DoubleWritable(ratio));
}
}
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);
}
@Override
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int movieId = Integer.parseInt(tokenizer.nextToken());
while (tokenizer.hasMoreTokens()) {
String word = tokenizer.nextToken();
context.write(new Text("1"), new IntWritable(1));
}
}
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
String[] pair = new String[2];
int count = 0;
for (Text txt : values) {
pair[count] = txt.toString();
count++;
}
// word exists in training
if (count == 2) {
StringTokenizer st_one, st_two;
if (pair[0].contains(dlt)) {
st_one = new StringTokenizer(pair[1]);
st_two = new StringTokenizer(pair[0]);
} else {
st_one = new StringTokenizer(pair[0]);
st_two = new StringTokenizer(pair[1]);
}
// outputting the data
String f_id = st_one.nextToken();
StringBuilder builder = new StringBuilder(dlt);
builder.append(f_id);
builder.append(dlt);
while (st_two.hasMoreTokens()) {
String filename = st_two.nextToken();
String tf_idf = st_two.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myVal.set(builder.toString());
context.write(key, myVal);
}
}
public void map(Text key, Text value, Context context)
throws InterruptedException, IOException {
String filename = key.toString();
String json = value.toString();
// Make sure the input is valid
if (!(filename.isEmpty() || json.isEmpty())) {
// Change the json-type feature to Mat-type feature
Mat descriptor = json2mat(json);
if (descriptor != null) {
// Read the query feature from the cache in Hadoop
Mat query_features;
String pathStr = context.getConfiguration().get("featureFilePath");
FileSystem fs = FileSystem.get(context.getConfiguration());
FSDataInputStream fsDataInputStream = fs.open(new Path(pathStr));
StringBuilder sb = new StringBuilder();
// Use a buffer to read the query_feature
int remain = fsDataInputStream.available();
while (remain > 0) {
int read;
byte[] buf = new byte[BUF_SIZE];
read = fsDataInputStream.read(buf, fsDataInputStream.available() - remain, BUF_SIZE);
sb.append(new String(buf, 0, read, StandardCharsets.UTF_8));
remain = remain - read;
System.out.println("remain:" + remain + "\tread:" + read + "\tsb.size:" + sb.length());
}
// Read the query_feature line by line
// Scanner sc = new Scanner(fsDataInputStream, "UTF-8");
// StringBuilder sb = new StringBuilder();
// while (sc.hasNextLine()) {
// sb.append(sc.nextLine());
// }
// String query_json = sb.toString();
// String query_json = new String(buf, StandardCharsets.UTF_8);
String query_json = sb.toString();
fsDataInputStream.close();
query_features = json2mat(query_json);
// Get the similarity of the current database image against the query image
DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.FLANNBASED);
MatOfDMatch matches = new MatOfDMatch();
// Ensure the two features have same length of cols (the feature extracted are all 128
// cols(at least in this case))
if (query_features.cols() == descriptor.cols()) {
matcher.match(query_features, descriptor, matches);
DMatch[] dMatches = matches.toArray();
// Calculate the max/min distances
// double max_dist = Double.MAX_VALUE;
// double min_dist = Double.MIN_VALUE;
double max_dist = 0;
double min_dist = 100;
for (int i = 0; i < dMatches.length; i++) {
double dist = dMatches[i].distance;
if (min_dist > dist) min_dist = dist;
if (max_dist < dist) max_dist = dist;
}
// Only distances ≤ threshold are good matches
double threshold = max_dist * THRESHOLD_FACTOR;
// double threshold = min_dist * 2;
LinkedList<DMatch> goodMatches = new LinkedList<DMatch>();
for (int i = 0; i < dMatches.length; i++) {
if (dMatches[i].distance <= threshold) {
goodMatches.addLast(dMatches[i]);
}
}
// Get the ratio of good_matches to all_matches
double ratio = (double) goodMatches.size() / (double) dMatches.length;
System.out.println("*** current_record_filename:" + filename + " ***");
System.out.println("feature:" + descriptor + "\nquery_feature:" + query_features);
System.out.println(
"min_dist of keypoints:" + min_dist + " max_dist of keypoints:" + max_dist);
System.out.println(
"total_matches:" + dMatches.length + "\tgood_matches:" + goodMatches.size());
// System.out.println("type:" + descriptor.type() + " channels:" +
// descriptor.channels() + " rows:" + descriptor.rows() + " cols:" + descriptor.cols());
// System.out.println("qtype:" + query_features.type() + "
// qchannels:" + query_features.channels() + " qrows:" + query_features.rows() + "
// qcols:" + query_features.cols());
System.out.println();
if (ratio > PERCENTAGE_THRESHOLD) {
// Key:1 Value:filename|ratio
context.write(ONE, new Text(filename + "|" + ratio));
// context.write(ONE, new Text(filename + "|" +
// String.valueOf(goodMatches.size())));
}
} else {
System.out.println("The size of the features are not equal");
}
} else {
// a null pointer, do nothing
System.out.println("A broken/null feature:" + filename);
System.out.println();
}
}
}
public void write(DataOutput out) throws IOException {
input.write(out);
Text.writeString(out, output);
}
public void readFields(DataInput in) throws IOException {
input.readFields(in);
output = Text.readString(in);
}
/** Delete the dst files/dirs which do not exist in src */
private static void deleteNonexisting(
FileSystem dstfs,
FileStatus dstroot,
Path dstsorted,
FileSystem jobfs,
Path jobdir,
JobConf jobconf,
Configuration conf)
throws IOException {
if (!dstroot.isDir()) {
throw new IOException(
"dst must be a directory when option "
+ Options.DELETE.cmd
+ " is set, but dst (= "
+ dstroot.getPath()
+ ") is not a directory.");
}
// write dst lsr results
final Path dstlsr = new Path(jobdir, "_distcp_dst_lsr");
final SequenceFile.Writer writer =
SequenceFile.createWriter(
jobfs,
jobconf,
dstlsr,
Text.class,
FileStatus.class,
SequenceFile.CompressionType.NONE);
try {
// do lsr to get all file statuses in dstroot
final Stack<FileStatus> lsrstack = new Stack<FileStatus>();
for (lsrstack.push(dstroot); !lsrstack.isEmpty(); ) {
final FileStatus status = lsrstack.pop();
if (status.isDir()) {
for (FileStatus child : dstfs.listStatus(status.getPath())) {
String relative = makeRelative(dstroot.getPath(), child.getPath());
writer.append(new Text(relative), child);
lsrstack.push(child);
}
}
}
} finally {
checkAndClose(writer);
}
// sort lsr results
final Path sortedlsr = new Path(jobdir, "_distcp_dst_lsr_sorted");
SequenceFile.Sorter sorter =
new SequenceFile.Sorter(
jobfs, new Text.Comparator(), Text.class, FileStatus.class, jobconf);
sorter.sort(dstlsr, sortedlsr);
// compare lsr list and dst list
SequenceFile.Reader lsrin = null;
SequenceFile.Reader dstin = null;
try {
lsrin = new SequenceFile.Reader(jobfs, sortedlsr, jobconf);
dstin = new SequenceFile.Reader(jobfs, dstsorted, jobconf);
// compare sorted lsr list and sorted dst list
final Text lsrpath = new Text();
final FileStatus lsrstatus = new FileStatus();
final Text dstpath = new Text();
final Text dstfrom = new Text();
final FsShell shell = new FsShell(conf);
final String[] shellargs = {"-rmr", null};
boolean hasnext = dstin.next(dstpath, dstfrom);
for (; lsrin.next(lsrpath, lsrstatus); ) {
int dst_cmp_lsr = dstpath.compareTo(lsrpath);
for (; hasnext && dst_cmp_lsr < 0; ) {
hasnext = dstin.next(dstpath, dstfrom);
dst_cmp_lsr = dstpath.compareTo(lsrpath);
}
if (dst_cmp_lsr == 0) {
// lsrpath exists in dst, skip it
hasnext = dstin.next(dstpath, dstfrom);
} else {
// lsrpath does not exist, delete it
String s = new Path(dstroot.getPath(), lsrpath.toString()).toString();
if (shellargs[1] == null || !isAncestorPath(shellargs[1], s)) {
shellargs[1] = s;
int r = 0;
try {
r = shell.run(shellargs);
} catch (Exception e) {
throw new IOException("Exception from shell.", e);
}
if (r != 0) {
throw new IOException(
"\"" + shellargs[0] + " " + shellargs[1] + "\" returns non-zero value " + r);
}
}
}
}
} finally {
checkAndClose(lsrin);
checkAndClose(dstin);
}
}
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);
}
}
