public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
String keyS = key.toString();
if (keyS.startsWith("O") || keyS.startsWith("P") || keyS.startsWith("S")) {
String sum = new String();
for (Text val : values) {
sum += (" " + val.toString());
}
// String subKey = keyS.substring(0,keyS.length()-1);
// Text t = new Text();
// t.set(subKey);
result.set(sum);
context.write(key, result);
}
if (keyS.startsWith("L")) {
// String [] keyIdS = keyS.substring(1).split("[+]");
result.set(" ");
context.write(key, result);
// String KeyIdS1 = keyIdS[1];
// result.set(KeyIdS1);
// context.write(key, result);
// String KeyIdS2 = keyIdS[2];
// result.set(KeyIdS2);
// context.write(key, result);
}
}
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);
}
}
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(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum++;
}
context.write(new IntWritable(sum), NullWritable.get());
}
public void reduce(Text key, Iterable<LongWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (LongWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
@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(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, 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 map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] attributes = line.split("[|]");
String tableName = getTableName(line);
if (tableName.equalsIgnoreCase("lineitem")) {
word.set(
"LO"
+ attributes[0]
+ "+P"
+ attributes[1]
+ "+S"
+ attributes[2]); // orderkey+partkey+supplykey
Text v = new Text(" ");
context.write(word, v);
} else if (tableName.equalsIgnoreCase("supplier")) {
if (line.contains(k2)) {
Text v = new Text(attributes[6]);
word.set("S" + attributes[0] + "A");
context.write(word, v);
word.set("S" + attributes[0] + "B");
context.write(word, v);
word.set("S" + attributes[0] + "C");
context.write(word, v);
word.set("S" + attributes[0] + "D");
context.write(word, v);
}
} else if (tableName.equalsIgnoreCase("part")) {
if (line.contains(k1)) {
Text v =
new Text(
attributes[1] + " " + attributes[4] + " " + attributes[6] + " " + attributes[8]);
word.set("P" + attributes[0] + "A");
context.write(word, v);
word.set("P" + attributes[0] + "B");
context.write(word, v);
word.set("P" + attributes[0] + "C");
context.write(word, v);
word.set("P" + attributes[0] + "D");
context.write(word, v);
}
} else if (tableName.equalsIgnoreCase("order")) {
if (line.contains(k0)) {
Text v = new Text(attributes[8]);
word.set("O" + attributes[0] + "A");
context.write(word, v);
word.set("O" + attributes[0] + "B");
context.write(word, v);
word.set("O" + attributes[0] + "C");
context.write(word, v);
word.set("O" + attributes[0] + "D");
context.write(word, v);
}
} else {
}
}