本文整理了Java中org.apache.pig.data.Tuple.isNull()
方法的一些代码示例,展示了Tuple.isNull()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Tuple.isNull()
方法的具体详情如下:
包路径:org.apache.pig.data.Tuple
类名称:Tuple
方法名:isNull
[英]Find out if a given field is null.
[中]找出给定字段是否为空。
代码示例来源:origin: org.apache.pig/pig
@Override
public boolean isNull(int fieldNum) throws ExecException {
return t.isNull(fieldNum);
}
代码示例来源:origin: org.apache.pig/pig
protected boolean isKeyNull(Object key) throws ExecException {
if (key == null) return true;
if (key instanceof Tuple) {
Tuple t = (Tuple)key;
for (int i=0; i<t.size(); i++) {
if (t.isNull(i)) return true;
}
}
return false;
}
代码示例来源:origin: org.apache.pig/pig
protected int compareNull(boolean usNull, Tuple t, int pos) {
boolean themNull;
try {
themNull = t.isNull(pos);
} catch (ExecException e) {
throw new RuntimeException("Unable to check if position " + pos + " is null in Tuple: " + t, e);
}
return compareNull(usNull, themNull);
}
代码示例来源:origin: com.twitter.elephantbird/elephant-bird-pig
@Override
public boolean isNull(int idx) throws ExecException {
get(idx);
return realTuple.isNull(idx);
}
代码示例来源:origin: org.apache.pig/pig
private boolean isAppendedFieldNull(int i) throws ExecException {
return isAppendedFieldsNull() || appendedFields.isNull(i);
}
代码示例来源:origin: thedatachef/varaha
public boolean hasNext() {
if (tupleItr.hasNext()) {
Tuple t = tupleItr.next();
try {
if (!t.isNull(0) && !t.isNull(1)) {
currentId = t.get(0).toString();
currentText = t.get(1).toString();
if (currentId.isEmpty() || currentText.isEmpty()) {
return false;
} else {
return true;
}
}
} catch (ExecException e) {
throw new RuntimeException(e);
}
}
return false;
}
代码示例来源:origin: thedatachef/varaha
/**
Returns the scalar inner product of this and the other term vector by
multiplying each entry for the same term.
<p>
There are undoubtedly ways to optimize this. Please, enlighten me.
@param other: Another term vector
@return the dot product
*/
public Double dotProduct(TermVector other) throws ExecException {
Double result = 0.0;
for (Tuple x_i : this) {
for (Tuple y_i : other) {
if ( !(x_i.isNull(0) || x_i.isNull(1) || y_i.isNull(0) || y_i.isNull(1)) ) {
if (x_i.get(0).toString().equals(y_i.get(0).toString())) {
result += (Double)x_i.get(1)*(Double)y_i.get(1);
}
}
}
}
return result;
}
代码示例来源:origin: thedatachef/varaha
public Double exec(Tuple input) throws IOException {
if (input == null || input.size() < 2 || input.isNull(0) || input.isNull(1))
return null;
TermVector t1 = new TermVector((DataBag)input.get(0));
TermVector t2 = new TermVector((DataBag)input.get(1));
return t1.cosineSimilarity(t2);
}
代码示例来源:origin: thedatachef/varaha
public DataBag exec(Tuple input) throws IOException {
if (input == null || input.size() < 1 || input.isNull(0))
return null;
DataBag v = (DataBag)t.get(0);
for (Tuple v_i : v) {
if (!(v_i.isNull(0) || v_i.isNull(1))) {
String term = v_i.get(0).toString();
Object currentValue = termSums.get(term);
代码示例来源:origin: infochimps-labs/wonderdog
/**
Map a tuple object into a map-writable object for elasticsearch.
*/
@SuppressWarnings("unchecked")
@Override
public void putNext(Tuple t) throws IOException {
if (!t.isNull(0)) {
MapWritable record = new MapWritable();
String jsonData = t.get(0).toString();
// parse json data and put into mapwritable record
try {
HashMap<String,Object> data = mapper.readValue(jsonData, HashMap.class);
record = (MapWritable)toWritable(data);
} catch (JsonParseException e) {
e.printStackTrace();
} catch (JsonMappingException e) {
e.printStackTrace();
}
try {
writer.write(NullWritable.get(), record);
} catch (InterruptedException e) {
throw new IOException(e);
}
}
}
代码示例来源:origin: infochimps-labs/wonderdog
if (!t.isNull(0)) {
String jsonData = t.get(0).toString();
代码示例来源:origin: thedatachef/varaha
public DataBag exec(Tuple input) throws IOException {
if (input == null || input.size() < 1 || input.isNull(0))
return null;
// Output bag
DataBag bagOfTokens = bagFactory.newDefaultBag();
StringReader textInput = new StringReader(input.get(0).toString());
PTBTokenizer ptbt = new PTBTokenizer(textInput, new CoreLabelTokenFactory(), "");
for (CoreLabel label; ptbt.hasNext(); ) {
label = (CoreLabel)ptbt.next();
Tuple termText = tupleFactory.newTuple(label.toString());
bagOfTokens.add(termText);
}
return bagOfTokens;
}
}
代码示例来源:origin: thedatachef/varaha
/**
Uses Lucene's StandardAnalyzer and tuns the tokens through several lucene filters
- LengthFilter: Filter individual words to be of length > minWordSize
- ShingleFilter: Converts word stream into n-gram stream
- PatternReplaceFilter: Removes the 'filler' character that ShingleFilter puts in to
replace stopwords
*/
public DataBag exec(Tuple input) throws IOException {
if (input == null || input.size() < 1 || input.isNull(0))
return null;
TokenStream stream = analyzer.tokenStream(NOFIELD, input.get(0).toString());
LengthFilter filtered = new LengthFilter(Version.LUCENE_44, stream, minWordSize, Integer.MAX_VALUE); // Let words be long
DataBag result;
if (minGramSize == 1 && maxGramSize == 1) {
result = fillBag(filtered);
} else {
ShingleFilter nGramStream = new ShingleFilter(filtered, minGramSize, maxGramSize);
nGramStream.setOutputUnigrams(outputUnigrams);
PatternReplaceFilter replacer = new PatternReplaceFilter(nGramStream, SHINGLE_FILLER, NOFIELD, true);
result = fillBag(replacer);
}
return result;
}
代码示例来源:origin: thedatachef/varaha
public DataBag exec(Tuple input) throws IOException {
if (input == null || input.size() < 2 || input.isNull(0) || input.isNull(1))
return null;
代码示例来源:origin: com.twitter/parquet-pig
assert fields.size() == pigFields.size();
for (int i = 0; i < fields.size(); i++) {
if (t.isNull(i)) {
continue;
内容来源于网络,如有侵权,请联系作者删除!