本文整理了Java中org.apache.pig.data.DataBag.size()
方法的一些代码示例,展示了DataBag.size()
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。DataBag.size()
方法的具体详情如下:
包路径:org.apache.pig.data.DataBag
类名称:DataBag
方法名:size
[英]Get the number of elements in the bag, both in memory and on disk.
[中]获取包中的元素数,包括内存和磁盘中的元素数。
代码示例来源:origin: apache/hive
HCatFieldSchema tupFS = hcatFS.getArrayElementSchema().get(0);
boolean needTuple = tupFS.getType() == Type.STRUCT;
List<Object> bagContents = new ArrayList<Object>((int) pigBag.size());
Iterator<Tuple> bagItr = pigBag.iterator();
代码示例来源:origin: org.apache.pig/pig
@Override
public int getListLength(Object list) {
return (int)((DataBag)list).size();
}
代码示例来源:origin: com.twitter.elephantbird/elephant-bird-pig
private static Set<Object> toThriftSet(Field elemField, DataBag bag) {
Set<Object> set = new HashSet<Object>((int)bag.size());
fillThriftCollection(set, elemField, bag);
return set;
}
代码示例来源:origin: com.twitter.elephantbird/elephant-bird-pig
private static List<Object> toThriftList(Field elemField, DataBag bag) {
List<Object> list = new ArrayList<Object>((int)bag.size());
fillThriftCollection(list, elemField, bag);
return list;
}
代码示例来源:origin: org.apache.pig/pig
@Override
public Long exec(Tuple input) throws IOException {
try {
DataBag bag = (DataBag)(input.get(0));
return bag == null ? null : Long.valueOf(bag.size());
} catch (ExecException exp) {
throw exp;
} catch (Exception e) {
int errCode = 2106;
String msg = "Error while computing size in " + this.getClass().getSimpleName();
throw new ExecException(msg, errCode, PigException.BUG, e);
}
}
代码示例来源:origin: org.apache.pig/pig
@Override
public Long exec(Tuple input) throws IOException {
try {
DataBag bag = (DataBag)input.get(0);
return bag.size();
} catch (ExecException ee) {
throw ee;
} catch (Exception e) {
int errCode = 2106;
String msg = "Error while computing count in " + this.getClass().getSimpleName();
throw new ExecException(msg, errCode, PigException.BUG, e);
}
}
代码示例来源:origin: com.linkedin.datafu/datafu
@Override
public DataBag exec(Tuple input) throws IOException
{
DataBag samples = (DataBag)input.get(0);
if (samples.size() <= numSamples) {
return samples;
}
else
{
return super.exec(input);
}
}
代码示例来源:origin: org.apache.pig/pig
/**
* This method returns a string representation of the RubyDataBag. If given an optional
* argument, then if that argument is true, the contents of the bag will also be printed.
*
* @param context the context the method is being executed in
* @param args optional true/false argument passed to inspect
* @return string representation of the RubyDataBag
*/
@JRubyMethod(name = {"inspect", "to_s", "to_string"}, optional = 1)
public RubyString inspect(ThreadContext context, IRubyObject[] args) {
Ruby runtime = context.getRuntime();
StringBuilder sb = new StringBuilder();
sb.append("[DataBag: size: ").append(internalDB.size());
if (args.length > 0 && args[0].isTrue())
sb.append(" = ").append(internalDB.toString());
sb.append("]");
return RubyString.newString(runtime, sb);
}
代码示例来源:origin: com.linkedin.datafu/datafu
@Override
public void accumulate(Tuple b) throws IOException
{
DataBag bag = (DataBag) b.get(0);
if (bag == null || bag.size() == 0)
return;
for (Tuple t : bag) {
Object o = t.get(0);
if (!(o instanceof Number)) {
throw new IllegalStateException("bag must have numerical values (and be non-null)");
}
estimator.add(((Number) o).doubleValue());
}
}
代码示例来源:origin: org.apache.pig/pig
/**
* This method returns whether or not the encapsulated DataBag is empty.
*
* @param context the context the method is being executed in
i @return true if the encapsulated DAtaBag is empty, false otherwise
*/
@JRubyMethod(name = "empty?")
public RubyBoolean isEmpty(ThreadContext context) {
return RubyBoolean.newBoolean(context.getRuntime(), internalDB.size() == 0);
}
代码示例来源:origin: org.apache.pig/pig
/**
* This returns the size of the encapsulated DataBag.
*
* @param context the context the method is being executed in
* @return the size of the encapsulated DataBag
*/
@JRubyMethod(name={"size","length"})
public RubyFixnum size(ThreadContext context) {
return RubyFixnum.newFixnum(context.getRuntime(), internalDB.size());
}
代码示例来源:origin: org.apache.pig/pig
@Override
public Boolean exec(Tuple input) throws IOException {
try {
Object values = input.get(0);
if (values instanceof DataBag)
return ((DataBag)values).size() == 0;
else if (values instanceof Map)
return ((Map)values).size() == 0;
else {
int errCode = 2102;
String msg = "Cannot test a " +
DataType.findTypeName(values) + " for emptiness.";
throw new ExecException(msg, errCode, PigException.BUG);
}
} catch (ExecException ee) {
throw ee;
}
}
代码示例来源:origin: aseldawy/pigeon
static protected OGCGeometry union(Tuple input) throws ExecException {
DataBag values = (DataBag)input.get(0);
if (values.size() == 0)
return null;
ArrayList<OGCGeometry> all_geoms = new ArrayList<OGCGeometry>();
for (Tuple one_geom : values) {
OGCGeometry parsedGeom = geometryParser.parseGeom(one_geom.get(0));
all_geoms.add(parsedGeom);
}
// Do a union of all_geometries in the recommended way (using buffer(0))
OGCGeometryCollection geom_collection = new OGCConcreteGeometryCollection(
all_geoms, all_geoms.get(0).getEsriSpatialReference());
return geom_collection.union(all_geoms.get(0));
}
代码示例来源:origin: org.apache.pig/pig
static String[][] MakeArray(Operator op, DataBag bag)
throws Exception {
int rows = (int) bag.size();
int cols = ((LogicalRelationalOperator)op).getSchema().getFields().size();
String[][] table = new String[rows][cols];
Iterator<Tuple> it = bag.iterator();
for (int i = 0; i < rows; ++i) {
Tuple t = it.next();
for (int j = 0; j < cols; ++j) {
table[i][j] = ShortenField(t.get(j));
}
}
return table;
}
代码示例来源:origin: aseldawy/pigeon
static protected OGCGeometry extent(Tuple input) throws ExecException {
DataBag values = (DataBag)input.get(0);
if (values.size() == 0)
return null;
ArrayList<OGCGeometry> all_geoms = new ArrayList<OGCGeometry>();
for (Tuple one_geom : values) {
OGCGeometry parsedGeom = geometryParser.parseGeom(one_geom.get(0));
all_geoms.add(parsedGeom);
}
// Do a union of all_geometries in the recommended way (using buffer(0))
OGCGeometryCollection geom_collection = new OGCConcreteGeometryCollection(
all_geoms, all_geoms.get(0).getEsriSpatialReference());
return geom_collection.envelope();
}
代码示例来源:origin: aseldawy/pigeon
static protected OGCGeometry convexHull(Tuple input) throws ExecException {
DataBag values = (DataBag)input.get(0);
if (values.size() == 0)
return null;
ArrayList<OGCGeometry> all_geoms =
new ArrayList<OGCGeometry>();
for (Tuple one_geom : values) {
OGCGeometry parsedGeom = geometryParser.parseGeom(one_geom.get(0));
all_geoms.add(parsedGeom);
}
// Do a convex null of all_geometries
OGCGeometryCollection geom_collection = new OGCConcreteGeometryCollection(
all_geoms, all_geoms.get(0).getEsriSpatialReference());
return geom_collection.convexHull();
}
代码示例来源:origin: com.twitter/parquet-pig
/**
* add a bag to the summary data
*
* @param bag
*/
public void add(Schema schema, DataBag bag) {
super.add(bag);
size.add(bag.size());
FieldSchema field = getField(schema, 0);
if (bag.size() > 0 && content == null) {
content = new FieldSummaryData();
content.setName(getName(field));
}
for (Tuple tuple : bag) {
content.add(getSchema(field), tuple);
}
}
代码示例来源:origin: org.apache.pig/pig
public Result getNextDataBag() throws ExecException {
Result val = new Result();
DataBag tmpBag = mBagFactory.newDefaultBag();
for (Result ret = getNextTuple(); ret.returnStatus != POStatus.STATUS_EOP; ret = getNextTuple()) {
if (ret.returnStatus == POStatus.STATUS_ERR) {
return ret;
} else if (ret.returnStatus == POStatus.STATUS_NULL) {
continue;
} else {
tmpBag.add((Tuple) ret.result);
}
}
val.result = tmpBag;
val.returnStatus = (tmpBag.size() == 0)? POStatus.STATUS_EOP : POStatus.STATUS_OK;
return val;
}
代码示例来源:origin: aseldawy/pigeon
@Override
public DataByteArray exec(Tuple b) throws IOException {
DataBag points = (DataBag) b.get(0);
Coordinate[] coordinates = new Coordinate[(int) points.size()];
int i = 0;
for (Tuple t : points) {
Geometry point = geometryParser.parseGeom(t.get(0));
coordinates[i++] = point.getCoordinate();
}
Geometry line = geometryFactory.createLineString(coordinates);
return new DataByteArray(wkbWriter.write(line));
}
代码示例来源:origin: com.linkedin.datafu/datafu
public DataBag call(DataBag inputBag) throws IOException
{
DataBag outputBag = BagFactory.getInstance().newDefaultBag();
long i = start, count = 0;
i = inputBag.size() - 1 + start;
for (Tuple t : inputBag) {
Tuple t1 = TupleFactory.getInstance().newTuple(t.getAll());
t1.append(i);
outputBag.add(t1);
if (count % 1000000 == 0) {
outputBag.spill();
count = 0;
}
i--;
count++;
}
return outputBag;
}
内容来源于网络,如有侵权,请联系作者删除!