|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectcom.ebay.erl.mobius.core.criterion.TupleRestrictions
public class TupleRestrictions
Factory class that provides methods to define TupleCriterion
for filtering Tuple
s in a Dataset
.
This product is licensed under the Apache License, Version 2.0, available at http://www.apache.org/licenses/LICENSE-2.0. This product contains portions derived from Apache hadoop which is licensed under the Apache License, Version 2.0, available at http://hadoop.apache.org. © 2007 – 2012 eBay Inc., Evan Chiu, Woody Zhou, Neel Sundaresan
Field Summary | |
---|---|
protected static org.apache.hadoop.conf.Configuration |
conf
Hadoop configuration |
Constructor Summary | |
---|---|
TupleRestrictions()
|
Method Summary | |
---|---|
static void |
configure(org.apache.hadoop.conf.Configuration conf)
Setup Hadoop configuration. |
static TupleCriterion |
eq(java.lang.String column,
boolean trueFalse)
Specify the given column 's value equals to trueFalse |
static TupleCriterion |
eq(java.lang.String column,
java.util.Date date)
Return a TupleCriterion that only accepts tuples with
the value of column is equal to the specified
date . |
static TupleCriterion |
eq(java.lang.String column,
java.lang.Number value)
Specify the given column 's value equals to value |
static TupleCriterion |
eq(java.lang.String column,
java.lang.String value)
Specify the given column 's value equals to value |
static TupleCriterion |
eq(java.lang.String column,
java.lang.String columnDateFormat,
java.util.Date date)
Return a TupleCriterion that parses the value of date (B) and only accept tuples records when
A equals to B. |
static TupleCriterion |
eqColumns(java.lang.String column1,
java.lang.String column2)
Create a TupleCriterion that only accepts tuples with
the two columns' values are equals. |
static TupleCriterion |
ge(java.lang.String columnName,
java.util.Calendar date)
|
static TupleCriterion |
ge(java.lang.String columnName,
java.util.Date date)
|
static TupleCriterion |
ge(java.lang.String columnName,
java.lang.Number value)
|
static TupleCriterion |
ge(java.lang.String columnName,
java.lang.String value)
greater than or equal |
static TupleCriterion |
ge(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Calendar date)
|
static TupleCriterion |
ge(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Date date)
|
static TupleCriterion |
geColumns(java.lang.String column1,
java.lang.String column2)
compare if column1's value greater or equals to column2's value |
static TupleCriterion |
gt(java.lang.String columnName,
java.util.Calendar date)
|
static TupleCriterion |
gt(java.lang.String columnName,
java.util.Date date)
|
static TupleCriterion |
gt(java.lang.String columnName,
java.lang.Number value)
|
static TupleCriterion |
gt(java.lang.String columnName,
java.lang.String value)
greater than |
static TupleCriterion |
gt(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Calendar date)
|
static TupleCriterion |
gt(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Date date)
|
static TupleCriterion |
gtColumns(java.lang.String column1,
java.lang.String column2)
compare if column1's value greater than column2's value |
static TupleCriterion |
le(java.lang.String columnName,
java.util.Calendar date)
|
static TupleCriterion |
le(java.lang.String columnName,
java.util.Date date)
|
static TupleCriterion |
le(java.lang.String columnName,
java.lang.Number value)
|
static TupleCriterion |
le(java.lang.String columnName,
java.lang.String value)
less than or equal |
static TupleCriterion |
le(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Calendar date)
|
static TupleCriterion |
le(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Date date)
|
static TupleCriterion |
leColumns(java.lang.String column1,
java.lang.String column2)
compare if column1's value less than column2's value |
static TupleCriterion |
lt(java.lang.String columnName,
java.util.Calendar date)
|
static TupleCriterion |
lt(java.lang.String columnName,
java.util.Date date)
|
static TupleCriterion |
lt(java.lang.String columnName,
java.lang.Number value)
|
static TupleCriterion |
lt(java.lang.String columnName,
java.lang.String value)
less than |
static TupleCriterion |
lt(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Calendar date)
|
static TupleCriterion |
lt(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Date date)
|
static TupleCriterion |
ltColumns(java.lang.String column1,
java.lang.String column2)
compare if column1's value less or equals to column2's value |
static TupleCriterion |
ne(java.lang.String column,
boolean trueFalse)
|
static TupleCriterion |
ne(java.lang.String columnName,
java.util.Calendar date)
|
static TupleCriterion |
ne(java.lang.String columnName,
java.util.Date date)
|
static TupleCriterion |
ne(java.lang.String columnName,
java.lang.Number value)
|
static TupleCriterion |
ne(java.lang.String columnName,
java.lang.String value)
not equals |
static TupleCriterion |
ne(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Calendar date)
|
static TupleCriterion |
ne(java.lang.String columnName,
java.lang.String columnFormat,
java.util.Date date)
|
static TupleCriterion |
neColumns(java.lang.String column1,
java.lang.String column2)
compare if two column's values are not equals. |
static TupleCriterion |
not_within(java.lang.String column,
java.io.File file)
Create a tuple criterion that only accepts tuples with the value of column that is NOT
presented in the given file
The assumption of the file is that, it's single column and one to many
line text file. |
static TupleCriterion |
notNull(java.lang.String column)
Create a TupleCriterion that only accepts
tuples with the value of the given column |
static TupleCriterion |
notWithinNumber(java.lang.String column,
java.util.ArrayList<java.lang.Double> values)
Create a TupleCriterion that only accept tuples with
the value of the specified column is not
within the provide list . |
static TupleCriterion |
notWithinString(java.lang.String column,
java.util.ArrayList<java.lang.String> values)
Create a TupleCriterion that only accept tuples with
the value of the specified column is not
within the provide list . |
static TupleCriterion |
regex(java.lang.String column,
java.lang.String regex)
Define a TupleCriterion that only extracts records when the value of the
column meets the |
static TupleCriterion |
within(java.lang.String column,
java.io.File file)
Create a tuple criterion that only accepts tuples when the value of the column are presented in the given file |
static TupleCriterion |
withinNumber(java.lang.String column,
java.util.ArrayList<java.lang.Double> list)
Create a TupleCriterion that only accepts tuples with
the value of the specified column that is within
the provide list . |
static TupleCriterion |
withinString(java.lang.String column,
java.util.ArrayList<java.lang.String> list)
Create a TupleCriterion that only accept tuples with
the value of the specified column that is within
the provide list . |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
protected static org.apache.hadoop.conf.Configuration conf
Constructor Detail |
---|
public TupleRestrictions()
Method Detail |
---|
public static final void configure(org.apache.hadoop.conf.Configuration conf)
public static TupleCriterion withinString(java.lang.String column, java.util.ArrayList<java.lang.String> list)
TupleCriterion
that only accept tuples with
the value of the specified column
that is within
the provide list
.
The value of the column
will be converted into
string, if it's not string, to compare.
public static TupleCriterion withinNumber(java.lang.String column, java.util.ArrayList<java.lang.Double> list)
TupleCriterion
that only accepts tuples with
the value of the specified column
that is within
the provide list
.
The value of the column
will be converted into
double, if it's not number, to compare.
public static TupleCriterion within(java.lang.String column, java.io.File file) throws java.io.FileNotFoundException
column
are presented in the given file
The assumption of the file is that, it's single column and one to many
line text file. Each line is read into a case insensitive set, and
using the set to check the value of the column
within
the set or not.
column
- the name of a column to be tested that whether its value is in
the given file
or notfile
- a single column and multiple lines of file that contains strings/numbers,
each line is treated as a single unit.
TupleCriterion
that extracts only the records
when the value of its column
are presented in the given
file
.
java.io.FileNotFoundException
- if the given file cannot be found.public static TupleCriterion not_within(java.lang.String column, java.io.File file) throws java.io.FileNotFoundException
column
that is NOT
presented in the given file
The assumption of the file is that, it's single column and one to many
line text file. Each line is read into a case insensitive set, and
using the set to check the value of the column
within
the set or not.
column
- the name of a column to be tested that whether its value is in
the given file
or notfile
- a single column and multiple lines of file that contains strings/numbers,
each line is treated as a single unit.
TupleCriterion
that extracts only the records
when the value of its column
are NOTpresented in the given
file
.
java.io.FileNotFoundException
- if the given file cannot be found.public static TupleCriterion notWithinNumber(java.lang.String column, java.util.ArrayList<java.lang.Double> values)
TupleCriterion
that only accept tuples with
the value of the specified column
is not
within the provide list
.
The value of the column
will be converted into
double to compare, if it's not double.
public static TupleCriterion notWithinString(java.lang.String column, java.util.ArrayList<java.lang.String> values)
TupleCriterion
that only accept tuples with
the value of the specified column
is not
within the provide list
.
The value of the column
will be converted into
string to compare, if it's not string.
public static TupleCriterion regex(java.lang.String column, java.lang.String regex)
TupleCriterion
that only extracts records when the value of the
column
meets the
column
- the name of a column to be tested on its value whether it meets
the specified regex
or not.regex
- a regular expression to test.
TupleCriterion
accepts value from the column
match the given regex
.public static TupleCriterion notNull(java.lang.String column)
TupleCriterion
that only accepts
tuples with the value of the given column
is not null nor empty string.
public static TupleCriterion eq(java.lang.String column, java.lang.String value)
column
's value equals to value
public static TupleCriterion eq(java.lang.String column, java.lang.Number value)
column
's value equals to value
public static TupleCriterion eq(java.lang.String column, boolean trueFalse)
column
's value equals to trueFalse
public static TupleCriterion eq(java.lang.String column, java.lang.String columnDateFormat, java.util.Date date)
TupleCriterion
that parses the value of date
(B) and only accept tuples records when
A equals to B.
column
- name of a column to be tested in a dataset.columnDateFormat
- the date format of the specified column
in the dataset.
The columnFormat
pattern is the same as SimpleDateFormat
date
- a date constraint to be test.public static TupleCriterion eq(java.lang.String column, java.util.Date date)
TupleCriterion
that only accepts tuples with
the value of column
is equal to the specified
date
.
If the type of the value for the column
is and instance
of Date
, then the comparison is done by calling the
method of Date.getTime()
for the value and compare
it with date.getTime()
.
If the type of the value is not an instance of Date
,
then it will be parsed into date format using either the format of
yyyy-MM-dd
or yyyy-MM-dd HH:mm:ss
.
public static TupleCriterion eqColumns(java.lang.String column1, java.lang.String column2)
TupleCriterion
that only accepts tuples with
the two columns' values are equals.
public static TupleCriterion ne(java.lang.String columnName, java.lang.String value)
public static TupleCriterion ne(java.lang.String columnName, java.lang.Number value)
public static TupleCriterion ne(java.lang.String columnName, java.lang.String columnFormat, java.util.Date date)
public static TupleCriterion ne(java.lang.String columnName, java.util.Date date)
public static TupleCriterion ne(java.lang.String columnName, java.lang.String columnFormat, java.util.Calendar date)
public static TupleCriterion ne(java.lang.String columnName, java.util.Calendar date)
public static TupleCriterion ne(java.lang.String column, boolean trueFalse)
public static TupleCriterion neColumns(java.lang.String column1, java.lang.String column2)
public static TupleCriterion gt(java.lang.String columnName, java.lang.String value)
public static TupleCriterion gt(java.lang.String columnName, java.lang.Number value)
public static TupleCriterion gt(java.lang.String columnName, java.lang.String columnFormat, java.util.Date date)
public static TupleCriterion gt(java.lang.String columnName, java.util.Date date)
public static TupleCriterion gt(java.lang.String columnName, java.lang.String columnFormat, java.util.Calendar date)
public static TupleCriterion gt(java.lang.String columnName, java.util.Calendar date)
public static TupleCriterion gtColumns(java.lang.String column1, java.lang.String column2)
public static TupleCriterion ge(java.lang.String columnName, java.lang.String value)
public static TupleCriterion ge(java.lang.String columnName, java.lang.Number value)
public static TupleCriterion ge(java.lang.String columnName, java.lang.String columnFormat, java.util.Date date)
public static TupleCriterion ge(java.lang.String columnName, java.util.Date date)
public static TupleCriterion ge(java.lang.String columnName, java.lang.String columnFormat, java.util.Calendar date)
public static TupleCriterion ge(java.lang.String columnName, java.util.Calendar date)
public static TupleCriterion geColumns(java.lang.String column1, java.lang.String column2)
public static TupleCriterion le(java.lang.String columnName, java.lang.String value)
public static TupleCriterion le(java.lang.String columnName, java.lang.Number value)
public static TupleCriterion le(java.lang.String columnName, java.lang.String columnFormat, java.util.Date date)
public static TupleCriterion le(java.lang.String columnName, java.util.Date date)
public static TupleCriterion le(java.lang.String columnName, java.lang.String columnFormat, java.util.Calendar date)
public static TupleCriterion le(java.lang.String columnName, java.util.Calendar date)
public static TupleCriterion leColumns(java.lang.String column1, java.lang.String column2)
public static TupleCriterion lt(java.lang.String columnName, java.lang.String value)
public static TupleCriterion lt(java.lang.String columnName, java.lang.Number value)
public static TupleCriterion lt(java.lang.String columnName, java.lang.String columnFormat, java.util.Date date)
public static TupleCriterion lt(java.lang.String columnName, java.util.Date date)
public static TupleCriterion lt(java.lang.String columnName, java.lang.String columnFormat, java.util.Calendar date)
public static TupleCriterion lt(java.lang.String columnName, java.util.Calendar date)
public static TupleCriterion ltColumns(java.lang.String column1, java.lang.String column2)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |