com.google.myanmartools

Class ZawgyiDetector

java.lang.Object

com.google.myanmartools.ZawgyiDetector

public final class ZawgyiDetector
extends Object

Uses a machine learning model to determine whether a string of text is Zawgyi or Unicode.

For more details and documentation, see https://github.com/googlei18n/myanmar-tools

Constructor Summary

Constructors

Constructor and Description
ZawgyiDetector() Loads the model from the resource and returns a ZawgyiDetector instance.

Method Summary

Modifier and Type	Method and Description
double	getZawgyiProbability(String input) Performs detection on the given string.
double	getZawgyiProbability(String input, boolean verbose) Performs detection on the given string.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ZawgyiDetector

public ZawgyiDetector()

Loads the model from the resource and returns a ZawgyiDetector instance.

Method Detail

getZawgyiProbability

public double getZawgyiProbability(String input,
                                   boolean verbose)

Performs detection on the given string. Returns the probability that the string is Zawgyi given that it is either Unicode or Zawgyi. Values approaching 1 are strong Zawgyi; values approaching 0 are strong Unicode; and values close to 0.5 are toss-ups.

If the string does not contain any Myanmar range code points, -Infinity is returned.

Parameters:

input - The string on which to run detection.

verbose - If true, print debugging information to standard output.

Returns:

The probability that the string is Zawgyi (between 0 and 1), or -Infinity if the string contains no Myanmar range code points.

getZawgyiProbability

public double getZawgyiProbability(String input)

Performs detection on the given string. Returns the probability that the string is Zawgyi given that it is either Unicode or Zawgyi. Values approaching 1 are strong Zawgyi; values approaching 0 are strong Unicode; and values close to 0.5 are toss-ups.

If the string does not contain any Myanmar range code points, -Infinity is returned.

Parameters:

input - The string on which to run detection.

Returns:

The probability that the string is Zawgyi (between 0 and 1), or -Infinity if the string contains no Myanmar range code points.