org.apache.tika.parser.txt.CharsetRecog_2022 Maven / Gradle / Ivy
/*
*******************************************************************************
* Copyright (C) 2005 - 2008, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
package org.apache.tika.parser.txt;
/**
* class CharsetRecog_2022 part of the ICU charset detection imlementation.
* This is a superclass for the individual detectors for
* each of the detectable members of the ISO 2022 family
* of encodings.
*
* The separate classes are nested within this class.
*
* @internal
*/
abstract class CharsetRecog_2022 extends CharsetRecognizer {
/**
* Matching function shared among the 2022 detectors JP, CN and KR
* Counts up the number of legal an unrecognized escape sequences in
* the sample of text, and computes a score based on the total number &
* the proportion that fit the encoding.
*
*
* @param text the byte buffer containing text to analyse
* @param textLen the size of the text in the byte.
* @param escapeSequences the byte escape sequences to test for.
* @return match quality, in the range of 0-100.
*/
int match(byte [] text, int textLen, byte [][] escapeSequences) {
int i, j;
int escN;
int hits = 0;
int misses = 0;
int shifts = 0;
int quality;
scanInput:
for (i=0; i