AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-3295 RBBI runtime port to Java

Browse Source 
X-SVN-Rev: 15006
This commit is contained in:
Andy Heninger 2004-04-19 06:07:21 +00:00
parent 7ca61b13cc
commit 9f3b055b1e
1 changed files with 42 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
icu4j/src/com/ibm/icu/text/RuleBasedBreakIterator.java
View File

@ -8,6 +8,8 @@
package com.ibm.icu.text;
import java.text.CharacterIterator;
import java.io.InputStream;
import java.io.IOException;
/**
* <p>A subclass of BreakIterator whose behavior is specified using a list of rules.</p>
@ -46,6 +48,22 @@ public class RuleBasedBreakIterator extends BreakIterator {
protected RuleBasedBreakIterator() {
delegatedThis = this;
}
/**
* Get a break iterator based on a set of pre-compiled break rules.
*
* @param is An input stream that supplies the compiled rule data. The
* format of the rule data on the stream is that of a rule data file
* produced by the ICU4C tool "genbrk".
* @return A RuleBasedBreakIterator based on the supplied break rules.
* @throws IOException
*/
public static RuleBasedBreakIterator getInstanceFromCompiledRules(InputStream is) throws IOException {
// TODO:
return null;
}
//=======================================================================
// boilerplate
//=======================================================================
@ -92,6 +110,30 @@ public class RuleBasedBreakIterator extends BreakIterator {
return delegatedThis.hashCode();
}
/** Tag value for "words" that do not fit into any of other categories.
* Includes spaces and most punctuation. */
public static final int UBRK_WORD_NONE = 0;
/** Upper bound for tags for uncategorized words. */
public static final int UBRK_WORD_NONE_LIMIT = 100;
/** Tag value for words that appear to be numbers, lower limit. */
public static final int UBRK_WORD_NUMBER = 100;
/** Tag value for words that appear to be numbers, upper limit. */
public static final int UBRK_WORD_NUMBER_LIMIT = 200;
/** Tag value for words that contain letters, excluding
* hiragana, katakana or ideographic characters, lower limit. */
public static final int UBRK_WORD_LETTER = 200;
/** Tag value for words containing letters, upper limit */
public static final int UBRK_WORD_LETTER_LIMIT = 300;
/** Tag value for words containing kana characters, lower limit */
public static final int UBRK_WORD_KANA = 300;
/** Tag value for words containing kana characters, upper limit */
public static final int UBRK_WORD_KANA_LIMIT = 400;
/** Tag value for words containing ideographic characters, lower limit */
public static final int UBRK_WORD_IDEO = 400;
/** Tag value for words containing ideographic characters, upper limit */
public static final int UBRK_WORD_IDEO_LIMIT = 500;
//=======================================================================
// BreakIterator overrides
//=======================================================================