archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-28 15:24:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8264765: BreakIterator sees bogus sentence boundary in parenthesized “i.e.” phrase

Browse source 
Reviewed-by: joehw
This commit is contained in:
Naoto Sato 2021-04-09 18:12:08 +00:00
parent ec31b3a137
commit 9ebc497b53
2 changed files with 19 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/java.base/share/classes/sun/text/resources/BreakIteratorRules.java
View file

@ -1,5 +1,5 @@
/*
* Copyright (c) 1999, 2007, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 1999, 2021, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
@ -310,7 +310,7 @@ public class BreakIteratorRules extends ListResourceBundle {
// punctuation" and quotation marks
+ "<start-punctuation>=[:Ps::Pi:\\\"\\\'];"
// punctuation with may occur at the end of a sentence: "ending punctuation"
// punctuation which may occur at the end of a sentence: "ending punctuation"
// and quotation marks
+ "<end>=[:Pe::Pf:\\\"\\\'];"
@ -323,9 +323,12 @@ public class BreakIteratorRules extends ListResourceBundle {
// periods, which MAY signal the end of a sentence
+ "<period>=[\\.\uff0e];"
// comma, which may not occur at the start of a sentence
+ "<comma>=[\\,];"
// characters that may occur at the beginning of a sentence: basically anything
// not mentioned above (letters and digits are specifically excluded)
+ "<sent-start>=[^[:L:<space><start-punctuation><end><digit><term><period>\u2029<ignore>]];"
+ "<sent-start>=[^[:L:<space><start-punctuation><end><digit><term><period><comma>\u2029<ignore>]];"
// Hindi phrase separator
+ "<danda>=[\u0964\u0965];"