archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-27 14:54:52 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8247546: Pattern matching does not skip correctly over supplementary characters

Browse source 
Reviewed-by: joehw
This commit is contained in:
Naoto Sato 2020-07-29 09:49:43 -07:00
parent 6e32338330
commit 4946a162aa
3 changed files with 36 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/java.base/share/classes/java/util/regex/Pattern.java
View file

@ -1049,9 +1049,10 @@ public final class Pattern
private transient int patternLength;
/**
* If the Start node might possibly match supplementary characters.
* If the Start node might possibly match supplementary or surrogate
* code points.
* It is set to true during compiling if
* (1) There is supplementary char in pattern, or
* (1) There is supplementary or surrogate code point in pattern, or
* (2) There is complement node of a "family" CharProperty
*/
private transient boolean hasSupplementary;
@ -2948,8 +2949,10 @@ loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
return null;
if (p instanceof BmpCharPredicate)
return new BmpCharProperty((BmpCharPredicate)p);
else
else {
hasSupplementary = true;
return new CharProperty(p);
}
}
/**
@ -5785,18 +5788,18 @@ NEXT: while (i <= last) {
}
/**
* Charactrs within a explicit value range
* Characters within a explicit value range
*/
static CharPredicate Range(int lower, int upper) {
if (upper < Character.MIN_HIGH_SURROGATE ||
lower > Character.MAX_HIGH_SURROGATE &&
lower > Character.MAX_LOW_SURROGATE &&
upper < Character.MIN_SUPPLEMENTARY_CODE_POINT)
return (BmpCharPredicate)(ch -> inRange(lower, ch, upper));
return ch -> inRange(lower, ch, upper);
}
/**
* Charactrs within a explicit value range in a case insensitive manner.
* Characters within a explicit value range in a case insensitive manner.
*/
static CharPredicate CIRange(int lower, int upper) {
return ch -> inRange(lower, ch, upper) ||