archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-27 06:45:07 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8302877: Speed up latin1 case conversions

Browse source 
Reviewed-by: naoto, redestad
This commit is contained in:
Eirik Bjorsnos 2023-02-21 20:54:36 +00:00 • committed by Naoto Sato
parent 1ea5f9f7cd
commit ef1f7bd3b8
5 changed files with 166 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

46
src/java.base/share/classes/java/lang/CharacterDataLatin1.java.template
View file

@ -1,5 +1,5 @@
/*
* Copyright (c) 2002, 2021, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2002, 2023, 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
@ -135,30 +135,36 @@ class CharacterDataLatin1 extends CharacterData {
}
int toLowerCase(int ch) {
int mapChar = ch;
int val = getProperties(ch);
if (((val & $$maskLowerCase) != 0) &&
((val & $$maskCaseOffset) != $$maskCaseOffset)) {
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
mapChar = ch + offset;
if (ch < 'A') { // Fast path for low code points
return ch;
}
return mapChar;
int l = ch | 0x20; // Lowercase using 'oldest ASCII trick in the book'
if (l <= 'z' // In range a-z
|| (l >= 0xE0 && l <= 0xFE && l != 0xF7)) { // ..or agrave-thorn, excluding division
return l;
}
return ch;
}
int toUpperCase(int ch) {
int mapChar = ch;
int val = getProperties(ch);
if ((val & $$maskUpperCase) != 0) {
if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
mapChar = ch - offset;
} else if (ch == 0x00B5) {
mapChar = 0x039C;
}
if (ch < 'a') { // Fast path for low code points
return ch;
}
return mapChar;
int U = ch & 0xDF; // Uppercase using 'oldest ASCII trick in the book'
if (U <= 'Z' // In range A-Z
|| (U >= 0xC0 && U <= 0xDE && U != 0xD7)) { // ..or Agrave-Thorn, excluding multiplication
return U;
}
// Special-case for 'y with Diaeresis' which uppercases out of latin1
if (ch == 0xFF) {
return 0x178; // Capital Letter Y with Diaeresis
}
// Special-case for 'Micro Sign' which uppercases out of latin1
if (ch == 0xB5) {
return 0x39C; // Greek Capital Letter Mu
}
return ch;
}
int toTitleCase(int ch) {