mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-17 18:56:53 +00:00
ICU-10532 Improve UTF-16 charset detection.
X-SVN-Rev: 34646
This commit is contained in:
Andy Heninger
parent
2f0c821f16
commit
cc2d6e41f8
3 changed files with 98 additions and 48 deletions
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 1996-2012, International Business Machines Corporation and *
|
||||
* Copyright (C) 1996-2013, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*
|
||||
|
|
@ -24,6 +24,29 @@ abstract class CharsetRecog_Unicode extends CharsetRecognizer {
|
|||
*/
|
||||
abstract CharsetMatch match(CharsetDetector det);
|
||||
|
||||
static int codeUnit16FromBytes(byte hi, byte lo) {
|
||||
return ((hi & 0xff) << 8) | (lo & 0xff);
|
||||
}
|
||||
|
||||
// UTF-16 confidence calculation. Very simple minded, but better than nothing.
|
||||
// Any 8 bit non-control characters bump the confidence up. These have a zero high byte,
|
||||
// and are very likely to be UTF-16, although they could also be part of a UTF-32 code.
|
||||
// NULs are a contra-indication, they will appear commonly if the actual encoding is UTF-32.
|
||||
// NULs should be rare in actual text.
|
||||
static int adjustConfidence(int codeUnit, int confidence) {
|
||||
if (codeUnit == 0) {
|
||||
confidence -= 10;
|
||||
} else if ((codeUnit >= 0x20 && codeUnit <= 0xff) || codeUnit == 0x0a) {
|
||||
confidence += 10;
|
||||
}
|
||||
if (confidence < 0) {
|
||||
confidence = 0;
|
||||
} else if (confidence > 100) {
|
||||
confidence = 100;
|
||||
}
|
||||
return confidence;
|
||||
}
|
||||
|
||||
static class CharsetRecog_UTF_16_BE extends CharsetRecog_Unicode
|
||||
{
|
||||
String getName()
|
||||
|
|
@ -34,13 +57,26 @@ abstract class CharsetRecog_Unicode extends CharsetRecognizer {
|
|||
CharsetMatch match(CharsetDetector det)
|
||||
{
|
||||
byte[] input = det.fRawInput;
|
||||
int confidence = 10;
|
||||
|
||||
if (input.length>=2 && ((input[0] & 0xFF) == 0xFE && (input[1] & 0xFF) == 0xFF)) {
|
||||
int confidence = 100;
|
||||
int bytesToCheck = Math.min(input.length, 30);
|
||||
for (int charIndex=0; charIndex<bytesToCheck-1; charIndex+=2) {
|
||||
int codeUnit = codeUnit16FromBytes(input[charIndex], input[charIndex + 1]);
|
||||
if (charIndex == 0 && codeUnit == 0xFEFF) {
|
||||
confidence = 100;
|
||||
break;
|
||||
}
|
||||
confidence = adjustConfidence(codeUnit, confidence);
|
||||
if (confidence == 0 || confidence == 100) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (bytesToCheck < 4 && confidence < 100) {
|
||||
confidence = 0;
|
||||
}
|
||||
if (confidence > 0) {
|
||||
return new CharsetMatch(det, this, confidence);
|
||||
}
|
||||
|
||||
// TODO: Do some statistics to check for unsigned UTF-16BE
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
|
@ -55,19 +91,26 @@ abstract class CharsetRecog_Unicode extends CharsetRecognizer {
|
|||
CharsetMatch match(CharsetDetector det)
|
||||
{
|
||||
byte[] input = det.fRawInput;
|
||||
int confidence = 10;
|
||||
|
||||
if (input.length >= 2 && ((input[0] & 0xFF) == 0xFF && (input[1] & 0xFF) == 0xFE))
|
||||
{
|
||||
// An LE BOM is present.
|
||||
if (input.length>=4 && input[2] == 0x00 && input[3] == 0x00) {
|
||||
// It is probably UTF-32 LE, not UTF-16
|
||||
return null;
|
||||
}
|
||||
int confidence = 100;
|
||||
return new CharsetMatch(det, this, confidence);
|
||||
}
|
||||
|
||||
// TODO: Do some statistics to check for unsigned UTF-16LE
|
||||
int bytesToCheck = Math.min(input.length, 30);
|
||||
for (int charIndex=0; charIndex<bytesToCheck-1; charIndex+=2) {
|
||||
int codeUnit = codeUnit16FromBytes(input[charIndex+1], input[charIndex]);
|
||||
if (charIndex == 0 && codeUnit == 0xFEFF) {
|
||||
confidence = 100;
|
||||
break;
|
||||
}
|
||||
confidence = adjustConfidence(codeUnit, confidence);
|
||||
if (confidence == 0 || confidence == 100) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (bytesToCheck < 4 && confidence < 100) {
|
||||
confidence = 0;
|
||||
}
|
||||
if (confidence > 0) {
|
||||
return new CharsetMatch(det, this, confidence);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<!-- See individual test cases for their specific copyright. -->
|
||||
|
||||
<charset-detection-tests>
|
||||
<test-case id="IUC10-ar" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-6/ar windows-1256/ar">
|
||||
<test-case id="IUC10-ar" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-6/ar windows-1256/ar">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
أوروبا, برمجيات الحاسوب + انترنيت :
|
||||
|
|
@ -20,7 +20,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-da-Q" encodings="UTF-8 UTF-32BE UTF-32LE windows-1252/da">
|
||||
<test-case id="IUC10-da-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1252/da">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software + Internet:
|
||||
|
|
@ -36,7 +36,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-da" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/da">
|
||||
<test-case id="IUC10-da" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/da">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software + Internet:
|
||||
|
|
@ -52,7 +52,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-de" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/de">
|
||||
<test-case id="IUC10-de" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/de">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software + das Internet:
|
||||
|
|
@ -69,7 +69,7 @@
|
|||
</test-case>
|
||||
|
||||
<!-- No UTF-8 in this test because there are no non-ASCII characters. -->
|
||||
<test-case id="IUC10-en" encodings="UTF-32BE UTF-32LE ISO-8859-1/en">
|
||||
<test-case id="IUC10-en" encodings="UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/en">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europe, Software + the Internet:
|
||||
|
|
@ -85,7 +85,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-es" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/es">
|
||||
<test-case id="IUC10-es" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/es">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software + el Internet:
|
||||
|
|
@ -101,7 +101,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-fr" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/fr">
|
||||
<test-case id="IUC10-fr" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/fr">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
L'Europe, le logiciel et l'Internet :
|
||||
|
|
@ -118,7 +118,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-he" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-8-I/he">
|
||||
<test-case id="IUC10-he" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-8-I/he">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
אירופה, תוכנה והאינטרנט:
|
||||
|
|
@ -133,7 +133,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-he-Q" encodings="UTF-8 UTF-32BE UTF-32LE windows-1255/he">
|
||||
<test-case id="IUC10-he-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1255/he">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
אירופה, תוכנה והאינטרנט:
|
||||
|
|
@ -148,7 +148,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-hu" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-2/hu">
|
||||
<test-case id="IUC10-hu" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-2/hu">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Európa, a Szoftver s az Internet -
|
||||
|
|
@ -165,7 +165,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-hu-Q" encodings="UTF-8 UTF-32BE UTF-32LE windows-1250/hu">
|
||||
<test-case id="IUC10-hu-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1250/hu">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Európa, a Szoftver s az Internet -
|
||||
|
|
@ -182,7 +182,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-it" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/it">
|
||||
<test-case id="IUC10-it" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/it">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, software e Internet:
|
||||
|
|
@ -199,7 +199,7 @@
|
|||
</test-case>
|
||||
|
||||
<!-- No EUC-JP in this test because it detects as GB18030 -->
|
||||
<test-case id="IUC10-jp" encodings="UTF-8 UTF-32BE UTF-32LE Shift_JIS/ja ISO-2022-JP">
|
||||
<test-case id="IUC10-jp" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE Shift_JIS/ja ISO-2022-JP">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
ヨーロッパ、ソフトウェア、そしてインターネット:
|
||||
|
|
@ -214,7 +214,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-ko" encodings="UTF-8 UTF-32BE UTF-32LE EUC-KR/ko ISO-2022-KR">
|
||||
<test-case id="IUC10-ko" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE EUC-KR/ko ISO-2022-KR">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
유럽, 소프트웨어 그리고 인터넷:
|
||||
|
|
@ -230,7 +230,7 @@
|
|||
</test-case>
|
||||
|
||||
<!-- No UTF-8 in this test because there are no non-ASCII characters. -->
|
||||
<test-case id="IUC10-nl" encodings="UTF-32BE UTF-32LE ISO-8859-1/nl">
|
||||
<test-case id="IUC10-nl" encodings="UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/nl">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software + het Internet:
|
||||
|
|
@ -247,7 +247,7 @@
|
|||
</test-case>
|
||||
|
||||
<!-- No language for ISO-8859-1 in this test because no-NO is recogonized as Danish... -->
|
||||
<test-case id="IUC10-no-NO" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/da">
|
||||
<test-case id="IUC10-no-NO" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/da">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Programvare og Internet:
|
||||
|
|
@ -262,7 +262,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-no-NO-NY" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/no">
|
||||
<test-case id="IUC10-no-NO-NY" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/no">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, programvare og Internett:
|
||||
|
|
@ -278,7 +278,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-pt-BR" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/pt">
|
||||
<test-case id="IUC10-pt-BR" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/pt">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software e a Internet:
|
||||
|
|
@ -294,7 +294,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-pt-PT" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/pt">
|
||||
<test-case id="IUC10-pt-PT" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/pt">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software e a Internet:
|
||||
|
|
@ -311,7 +311,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-ro" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-2/ro">
|
||||
<test-case id="IUC10-ro" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-2/ro">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, Software şi Internet:
|
||||
|
|
@ -328,7 +328,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-ru" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-5/ru windows-1251/ru KOI8-R/ru">
|
||||
<test-case id="IUC10-ru" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-5/ru windows-1251/ru KOI8-R/ru">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Европа, Программное обеспечение + Интернет:
|
||||
|
|
@ -345,7 +345,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-sv" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-1/sv">
|
||||
<test-case id="IUC10-sv" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-1/sv">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Europa, programvara och Internet:
|
||||
|
|
@ -361,7 +361,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-yi" encodings="UTF-8 UTF-32BE UTF-32LE">
|
||||
<test-case id="IUC10-yi" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
אײראָפּע: פּראָגראַמװאַרג און די װעלטנעץ:
|
||||
|
|
@ -377,7 +377,7 @@
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="IUC10-zh-Hant" encodings="UTF-8 UTF-32BE UTF-32LE Big5/zh">
|
||||
<test-case id="IUC10-zh-Hant" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE Big5/zh">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
歐洲，軟體及網際網路：
|
||||
|
|
@ -393,7 +393,7 @@
|
|||
</test-case>
|
||||
|
||||
<!-- No ISO-2022-CN in this test because Java doesn't support it in both directions :-( -->
|
||||
<test-case id="IUC10-zh-Hans" encodings="UTF-8 UTF-32BE UTF-32LE ISO-2022-CN GB18030/zh">
|
||||
<test-case id="IUC10-zh-Hans" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-2022-CN GB18030/zh">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
欧洲，软件＋互联网
|
||||
|
|
@ -409,7 +409,7 @@
|
|||
Conference Program
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-cz" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-2/cs">
|
||||
<test-case id="WIU-cz" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-2/cs">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Co je Unicode?
|
||||
|
|
@ -432,7 +432,7 @@ Conference Program
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-el" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-7/el">
|
||||
<test-case id="WIU-el" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-7/el">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Τι είναι το Unicode;
|
||||
|
|
@ -458,7 +458,7 @@ Conference Program
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-el-Q" encodings="UTF-8 UTF-32BE UTF-32LE windows-1253/el">
|
||||
<test-case id="WIU-el-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1253/el">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Τι είναι το “Unicode”;
|
||||
|
|
@ -484,7 +484,7 @@ Conference Program
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-pl" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-2/pl">
|
||||
<test-case id="WIU-pl" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-2/pl">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Czym jest Unikod ?
|
||||
|
|
@ -505,7 +505,7 @@ Conference Program
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-tr" encodings="UTF-8 UTF-32BE UTF-32LE ISO-8859-9/tr">
|
||||
<test-case id="WIU-tr" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-9/tr">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
Evrensel Kod Nedir?
|
||||
|
|
@ -527,7 +527,7 @@ Conference Program
|
|||
|
||||
</test-case>
|
||||
|
||||
<test-case id="WIU-tr-Q" encodings="UTF-8 UTF-32BE UTF-32LE windows-1254/tr">
|
||||
<test-case id="WIU-tr-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1254/tr">
|
||||
<!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
|
||||
|
||||
“Evrensel Kod” Nedir?
|
||||
|
|
@ -548,4 +548,9 @@ Conference Program
|
|||
şifrelemeyi desteklemek zorundadırlar; veriler, farklı şifreleme ve altyapılardan geçerken bozulma riski taşırlar.
|
||||
|
||||
</test-case>
|
||||
|
||||
|
||||
<test-case id="bug-10532-utf-16" encodings="UTF-8 UTF-16BE UTF-16LE UTF-32BE UTF-32LE">
|
||||
foo 東京・銀座の歌舞伎座。４月に新調された４枚の緞帳のうち３枚は、京都の川島織物セルコンが織った朝日新聞デジタル会員（有料・無料）にご登録いただくと、様々な特典・サービスが受けられます。
|
||||
</test-case>
|
||||
</charset-detection-tests>
|
||||
|
|
|
|||
|
|
@ -444,10 +444,12 @@ public class TestCharsetDetector extends TestFmwk
|
|||
|
||||
// Ignore any other converters that can't
|
||||
// convert from Unicode.
|
||||
logln("Unsupported encoding" + from);
|
||||
return;
|
||||
} catch (UnsupportedEncodingException uee) {
|
||||
// Ignore any encodings that this runtime
|
||||
// doesn't support.
|
||||
logln("Unsupported encoding" + from);
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue