You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
44 lines
1.5 KiB
44 lines
1.5 KiB
package de.anomic.document.parser;
|
|
|
|
import java.nio.charset.Charset;
|
|
|
|
import net.yacy.document.parser.htmlParser;
|
|
|
|
import junit.framework.TestCase;
|
|
|
|
public class htmlParserTest extends TestCase {
|
|
|
|
public void testGetRealCharsetEncoding() {
|
|
String[][] testStrings = new String[][] {
|
|
new String[]{null,null},
|
|
new String[]{"windows1250","windows-1250"},
|
|
new String[]{"windows_1250","windows-1250"},
|
|
new String[]{"ISO-8859-1","ISO-8859-1"},
|
|
new String[]{"ISO8859-1","ISO-8859-1"},
|
|
new String[]{"ISO-88591","ISO-8859-1"},
|
|
new String[]{"ISO88591","ISO-8859-1"},
|
|
new String[]{"iso_8859_1","ISO-8859-1"},
|
|
new String[]{"cp-1252","windows-1252"},
|
|
new String[]{"gb_2312","gb2312"}, // was: x-EUC-CN
|
|
new String[]{"gb_2312-80","gb2312"}, // was: x-EUC-CN
|
|
new String[]{"UTF-8;","UTF-8"}
|
|
};
|
|
|
|
for (int i=0; i < testStrings.length; i++) {
|
|
// desired conversion result
|
|
String shouldBe = testStrings[i][1];
|
|
shouldBe = shouldBe!=null ? shouldBe.toLowerCase() : null;
|
|
|
|
// conversion result
|
|
String charset = htmlParser.patchCharsetEncoding(testStrings[i][0]);
|
|
|
|
// test if equal
|
|
assertEquals(shouldBe, charset!=null ? charset.toLowerCase() : null);
|
|
System.out.println("testGetRealCharsetEncoding: " + (testStrings[i][0]!=null?testStrings[i][0]:"null") + " -> " + (charset!=null?charset:"null") + " | Supported: " + (charset!=null?Charset.isSupported(charset):false));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|