Add tests for StringBlock#decodeString with failing tests for code points above 0x10FFFF (issue 2299).

This commit is contained in:
Comnir 2020-12-10 12:25:16 +02:00
parent 6d4e503b16
commit 201b5976bb
2 changed files with 59 additions and 1 deletions

View File

@ -18,6 +18,8 @@ package brut.androlib.res.decoder;
import brut.androlib.res.xml.ResXmlEncoders; import brut.androlib.res.xml.ResXmlEncoders;
import brut.util.ExtDataInput; import brut.util.ExtDataInput;
import com.google.common.annotations.VisibleForTesting;
import java.io.IOException; import java.io.IOException;
import java.nio.ByteBuffer; import java.nio.ByteBuffer;
import java.nio.charset.*; import java.nio.charset.*;
@ -254,6 +256,12 @@ public class StringBlock {
private StringBlock() { private StringBlock() {
} }
@VisibleForTesting
StringBlock(byte[] strings, boolean isUTF8) {
m_strings = strings;
m_isUTF8 = isUTF8;
}
/** /**
* Returns style information - array of int triplets, where in each triplet: * Returns style information - array of int triplets, where in each triplet:
* * first int is index of tag name ('b','i', etc.) * second int is tag * * first int is index of tag name ('b','i', etc.) * second int is tag
@ -288,7 +296,8 @@ public class StringBlock {
return style; return style;
} }
private String decodeString(int offset, int length) { @VisibleForTesting
String decodeString(int offset, int length) {
try { try {
return (m_isUTF8 ? UTF8_DECODER : UTF16LE_DECODER).decode( return (m_isUTF8 ? UTF8_DECODER : UTF16LE_DECODER).decode(
ByteBuffer.wrap(m_strings, offset, length)).toString(); ByteBuffer.wrap(m_strings, offset, length)).toString();

View File

@ -0,0 +1,49 @@
package brut.androlib.res.decoder;
import org.junit.Test;
import java.nio.charset.StandardCharsets;
import static org.junit.Assert.assertEquals;
public class StringBlockWithSurrogatePairInUtf8Test {
@Test
public void decodeSingleOctet() {
final String actual = new StringBlock("abcDEF123".getBytes(StandardCharsets.UTF_8), true).decodeString(0, 9);
assertEquals("Incorrect decoding", "abcDEF123", actual);
}
@Test
public void decodeTwoOctets() {
final String actual0 = new StringBlock(new byte[] { (byte) 0xC2, (byte) 0x80}, true).decodeString(0, 2);
assertEquals("Incorrect decoding", "\u0080", actual0);
final String actual1 = new StringBlock(new byte[] { (byte) 0xDF, (byte) 0xBF}, true).decodeString(0, 2);
assertEquals("Incorrect decoding", "\u07FF", actual1);
}
@Test
public void decodeThreeOctets() {
final String actual0 = new StringBlock(new byte[] { (byte) 0xE0, (byte) 0xA0, (byte) 0x80}, true).decodeString(0, 3);
assertEquals("Incorrect decoding", "\u0800", actual0);
final String actual1 = new StringBlock(new byte[] { (byte) 0xEF, (byte) 0xBF, (byte) 0xBF}, true).decodeString(0, 3);
assertEquals("Incorrect decoding", "\uFFFF", actual1);
}
@Test
public void decodeSurrogatePair_when_givesAsThreeOctetsFromInvalidRangeOfUtf8() {
// See: https://github.com/iBotPeaches/Apktool/issues/2299
final String actual0 = new StringBlock(new byte[] { (byte) 0xED, (byte) 0xA0, (byte) 0xBD, (byte) 0xED, (byte) 0xB4, (byte) 0x86}, true).decodeString(0, 6);
assertEquals("Incorrect decoding", "\uD83D\uDD06", actual0);
}
@Test
public void decodeSurrogatePair_when_givesAsThreeOctetsFromTheValidRangeOfUtf8() {
// \u10FFFF is encoded in UTF-8 as "0xDBFF 0xDFFF" (4-byte encoding),
// but when used in Android resources which are encoded in UTF-8, 3-byte encoding is used,
// so each of these is encoded as 3-bytes
final String actual0 = new StringBlock(new byte[] { (byte) 0xED, (byte) 0xAF, (byte) 0xBF, (byte) 0xED, (byte) 0xBF, (byte) 0xBF}, true).decodeString(0, 6);
assertEquals("Incorrect decoding", "\uDBFF\uDFFF", actual0);
}
}