Ghidra is a software reverse engineering (SRE) framework
Fixed string mem search for utf8 in case insensitive mode
dragonmacherb2db7056dba2
diff --git a/Ghidra/Features/Base/src/main/java/ghidra/features/base/memsearch/format/StringSearchFormat.java b/Ghidra/Features/Base/src/main/java/ghidra/features/base/memsearch/format/StringSearchFormat.javaindex 2ed5294f0d..7e80d998e8 100644--- a/Ghidra/Features/Base/src/main/java/ghidra/features/base/memsearch/format/StringSearchFormat.java+++ b/Ghidra/Features/Base/src/main/java/ghidra/features/base/memsearch/format/StringSearchFormat.java@@ -107,9 +107,8 @@ class StringSearchFormat extends SearchFormat {private int bytesPerCharUTF8(byte zByte) {// This method is intended for UTF-8 encoding.- // The first byte in a sequence of UTF-8 bytes can tell- // us how many bytes make up a char.- int offset = 1;+ // The first byte in a sequence of UTF-8 bytes can tell us how many bytes make up a char.+ int offset = 0;// If the char is ascii, this loop will be skipped.while ((zByte & 0x80) != 0x00) {zByte <<= 1;diff --git a/Ghidra/Features/Base/src/test/java/ghidra/features/base/memsearch/format/StringSearchFormatTest.java b/Ghidra/Features/Base/src/test/java/ghidra/features/base/memsearch/format/StringSearchFormatTest.javaindex dfc94da9b6..781c64d116 100644--- a/Ghidra/Features/Base/src/test/java/ghidra/features/base/memsearch/format/StringSearchFormatTest.java+++ b/Ghidra/Features/Base/src/test/java/ghidra/features/base/memsearch/format/StringSearchFormatTest.java@@ -64,6 +64,16 @@ public class StringSearchFormatTest extends AbstractSearchFormatTest {assertMask(0xdf, 0xdf, 0xdf, 0xff, 0xff);}+ @Test+ public void testFoo() {+ settings = settings.withStringCharset(StandardCharsets.UTF_8);+ settings = settings.withCaseSensitive(false);+ matcher = parse("éa");++ assertBytes(0xc3, 0xa9, 0x41); // éA upper-case the ASCII portion of the bytes+ assertMask(0xff, 0xff, 0xdf);+ }+@Testpublic void testEscapeSequence() {settings = settings.withUseEscapeSequence(false);