Merge remote-tracking branch 'origin/GT-3347_dev747368_PR-1241_agatti_convert_char_seq'

Author: GhidorahRex

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/codebrowser/hover/DataTypeListingHover.java

@@ -146,7 +146,7 @@ private String getLocationSupplimentalToolTipText(DataType dt, Data dataInstance
 				result += String.format("<br>Translated value: %s",
 					HTMLUtilities.friendlyEncodeHTML(sdi.getTranslatedValue()));
 			}
-			if (!sdi.isPascal() && !sdi.hasNullTerminator()) {
+			if (sdi.isMissingNullTerminator()) {
 				result += "<br>Missing NULL terminator.";
 			}
 			if (sdi.getStringLength() > dataInstance.getLength()) {

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/equate/ConvertToCharAction.java

@@ -16,9 +16,10 @@
 package ghidra.app.plugin.core.equate;
 
 import ghidra.docking.settings.FormatSettingsDefinition;
+import ghidra.program.model.data.ByteDataType;
+import ghidra.program.model.data.StringDataInstance;
 import ghidra.program.model.listing.Program;
 import ghidra.program.model.scalar.Scalar;
-import ghidra.util.StringUtilities;
 
 public class ConvertToCharAction extends AbstractConvertAction {
 	public static final String ACTION_NAME = "Convert To Char";
@@ -46,27 +47,9 @@ protected int getFormatChoice() {
 
 	@Override
 	protected String convertToString(Program program, Scalar scalar, boolean isData) {
-		long value = scalar.getUnsignedValue();
-		if (value >= 0 && value <= 255) {
-			return StringUtilities.toQuotedString(new byte[] { (byte) value });
-		}
-
 		byte[] bytes = scalar.byteArrayValue();
-		if (!program.getMemory().isBigEndian()) {
-			// assume we want to see characters as they would appear
-			// if read from memory one byte at a time
-			reverseBytes(bytes);
-		}
-		return StringUtilities.toQuotedString(bytes);
-	}
 
-	private void reverseBytes(byte[] bytes) {
-		int n = bytes.length / 2;
-		int j = bytes.length - 1;
-		for (int i = 0; i < n; i++, j--) {
-			byte b = bytes[i];
-			bytes[i] = bytes[j];
-			bytes[j] = b;
-		}
+		return StringDataInstance.getCharRepresentation(ByteDataType.dataType, bytes, null,
+			program.getMemory().isBigEndian());
 	}
 }

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/hover/AbstractScalarOperandHover.java

@@ -221,7 +221,7 @@ protected String formatScalar(Program program, Address addr, Scalar scalar) {
 
 	private boolean hasEncodingError(String s) {
 		return s.codePoints().anyMatch(
-			codePoint -> StringUtilities.isUnicodeReplacementCodePoint(codePoint));
+			codePoint -> codePoint == StringUtilities.UNICODE_REPLACEMENT);
 	}
 
 	private ByteMemBufferImpl getScalarOperandAsMemBuffer(Address addr, Scalar scalar,

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/string/StringTableProvider.java

@@ -568,8 +568,9 @@ private void updatePreview() {
 			FoundString foundString = stringModel.getRowObject(table.getSelectedRow());
 			MemBuffer membuf =
 				new DumbMemBufferImpl(currentProgram.getMemory(), foundString.getAddress());
-			StringDataInstance stringInstance = new StringDataInstance(foundString.getDataType(),
-				SettingsImpl.NO_SETTINGS, membuf, foundString.getLength());
+			StringDataInstance stringInstance =
+				StringDataInstance.getStringDataInstance(foundString.getDataType(), membuf,
+					SettingsImpl.NO_SETTINGS, foundString.getLength());
 			if (charOffset != 0) {
 				stringInstance = stringInstance.getCharOffcut(charOffset);
 			}

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/strings/HasEncodingErrorColumnConstraint.java

@@ -32,7 +32,7 @@ public class HasEncodingErrorColumnConstraint extends StringDataInstanceColumnCo
 	public boolean accepts(StringDataInstance value, TableFilterContext context) {
 		String s = value.getStringValue();
 		return (s != null) && s.chars().anyMatch(
-			codePoint -> StringUtilities.isUnicodeReplacementCodePoint(codePoint));
+			codePoint -> codePoint == StringUtilities.UNICODE_REPLACEMENT);
 	}
 
 	@Override

Ghidra/Features/Base/src/main/java/ghidra/app/plugin/core/strings/ViewStringsTableModel.java

@@ -361,7 +361,7 @@ public Boolean getValue(ProgramLocation rowObject, Settings settings, Program pr
 			String s = StringDataInstance.getStringDataInstance(data).getStringValue();
 
 			return (s != null) && s.chars().anyMatch(
-				codePoint -> StringUtilities.isUnicodeReplacementCodePoint(codePoint));
+				codePoint -> codePoint == StringUtilities.UNICODE_REPLACEMENT);
 		}
 
 		@Override

Ghidra/Framework/Generic/src/main/java/ghidra/util/StringUtilities.java

@@ -1081,16 +1081,4 @@ public static String convertCodePointToEscapeSequence(int codePoint) {
 		}
 		return new String(new int[] { codePoint }, 0, 1);
 	}
-
-	/**
-	 * Returns true if the specified code point is the 'replacement' code point 0xFFFD,
-	 * which is used when decoding bytes into unicode chars and there was a bad or invalid
-	 * sequence that does not have a mapping. (ie. decoding byte char 0x80 as US-ASCII)
-	 *
-	 * @param codePoint to test
-	 * @return boolean true if the char is 0xFFFD (ie. UNICODE REPLACEMENT char)
-	 */
-	public static boolean isUnicodeReplacementCodePoint(int codePoint) {
-		return codePoint == UNICODE_REPLACEMENT;
-	}
 }

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/program/model/data/AbstractIntegerDataType.java

@@ -18,10 +18,10 @@
 import java.math.BigInteger;
 
 import ghidra.docking.settings.*;
-import ghidra.program.model.mem.ByteMemBufferImpl;
 import ghidra.program.model.mem.MemBuffer;
 import ghidra.program.model.scalar.Scalar;
 import ghidra.util.StringFormat;
+import utilities.util.ArrayUtilities;
 
 /**
  * Base type for integer data types such as {@link CharDataType chars}, {@link IntegerDataType ints},
@@ -225,27 +225,29 @@ public String getRepresentation(MemBuffer buf, Settings settings, int length) {
 			return "??";
 		}
 
-		boolean isBigEndian = ENDIAN.isBigEndian(settings, buf);
+		boolean isLE = !ENDIAN.isBigEndian(settings, buf);
+		if (isLE) {
+			bytes = ArrayUtilities.reverse(bytes);
+		}
 
-		if (!isBigEndian) {
-			byte[] flipped = new byte[size];
-			for (int i = 0; i < size; i++) {
-				flipped[i] = bytes[size - i - 1];
-			}
-			bytes = flipped;
+		if (getFormatSettingsDefinition().getFormat(settings) == FormatSettingsDefinition.CHAR) {
+			return StringDataInstance.getCharRepresentation(this, bytes, settings, !isLE);
 		}
 
 		return getRepresentation(new BigInteger(bytes), settings, 8 * length);
 	}
 
 	/**
 	 * Get integer representation of the big-endian value.
+	 * <p>
+	 * Does not handle CHAR format, use {@link StringDataInstance#getCharRepresentation(DataType, byte[], Settings)}
+	 * 
 	 * @param bigInt BigInteger value with the appropriate sign
 	 * @param settings integer format settings (PADDING, FORMAT, etc.)
 	 * @param bitLength number of value bits to be used from bigInt
 	 * @return formatted integer string
 	 */
-	public String getRepresentation(BigInteger bigInt, Settings settings, int bitLength) {
+	/*package*/ String getRepresentation(BigInteger bigInt, Settings settings, int bitLength) {
 
 		int format = getFormatSettingsDefinition().getFormat(settings);
 		boolean padded = PADDING.isPadded(settings);
@@ -257,29 +259,8 @@ public String getRepresentation(BigInteger bigInt, Settings settings, int bitLen
 			bigInt = bigInt.add(BigInteger.valueOf(2).pow(bitLength));
 		}
 
-		int nominalLen;
-
-		if (format == FormatSettingsDefinition.CHAR) {
-			int charSize = Math.min(getDataOrganization().getCharSize(), getLength());
-			nominalLen = (bitLength + 7) / 8;
-			byte[] bytes = bigInt.toByteArray();
-			if (bytes.length > nominalLen) {
-				// BigInteger supplied too many bytes
-				byte[] chars = new byte[nominalLen];
-				System.arraycopy(bytes, bytes.length - nominalLen, chars, 0, nominalLen);
-				bytes = chars;
-			}
-			else if (bytes.length < nominalLen) {
-				// BigInteger supplied too few bytes
-				byte[] chars = new byte[nominalLen];
-				System.arraycopy(bytes, 0, chars, nominalLen - bytes.length, bytes.length);
-				bytes = chars;
-			}
-			MemBuffer memBuf = new ByteMemBufferImpl(null, bytes, true);
-			return new StringDataInstance(this, settings, memBuf, charSize).getCharRepresentation();
-		}
-
 		String valStr;
+		int nominalLen;
 
 		switch (format) {
 			default:
@@ -316,7 +297,7 @@ public boolean hasStringValue(Settings settings) {
 	public String getArrayDefaultLabelPrefix(MemBuffer buf, Settings settings, int len,
 			DataTypeDisplayOptions options) {
 		if (hasStringValue(settings) && buf.isInitializedMemory()) {
-			return new StringDataInstance(this, settings, buf, len).getLabel(
+			return new StringDataInstance(this, settings, buf, len, true).getLabel(
 				AbstractStringDataType.DEFAULT_ABBREV_PREFIX + "_",
 				AbstractStringDataType.DEFAULT_LABEL_PREFIX, AbstractStringDataType.DEFAULT_LABEL,
 				options);
@@ -328,7 +309,7 @@ public String getArrayDefaultLabelPrefix(MemBuffer buf, Settings settings, int l
 	public String getArrayDefaultOffcutLabelPrefix(MemBuffer buf, Settings settings, int len,
 			DataTypeDisplayOptions options, int offcutOffset) {
 		if (hasStringValue(settings) && buf.isInitializedMemory()) {
-			return new StringDataInstance(this, settings, buf, len).getOffcutLabelString(
+			return new StringDataInstance(this, settings, buf, len, true).getOffcutLabelString(
 				AbstractStringDataType.DEFAULT_ABBREV_PREFIX + "_",
 				AbstractStringDataType.DEFAULT_LABEL_PREFIX, AbstractStringDataType.DEFAULT_LABEL,
 				options, offcutOffset);

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/program/model/data/AbstractStringDataType.java

@@ -15,9 +15,9 @@
  */
 package ghidra.program.model.data;
 
-import static ghidra.program.model.data.CharsetSettingsDefinition.CHARSET;
-import static ghidra.program.model.data.RenderUnicodeSettingsDefinition.RENDER;
-import static ghidra.program.model.data.TranslationSettingsDefinition.TRANSLATION;
+import static ghidra.program.model.data.CharsetSettingsDefinition.*;
+import static ghidra.program.model.data.RenderUnicodeSettingsDefinition.*;
+import static ghidra.program.model.data.TranslationSettingsDefinition.*;
 
 import ghidra.docking.settings.*;
 import ghidra.program.model.mem.MemBuffer;
@@ -28,7 +28,7 @@
  * See {@link StringDataType} for information about string variations and configuration details.
  * <p>
  * Sub-classes generally only need to implement a constructor that calls the mega-constructor
- * {@link #AbstractStringDataType(String, String, String, String, String, String, String, DataType, StringLayoutEnum, DataTypeManager) AbstractStringDataType.SAbstractStringDataType(lots,of,params)}
+ * {@link #AbstractStringDataType(String, String, String, String, String, String, String, DataType, StringLayoutEnum, DataTypeManager) AbstractStringDataType.AbstractStringDataType(lots,of,params)}
  * and the {@link DataType#clone(DataTypeManager) } method.
  * <p>
  *

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/program/model/data/Array.java

@@ -105,9 +105,9 @@ default public String getArrayRepresentation(MemBuffer buf, Settings settings, i
 		ArrayStringable stringableElementType = ArrayStringable.getArrayStringable(getDataType());
 		String value =
 			(stringableElementType != null && stringableElementType.hasStringValue(settings))
-				? new StringDataInstance(stringableElementType, settings, buf,
-					length).getStringRepresentation()
-				: null;
+					? new StringDataInstance(stringableElementType, settings, buf, length,
+						true).getStringRepresentation()
+					: null;
 		return (value != null) ? value : "";
 	}
 

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/program/model/data/ArrayStringable.java

@@ -47,7 +47,7 @@ public interface ArrayStringable extends DataType {
 	 */
 	public default String getArrayString(MemBuffer buf, Settings settings, int length) {
 		if (hasStringValue(settings) && buf.isInitializedMemory()) {
-			return new StringDataInstance(this, settings, buf, length).getStringValue();
+			return new StringDataInstance(this, settings, buf, length, true).getStringValue();
 		}
 		return null;
 	}

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/program/model/data/BitFieldDataType.java

@@ -17,11 +17,12 @@
 
 import java.math.BigInteger;
 
-import ghidra.docking.settings.Settings;
-import ghidra.docking.settings.SettingsDefinition;
+import ghidra.docking.settings.*;
 import ghidra.program.model.mem.MemBuffer;
 import ghidra.program.model.scalar.Scalar;
+import ghidra.util.DataConverter;
 import ghidra.util.exception.AssertException;
+import utilities.util.ArrayUtilities;
 
 /**
  * <code>BitFieldDataType</code> provides a means of defining a minimally sized bit-field
@@ -406,7 +407,23 @@ public String getRepresentation(MemBuffer buf, Settings settings, int length) {
 		if (dt instanceof Enum) {
 			return ((Enum) dt).getRepresentation(big, settings, effectiveBitSize);
 		}
-		return ((AbstractIntegerDataType) dt).getRepresentation(big, settings, effectiveBitSize);
+		AbstractIntegerDataType intDT = (AbstractIntegerDataType) dt;
+		if (intDT.getFormatSettingsDefinition().getFormat(
+			settings) == FormatSettingsDefinition.CHAR) {
+			if (big.signum() < 0) {
+				big = big.add(BigInteger.valueOf(2).pow(bitSize));
+			}
+			int bytesLen = BitFieldDataType.getMinimumStorageSize(bitSize);
+			byte[] bytes = DataConverter.getInstance(buf.isBigEndian()).getBytes(big, bytesLen);
+			if (!EndianSettingsDefinition.ENDIAN.isBigEndian(settings, buf)) {
+				bytes = ArrayUtilities.reverse(bytes);
+			}
+
+			return StringDataInstance.getCharRepresentation(this, bytes, settings,
+				buf.isBigEndian());
+		}
+
+		return intDT.getRepresentation(big, settings, effectiveBitSize);
 	}
 
 	@Override