GP-4287: Format. Revise. Certify.

Ghidra/Features/WildcardAssembler/certification.manifest

@@ -2,5 +2,5 @@
 ##MODULE IP: FAMFAMFAM Icons - CC 2.5
 ##MODULE IP: Oxygen Icons - LGPL 3.0
 Module.manifest||GHIDRA||||END|
-src/main/help/help/TOC_Source.xml||GHIDRA||reviewed||END|
+src/main/help/help/TOC_Source.xml||GHIDRA||||END|
 src/main/help/help/topics/WildcardAssemblerModule/Wildcard_Assembler.html||GHIDRA||||END|

Ghidra/Features/WildcardAssembler/ghidra_scripts/FindInstructionWithWildcard.java

@@ -29,35 +29,28 @@
 // See the "WildSleighAssemblerInfo" script for a simpler use of the WildSleighAssembler.
 // @category Examples
 
-import java.util.ArrayList;
+import java.util.*;
-import java.util.Collection;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.Set;
 
 import ghidra.app.plugin.assembler.AssemblySelector;
 import ghidra.app.plugin.assembler.sleigh.parse.AssemblyParseResult;
-import ghidra.app.plugin.assembler.sleigh.sem.AssemblyPatternBlock;
+import ghidra.app.plugin.assembler.sleigh.sem.*;
-import ghidra.app.plugin.assembler.sleigh.sem.AssemblyResolution;
-import ghidra.app.plugin.assembler.sleigh.sem.AssemblyResolutionResults;
 import ghidra.app.plugin.processors.sleigh.SleighLanguage;
 import ghidra.app.script.GhidraScript;
-import ghidra.asm.wild.WildOperandInfo;
+import ghidra.asm.wild.*;
-import ghidra.asm.wild.WildSleighAssembler;
-import ghidra.asm.wild.WildSleighAssemblerBuilder;
 import ghidra.asm.wild.sem.WildAssemblyResolvedPatterns;
-import ghidra.program.model.mem.*;
+import ghidra.program.model.address.Address;
-import ghidra.program.model.address.*;
+import ghidra.program.model.mem.Memory;
+import ghidra.program.model.mem.MemoryAccessException;
 
 public class FindInstructionWithWildcard extends GhidraScript {
 
+	@Override
 	public void run() throws Exception {
 
-		var instruction = askString("Instruction to search",
+		var instruction = askString("Instruction to search", """
-			"Instruction to search for with wildcard (example is for x86_64, adjust if you are using a different architecture):",
+				Instruction to search for with wildcard (example is for x86_64, adjust if you are \
-			"XOR R13D,`Q1/R1(2|3)D`");
+				using a different architecture): \
+				XOR R13D,`Q1/R1(2|3)D`""");
 		var allValidResults = getAllResolvedPatterns(instruction);
 
 		var encodings = getMapOfUniqueInstructionEncodings(allValidResults);
@@ -175,8 +168,7 @@ public class FindInstructionWithWildcard extends GhidraScript {
 		 * Returns true of the given value shares the same {@code maskedInstruction} and wildcard(s)
 		 * as this instance.
 		 * 
-		 * @param other
+		 * @param other Value to compare against
-		 *            Value to compare against
 		 * @return True if both values share the same maskedInstruction and wildcard(s)
 		 */
 		boolean sameBaseEncoding(ReducedWildcardAssemblyResolvedPattern other) {
@@ -194,7 +186,7 @@ public class FindInstructionWithWildcard extends GhidraScript {
 				// Check all of other's WildOperandInfo
 				for (WildOperandInfo otherInfo : other.parent.getOperandInfo()) {
 					// Check if we have matching wildcards (names), expressions, and locations.
-					// Notice that we're *NOT* checking choice here, as we expect those to be different.
+					// We're *NOT* checking choice here, as we expect those to be different.
 					if (info.wildcard().equals(otherInfo.wildcard()) &&
 						info.expression().equals(otherInfo.expression()) &&
 						info.location().equals(otherInfo.location())) {
@@ -222,10 +214,8 @@ public class FindInstructionWithWildcard extends GhidraScript {
 	 * Does not currently print wildcard information about the search results, but this could be
 	 * added.
 	 * 
-	 * @param encodings
+	 * @param encodings Map of encodings to that encoding's possible WildOperandInfo values.
-	 *            HashMap of encodings to that encoding's possible WildOperandInfo values.
+	 * @throws MemoryAccessException If we find bytes but can't read them
-	 * @throws MemoryAccessException
-	 *             If we find bytes but can't read them
 	 */
 	private void searchMemoryForEncodings(
 			Map<AssemblyPatternBlock, Set<WildOperandInfo>> encodings,
@@ -274,12 +264,11 @@ public class FindInstructionWithWildcard extends GhidraScript {
 	 * NOTE: This is certainly not the highest performance way to do this, but it is reasonably
 	 * simple and shows what is possible.
 	 * 
-	 * @param matchAddress
+	 * @param matchAddress The address where our search hit occurred
-	 *            The address where our search hit occurred
+	 * @param matchData The bytes found at matchAddress. Must include the entire matching
-	 * @param matchData
+	 *            instruction!
-	 *            The bytes found at matchAddress. Must include the entire matching instruction!
+	 * @param allValidResolvedPatterns All resolved patterns which were searched from (used to find
-	 * @param allValidResolvedPatterns
+	 *            wildcard information)
-	 *            All resolved patterns which were searched from (used to find wildcard information)
 	 */
 	private void printSearchHitInfo(Address matchAddress, byte[] matchData,
 			List<WildAssemblyResolvedPatterns> allValidResolvedPatterns) {
@@ -321,8 +310,7 @@ public class FindInstructionWithWildcard extends GhidraScript {
 	 * Return all items from {@code results} which are instances of
 	 * {@link WildAssemblyResolvedPatterns}
 	 * 
-	 * @param results
+	 * @param results The results to return {@link WildAssemblyResolvePatterns} from
-	 *            The results to return {@link WildAssemblyResolvePatterns} from
 	 * @return All {@link WildAssemblyResolvedPatterns} which were found in the input
 	 */
 	private List<WildAssemblyResolvedPatterns> getValidResults(AssemblyResolutionResults results) {

Ghidra/Features/WildcardAssembler/ghidra_scripts/WildSleighAssemblerInfo.java

@@ -24,7 +24,6 @@
 // See the "FindInstructionWithWildcard" script for another example of using the WildSleighAssembler
 // @category Examples
 
-import java.util.Arrays;
 import java.util.Collection;
 import java.util.List;
 import java.util.stream.Collectors;
@@ -34,16 +33,17 @@ import ghidra.app.plugin.assembler.sleigh.parse.AssemblyParseResult;
 import ghidra.app.plugin.assembler.sleigh.sem.AssemblyResolution;
 import ghidra.app.plugin.processors.sleigh.SleighLanguage;
 import ghidra.app.script.GhidraScript;
-import ghidra.asm.wild.WildOperandInfo;
+import ghidra.asm.wild.*;
-import ghidra.asm.wild.WildSleighAssembler;
-import ghidra.asm.wild.WildSleighAssemblerBuilder;
 import ghidra.asm.wild.sem.WildAssemblyResolvedPatterns;
 
 public class WildSleighAssemblerInfo extends GhidraScript {
 
-	List<String> sampleInstructions =
+	List<String> sampleInstructions = List.of(
-		Arrays.asList("MOV EAX,`Q1`", "MOV RDI,qword ptr [`Q1` + -0x30]", "Custom");
+		"MOV EAX,`Q1`",
+		"MOV RDI,qword ptr [`Q1` + -0x30]",
+		"Custom");
 
+	@Override
 	public void run() throws Exception {
 
 		String instruction = askChoice("Instruction to assemble", "Assemble this instruction:",
@@ -61,8 +61,8 @@ public class WildSleighAssemblerInfo extends GhidraScript {
 	/**
 	 * Use a {@link WildSleighAssembler} to assemble the given {@code wildcardedInstruction}
 	 * 
-	 * @param wildcardedInstruction
+	 * @param wildcardedInstruction String of the instruction to assemble, possibly including a
-	 *            String of the instruction to assemble, possibly including a wildcard
+	 *            wildcard
 	 * @return All AssemblyParseResult produced from the given input
 	 */
 	private List<AssemblyResolution> getAllAssemblyResolutions(
@@ -74,10 +74,10 @@ public class WildSleighAssemblerInfo extends GhidraScript {
 		// correct architecture.
 		if (sampleInstructions.contains(wildcardedInstruction) &&
 			!language.getLanguageID().toString().equals("x86:LE:64:default")) {
-			popup(
+			popup("""
-				"The current program is not a \"x86:LE:64:default\" binary that the example was " +
+					The current program is not a \"x86:LE:64:default\" binary that the example was \
-					"designed for. This script will continue and try anyway, but the results might " +
+					designed for. This script will continue and try anyway, but the results might \
-					"not be as expected. Retry with a custom instruction in your architecture!");
+					not be as expected. Retry with a custom instruction in your architecture!""");
 		}
 
 		// Create a WildSleighAssembler that we'll use to assemble our wildcard-included instruction
@@ -123,8 +123,7 @@ public class WildSleighAssemblerInfo extends GhidraScript {
 		}
 
 		if (errorCount > 0) {
-			println(
+			println("Additionally, " + errorCount +
-				"Additionally " + errorCount +
 				" non-WildAssemblyResolvedPatterns were not printed");
 
 		}
@@ -134,8 +133,7 @@ public class WildSleighAssemblerInfo extends GhidraScript {
 	 * Print information about a single {@link WildAssemblyResolvedPatterns}, including information
 	 * about each of its wildcards.
 	 * 
-	 * @param x
+	 * @param x The value to print information about.
-	 *            The value to print information about.
 	 */
 	private void printWildAssemblyResolvedPatterns(WildAssemblyResolvedPatterns x) {
 		println("Instruction bits (including wildcard values): " + x.getInstruction());

Ghidra/Features/WildcardAssembler/src/main/help/help/topics/WildcardAssemblerModule/Wildcard_Assembler.html

@@ -2,6 +2,8 @@
 
 <HTML>
   <HEAD>
+    <META name="generator" content=
+    "HTML Tidy for Java (vers. 2009-12-01), see jtidy.sourceforge.net">
     <META http-equiv="Content-Language" content="en-us">
     <META http-equiv="Content-Type" content="text/html; charset=windows-1252">
 
@@ -13,84 +15,93 @@
     <H1><A name="Wildcard_Assembler_Module"></A>Wildcard Assembler Module</H1>
 
     <BLOCKQUOTE>
+      <P><B>This feature is currently only available as an API for Ghidra scripts and plugins. For
+      an example of how to use the API, see the FindInstructionWithWildcard and
+      WildSleighAssemblerInfo scripts in the Script Manager.</B></P>
 
-      <P><B>This feature is currently only available as an API for Ghidra
+      <P>The <I>Wildcard Assembler</I> extends Ghidra's assembler to enable assembling instructions
-      scripts and plugins. For an example of how to use the API, see the
+      with specific tokens replaced with wildcards.</P>
-      FindInstructionWithWildcard and WildSleighAssemblerInfo scripts in the
-      Script Manager.</B></P>
 
-      <P>The <I>Wildcard Assembler</I> extends Ghidra's assembler to enable
+      <P>This assembler will return metadata for each wildcard in an assembled instruction. This
-      assembling instructions with specific tokens replaced with wildcards.</P>
+      metadata includes details of which specific bits of an assembled instruction are used to
-
+      derive the value of the wildcarded token and the expression used to derive the value.</P>
-      <p>This assembler will return metadata for each wildcard in an assembled
-      instruction. This metadata includes details of which specific bits of an
-      assembled instruction are used to derive the value of the wildcarded token
-      and the expression used to derive the value.</p>
 
       <H2>Wildcard Syntax</H2>
 
-      <P>Wildcards in instructions are specified by replacing the
+      <P>Wildcards in instructions are specified by replacing the to-be-wildcarded token with a
-      to-be-wildcarded token with a wildcard name surrounded by backticks (e.g.
+      wildcard name surrounded by backticks (e.g. <CODE>`Q1`</CODE> where Q1 is an arbitrary
-      <CODE>`Q1`</CODE> where Q1 is an arbitrary wildcard name) and passing the
+      wildcard name) and passing the entire instruction to the Wildcard Assembler.</P>
-      entire instruction to the Wildcard Assembler.</P>
 
-      <P>By default, the Wildcard Assembler will return metadata about all
+      <P>By default, the Wildcard Assembler will return metadata about all possible values that a
-      possible values that a wildcarded token could take and all the encodings
+      wildcarded token could take and all the encodings of all these values. This behavior can be
-      of all these values. This behavior can be limited by filtering the
+      limited by filtering the wildcard by appending specific syntax after the wildcard name:</P>
-      wildcard by appending specific syntax after the wildcard name:</P>
 
       <UL>
-        <LI><B>Numeric Filter:</B>
+        <LI>
+          <B>Numeric Filter:</B> 
+
           <UL>
-            <LI>Appending <CODE>[..]</CODE> will constrain the wildcarded token
+            <LI>Appending <CODE>[..]</CODE> e.g., <CODE>MOV RAX, `Q1[..]`</CODE>, will constrain
-            to only numeric values (and not registers or other strings).</LI>
+            the wildcarded token to only numeric values (and not registers or other strings).</LI>
-            <LI>Appending <CODE>[0x0..0x100]</CODE> (where 0x0 and 0x100 are
+
-            arbitrary hexadecimal values with the smaller number first) will
+            <LI>Appending <CODE>[0x0..0x100]</CODE> (where 0x0 and 0x100 are arbitrary hexadecimal
-            constrain the wildcarded token to only numeric values between the
+            values with the smaller number first) will constrain the wildcarded token to only
-            two given values. This can be used to ensure that the returned
+            numeric values between the two given values. This can be used to ensure that the
-            encodings can hold values of a desired size. Multiple non-contiguous
+            returned encodings can hold values of a desired size. Multiple non-contiguous ranges
-            ranges can be specified by separating them with commas (e.g.
+            can be specified by separating them with commas (e.g.
-            <CODE>[0x0..0x5,0x1000-0x4000]</CODE>)</LI>
+            <CODE>[0x0..0x5,0x1000..0x4000]</CODE>)</LI>
           </UL>
         </LI>
-          <LI><B>Regex Filter:</B>
+
+        <LI>
+          <B>Regex Filter:</B> 
+
           <UL>
-              <LI>Appending <CODE>/ABCD</CODE> where ABCD is an arbitrary
+            <LI>Appending <CODE>/ABCD</CODE> where ABCD is an arbitrary regular expression will
-              regular expression will constrain the wildcarded token to only be
+            constrain the wildcarded token to only be string tokens matching the given regular
-              string tokens matching the given regular expression. This is most
+            expression. This is most likely used for filtering register names; for example
-              likely used for filtering register names; for example appending
+            appending <CODE>/(sp)|(lr)</CODE> to a wildcard in a register position in ARM assembly
-              <CODE>/(sp)|(lr)</CODE> to a wildcard in a register position in
+            will limit the wildcard results to only encodings using the <CODE>sp</CODE> or
-              ARM assembly will limit the wildcard results to only encodings
+            <CODE>lr</CODE> registers in that position.</LI>
-              using the <CODE>sp</CODE> or <CODE>lr</CODE> registers in that
-              position.</LI>
           </UL>
         </LI>
       </UL>
 
-      <P>Normally a wildcard will only match a single token. To allow a single
+      <P>Normally a wildcard will only match a single token. For example, in a x86:LE:32:default
-      wildcard to match multiple related tokens: precede the wildcard name with a
+      binary:</P>
-      <CODE>!</CODE> character. For example, in a x86:LE:32:default binary:</P>
+
       <BLOCKQUOTE>
         <DL>
           <DT>No wildcard:</DT>
+
           <DD><CODE>MOVSD.REP ES:EDI,ESI</CODE></DD>
 
           <DT>Single token:</DT>
+
           <DD><CODE>MOVSD.REP `Q1`:EDI,ESI</CODE></DD>
 
           <DT>Single token:</DT>
+
           <DD><CODE>MOVSD.REP ES:`Q2`,ESI</CODE></DD>
+        </DL>
+      </BLOCKQUOTE>
+
+      <P>To allow a single wildcard to match multiple related tokens: precede the wildcard name
+      with a <CODE>!</CODE> character:</P>
+
+      <BLOCKQUOTE>
+        <DL>
+          <DT>Multi-token:</DT>
+
+          <DD><CODE>MOVSD.REP `!Q4`,ESI</CODE></DD>
 
           <DT>Single token (Does <I>NOT</I> assemble):</DT>
-          <DD><CODE>MOVSD.REP `Q3`,ESI</CODE></DD>
 
-          <DT>Multi-token:</DT>
+          <DD><CODE>MOVSD.REP `Q3`,ESI</CODE></DD>
-          <DD><CODE>MOVSD.REP `!Q4`,ESI</CODE></DD>
         </DL>
       </BLOCKQUOTE>
 
       <P class="providedbyplugin">Provided by: <I>Wildcard Assembler Module</I></P>
-
     </BLOCKQUOTE>
   </BODY>
 </HTML>

Ghidra/Features/WildcardAssembler/src/main/java/ghidra/asm/wild/WildOperandInfo.java

@@ -21,9 +21,25 @@ import ghidra.app.plugin.assembler.sleigh.sem.AssemblyConstructorSemantic;
 import ghidra.app.plugin.assembler.sleigh.sem.AssemblyPatternBlock;
 import ghidra.app.plugin.processors.sleigh.expression.PatternExpression;
 
+/**
+ * Information about an operand that was matched to a wildcard
+ * 
+ * @param wildcard the name of the wildcard that matched the operand
+ * @param path the hierarchy of Sleigh constructors leading to the operand
+ * @param location the bit pattern giving the location of the operand's field(s) in the machine
+ *            instruction
+ * @param expression the expression describing how to encode the operand in the field(s)
+ * @param choice if applicable, the value encoded in the result containing this information
+ */
 public record WildOperandInfo(String wildcard, List<AssemblyConstructorSemantic> path,
 		AssemblyPatternBlock location, PatternExpression expression, Object choice) {
 
+	/**
+	 * Copy this wildcard info, but with an increased shift amount
+	 * 
+	 * @param amt the number of bits to shift (right)
+	 * @return the copy
+	 */
 	public WildOperandInfo shift(int amt) {
 		return new WildOperandInfo(wildcard, path, location.shift(amt), expression, choice);
 	}

Ghidra/Features/WildcardAssembler/src/main/java/ghidra/asm/wild/WildSleighAssembler.java

@@ -26,6 +26,12 @@ import ghidra.asm.wild.sem.WildAssemblyTreeResolver;
 import ghidra.program.model.address.Address;
 import ghidra.program.model.listing.Program;
 
+/**
+ * An assembler implementation that allows for wildcard operands
+ * 
+ * <p>
+ * Construct these using {@link WildSleighAssemblerBuilder}. 
+ */
 public class WildSleighAssembler extends AbstractSleighAssembler<WildAssemblyResolvedPatterns> {
 
 	protected WildSleighAssembler(

Ghidra/Features/WildcardAssembler/src/main/java/ghidra/asm/wild/WildSleighAssemblerBuilder.java

@@ -19,6 +19,7 @@ import java.util.*;
 
 import ghidra.app.plugin.assembler.AssemblySelector;
 import ghidra.app.plugin.assembler.sleigh.AbstractSleighAssemblerBuilder;
+import ghidra.app.plugin.assembler.sleigh.SleighAssemblerBuilder;
 import ghidra.app.plugin.assembler.sleigh.grammars.AssemblyGrammar;
 import ghidra.app.plugin.assembler.sleigh.grammars.AssemblySentential;
 import ghidra.app.plugin.assembler.sleigh.sem.AbstractAssemblyResolutionFactory;
@@ -33,11 +34,32 @@ import ghidra.asm.wild.sem.WildAssemblyResolvedPatterns;
 import ghidra.asm.wild.symbol.*;
 import ghidra.program.model.listing.Program;
 
+/**
+ * The builder for wildcard-enabled assemblers.
+ * 
+ * <p>
+ * Ideally, only one of these is created and cached per language, to save on the cost of building
+ * the assembler. However, if heap space needs to be freed up, then the builder must be disposed.
+ * 
+ * <p>
+ * This is based on the same abstract class as {@link SleighAssemblerBuilder}. See its documentation
+ * for more information.
+ */
 public class WildSleighAssemblerBuilder
 		extends AbstractSleighAssemblerBuilder<WildAssemblyResolvedPatterns, WildSleighAssembler> {
 
 	protected final Map<AssemblySymbol, AssemblyNonTerminal> wildNTs = new HashMap<>();
 
+	/**
+	 * Construct a builder for the given language
+	 * 
+	 * <p>
+	 * Once a builder is prepared for the given language, it can be used to build an assembler for
+	 * any number of programs using that same language. Clients should take advantage of this to
+	 * avoid re-incurring the steep cost of constructing an assembler for the same language.
+	 * 
+	 * @param lang the language
+	 */
 	public WildSleighAssemblerBuilder(SleighLanguage lang) {
 		super(lang);
 	}

Ghidra/Features/WildcardAssembler/src/main/java/ghidra/asm/wild/sem/WildAssemblyFixedNumericStateGenerator.java

@@ -20,7 +20,6 @@ import java.util.stream.Stream;
 import ghidra.app.plugin.assembler.sleigh.sem.*;
 import ghidra.app.plugin.processors.sleigh.symbol.OperandSymbol;
 import ghidra.asm.wild.tree.WildAssemblyParseToken;
-import ghidra.asm.wild.tree.WildAssemblyParseToken.RegexWildcard;
 
 public class WildAssemblyFixedNumericStateGenerator
 		extends AbstractAssemblyStateGenerator<WildAssemblyParseToken> {

Ghidra/Features/WildcardAssembler/src/main/java/ghidra/asm/wild/sem/WildAssemblyResolvedPatterns.java

@@ -22,10 +22,28 @@ import ghidra.app.plugin.assembler.sleigh.sem.*;
 import ghidra.app.plugin.processors.sleigh.expression.PatternExpression;
 import ghidra.asm.wild.WildOperandInfo;
 
+/**
+ * The result of assembling an instruction with the wildcard assembler
+ */
 public interface WildAssemblyResolvedPatterns extends AssemblyResolvedPatterns {
 
+	/**
+	 * The information for wildcarded operands in this instruction
+	 * 
+	 * @return the set of information
+	 */
 	Set<WildOperandInfo> getOperandInfo();
 
+	/**
+	 * Create a copy of this result with added wilcard information
+	 * 
+	 * @param wildcard see {@link WildOperandInfo}
+	 * @param path see {@link WildOperandInfo}
+	 * @param location see {@link WildOperandInfo}
+	 * @param expression see {@link WildOperandInfo}
+	 * @param choice see {@link WildOperandInfo}
+	 * @return the copy
+	 */
 	WildAssemblyResolvedPatterns withWildInfo(String wildcard,
 			List<AssemblyConstructorSemantic> path, AssemblyPatternBlock location,
 			PatternExpression expression, Object choice);

Ghidra/Framework/SoftwareModeling/src/main/java/ghidra/app/plugin/assembler/sleigh/sem/AssemblyPatternBlock.java

@@ -157,6 +157,7 @@ public class AssemblyPatternBlock implements Comparable<AssemblyPatternBlock> {
 	 * Convert a block from a disjoint pattern into an assembly pattern block
 	 * 
 	 * @param pat the pattern to convert
+	 * @param minLen the minimum byte length of the block
 	 * @param context true to select the context block, false to select the instruction block
 	 * @return the converted pattern block
 	 */