Implement Format 31c (const-string/jumbo) Dalvik bytecode parser

DALVIK_MISSING_PARSERS.md

@@ -7,30 +7,10 @@ Reference: [Android Dalvik Bytecode Specification](https://source.android.com/do
 ## Implementation Status
 
 **Total formats:** 32  
-**Implemented:** 23  
-**Missing:** 9
+**Implemented:** 24  
+**Missing:** 8
 
-## Missing Format Parsers Checklist
-
-### High Priority Formats
-
-- [x] **Format 11n** (const/4) - ✅ IMPLEMENTED
-  - **Description:** vA, #+B - Immediate constant with 4-bit register and 4-bit signed immediate value
-  - **Size:** 2 bytes (1 unit)
-  - **Syntax:** `AA|op BBBB`
-  - **Use case:** Small constant values (e.g., `const/4`)
-
-- [x] **Format 51l** (const-wide) - ✅ IMPLEMENTED
-  - **Description:** vAA, #+BBBBBBBBBBBBBBBB - 64-bit immediate constant
-  - **Size:** 10 bytes (5 units)
-  - **Syntax:** `AA|op BBBBlo BBBBhi`
-  - **Use case:** Wide (64-bit) constant values
-
-- [ ] **Format 31c** (const-string/jumbo)
-  - **Description:** vAA, thing@BBBBBBBB - Constant pool index with 8-bit register
-  - **Size:** 6 bytes (3 units)
-  - **Syntax:** `AA|op BBBBlo BBBBhi`
-  - **Use case:** Large constant pool references (> 65535 items)
+## Missing Format Parsers
 
 ### Method Invocation Formats (Deprecated/Optimized)
 
@@ -88,22 +68,17 @@ Reference: [Android Dalvik Bytecode Specification](https://source.android.com/do
   - **Syntax:** `AA|op BBBB CCCC HHHH`
   - **Use case:** Range version of polymorphic invocation
 
-## Implementation Notes
-
-### Priority Recommendations
+## Priority Recommendations
 
-1. **Immediate Priority:**
-   - Format 31c - Needed for large DEX files with many string/type references
-
-2. **Medium Priority:**
+1. **Medium Priority:**
    - Format 45cc and 4rcc - Required for Android 8.0+ features (method handles)
    - Format 20bc - Needed for complete verification error handling
 
-3. **Low Priority (Deprecated):**
+2. **Low Priority (Deprecated):**
    - Formats 35mi, 35ms, 3rmi, 3rms, 22cs - These are deprecated optimization formats
    - Only implement if parsing legacy/optimized DEX files is required
 
-### Implementation Guidelines
+## Implementation Guidelines
 
 For each format parser, the following should be implemented:
 
@@ -115,66 +90,14 @@ For each format parser, the following should be implemented:
 
 ### Example Implementation Pattern
 
-```typescript
-type DalvikBytecodeFormat11n = {
-    value: number;
-    registers: number[];
-};
-
-export const dalvikBytecodeFormat11nParser: Parser<DalvikBytecodeFormat11n, Uint8Array> = promiseCompose(
-    nibblesParser,
-    ([value, register0]) => ({
-        value: value << 28 >> 28, // Sign extend 4-bit value
-        registers: [register0],
-    }),
-);
-```
+See existing parsers in `src/dalvikBytecodeParser/formatParsers.ts` for reference.
 
 ## References
 
 - [Android Dalvik Bytecode Format](https://source.android.com/docs/core/runtime/dalvik-bytecode)
 - [Dalvik Instruction Formats](https://source.android.com/docs/core/runtime/instruction-formats)
 - [DEX File Format Specification](https://source.android.com/docs/core/runtime/dex-format)
 
-## Current Implementation Status
-
-### Implemented Formats (23/32)
-
-- ✓ Format 10t
-- ✓ Format 10x
-- ✓ Format 11n
-- ✓ Format 11x
-- ✓ Format 12x
-- ✓ Format 20t
-- ✓ Format 21c
-- ✓ Format 21h
-- ✓ Format 21s
-- ✓ Format 21t
-- ✓ Format 22b
-- ✓ Format 22c
-- ✓ Format 22s
-- ✓ Format 22t
-- ✓ Format 22x
-- ✓ Format 23x
-- ✓ Format 30t
-- ✓ Format 31i
-- ✓ Format 31t
-- ✓ Format 32x
-- ✓ Format 35c
-- ✓ Format 3rc
-- ✓ Format 51l
-
-### Not Implemented Formats (9/32)
-- ✗ Format 20bc
-- ✗ Format 22cs
-- ✗ Format 31c
-- ✗ Format 35mi
-- ✗ Format 35ms
-- ✗ Format 3rmi
-- ✗ Format 3rms
-- ✗ Format 45cc
-- ✗ Format 4rcc
-
 ---
 
 *Last updated: 2025-11-09*

src/dalvikBytecodeParser.ts

@@ -8,6 +8,7 @@ import {
 	createDalvikBytecodeFormat22sParser,
 	createDalvikBytecodeFormat22tParser,
 	dalvikBytecodeFormat23xParser,
+	createDalvikBytecodeFormat31cParser,
 	dalvikBytecodeFormat31iParser,
 	dalvikBytecodeFormat31tParser,
 	createDalvikBytecodeFormat35cParser,
@@ -1605,6 +1606,28 @@ const dalvikBytecodeOperationConstStringParser: Parser<DalvikBytecodeOperationCo
 
 setParserName(dalvikBytecodeOperationConstStringParser, 'dalvikBytecodeOperationConstStringParser');
 
+type DalvikBytecodeOperationConstStringJumbo = {
+	operation: 'const-string/jumbo';
+	stringIndex: IndexIntoStringIds;
+	registers: number[];
+};
+
+const dalvikBytecodeOperationConstStringJumboParser: Parser<DalvikBytecodeOperationConstStringJumbo, Uint8Array> = promiseCompose(
+	createTupleParser([
+		createExactElementParser(0x1b),
+		createDalvikBytecodeFormat31cParser({
+			isoIndex: isoIndexIntoStringIds,
+		}),
+	]),
+	([ _opcode, { index, registers } ]) => ({
+		operation: 'const-string/jumbo',
+		stringIndex: index,
+		registers,
+	}),
+);
+
+setParserName(dalvikBytecodeOperationConstStringJumboParser, 'dalvikBytecodeOperationConstStringJumboParser');
+
 type DalvikBytecodeOperationConstMethodHandle = {
 	operation: 'const-method-handle';
 	methodIndex: IndexIntoMethodIds;
@@ -2195,6 +2218,7 @@ const dalvikBytecodeOperationParser: Parser<DalvikBytecodeOperation | undefined,
 			dalvikBytecodeOperationStaticFieldParser,
 
 			dalvikBytecodeOperationConstStringParser,
+			dalvikBytecodeOperationConstStringJumboParser,
 			dalvikBytecodeOperationConstMethodHandleParser,
 			dalvikBytecodeOperationConstClassParser,
 

src/dalvikBytecodeParser/formatParsers.ts

@@ -1,5 +1,5 @@
 import { Iso } from "monocle-ts";
-import { byteParser, intParser, longParser, shortParser, ubyteParser, ushortParser } from "../dalvikExecutableParser/typeParsers.js";
+import { byteParser, intParser, longParser, shortParser, ubyteParser, uintParser, ushortParser } from "../dalvikExecutableParser/typeParsers.js";
 import { createElementParser } from "../elementParser.js";
 import { Parser, setParserName } from "../parser.js";
 import { promiseCompose } from "../promiseCompose.js";
@@ -366,6 +366,31 @@ export const dalvikBytecodeFormat31iParser: Parser<DalvikBytecodeFormat31i, Uint
 	}),
 );
 
+type DalvikBytecodeFormat31c<Index> = {
+	index: Index;
+	registers: number[];
+};
+
+export const createDalvikBytecodeFormat31cParser = <Index>({
+	isoIndex,
+}: {
+	isoIndex: Iso<Index, number>;
+}): Parser<DalvikBytecodeFormat31c<Index>, Uint8Array> => promiseCompose(
+	createTupleParser([
+		ubyteParser,
+		uintParser,
+	]),
+	([
+		register0,
+		index,
+	]) => ({
+		index: isoIndex.wrap(index),
+		registers: [
+			register0,
+		],
+	}),
+);
+
 type DalvikBytecodeFormat31t = {
 	branchOffset: number;
 	registers: number[];