Merge pull request #156 from ethdebug/pointer-template-rename

Add $concat operator to pointer expression schema

Author: gnidan

packages/format/src/types/pointer/pointer.ts

@@ -225,6 +225,7 @@ export namespace Pointer {
     | Expression.Lookup
     | Expression.Read
     | Expression.Keccak256
+    | Expression.Concat
     | Expression.Resize;
 
   export const isExpression = (value: unknown): value is Expression =>
@@ -236,6 +237,7 @@ export namespace Pointer {
       Expression.isLookup,
       Expression.isRead,
       Expression.isKeccak256,
+      Expression.isConcat,
       Expression.isResize
     ].some(guard => guard(value));
 
@@ -394,6 +396,12 @@ export namespace Pointer {
     export const isKeccak256 =
       makeIsOperation<"$keccak256", Keccak256>("$keccak256", isOperands);
 
+    export interface Concat {
+      $concat: Expression[];
+    }
+    export const isConcat =
+      makeIsOperation<"$concat", Concat>("$concat", isOperands);
+
     export type Resize<N extends number = number> =
       | Resize.ToNumber<N>
       | Resize.ToWordsize;

packages/pointers/src/evaluate.test.ts

@@ -127,6 +127,69 @@ describe("evaluate", () => {
       .toEqual(Data.fromUint(42n % 0x1fn));
   });
 
+  describe("evaluates concat expressions", () => {
+    it("concatenates hex literals", async () => {
+      const expression: Pointer.Expression = {
+        $concat: ["0x00", "0x00"]
+      };
+      expect(await evaluate(expression, options))
+        .toEqual(Data.fromHex("0x0000"));
+    });
+
+    it("concatenates multiple values preserving byte widths", async () => {
+      const expression: Pointer.Expression = {
+        $concat: ["0xdead", "0xbeef"]
+      };
+      expect(await evaluate(expression, options))
+        .toEqual(Data.fromHex("0xdeadbeef"));
+    });
+
+    it("returns empty data for empty operand list", async () => {
+      const expression: Pointer.Expression = {
+        $concat: []
+      };
+      expect(await evaluate(expression, options))
+        .toEqual(Data.zero());
+    });
+
+    it("preserves single operand unchanged", async () => {
+      const expression: Pointer.Expression = {
+        $concat: ["0xabcdef"]
+      };
+      expect(await evaluate(expression, options))
+        .toEqual(Data.fromHex("0xabcdef"));
+    });
+
+    it("concatenates variables", async () => {
+      const expression: Pointer.Expression = {
+        $concat: ["foo", "bar"]
+      };
+      // foo = 0x2a (42), bar = 0x1f
+      expect(await evaluate(expression, options))
+        .toEqual(Data.fromHex("0x2a1f"));
+    });
+
+    it("concatenates nested expressions", async () => {
+      const expression: Pointer.Expression = {
+        $concat: [
+          { $sum: [1, 2] },  // 3 = 0x03
+          "0xff"
+        ]
+      };
+      expect(await evaluate(expression, options))
+        .toEqual(Data.fromHex("0x03ff"));
+    });
+
+    it("preserves leading zeros in hex literals", async () => {
+      const expression: Pointer.Expression = {
+        $concat: ["0x0001", "0x0002"]
+      };
+      const result = await evaluate(expression, options);
+      expect(result).toEqual(Data.fromHex("0x00010002"));
+      expect(result.length).toBe(4);
+    });
+  });
+
   // skipped because test does not perform proper padding
   it.skip("evaluates keccak256 expressions", async () => {
     const expression: Pointer.Expression = {

packages/pointers/src/evaluate.ts

@@ -58,6 +58,10 @@ export async function evaluate(
     return evaluateKeccak256(expression, options);
   }
 
+  if (Pointer.Expression.isConcat(expression)) {
+    return evaluateConcat(expression, options);
+  }
+
   if (Pointer.Expression.isResize(expression)) {
     return evaluateResize(expression, options);
   }
@@ -219,6 +223,17 @@ async function evaluateKeccak256(
   return hash;
 }
 
+async function evaluateConcat(
+  expression: Pointer.Expression.Concat,
+  options: EvaluateOptions
+): Promise<Data> {
+  const operands = await Promise.all(expression.$concat.map(
+    async expression => await evaluate(expression, options)
+  ));
+
+  return Data.zero().concat(...operands);
+}
+
 async function evaluateResize(
   expression: Pointer.Expression.Resize,
   options: EvaluateOptions

packages/web/docs/implementation-guides/pointers/evaluating-expressions.mdx

@@ -158,6 +158,18 @@ use of hashing to allocate persistent data.
     sourceFile => sourceFile.getFunction("evaluateKeccak256")
   } />
 
+## Evaluating concatenation
+
+Byte concatenation is straightforward: recursively evaluate the operands and
+join them together, preserving the byte width of each operand.
+
+<CodeListing
+  packageName="@ethdebug/pointers"
+  sourcePath="src/evaluate.ts"
+  extract={
+    sourceFile => sourceFile.getFunction("evaluateConcat")
+  } />
+
 ## Evaluating property lookups
 
 Pointer expressions can compose values taken from the properties of other,

packages/web/spec/pointer/expression.mdx

@@ -92,6 +92,21 @@ hash of the concatenation of bytes specified by the list.
   pointer="#/$defs/Keccak256"
   />
 
+## Bytes concatenation
+
+An expression can be an object of form `{ "$concat": [...] }`, indicating
+that the value of the expression is the concatenation of bytes from each
+value in the list. The byte width of each operand is preserved; no padding
+is added or removed between operands.
+
+This is useful for building composite byte sequences, for example when
+constructing storage slot keys or preparing data for hashing.
+
+<SchemaViewer
+  schema={{ id: "schema:ethdebug/format/pointer/expression" }}
+  pointer="#/$defs/Concat"
+  />
+
 ## Resize operations
 
 In certain situations, e.g. keccak256 hashes, it's crucially important to be

packages/web/src/schemas.ts

@@ -147,6 +147,10 @@ const pointerSchemaIndex: SchemaIndex = {
       title: "Keccak256 hash expression schema",
       anchor: "#keccak256-hashes"
     },
+    Concat: {
+      title: "Bytes concatenation schema",
+      anchor: "#bytes-concatenation"
+    },
     Resize: {
       title: "Resize operation schema",
       anchor: "#resize-operations"

schemas/pointer/expression.schema.yaml

@@ -13,6 +13,7 @@ oneOf:
   - $ref: "#/$defs/Lookup"
   - $ref: "#/$defs/Read"
   - $ref: "#/$defs/Keccak256"
+  - $ref: "#/$defs/Concat"
   - $ref: "#/$defs/Resize"
 
 $defs:
@@ -188,6 +189,32 @@ $defs:
           - 0
           - "0x00"
 
+  Concat:
+    title: Concatenate values
+    description: |
+      An object of the form `{ "$concat": [...values] }`, indicating that this
+      expression evaluates to the concatenation of bytes from each value.
+      The byte width of each operand is preserved; no padding is added or
+      removed between operands.
+    type: object
+    properties:
+      $concat:
+        title: Array of values to concatenate
+        type: array
+        items:
+          $ref: "schema:ethdebug/format/pointer/expression"
+    additionalProperties: false
+    required:
+      - $concat
+    examples:
+      - $concat:
+          - "0x00"
+          - "0x00"
+      - $concat:
+          - "0xdead"
+          - "0xbeef"
+      - $concat: []
+
   Resize:
     title: Resize data
     description: |