Merge pull request #4 from barrytra/bytes-to-utf8

added function bytes to Utf8
bitcoinjs · Apr 11, 2024 · bfe4c9e · bfe4c9e
2 parents c0a0a04 + 8449d4f
commit bfe4c9e
Show file tree

Hide file tree

Showing 8 changed files with 42 additions and 5 deletions.
diff --git a/src/cjs/browser.cjs b/src/cjs/browser.cjs
@@ -1,6 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.compare = exports.fromHex = exports.toHex = void 0;
+exports.compare = exports.fromHex = exports.toHex = exports.toUtf8 = void 0;
 const HEX_STRINGS = "0123456789abcdefABCDEF";
 const HEX_CODES = HEX_STRINGS.split("").map((c) => c.codePointAt(0));
 const HEX_CODEPOINTS = Array(256)
@@ -12,7 +12,11 @@ const HEX_CODEPOINTS = Array(256)
     return index < 0 ? undefined : index < 16 ? index : index - 6;
 });
 const ENCODER = new TextEncoder();
-const DECODER = new TextDecoder("ascii");
+const DECODER = new TextDecoder();
+function toUtf8(bytes) {
+    return DECODER.decode(bytes);
+}
+exports.toUtf8 = toUtf8;
 // There are two implementations.
 // One optimizes for length of the bytes, and uses TextDecoder.
 // One optimizes for iteration count, and appends strings.

diff --git a/src/cjs/index.cjs b/src/cjs/index.cjs
@@ -1,6 +1,10 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.compare = exports.fromHex = exports.toHex = void 0;
+exports.compare = exports.fromHex = exports.toHex = exports.toUtf8 = void 0;
+function toUtf8(bytes) {
+    return Buffer.from(bytes || []).toString();
+}
+exports.toUtf8 = toUtf8;
 function toHex(bytes) {
     return Buffer.from(bytes || []).toString("hex");
 }

diff --git a/src/cjs/index.d.ts b/src/cjs/index.d.ts
@@ -1,3 +1,4 @@
+export declare function toUtf8(bytes: Uint8Array): string;
 export declare function toHex(bytes: Uint8Array): string;
 export declare function fromHex(hexString: string): Uint8Array;
 export declare type CompareResult = -1 | 0 | 1;

diff --git a/src/mjs/browser.js b/src/mjs/browser.js
@@ -9,7 +9,10 @@ const HEX_CODEPOINTS = Array(256)
     return index < 0 ? undefined : index < 16 ? index : index - 6;
 });
 const ENCODER = new TextEncoder();
-const DECODER = new TextDecoder("ascii");
+const DECODER = new TextDecoder();
+export function toUtf8(bytes) {
+    return DECODER.decode(bytes);
+}
 // There are two implementations.
 // One optimizes for length of the bytes, and uses TextDecoder.
 // One optimizes for iteration count, and appends strings.

diff --git a/src/mjs/index.js b/src/mjs/index.js
@@ -1,3 +1,6 @@
+export function toUtf8(bytes) {
+    return Buffer.from(bytes || []).toString();
+}
 export function toHex(bytes) {
     return Buffer.from(bytes || []).toString("hex");
 }

diff --git a/ts_src/browser.ts b/ts_src/browser.ts
@@ -9,7 +9,11 @@ const HEX_CODEPOINTS: (number | undefined)[] = Array(256)
     return index < 0 ? undefined : index < 16 ? index : index - 6;
   });
 const ENCODER = new TextEncoder();
-const DECODER = new TextDecoder("ascii");
+const DECODER = new TextDecoder();
+
+export function toUtf8(bytes: Uint8Array): string {
+  return DECODER.decode(bytes);
+}
 
 // There are two implementations.
 // One optimizes for length of the bytes, and uses TextDecoder.

diff --git a/ts_src/index.ts b/ts_src/index.ts
@@ -1,3 +1,7 @@
+export function toUtf8(bytes: Uint8Array): string {
+  return Buffer.from(bytes || []).toString();
+}
+
 export function toHex(bytes: Uint8Array): string {
   return Buffer.from(bytes || []).toString("hex");
 }

diff --git a/ts_src/tests.spec.ts b/ts_src/tests.spec.ts
@@ -14,6 +14,14 @@ const bytes2Larger = f([0xff, 0x01, 0x00]);
 const bytes2LargerLeft = f([0x00, 0xff, 0x01]);
 const longBytes = new Uint8Array(513).fill(0xfa);
 const longHex = "fa".repeat(513);
+const bytes3 = f([0x21, 0x7e]);
+const utf8 = "!~";
+const longBytes2 = new Uint8Array(513).fill(0x61);
+const longUtf8 = "a".repeat(513);
+const testBytes = f([
+  227, 129, 147, 227, 130, 147, 227, 129, 171, 227, 129, 161, 227, 129, 175,
+]);
+const str = "こんにちは";
 
 const brokenHexes = [
   [" ff00", f([]), "leading space"],
@@ -39,6 +47,12 @@ describe(`Uint8Array tools`, () => {
         expect(tools.toHex(longBytes)).toEqual(longHex);
         expect((tools.toHex as any)()).toEqual("");
       });
+      it(`should output utf8 with toUtf8`, () => {
+        expect(tools.toUtf8(bytes3)).toEqual(utf8);
+        expect(tools.toUtf8(testBytes)).toEqual(str);
+        expect(tools.toUtf8(longBytes2)).toEqual(longUtf8);
+        expect((tools.toUtf8 as any)()).toEqual("");
+      });
       it(`should compare Uint8Arrays`, () => {
         expect(tools.compare(bytes, bytes2)).toBe(-1);
         expect(tools.compare(bytes, bytes)).toBe(0);