From 759febdf533acba401bc1e0a758328e0857e727c Mon Sep 17 00:00:00 2001
From: Philip Le Riche <7701190+p-leriche@users.noreply.github.com>
Date: Sat, 7 Mar 2026 19:16:40 +0000
Subject: [PATCH] Add error handling for Unicode characters beyond Latin-1 and
test for Latin-1 accepted
---
src/core/operations/TextIntegerConverter.mjs | 11 ++++++++++-
.../operations/tests/TextIntegerConverter.mjs | 19 +++++++++++++++++++
2 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/src/core/operations/TextIntegerConverter.mjs b/src/core/operations/TextIntegerConverter.mjs
index e7ff4547..4e740100 100644
--- a/src/core/operations/TextIntegerConverter.mjs
+++ b/src/core/operations/TextIntegerConverter.mjs
@@ -5,6 +5,7 @@
*/
import Operation from "../Operation.mjs";
+import OperationError from "../errors/OperationError.mjs";
/* ---------- helper functions ---------- */
@@ -17,6 +18,11 @@ function textToBigInt(text) {
let result = 0n;
for (let i = 0; i < text.length; i++) {
const charCode = BigInt(text.charCodeAt(i));
+ if (charCode > 255n) {
+ throw new OperationError(
+ `Character at position ${i} exceeds Latin-1 range (0-255).\n` +
+ "Only ASCII and Latin-1 characters are supported.");
+ }
result = (result << 8n) | charCode;
}
return result;
@@ -58,7 +64,10 @@ class TextIntegerConverter extends Operation {
"Input format detection:
" +
"Decimal: digits 0-9 only
" +
"Hexadecimal: 0x... prefix
" +
- "Quoted or unquoted text: treated as string
" ;
+ "Quoted or unquoted text: treated as string
" +
+ "Character limitations:
" +
+ "Text input may only contain ASCII and Latin-1 characters (code point < 256).
" +
+ "Multi-byte Unicode characters will generate an error.
." ;
this.infoURL = "https://wikipedia.org/wiki/Endianness";
this.inputType = "string";
this.outputType = "string";
diff --git a/tests/operations/tests/TextIntegerConverter.mjs b/tests/operations/tests/TextIntegerConverter.mjs
index 17466564..d05aa24a 100644
--- a/tests/operations/tests/TextIntegerConverter.mjs
+++ b/tests/operations/tests/TextIntegerConverter.mjs
@@ -94,6 +94,25 @@ TestRegister.addTests([
},
],
},
+ {
+ name: "Text-Integer Conversion implicit round trip string-string Latin-1",
+ input: "U+00FF",
+ expectedOutput: "U+00FF", // U+00FF (Latin small letter y with diaeresis)
+ recipeConfig: [
+ {
+ op: "Unescape Unicode Characters",
+ args: ["U+"],
+ },
+ {
+ op: "Text-Integer Conversion",
+ args: ["String"],
+ },
+ {
+ op: "Escape Unicode Characters",
+ args: ["U+", false, 4, true],
+ },
+ ],
+ },
{
name: "Text-Integer Conversion unquoted text to decimal",
input: "Hi",