fix unit test to not include invalid surrogate

Author: milaGGL

packages/firestore/src/util/misc.ts

@@ -77,7 +77,8 @@ export interface Equatable<T> {
 
 /** Compare strings in UTF-8 encoded byte order */
 export function compareUtf8Strings(left: string, right: string): number {
-  for (let i = 0; i < left.length && i < right.length; i++) {
+  let i = 0;
+  while (i < left.length && i < right.length) {
     const leftCodePoint = left.codePointAt(i)!;
     const rightCodePoint = right.codePointAt(i)!;
 
@@ -89,7 +90,7 @@ export function compareUtf8Strings(left: string, right: string): number {
         // Lazy instantiate TextEncoder
         const encoder = newTextEncoder();
 
-        // Substring and do UTF-8 encoded byte comparison
+        // UTF-8 encode the character at index i for byte comparison.
         const leftBytes = encoder.encode(getUtf8SafeSubstring(left, i));
         const rightBytes = encoder.encode(getUtf8SafeSubstring(right, i));
         for (
@@ -102,8 +103,17 @@ export function compareUtf8Strings(left: string, right: string): number {
             return comp;
           }
         }
+        // EXTREMELY RARE CASE: Code points differ, but their UTF-8 byte
+        // representations are identical. This can happen with malformed input
+        // (invalid surrogate pairs). The backend also actively prevents invalid
+        // surrogates as INVALID_ARGUMENT errors, so we almost never receive
+        // invalid strings from backend.
+        // Fallback to code point comparison for graceful handling.
+        return primitiveComparator(leftCodePoint, rightCodePoint);
       }
     }
+    // Increment by 2 for surrogate pairs, 1 otherwise
+    i += leftCodePoint > 0xffff ? 2 : 1;
   }
 
   // Compare lengths if all characters are equal

packages/firestore/test/unit/util/misc.test.ts

@@ -73,22 +73,6 @@ class StringGenerator {
   private static readonly DEFAULT_SURROGATE_PAIR_PROBABILITY = 0.33;
   private static readonly DEFAULT_MAX_LENGTH = 20;
 
-  // The first Unicode code point that is in the basic multilingual plane ("BMP") and,
-  // therefore requires 1 UTF-16 code unit to be represented in UTF-16.
-  private static readonly MIN_BMP_CODE_POINT = 0x00000000;
-
-  // The last Unicode code point that is in the basic multilingual plane ("BMP") and,
-  // therefore requires 1 UTF-16 code unit to be represented in UTF-16.
-  private static readonly MAX_BMP_CODE_POINT = 0x0000ffff;
-
-  // The first Unicode code point that is outside of the basic multilingual plane ("BMP") and,
-  // therefore requires 2 UTF-16 code units, a surrogate pair, to be represented in UTF-16.
-  private static readonly MIN_SUPPLEMENTARY_CODE_POINT = 0x00010000;
-
-  // The last Unicode code point that is outside of the basic multilingual plane ("BMP") and,
-  // therefore requires 2 UTF-16 code units, a surrogate pair, to be represented in UTF-16.
-  private static readonly MAX_SUPPLEMENTARY_CODE_POINT = 0x0010ffff;
-
   private readonly rnd: Random;
   private readonly surrogatePairProbability: number;
   private readonly maxLength: number;
@@ -198,31 +182,19 @@ class StringGenerator {
   }
 
   private nextNonSurrogateCodePoint(): number {
-    return this.nextCodePointRange(
-      StringGenerator.MIN_BMP_CODE_POINT,
-      StringGenerator.MAX_BMP_CODE_POINT
-    );
+    let codePoint;
+    do {
+      codePoint = this.nextCodePointRange(0, 0xffff); // BMP range
+    } while (codePoint >= 0xd800 && codePoint <= 0xdfff); // Exclude surrogate range
+
+    return codePoint;
   }
 
   private nextCodePointRange(min: number, max: number): number {
     const rangeSize = max - min + 1;
     const offset = this.rnd.nextInt(rangeSize);
     return min + offset;
   }
-
-  // private nextCodePointRange(min: number, max: number, expectedCharCount: number): number {
-  //   const rangeSize = max - min;
-  //   const offset = this.rnd.nextInt(rangeSize);
-  //   const codePoint = min + offset;
-  //   if (String.fromCharCode(codePoint).length !== expectedCharCount) {
-  //     throw new Error(
-  //       `internal error vqgqnxcy97: Character.charCount(${codePoint}) returned ${
-  //         String.fromCharCode(codePoint).length
-  //       }, but expected ${expectedCharCount}`,
-  //     );
-  //   }
-  //   return codePoint;
-  // }
 }
 
 class Random {