ICU-23264 Add isAvailable method to MeasureUnit for efficient unit validation

This new method checks if a specific unit is available for a given type and subtype, improving performance by avoiding the need to retrieve all available units. Updated parseMeasureUnitOption to utilize this method for better error handling when validating measure units.

Author: younies

icu4c/source/i18n/measunit.cpp

@@ -2729,6 +2729,28 @@ StringEnumeration* MeasureUnit::getAvailableTypes(UErrorCode &errorCode) {
     return result;
 }
 
+bool MeasureUnit::isAvailable(const char *type, const char *subtype, MeasureUnit &result) {
+    if (type == nullptr || subtype == nullptr) {
+        return false;
+    }
+    
+    // Find the type index using binary search
+    int32_t typeIdx = binarySearch(gTypes, 0, UPRV_LENGTHOF(gTypes), type);
+    if (typeIdx == -1) {
+        return false;  // Type not found
+    }
+    
+    // Find the subtype within the type's range using binary search
+    int32_t subtypeIdx = binarySearch(gSubTypes, gOffsets[typeIdx], gOffsets[typeIdx + 1], subtype);
+    if (subtypeIdx == -1) {
+        return false;  // Subtype not found
+    }
+    
+    // Create the MeasureUnit and return it
+    result.setTo(typeIdx, subtypeIdx - gOffsets[typeIdx]);
+    return true;
+}
+
 bool MeasureUnit::findBySubType(StringPiece subType, MeasureUnit* output) {
     // Sanity checking kCurrencyOffset and final entry in gOffsets
     U_ASSERT(uprv_strcmp(gTypes[kCurrencyOffset], "currency") == 0);

icu4c/source/i18n/number_skeletons.cpp

@@ -1072,25 +1072,12 @@ void blueprint_helpers::parseMeasureUnitOption(const StringSegment& segment, Mac
     CharString subType;
     SKELETON_UCHAR_TO_CHAR(subType, stemString, firstHyphen + 1, stemString.length(), status);
 
-    // Note: the largest type as of this writing (Aug 2020) is "volume", which has 33 units.
-    static constexpr int32_t CAPACITY = 40;
-    MeasureUnit units[CAPACITY];
-    UErrorCode localStatus = U_ZERO_ERROR;
-    int32_t numUnits = MeasureUnit::getAvailable(type.data(), units, CAPACITY, localStatus);
-    if (U_FAILURE(localStatus)) {
-        // More than 30 units in this type?
-        status = U_INTERNAL_PROGRAM_ERROR;
+    MeasureUnit unit;
+    if (MeasureUnit::isAvailable(type.data(), subType.data(), unit)) {
+        macros.unit = unit;
         return;
-    }
-    for (int32_t i = 0; i < numUnits; i++) {
-        auto& unit = units[i];
-        if (uprv_strcmp(subType.data(), unit.getSubtype()) == 0) {
-            macros.unit = unit;
-            return;
-        }
-    }
-
-    // throw new SkeletonSyntaxException("Unknown measure unit", segment);
+    } 
+    
     status = U_NUMBER_SKELETON_SYNTAX_ERROR;
 }
 

icu4c/source/i18n/unicode/measunit.h

@@ -720,6 +720,22 @@ class U_I18N_API MeasureUnit: public UObject {
      */
     static StringEnumeration* getAvailableTypes(UErrorCode &errorCode);
 
+#ifndef U_HIDE_INTERNAL_API
+    /**
+     * Check if a specific unit is available for the given type and subtype.
+     * 
+     * <p> Note: This is more efficient than calling getAvailable() when you only need
+     * to validate and retrieve a single unit.
+     *
+     * @param type the unit type (e.g., "length", "mass", "volume")
+     * @param subtype the unit subtype (e.g., "meter", "kilogram", "liter")
+     * @param result if the unit is found, this will be set to the MeasureUnit
+     * @return true if the unit exists, false otherwise
+     * @internal
+     */
+    static bool isAvailable(const char *type, const char *subtype, MeasureUnit &result);
+#endif /* U_HIDE_INTERNAL_API */
+
     /**
      * Return the class ID for this class. This is useful only for comparing to
      * a return value from getDynamicClassID(). For example: