remove localizedStandardRangeOfString

dotnet · mkhamoyan · Jun 29, 2023 · May 30, 2023 · May 31, 2023 · May 31, 2023
commit 460aba0101bc6c48a6f7304d72c07cdd666c7a2f
diff --git a/docs/design/features/globalization-hybrid-mode.md b/docs/design/features/globalization-hybrid-mode.md
@@ -361,13 +361,13 @@ Affected public APIs:
 Mapped to Apple Native API `rangeOfString:options:range:locale:`(https://developer.apple.com/documentation/foundation/nsstring/1417348-rangeofstring?language=objc)
 
 In `rangeOfString:options:range:locale:` objects are compared by checking the Unicode canonical equivalence of their code point sequences.
-In cases where search string contains diaeresis and has different normalization form than in source string result can be incorrect.
+In cases where search string contains diacritics and has different normalization form than in source string result can be incorrect.
 
 Characters in general are represented by unicode code points, and some characters can be represented in a single code point or by combining multiple characters (like diacritics/diaeresis). Normalization Form C will look to compress characters to their single code point format if they were originally represented as a sequence of multiple code points. Normalization Form D does the opposite and expands characters into their multiple code point formats if possible.
 
 `NSString` `rangeOfString:options:range:locale:` uses canonical equivalence to find the position of the `searchString` within the `sourceString`, however, it does not automatically handle comparison of precomposed (single code point representation) or decomposed (most code points representation). Because the `searchString` and `sourceString` can be of differing formats, to properly find the index, we need to ensure that the searchString is in the same form as the sourceString by checking the `rangeOfString:options:range:locale:` using every single normalization form.
 
-Here are the covered cases with diaeresis:
+Here are the covered cases with diacritics:
   1. Search string contains diaeresis and has same normalization form as in source string.
   2. Search string contains diaeresis but with source string they have same letters with different char lengths but substring is normalized in source.
 
@@ -377,8 +377,8 @@ Here are the covered cases with diaeresis:
 
 Not covered case:
 
-      Search string contains diaeresis and with source string they have same letters with different char lengths but substring is not
-      normalized in source. example: search string: `U\u0308 and \u00FC` source string: `Source is a\u0308\u0308a and \u0075\u0308`
+      Search string contains diacritics and with source string they have same letters with different char lengths but substring is not
+      normalized in source. example: search string: `U\u0308 and \u00FC` (Ü and ü) source string: `Source is \u00DC and \u0075\u0308` (Source is Ü and ü)
       as it is visible from example normalizaing search string to form C or D will not help to find substring in source string.
 
 - `IgnoreSymbols`

diff --git a/src/native/libs/System.Globalization.Native/pal_collation.m b/src/native/libs/System.Globalization.Native/pal_collation.m
@@ -95,6 +95,17 @@ int32_t GlobalizationNative_CompareStringNative(const uint16_t* localeName, int3
     return modifiedString;
 }
 
+static int32_t IsIndexFound(int32_t fromBeginning, int32_t foundLocation, int32_t newLocation)
+{
+    // last index
+    if (!fromBeginning && foundLocation > newLocation)
+        return 1;
+    // first index
+    if (fromBeginning && foundLocation != -2 && foundLocation < newLocation)
+        return 1;
+    return 0;
+}
+
 /*
 Function: IndexOf
 Find detailed explanation how this function works in https://github.com/dotnet/runtime/blob/main/docs/design/features/globalization-hybrid-mode.md
@@ -138,22 +149,10 @@ Range GlobalizationNative_IndexOfNative(const uint16_t* localeName, int32_t lNam
                                                   locale:currentLocale];
 
     if (containsRange.location == NSNotFound)
-    {
         return result;
-    }
-
-    // localizedStandardRangeOfString is performing a case and diacritic insensitive, locale-aware search and finding first occurance
-    if ((comparisonOptions & IgnoreCase) && lNameLength == 0 && fromBeginning)
-    {      
-        NSRange localizedStandardRange = [sourceStrCleaned localizedStandardRangeOfString:searchStrCleaned];
-        if (localizedStandardRange.location != NSNotFound)
-        {
-            result.location = localizedStandardRange.location;
-            result.length = localizedStandardRange.length;                    
-            return result;
-        }       
-    }
 
+    // in case search string is inside source string but we can't find the index return -2
+    result.location = -2;
     // sourceString and searchString possibly have the same composition of characters
     rangeOfReceiverToSearch = NSMakeRange(0, sourceStrCleaned.length);
     NSRange nsRange = [sourceStrCleaned rangeOfString:searchStrCleaned
@@ -165,35 +164,34 @@ Range GlobalizationNative_IndexOfNative(const uint16_t* localeName, int32_t lNam
     {   
         result.location = nsRange.location;
         result.length = nsRange.length;
-        // in case of last index and CompareOptions.IgnoreCase 
-        // if letters have different representations in source and search strings
-        // and case insensitive search appears more than one time in source string take last index
+        // in case of CompareOptions.IgnoreCase if letters have different representations in source and search strings
+        // and case insensitive search appears more than one time in source string take last index for LastIndexOf and first index for IndexOf
         // e.g. new CultureInfo().CompareInfo.LastIndexOf("Is \u0055\u0308 or \u0075\u0308 the same as \u00DC or \u00FC?", "U\u0308", 25,18, CompareOptions.IgnoreCase);
         // should return 24 but here it will be 9
-        if (fromBeginning || !(comparisonOptions & IgnoreCase))
+        if (!(comparisonOptions & IgnoreCase))
             return result;
     }
-
-    rangeOfReceiverToSearch = NSMakeRange(0, sourceStrCleaned.length);
+
     // check if sourceString has precomposed form of characters and searchString has decomposed form of characters
     // convert searchString to a precomposed form
     NSRange precomposedRange = [sourceStrCleaned rangeOfString:searchStrPrecomposed
-                                                  options:options
-                                                  range:rangeOfReceiverToSearch
-                                                  locale:currentLocale];
+                                                 options:options
+                                                 range:rangeOfReceiverToSearch
+                                                 locale:currentLocale];
 
     if (precomposedRange.location != NSNotFound)
     {
-        // in case of last index and CompareOptions.IgnoreCase 
-        // if letters have different representations in source and search strings
-        // and search appears more than one time in source string take last index
+        // in case of CompareOptions.IgnoreCase if letters have different representations in source and search strings
+        // and search appears more than one time in source string take last index for LastIndexOf and first index for IndexOf
         // e.g. new CultureInfo().CompareInfo.LastIndexOf("Is \u0055\u0308 or \u0075\u0308 the same as \u00DC or \u00FC?", "U\u0308", 25,18, CompareOptions.IgnoreCase);
-        // this will return 24 
-        if ((int32_t)result.location > (int32_t)precomposedRange.location && !fromBeginning && (comparisonOptions & IgnoreCase))
+        // this will return 24
+        if ((comparisonOptions & IgnoreCase) && IsIndexFound(fromBeginning, (int32_t)result.location, (int32_t)precomposedRange.location))
             return result;
+
         result.location = precomposedRange.location;
         result.length = precomposedRange.length;
-        return result;
+        if (!(comparisonOptions & IgnoreCase))
+           return result;
     }
 
     // check if sourceString has decomposed form of characters and searchString has precomposed form of characters
@@ -206,21 +204,22 @@ Range GlobalizationNative_IndexOfNative(const uint16_t* localeName, int32_t lNam
 
     if (decomposedRange.location != NSNotFound)
     {
+        if ((comparisonOptions & IgnoreCase) && IsIndexFound(fromBeginning, (int32_t)result.location, (int32_t)decomposedRange.location))
+            return result;
+
         result.location = decomposedRange.location;
         result.length = decomposedRange.length;                    
         return result;
     }
 
-    result.location = -2;
     return result;
 }
 
 /*
  Return value is a "Win32 BOOL" (1 = true, 0 = false)
  */
 int32_t GlobalizationNative_StartsWithNative(const uint16_t* localeName, int32_t lNameLength, const uint16_t* lpPrefix, int32_t cwPrefixLength, 
-                                             const uint16_t* lpSource, int32_t cwSourceLength, int32_t comparisonOptions)
-
+                                             const uint16_t* lpSource, int32_t cwSourceLength, int32_t comparisonOptions)          
 {
     NSStringCompareOptions options = ConvertFromCompareOptionsToNSStringCompareOptions(comparisonOptions);
 
@@ -247,8 +246,7 @@ int32_t GlobalizationNative_StartsWithNative(const uint16_t* localeName, int32_t
  Return value is a "Win32 BOOL" (1 = true, 0 = false)
  */
 int32_t GlobalizationNative_EndsWithNative(const uint16_t* localeName, int32_t lNameLength, const uint16_t* lpSuffix, int32_t cwSuffixLength,
-                                           const uint16_t* lpSource, int32_t cwSourceLength, int32_t comparisonOptions)
-
+                                           const uint16_t* lpSource, int32_t cwSourceLength, int32_t comparisonOptions)                
 {
     NSStringCompareOptions options = ConvertFromCompareOptionsToNSStringCompareOptions(comparisonOptions);