Add function to calculate equal range for UTF-16 strings.

base/base_tests/string_utils_test.cpp

@@ -434,3 +434,63 @@ UNIT_TEST(IsUtf8Test)
   TEST(strings::IsASCIIString("YES"), ());
   TEST(strings::IsASCIIString("Nice places in Zhodino.kml"), ());
 }
+
+UNIT_TEST(CountNormLowerSymbols)
+{
+  char const * strs[] = {
+    "æüßs",
+    "üßü",
+    "İʼnẖtestὒ",
+    "İʼnẖ",
+    "İʼnẖtestὒ",
+    "HelloWorld",
+    "üßü",
+    "",
+    "",
+    "Тест на не корректную русскую строку",
+    "В ответе пустая строка",
+    "Überstraße"
+  };
+
+  char const * low_strs[] = {
+    "æusss",
+    "ussu",
+    "i\u0307\u02bcnh\u0331testυ\u0313\u0300",
+    "i\u0307\u02bcnh\u0331testυ\u0313\u0300",
+    "i\u0307\u02bcnh\u0331",
+    "helloworld",
+    "usu",
+    "",
+    "empty",
+    "Тест на не корректную строку",
+    "",
+    "uberstras"
+  };
+
+  size_t const results [] = {
+    4,
+    3,
+    8,
+    0,
+    3,
+    10,
+    0,
+    0,
+    0,
+    0,
+    0,
+    9
+  };
+
+
+  size_t const test_count = ARRAY_SIZE(strs);
+
+  for (size_t i = 0; i < test_count; ++i)
+  {
+    strings::UniString source = strings::MakeUniString(strs[i]);
+    strings::UniString result = strings::MakeUniString(low_strs[i]);
+
+    size_t res = strings::CountNormLowerSymbols(source, result);
+    TEST_EQUAL(res, results[i], ());
+  }
+}

base/lower_case.cpp

@@ -194,4 +194,33 @@ void MakeLowerCase(UniString & s)
   s.swap(r);
 }
 
+size_t CountNormLowerSymbols(UniString const & s, UniString const & lowStr)
+{
+  size_t const size = s.size();
+  size_t const lowSize = lowStr.size();
+  size_t lowIdx = 0, sIdx = 0;
+
+  while (lowIdx < lowSize)
+  {
+    if (sIdx == size)
+      return 0; // low_s has more length than s
+
+    UniString strCharNorm;
+    strCharNorm.push_back(s[sIdx++]);
+    MakeLowerCase(strCharNorm);
+    Normalize(strCharNorm);
+
+    for (size_t i = 0; i < strCharNorm.size(); ++i)
+    {
+      if (lowIdx >= lowSize)
+        return sIdx;
+      else
+        if (lowStr[lowIdx++] != strCharNorm[i])
+          return 0;
+    }
+  }
+
+  return sIdx;
+}
+
 } // namespace strings

base/string_utils.hpp

@@ -36,6 +36,12 @@ UniString Normalize(UniString const & s);
 /// For implementation @see base/normilize_unicode.cpp
 void Normalize(UniString & s);
 
+/// Counts number of start symbols in string s (that is not lower and not normalized) that maches
+/// to lower and normalized string low_s. If s doen't starts with low_s then returns 0; otherwise
+/// returns number of start symbols in s that equivalent to lowStr
+/// For implementation @see base/lower_case.cpp
+size_t CountNormLowerSymbols(UniString const & s, UniString const & lowStr);
+
 void AsciiToLower(string & s);
 void Trim(string & s);