WTF: Add comments and tests for Unicode aware case-insensitive string operations.

third_party/WebKit/Source/wtf/text/WTFStringTest.cpp

 /*
  * Copyright (C) 2012 Apple Inc. All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
  * 1. Redistributions of source code must retain the above copyright
  *    notice, this list of conditions and the following disclaimer.
  * 2. Redistributions in binary form must reproduce the above copyright
  *    notice, this list of conditions and the following disclaimer in the
@@ skipping 318 matching lines @@
     const char* expected = testDataList[i].expected;
     String source = String::fromUTF8(testDataList[i].source);
     for (size_t j = 0; j < testDataList[i].localeListLength; ++j) {
       const char* locale = testDataList[i].localeList[j];
       EXPECT_STREQ(expected, source.lower(locale).utf8().data())
           << testDataList[i].sourceDescription << "; locale=" << locale;
     }
   }
 }
 
+TEST(StringTest, StartsWithIgnoringUnicodeCase) {
+  // [U+017F U+212A i a] starts with "sk".
+  EXPECT_TRUE(String::fromUTF8("\xC5\xBF\xE2\x84\xAAia")
+                  .startsWith("sk", TextCaseInsensitive));
+}
+
 TEST(StringTest, StartsWithIgnoringASCIICase) {
   String allASCII("LINK");
   String allASCIILowerCase("link");
   EXPECT_TRUE(allASCII.startsWith(allASCIILowerCase, TextCaseASCIIInsensitive));
   String allASCIIMixedCase("lInK");
   EXPECT_TRUE(allASCII.startsWith(allASCIIMixedCase, TextCaseASCIIInsensitive));
   String allASCIIDifferent("foo");
   EXPECT_FALSE(
       allASCII.startsWith(allASCIIDifferent, TextCaseASCIIInsensitive));
   String nonASCII = String::fromUTF8("LIN\xE2\x84\xAA");
@@ skipping 59 matching lines @@
   String haystack2 = String::fromUTF8("aA\xCC\x88QA\xCC\x88qa\xCC\x88rfi");
   EXPECT_EQ(1u, haystack2.findIgnoringASCIICase(needle));
   EXPECT_EQ(4u, haystack2.findIgnoringASCIICase(needle, 2));
   EXPECT_EQ(kNotFound, haystack2.findIgnoringASCIICase(needle, 5));
 }
 
 TEST(StringTest, Lower) {
   EXPECT_STREQ("link", String("LINK").lower().ascii().data());
   EXPECT_STREQ("link", String("lInk").lower().ascii().data());
   EXPECT_STREQ("lin\xE1k", String("lIn\xC1k").lower().latin1().data());
+  // U+212A -> k
   EXPECT_STREQ("link",
                String::fromUTF8("LIN\xE2\x84\xAA").lower().utf8().data());
 }
 
+TEST(StringTest, Upper) {
+  EXPECT_STREQ("CROSS", String("cross").upper().utf8().data());
+  // U+017F -> S
+  EXPECT_STREQ("CROSS", String::fromUTF8("cro\xC5\xBFs").upper().utf8().data());
+}
+
 TEST(StringTest, Ensure16Bit) {
   String string8("8bit");
   EXPECT_TRUE(string8.is8Bit());
   string8.ensure16Bit();
   EXPECT_FALSE(string8.is8Bit());
   EXPECT_EQ("8bit", string8);
 
   String string16(reinterpret_cast<const UChar*>(u"16bit"));
   EXPECT_FALSE(string16.is8Bit());
   string16.ensure16Bit();
@@ skipping 48 matching lines @@
   EXPECT_EQ(CString("<null>"), toCStringThroughPrinter(String()));
 
   static const UChar unicodeSample[] = {0x30C6, 0x30B9,
                                         0x30C8};  // "Test" in Japanese.
   EXPECT_EQ(CString("\"\\u30C6\\u30B9\\u30C8\""),
             toCStringThroughPrinter(
                 String(unicodeSample, WTF_ARRAY_LENGTH(unicodeSample))));
 }
 
 }  // namespace WTF