WebCore/editing/SmartReplaceICU.cpp

   1 /*
   2  * Copyright (C) 2007 Apple Inc.  All rights reserved.
   3  * Copyright (C) 2008 Tony Chang <idealisms@gmail.com>
   4  *
   5  * Redistribution and use in source and binary forms, with or without
   6  * modification, are permitted provided that the following conditions
   7  * are met:
   8  *
   9  * 1.  Redistributions of source code must retain the above copyright
  10  *     notice, this list of conditions and the following disclaimer.
  11  * 2.  Redistributions in binary form must reproduce the above copyright
  12  *     notice, this list of conditions and the following disclaimer in the
  13  *     documentation and/or other materials provided with the distribution.
  14  * 3.  Neither the name of Apple Computer, Inc. ("Apple") nor the names of
  15  *     its contributors may be used to endorse or promote products derived
  16  *     from this software without specific prior written permission.
  17  *
  18  * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY
  19  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
  20  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  21  * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY
  22  * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
  23  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  24  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
  25  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  26  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
  27  * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  28  */
  29
  30 #include "config.h"
  31 #include "SmartReplace.h"
  32
  33 #if !PLATFORM(CF) && USE(ICU_UNICODE)
  34 #include "PlatformString.h"
  35 #include <unicode/uset.h>
  36 #include <wtf/Assertions.h>
  37
  38 namespace WebCore {
  39
  40 static void addAllCodePoints(USet* smartSet, const String& string) {
  41     const UChar* characters = string.characters();
  42     for (size_t i = 0; i < string.length(); i++)
  43         uset_add(smartSet, characters[i]);
  44 }
  45
  46 // This is mostly a port of the code in WebCore/editing/SmartReplaceCF.cpp
  47 // except we use icu in place of CoreFoundations character classes.
  48 static USet* getSmartSet(bool isPreviousCharacter)
  49 {
  50     static USet* preSmartSet = NULL;
  51     static USet* postSmartSet = NULL;
  52     USet* smartSet = isPreviousCharacter ? preSmartSet : postSmartSet;
  53     if (!smartSet) {
  54         // Whitespace and newline (kCFCharacterSetWhitespaceAndNewline)
  55         UErrorCode ec = U_ZERO_ERROR;
  56         String whitespaceAndNewline = "[[:WSpace:] [\\u000A\\u000B\\u000C\\u000D\\u0085]]";
  57         smartSet = uset_openPattern(whitespaceAndNewline.characters(), whitespaceAndNewline.length(), &ec);
  58         ASSERT(U_SUCCESS(ec));
  59
  60         // CJK ranges
  61         uset_addRange(smartSet, 0x1100, 0x1100 + 256); // Hangul Jamo (0x1100 - 0x11FF)
  62         uset_addRange(smartSet, 0x2E80, 0x2E80 + 352); // CJK & Kangxi Radicals (0x2E80 - 0x2FDF)
  63         uset_addRange(smartSet, 0x2FF0, 0x2FF0 + 464); // Ideograph Descriptions, CJK Symbols, Hiragana, Katakana, Bopomofo, Hangul Compatibility Jamo, Kanbun, & Bopomofo Ext (0x2FF0 - 0x31BF)
  64         uset_addRange(smartSet, 0x3200, 0x3200 + 29392); // Enclosed CJK, CJK Ideographs (Uni Han & Ext A), & Yi (0x3200 - 0xA4CF)
  65         uset_addRange(smartSet, 0xAC00, 0xAC00 + 11183); // Hangul Syllables (0xAC00 - 0xD7AF)
  66         uset_addRange(smartSet, 0xF900, 0xF900 + 352); // CJK Compatibility Ideographs (0xF900 - 0xFA5F)
  67         uset_addRange(smartSet, 0xFE30, 0xFE30 + 32); // CJK Compatibility From (0xFE30 - 0xFE4F)
  68         uset_addRange(smartSet, 0xFF00, 0xFF00 + 240); // Half/Full Width Form (0xFF00 - 0xFFEF)
  69         uset_addRange(smartSet, 0x20000, 0x20000 + 0xA6D7); // CJK Ideograph Exntension B
  70         uset_addRange(smartSet, 0x2F800, 0x2F800 + 0x021E); // CJK Compatibility Ideographs (0x2F800 - 0x2FA1D)
  71
  72         if (isPreviousCharacter) {
  73             addAllCodePoints(smartSet, "([\"\'#$/-`{");
  74             preSmartSet = smartSet;
  75         } else {
  76             addAllCodePoints(smartSet, ")].,;:?\'!\"%*-/}");
  77
  78             // Punctuation (kCFCharacterSetPunctuation)
  79             UErrorCode ec = U_ZERO_ERROR;
  80             String punctuationClass = "[:P:]";
  81             USet* icuPunct = uset_openPattern(punctuationClass.characters(), punctuationClass.length(), &ec);
  82             ASSERT(U_SUCCESS(ec));
  83             uset_addAll(smartSet, icuPunct);
  84             uset_close(icuPunct);
  85
  86             postSmartSet = smartSet;
  87         }
  88     }
  89     return smartSet;
  90 }
  91
  92 bool isCharacterSmartReplaceExempt(UChar32 c, bool isPreviousCharacter)
  93 {
  94     return uset_contains(getSmartSet(isPreviousCharacter), c);
  95 }
  96
  97 }
  98
  99 #endif // !PLATFORM(CF) && USE(ICU_UNICODE)