JavaScriptCore/wrec/CharacterClass.cpp

   1 /*
   2  * Copyright (C) 2008 Apple Inc. All rights reserved.
   3  *
   4  * Redistribution and use in source and binary forms, with or without
   5  * modification, are permitted provided that the following conditions
   6  * are met:
   7  * 1. Redistributions of source code must retain the above copyright
   8  *    notice, this list of conditions and the following disclaimer.
   9  * 2. Redistributions in binary form must reproduce the above copyright
  10  *    notice, this list of conditions and the following disclaimer in the
  11  *    documentation and/or other materials provided with the distribution.
  12  *
  13  * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
  14  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  15  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  16  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
  17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  19  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  20  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  21  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  22  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  23  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  24  */
  25
  26 #include "config.h"
  27 #include "CharacterClass.h"
  28
  29 #if ENABLE(WREC)
  30
  31 using namespace WTF;
  32
  33 namespace JSC { namespace WREC {
  34
  35 const CharacterClass& CharacterClass::newline() {
  36     static const UChar asciiNewlines[2] = { '\n', '\r' };
  37     static const UChar unicodeNewlines[2] = { 0x2028, 0x2029 };
  38     static const CharacterClass charClass = {
  39         asciiNewlines, 2,
  40         0, 0,
  41         unicodeNewlines, 2,
  42         0, 0,
  43     };
  44
  45     return charClass;
  46 }
  47
  48 const CharacterClass& CharacterClass::digits() {
  49     static const CharacterRange asciiDigitsRange[1] = { { '0', '9' } };
  50     static const CharacterClass charClass = {
  51         0, 0,
  52         asciiDigitsRange, 1,
  53         0, 0,
  54         0, 0,
  55     };
  56
  57     return charClass;
  58 }
  59
  60 const CharacterClass& CharacterClass::spaces() {
  61     static const UChar asciiSpaces[1] = { ' ' };
  62     static const CharacterRange asciiSpacesRange[1] = { { '\t', '\r' } };
  63     static const UChar unicodeSpaces[8] = { 0x00a0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f, 0x3000 };
  64     static const CharacterRange unicodeSpacesRange[1] = { { 0x2000, 0x200a } };
  65     static const CharacterClass charClass = {
  66         asciiSpaces, 1,
  67         asciiSpacesRange, 1,
  68         unicodeSpaces, 8,
  69         unicodeSpacesRange, 1,
  70     };
  71
  72     return charClass;
  73 }
  74
  75 const CharacterClass& CharacterClass::wordchar() {
  76     static const UChar asciiWordchar[1] = { '_' };
  77     static const CharacterRange asciiWordcharRange[3] = { { '0', '9' }, { 'A', 'Z' }, { 'a', 'z' } };
  78     static const CharacterClass charClass = {
  79         asciiWordchar, 1,
  80         asciiWordcharRange, 3,
  81         0, 0,
  82         0, 0,
  83     };
  84
  85     return charClass;
  86 }
  87
  88 const CharacterClass& CharacterClass::nondigits() {
  89     static const CharacterRange asciiNondigitsRange[2] = { { 0, '0' - 1 }, { '9' + 1, 0x7f } };
  90     static const CharacterRange unicodeNondigitsRange[1] = { { 0x0080, 0xffff } };
  91     static const CharacterClass charClass = {
  92         0, 0,
  93         asciiNondigitsRange, 2,
  94         0, 0,
  95         unicodeNondigitsRange, 1,
  96     };
  97
  98     return charClass;
  99 }
 100
 101 const CharacterClass& CharacterClass::nonspaces() {
 102     static const CharacterRange asciiNonspacesRange[3] = { { 0, '\t' - 1 }, { '\r' + 1, ' ' - 1 }, { ' ' + 1, 0x7f } };
 103     static const CharacterRange unicodeNonspacesRange[9] = {
 104         { 0x0080, 0x009f },
 105         { 0x00a1, 0x167f },
 106         { 0x1681, 0x180d },
 107         { 0x180f, 0x1fff },
 108         { 0x200b, 0x2027 },
 109         { 0x202a, 0x202e },
 110         { 0x2030, 0x205e },
 111         { 0x2060, 0x2fff },
 112         { 0x3001, 0xffff }
 113     };
 114     static const CharacterClass charClass = {
 115         0, 0,
 116         asciiNonspacesRange, 3,
 117         0, 0,
 118         unicodeNonspacesRange, 9,
 119     };
 120
 121     return charClass;
 122 }
 123
 124 const CharacterClass& CharacterClass::nonwordchar() {
 125     static const UChar asciiNonwordchar[1] = { '`' };
 126     static const CharacterRange asciiNonwordcharRange[4] = { { 0, '0' - 1 }, { '9' + 1, 'A' - 1 }, { 'Z' + 1, '_' - 1 }, { 'z' + 1, 0x7f } };
 127     static const CharacterRange unicodeNonwordcharRange[1] = { { 0x0080, 0xffff } };
 128     static const CharacterClass charClass = {
 129         asciiNonwordchar, 1,
 130         asciiNonwordcharRange, 4,
 131         0, 0,
 132         unicodeNonwordcharRange, 1,
 133     };
 134
 135     return charClass;
 136 }
 137
 138 } } // namespace JSC::WREC
 139
 140 #endif // ENABLE(WREC)