1 /*
2  * Copyright (C) 2007 Apple Computer, Inc.
3  *
4  * Portions are Copyright (C) 1998 Netscape Communications Corporation.
5  *
6  * This library is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * This library is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with this library; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
19  *
20  * Alternatively, the contents of this file may be used under the terms
21  * of either the Mozilla Public License Version 1.1, found at
22  * http://www.mozilla.org/MPL/ (the "MPL") or the GNU General Public
23  * License Version 2.0, found at http://www.fsf.org/copyleft/gpl.html
24  * (the "GPL"), in which case the provisions of the MPL or the GPL are
25  * applicable instead of those above.  If you wish to allow use of your
26  * version of this file only under the terms of one of those two
27  * licenses (the MPL or the GPL) and not to allow others to use your
28  * version of this file under the LGPL, indicate your decision by
29  * deletingthe provisions above and replace them with the notice and
30  * other provisions required by the MPL or the GPL, as the case may be.
31  * If you do not delete the provisions above, a recipient may use your
32  * version of this file under any of the LGPL, the MPL or the GPL.
33  */
34 
35 #ifndef UnicodeRange_H
36 #define UnicodeRange_H
37 
38 #if PLATFORM(HAIKU)
39 #include "stdint.h"
40 #endif
41 
42 #include <wtf/unicode/Unicode.h>
43 
44 namespace WebCore {
45 
46 // The following constants define unicode subranges
47 // values below cRangeNum must be continuous so that we can map to
48 // a lang group directly.
49 // All ranges we care about should fit within 32 bits.
50 
51 // Frequently used range definitions
52 const unsigned char   cRangeCyrillic =    0;
53 const unsigned char   cRangeGreek    =    1;
54 const unsigned char   cRangeTurkish  =    2;
55 const unsigned char   cRangeHebrew   =    3;
56 const unsigned char   cRangeArabic   =    4;
57 const unsigned char   cRangeBaltic   =    5;
58 const unsigned char   cRangeThai     =    6;
59 const unsigned char   cRangeKorean   =    7;
60 const unsigned char   cRangeJapanese =    8;
61 const unsigned char   cRangeSChinese =    9;
62 const unsigned char   cRangeTChinese =   10;
63 const unsigned char   cRangeDevanagari = 11;
64 const unsigned char   cRangeTamil    =   12;
65 const unsigned char   cRangeArmenian =   13;
66 const unsigned char   cRangeBengali  =   14;
67 const unsigned char   cRangeCanadian =   15;
68 const unsigned char   cRangeEthiopic =   16;
69 const unsigned char   cRangeGeorgian =   17;
70 const unsigned char   cRangeGujarati =   18;
71 const unsigned char   cRangeGurmukhi =   19;
72 const unsigned char   cRangeKhmer    =   20;
73 const unsigned char   cRangeMalayalam =  21;
74 
75 const unsigned char   cRangeSpecificItemNum = 22;
76 
77 //range/rangeSet grow to this place 22-29
78 
79 const unsigned char   cRangeSetStart  =  30;    // range set definition starts from here
80 const unsigned char   cRangeSetLatin  =  30;
81 const unsigned char   cRangeSetCJK    =  31;
82 const unsigned char   cRangeSetEnd    =  31;   // range set definition ends here
83 
84 // less frequently used range definition
85 const unsigned char   cRangeSurrogate            = 32;
86 const unsigned char   cRangePrivate              = 33;
87 const unsigned char   cRangeMisc                 = 34;
88 const unsigned char   cRangeUnassigned           = 35;
89 const unsigned char   cRangeSyriac               = 36;
90 const unsigned char   cRangeThaana               = 37;
91 const unsigned char   cRangeOriya                = 38;
92 const unsigned char   cRangeTelugu               = 39;
93 const unsigned char   cRangeKannada              = 40;
94 const unsigned char   cRangeSinhala              = 41;
95 const unsigned char   cRangeLao                  = 42;
96 const unsigned char   cRangeTibetan              = 43;
97 const unsigned char   cRangeMyanmar              = 44;
98 const unsigned char   cRangeCherokee             = 45;
99 const unsigned char   cRangeOghamRunic           = 46;
100 const unsigned char   cRangeMongolian            = 47;
101 const unsigned char   cRangeMathOperators        = 48;
102 const unsigned char   cRangeMiscTechnical        = 49;
103 const unsigned char   cRangeControlOpticalEnclose = 50;
104 const unsigned char   cRangeBoxBlockGeometrics   = 51;
105 const unsigned char   cRangeMiscSymbols          = 52;
106 const unsigned char   cRangeDingbats             = 53;
107 const unsigned char   cRangeBraillePattern       = 54;
108 const unsigned char   cRangeYi                   = 55;
109 const unsigned char   cRangeCombiningDiacriticalMarks = 56;
110 const unsigned char   cRangeSpecials             = 57;
111 
112 const unsigned char   cRangeTableBase   = 128;    //values over 127 are reserved for internal use only
113 const unsigned char   cRangeTertiaryTable  = 145; // leave room for 16 subtable
114                                             // indices (cRangeTableBase + 1 ..
115                                             // cRangeTableBase + 16)
116 
117 
118 
119 unsigned int findCharUnicodeRange(UChar32 ch);
120 const char* langGroupFromUnicodeRange(unsigned char unicodeRange);
121 
122 }
123 
124 #endif // UnicodeRange_H
125