1/*
2 * Copyright (C) 2014 Google 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 are
6 * met:
7 *
8 *     * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 *     * Redistributions in binary form must reproduce the above
11 * copyright notice, this list of conditions and the following disclaimer
12 * in the documentation and/or other materials provided with the
13 * distribution.
14 *     * Neither the name of Google Inc. nor the names of its
15 * contributors may be used to endorse or promote products derived from
16 * this software without specific prior written permission.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 */
30
31#ifndef Character_h
32#define Character_h
33
34#include "platform/PlatformExport.h"
35#include "platform/text/TextDirection.h"
36#include "platform/text/TextPath.h"
37#include "wtf/HashSet.h"
38#include "wtf/text/WTFString.h"
39#include "wtf/unicode/CharacterNames.h"
40
41namespace blink {
42
43class PLATFORM_EXPORT Character {
44public:
45    static CodePath characterRangeCodePath(const LChar*, unsigned) { return SimplePath; }
46    static CodePath characterRangeCodePath(const UChar*, unsigned len);
47
48    static bool isCJKIdeograph(UChar32);
49    static bool isCJKIdeographOrSymbol(UChar32);
50
51    static unsigned expansionOpportunityCount(const LChar*, size_t length, TextDirection, bool& isAfterExpansion);
52    static unsigned expansionOpportunityCount(const UChar*, size_t length, TextDirection, bool& isAfterExpansion);
53
54    static bool treatAsSpace(UChar c) { return c == space || c == characterTabulation || c == newlineCharacter || c == noBreakSpace; }
55    static bool treatAsZeroWidthSpace(UChar c) { return treatAsZeroWidthSpaceInComplexScript(c) || c == 0x200c || c == 0x200d; }
56    static bool treatAsZeroWidthSpaceInComplexScript(UChar c) { return c < 0x20 || (c >= 0x7F && c < 0xA0) || c == softHyphen || c == zeroWidthSpace || (c >= 0x200e && c <= 0x200f) || (c >= 0x202a && c <= 0x202e) || c == zeroWidthNoBreakSpace || c == objectReplacementCharacter; }
57    static bool canReceiveTextEmphasis(UChar32);
58
59    static inline UChar normalizeSpaces(UChar character)
60    {
61        if (treatAsSpace(character))
62            return space;
63
64        if (treatAsZeroWidthSpace(character))
65            return zeroWidthSpace;
66
67        return character;
68    }
69
70    static inline bool isNormalizedCanvasSpaceCharacter(UChar c)
71    {
72        // According to specification all space characters should be replaced with 0x0020 space character.
73        // http://www.whatwg.org/specs/web-apps/current-work/multipage/the-canvas-element.html#text-preparation-algorithm
74        // The space characters according to specification are : U+0020, U+0009, U+000A, U+000C, and U+000D.
75        // http://www.whatwg.org/specs/web-apps/current-work/multipage/common-microsyntaxes.html#space-character
76        // This function returns true for 0x000B also, so that this is backward compatible.
77        // Otherwise, the test LayoutTests/canvas/philip/tests/2d.text.draw.space.collapse.space.html will fail
78        return c == 0x0009 || (c >= 0x000A && c <= 0x000D);
79    }
80
81    static String normalizeSpaces(const LChar*, unsigned length);
82    static String normalizeSpaces(const UChar*, unsigned length);
83
84private:
85    Character();
86};
87
88} // namespace blink
89
90#endif
91