1/*
2 * Copyright (c) 2010 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 ComplexTextControllerLinux_h
32#define ComplexTextControllerLinux_h
33
34#include "HarfbuzzSkia.h"
35#include "SkScalar.h"
36#include "TextRun.h"
37
38#include <unicode/uchar.h>
39#include <wtf/OwnArrayPtr.h>
40#include <wtf/OwnPtr.h>
41
42namespace WebCore {
43
44class Font;
45class FontPlatformData;
46class SimpleFontData;
47
48// ComplexTextController walks a TextRun and presents each script run in sequence. A
49// TextRun is a sequence of code-points with the same embedding level (i.e. they
50// are all left-to-right or right-to-left). A script run is a subsequence where
51// all the characters have the same script (e.g. Arabic, Thai etc). Shaping is
52// only ever done with script runs since the shapers only know how to deal with
53// a single script.
54//
55// Iteration is always in logical (aka reading) order.  For RTL text that means
56// the rightmost part of the text will be first.
57//
58// Once you have setup the object, call |nextScriptRun| to get the first script
59// run. This will return false when the iteration is complete. At any time you
60// can call |reset| to start over again.
61class ComplexTextController {
62public:
63    ComplexTextController(const TextRun&, unsigned, const Font*);
64    ~ComplexTextController();
65
66    bool isWordBreak(unsigned);
67    int determineWordBreakSpacing(unsigned);
68    // setPadding sets a number of pixels to be distributed across the TextRun.
69    // WebKit uses this to justify text.
70    void setPadding(int);
71    void reset(unsigned offset);
72    // Advance to the next script run, returning false when the end of the
73    // TextRun has been reached.
74    bool nextScriptRun();
75    float widthOfFullRun();
76
77    // setWordSpacingAdjustment sets a delta (in pixels) which is applied at
78    // each word break in the TextRun.
79    void setWordSpacingAdjustment(int wordSpacingAdjustment) { m_wordSpacingAdjustment = wordSpacingAdjustment; }
80
81    // setLetterSpacingAdjustment sets an additional number of pixels that is
82    // added to the advance after each output cluster. This matches the behaviour
83    // of WidthIterator::advance.
84    void setLetterSpacingAdjustment(int letterSpacingAdjustment) { m_letterSpacing = letterSpacingAdjustment; }
85    int letterSpacing() const { return m_letterSpacing; }
86
87    // Set the x offset for the next script run. This affects the values in
88    // |xPositions|
89    bool rtl() const { return m_run.rtl(); }
90    const uint16_t* glyphs() const { return m_glyphs16; }
91
92    // Return the length of the array returned by |glyphs|
93    const unsigned length() const { return m_item.num_glyphs; }
94
95    // Return the x offset for each of the glyphs. Note that this is translated
96    // by the current x offset and that the x offset is updated for each script
97    // run.
98    const SkScalar* xPositions() const { return m_xPositions; }
99
100    // Get the advances (widths) for each glyph.
101    const HB_Fixed* advances() const { return m_item.advances; }
102
103    // Return the width (in px) of the current script run.
104    const unsigned width() const { return m_pixelWidth; }
105
106    // Return the cluster log for the current script run. For example:
107    //   script run: f i a n c é  (fi gets ligatured)
108    //   log clutrs: 0 0 1 2 3 4
109    // So, for each input code point, the log tells you which output glyph was
110    // generated for it.
111    const unsigned short* logClusters() const { return m_item.log_clusters; }
112
113    // return the number of code points in the current script run
114    const unsigned numCodePoints() const { return m_item.item.length; }
115
116    // Return the current pixel position of the controller.
117    const unsigned offsetX() const { return m_offsetX; }
118
119    const FontPlatformData* fontPlatformDataForScriptRun() { return reinterpret_cast<FontPlatformData*>(m_item.font->userData); }
120
121private:
122    void setupFontForScriptRun();
123    HB_FontRec* allocHarfbuzzFont();
124    void deleteGlyphArrays();
125    void createGlyphArrays(int);
126    void resetGlyphArrays();
127    void shapeGlyphs();
128    void setGlyphXPositions(bool);
129
130    static void normalizeSpacesAndMirrorChars(const UChar* source, bool rtl, UChar* destination, int length);
131    static const TextRun& getNormalizedTextRun(const TextRun& originalRun, OwnPtr<TextRun>& normalizedRun, OwnArrayPtr<UChar>& normalizedBuffer);
132
133    // This matches the logic in RenderBlock::findNextLineBreak
134    static bool isCodepointSpace(HB_UChar16 c) { return c == ' ' || c == '\t'; }
135
136    const Font* const m_font;
137    const SimpleFontData* m_currentFontData;
138    HB_ShaperItem m_item;
139    uint16_t* m_glyphs16; // A vector of 16-bit glyph ids.
140    SkScalar* m_xPositions; // A vector of x positions for each glyph.
141    ssize_t m_indexOfNextScriptRun; // Indexes the script run in |m_run|.
142    unsigned m_offsetX; // Offset in pixels to the start of the next script run.
143    unsigned m_pixelWidth; // Width (in px) of the current script run.
144    unsigned m_glyphsArrayCapacity; // Current size of all the Harfbuzz arrays.
145
146    OwnPtr<TextRun> m_normalizedRun;
147    OwnArrayPtr<UChar> m_normalizedBuffer; // A buffer for normalized run.
148    const TextRun& m_run;
149    int m_wordSpacingAdjustment; // delta adjustment (pixels) for each word break.
150    float m_padding; // pixels to be distributed over the line at word breaks.
151    float m_padPerWordBreak; // pixels to be added to each word break.
152    float m_padError; // |m_padPerWordBreak| might have a fractional component.
153                      // Since we only add a whole number of padding pixels at
154                      // each word break we accumulate error. This is the
155                      // number of pixels that we are behind so far.
156    int m_letterSpacing; // pixels to be added after each glyph.
157    String m_smallCapsString; // substring of m_run converted to small caps.
158};
159
160} // namespace WebCore
161
162#endif // ComplexTextControllerLinux_h
163