Kaydet (Commit) 1615b7f1 authored tarafından Khaled Hosny's avatar Khaled Hosny

Do proper script itemization with HarfBuzz

This implements http://www.unicode.org/reports/tr24/ by using ICU’s
implementation of it, but since the code in question is private API, I
simply copied the two self-contained files.

This commit is best viewed with --ignore-space-change.

Change-Id: I38c385d4fb6f8a2edc804d48f0aa14df9f0a8b3b
üst 97ed0bdc
......@@ -464,6 +464,7 @@ vcl_generic_code= \
vcl/generic/glyphs/gcach_layout \
vcl/generic/glyphs/gcach_rbmp \
vcl/generic/glyphs/glyphcache \
vcl/generic/glyphs/scrptrun \
vcl/generic/fontmanager/fontcache \
vcl/generic/fontmanager/fontconfig \
vcl/generic/fontmanager/fontmanager \
......
/*
*******************************************************************************
*
* Copyright (c) 1995-2013 International Business Machines Corporation and others
*
* All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy of
* this software and associated documentation files (the "Software"), to deal in
* the Software without restriction, including without limitation the rights to
* use, copy, modify, merge, publish, distribute, and/or sell copies of the
* Software, and to permit persons to whom the Software is furnished to do so,
* provided that the above copyright notice(s) and this permission notice appear
* in all copies of the Software and that both the above copyright notice(s) and
* this permission notice appear in supporting documentation.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN
* NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE
* LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY
* DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
* CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*
* Except as contained in this notice, the name of a copyright holder shall not be
* used in advertising or otherwise to promote the sale, use or other dealings in
* this Software without prior written authorization of the copyright holder.
*
*******************************************************************************
* file name: scrptrun.cpp
*
* created on: 10/17/2001
* created by: Eric R. Mader
*/
#include "unicode/utypes.h"
#include "unicode/uscript.h"
#include "scrptrun.h"
#define ARRAY_SIZE(array) (sizeof array / sizeof array[0])
const char ScriptRun::fgClassID=0;
UChar32 ScriptRun::pairedChars[] = {
0x0028, 0x0029, // ascii paired punctuation
0x003c, 0x003e,
0x005b, 0x005d,
0x007b, 0x007d,
0x00ab, 0x00bb, // guillemets
0x2018, 0x2019, // general punctuation
0x201c, 0x201d,
0x2039, 0x203a,
0x3008, 0x3009, // chinese paired punctuation
0x300a, 0x300b,
0x300c, 0x300d,
0x300e, 0x300f,
0x3010, 0x3011,
0x3014, 0x3015,
0x3016, 0x3017,
0x3018, 0x3019,
0x301a, 0x301b
};
const int32_t ScriptRun::pairedCharCount = ARRAY_SIZE(pairedChars);
const int32_t ScriptRun::pairedCharPower = 1 << highBit(pairedCharCount);
const int32_t ScriptRun::pairedCharExtra = pairedCharCount - pairedCharPower;
int8_t ScriptRun::highBit(int32_t value)
{
if (value <= 0) {
return -32;
}
int8_t bit = 0;
if (value >= 1 << 16) {
value >>= 16;
bit += 16;
}
if (value >= 1 << 8) {
value >>= 8;
bit += 8;
}
if (value >= 1 << 4) {
value >>= 4;
bit += 4;
}
if (value >= 1 << 2) {
value >>= 2;
bit += 2;
}
if (value >= 1 << 1) {
value >>= 1;
bit += 1;
}
return bit;
}
int32_t ScriptRun::getPairIndex(UChar32 ch)
{
int32_t probe = pairedCharPower;
int32_t index = 0;
if (ch >= pairedChars[pairedCharExtra]) {
index = pairedCharExtra;
}
while (probe > (1 << 0)) {
probe >>= 1;
if (ch >= pairedChars[index + probe]) {
index += probe;
}
}
if (pairedChars[index] != ch) {
index = -1;
}
return index;
}
UBool ScriptRun::sameScript(int32_t scriptOne, int32_t scriptTwo)
{
return scriptOne <= USCRIPT_INHERITED || scriptTwo <= USCRIPT_INHERITED || scriptOne == scriptTwo;
}
UBool ScriptRun::next()
{
int32_t startSP = parenSP; // used to find the first new open character
UErrorCode error = U_ZERO_ERROR;
// if we've fallen off the end of the text, we're done
if (scriptEnd >= charLimit) {
return false;
}
scriptCode = USCRIPT_COMMON;
for (scriptStart = scriptEnd; scriptEnd < charLimit; scriptEnd += 1) {
UChar high = charArray[scriptEnd];
UChar32 ch = high;
// if the character is a high surrogate and it's not the last one
// in the text, see if it's followed by a low surrogate
if (high >= 0xD800 && high <= 0xDBFF && scriptEnd < charLimit - 1)
{
UChar low = charArray[scriptEnd + 1];
// if it is followed by a low surrogate,
// consume it and form the full character
if (low >= 0xDC00 && low <= 0xDFFF) {
ch = (high - 0xD800) * 0x0400 + low - 0xDC00 + 0x10000;
scriptEnd += 1;
}
}
UScriptCode sc = uscript_getScript(ch, &error);
int32_t pairIndex = getPairIndex(ch);
// Paired character handling:
//
// if it's an open character, push it onto the stack.
// if it's a close character, find the matching open on the
// stack, and use that script code. Any non-matching open
// characters above it on the stack will be poped.
if (pairIndex >= 0) {
if ((pairIndex & 1) == 0) {
parenStack[++parenSP].pairIndex = pairIndex;
parenStack[parenSP].scriptCode = scriptCode;
} else if (parenSP >= 0) {
int32_t pi = pairIndex & ~1;
while (parenSP >= 0 && parenStack[parenSP].pairIndex != pi) {
parenSP -= 1;
}
if (parenSP < startSP) {
startSP = parenSP;
}
if (parenSP >= 0) {
sc = parenStack[parenSP].scriptCode;
}
}
}
if (sameScript(scriptCode, sc)) {
if (scriptCode <= USCRIPT_INHERITED && sc > USCRIPT_INHERITED) {
scriptCode = sc;
// now that we have a final script code, fix any open
// characters we pushed before we knew the script code.
while (startSP < parenSP) {
parenStack[++startSP].scriptCode = scriptCode;
}
}
// if this character is a close paired character,
// pop it from the stack
if (pairIndex >= 0 && (pairIndex & 1) != 0 && parenSP >= 0) {
parenSP -= 1;
startSP -= 1;
}
} else {
// if the run broke on a surrogate pair,
// end it before the high surrogate
if (ch >= 0x10000) {
scriptEnd -= 1;
}
break;
}
}
return true;
}
/*
*******************************************************************************
*
* Copyright (c) 1995-2013 International Business Machines Corporation and others
*
* All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy of
* this software and associated documentation files (the "Software"), to deal in
* the Software without restriction, including without limitation the rights to
* use, copy, modify, merge, publish, distribute, and/or sell copies of the
* Software, and to permit persons to whom the Software is furnished to do so,
* provided that the above copyright notice(s) and this permission notice appear
* in all copies of the Software and that both the above copyright notice(s) and
* this permission notice appear in supporting documentation.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN
* NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE
* LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY
* DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
* CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*
* Except as contained in this notice, the name of a copyright holder shall not be
* used in advertising or otherwise to promote the sale, use or other dealings in
* this Software without prior written authorization of the copyright holder.
*
*******************************************************************************
* file name: scrptrun.h
*
* created on: 10/17/2001
* created by: Eric R. Mader
*/
#ifndef __SCRPTRUN_H
#define __SCRPTRUN_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/uscript.h"
struct ScriptRecord
{
UChar32 startChar;
UChar32 endChar;
UScriptCode scriptCode;
};
struct ParenStackEntry
{
int32_t pairIndex;
UScriptCode scriptCode;
};
class ScriptRun : public UObject {
public:
ScriptRun();
ScriptRun(const UChar chars[], int32_t length);
ScriptRun(const UChar chars[], int32_t start, int32_t length);
void reset();
void reset(int32_t start, int32_t count);
void reset(const UChar chars[], int32_t start, int32_t length);
int32_t getScriptStart();
int32_t getScriptEnd();
UScriptCode getScriptCode();
UBool next();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
private:
static UBool sameScript(int32_t scriptOne, int32_t scriptTwo);
int32_t charStart;
int32_t charLimit;
const UChar *charArray;
int32_t scriptStart;
int32_t scriptEnd;
UScriptCode scriptCode;
ParenStackEntry parenStack[128];
int32_t parenSP;
static int8_t highBit(int32_t value);
static int32_t getPairIndex(UChar32 ch);
static UChar32 pairedChars[];
static const int32_t pairedCharCount;
static const int32_t pairedCharPower;
static const int32_t pairedCharExtra;
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
};
inline ScriptRun::ScriptRun()
{
reset(NULL, 0, 0);
}
inline ScriptRun::ScriptRun(const UChar chars[], int32_t length)
{
reset(chars, 0, length);
}
inline ScriptRun::ScriptRun(const UChar chars[], int32_t start, int32_t length)
{
reset(chars, start, length);
}
inline int32_t ScriptRun::getScriptStart()
{
return scriptStart;
}
inline int32_t ScriptRun::getScriptEnd()
{
return scriptEnd;
}
inline UScriptCode ScriptRun::getScriptCode()
{
return scriptCode;
}
inline void ScriptRun::reset()
{
scriptStart = charStart;
scriptEnd = charStart;
scriptCode = USCRIPT_INVALID_CODE;
parenSP = -1;
}
inline void ScriptRun::reset(int32_t start, int32_t length)
{
charStart = start;
charLimit = start + length;
reset();
}
inline void ScriptRun::reset(const UChar chars[], int32_t start, int32_t length)
{
charArray = chars;
reset(start, length);
}
#endif
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment