1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
|
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*-
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
#include "nsTextFrameUtils.h"
#include "nsContentUtils.h"
#include "nsIWordBreaker.h"
#include "gfxFont.h"
#include "nsUnicharUtils.h"
#include "nsBidiUtils.h"
#include "nsIContent.h"
#include "nsStyleStruct.h"
#include <algorithm>
// XXX TODO implement transform of backslash to yen that nsTextTransform does
// when requested by PresContext->LanguageSpecificTransformType(). Do it with
// a new factory type that just munges the input stream. But first, check
// that we really still need this, it's only enabled via a hidden pref
// which defaults false...
#define UNICODE_ZWSP 0x200B
static bool IsDiscardable(PRUnichar ch, uint32_t* aFlags)
{
// Unlike IS_DISCARDABLE, we don't discard \r. \r will be ignored by gfxTextRun
// and discarding it would force us to copy text in many cases of preformatted
// text containing \r\n.
if (ch == CH_SHY) {
*aFlags |= nsTextFrameUtils::TEXT_HAS_SHY;
return true;
}
if ((ch & 0xFF00) != 0x2000) {
// Not a Bidi control character
return false;
}
return IS_BIDI_CONTROL_CHAR(ch);
}
static bool IsDiscardable(uint8_t ch, uint32_t* aFlags)
{
if (ch == CH_SHY) {
*aFlags |= nsTextFrameUtils::TEXT_HAS_SHY;
return true;
}
return false;
}
PRUnichar*
nsTextFrameUtils::TransformText(const PRUnichar* aText, uint32_t aLength,
PRUnichar* aOutput,
CompressionMode aCompression,
uint8_t* aIncomingFlags,
gfxSkipCharsBuilder* aSkipChars,
uint32_t* aAnalysisFlags)
{
uint32_t flags = 0;
PRUnichar* outputStart = aOutput;
bool lastCharArabic = false;
if (aCompression == COMPRESS_NONE ||
aCompression == DISCARD_NEWLINE) {
// Skip discardables.
uint32_t i;
for (i = 0; i < aLength; ++i) {
PRUnichar ch = *aText++;
if (IsDiscardable(ch, &flags) ||
(ch == '\n' && aCompression == DISCARD_NEWLINE)) {
aSkipChars->SkipChar();
} else {
aSkipChars->KeepChar();
if (ch > ' ') {
lastCharArabic = IS_ARABIC_CHAR(ch);
} else if (ch == '\t') {
flags |= TEXT_HAS_TAB;
}
*aOutput++ = ch;
}
}
if (lastCharArabic) {
*aIncomingFlags |= INCOMING_ARABICCHAR;
} else {
*aIncomingFlags &= ~INCOMING_ARABICCHAR;
}
*aIncomingFlags &= ~INCOMING_WHITESPACE;
} else {
bool inWhitespace = (*aIncomingFlags & INCOMING_WHITESPACE) != 0;
uint32_t i;
for (i = 0; i < aLength; ++i) {
PRUnichar ch = *aText++;
bool nowInWhitespace;
if (ch == ' ' &&
(i + 1 >= aLength ||
!IsSpaceCombiningSequenceTail(aText, aLength - (i + 1)))) {
nowInWhitespace = true;
} else if (ch == '\n' && aCompression == COMPRESS_WHITESPACE_NEWLINE) {
if (i > 0 && IS_CJ_CHAR(aText[-1]) &&
i + 1 < aLength && IS_CJ_CHAR(aText[1])) {
// Discard newlines between CJK chars.
// XXX this really requires more context to get right!
aSkipChars->SkipChar();
continue;
}
nowInWhitespace = true;
} else {
nowInWhitespace = ch == '\t';
}
if (!nowInWhitespace) {
if (IsDiscardable(ch, &flags)) {
aSkipChars->SkipChar();
nowInWhitespace = inWhitespace;
} else {
*aOutput++ = ch;
aSkipChars->KeepChar();
lastCharArabic = IS_ARABIC_CHAR(ch);
}
} else {
if (inWhitespace) {
aSkipChars->SkipChar();
} else {
if (ch != ' ') {
flags |= TEXT_WAS_TRANSFORMED;
}
*aOutput++ = ' ';
aSkipChars->KeepChar();
}
}
inWhitespace = nowInWhitespace;
}
if (lastCharArabic) {
*aIncomingFlags |= INCOMING_ARABICCHAR;
} else {
*aIncomingFlags &= ~INCOMING_ARABICCHAR;
}
if (inWhitespace) {
*aIncomingFlags |= INCOMING_WHITESPACE;
} else {
*aIncomingFlags &= ~INCOMING_WHITESPACE;
}
}
if (outputStart + aLength != aOutput) {
flags |= TEXT_WAS_TRANSFORMED;
}
*aAnalysisFlags = flags;
return aOutput;
}
uint8_t*
nsTextFrameUtils::TransformText(const uint8_t* aText, uint32_t aLength,
uint8_t* aOutput,
CompressionMode aCompression,
uint8_t* aIncomingFlags,
gfxSkipCharsBuilder* aSkipChars,
uint32_t* aAnalysisFlags)
{
uint32_t flags = 0;
uint8_t* outputStart = aOutput;
if (aCompression == COMPRESS_NONE ||
aCompression == DISCARD_NEWLINE) {
// Skip discardables.
uint32_t i;
for (i = 0; i < aLength; ++i) {
uint8_t ch = *aText++;
if (IsDiscardable(ch, &flags) ||
(ch == '\n' && aCompression == DISCARD_NEWLINE)) {
aSkipChars->SkipChar();
} else {
aSkipChars->KeepChar();
if (ch == '\t') {
flags |= TEXT_HAS_TAB;
}
*aOutput++ = ch;
}
}
*aIncomingFlags &= ~(INCOMING_ARABICCHAR | INCOMING_WHITESPACE);
} else {
bool inWhitespace = (*aIncomingFlags & INCOMING_WHITESPACE) != 0;
uint32_t i;
for (i = 0; i < aLength; ++i) {
uint8_t ch = *aText++;
bool nowInWhitespace = ch == ' ' || ch == '\t' ||
(ch == '\n' && aCompression == COMPRESS_WHITESPACE_NEWLINE);
if (!nowInWhitespace) {
if (IsDiscardable(ch, &flags)) {
aSkipChars->SkipChar();
nowInWhitespace = inWhitespace;
} else {
*aOutput++ = ch;
aSkipChars->KeepChar();
}
} else {
if (inWhitespace) {
aSkipChars->SkipChar();
} else {
if (ch != ' ') {
flags |= TEXT_WAS_TRANSFORMED;
}
*aOutput++ = ' ';
aSkipChars->KeepChar();
}
}
inWhitespace = nowInWhitespace;
}
*aIncomingFlags &= ~INCOMING_ARABICCHAR;
if (inWhitespace) {
*aIncomingFlags |= INCOMING_WHITESPACE;
} else {
*aIncomingFlags &= ~INCOMING_WHITESPACE;
}
}
if (outputStart + aLength != aOutput) {
flags |= TEXT_WAS_TRANSFORMED;
}
*aAnalysisFlags = flags;
return aOutput;
}
uint32_t
nsTextFrameUtils::ComputeApproximateLengthWithWhitespaceCompression(
nsIContent *aContent, const nsStyleText *aStyleText)
{
const nsTextFragment *frag = aContent->GetText();
// This is an approximation so we don't really need anything
// too fancy here.
uint32_t len;
if (aStyleText->WhiteSpaceIsSignificant()) {
len = frag->GetLength();
} else {
bool is2b = frag->Is2b();
union {
const char *s1b;
const PRUnichar *s2b;
} u;
if (is2b) {
u.s2b = frag->Get2b();
} else {
u.s1b = frag->Get1b();
}
bool prevWS = true; // more important to ignore blocks with
// only whitespace than get inline boundaries
// exactly right
len = 0;
for (uint32_t i = 0, i_end = frag->GetLength(); i < i_end; ++i) {
PRUnichar c = is2b ? u.s2b[i] : u.s1b[i];
if (c == ' ' || c == '\n' || c == '\t' || c == '\r') {
if (!prevWS) {
++len;
}
prevWS = true;
} else {
++len;
prevWS = false;
}
}
}
return len;
}
bool nsSkipCharsRunIterator::NextRun() {
do {
if (mRunLength) {
mIterator.AdvanceOriginal(mRunLength);
NS_ASSERTION(mRunLength > 0, "No characters in run (initial length too large?)");
if (!mSkipped || mLengthIncludesSkipped) {
mRemainingLength -= mRunLength;
}
}
if (!mRemainingLength)
return false;
int32_t length;
mSkipped = mIterator.IsOriginalCharSkipped(&length);
mRunLength = std::min(length, mRemainingLength);
} while (!mVisitSkipped && mSkipped);
return true;
}
|