eric/Crosspoint
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/jpirnay/crosspoint-reader into mybuild

Browse Source
This commit is contained in:
jpirnay
2026-03-13 21:24:04 +01:00
parent 2008060a81 dabdfcd683
commit 9b70ddc93b
83 changed files with 104973 additions and 120228 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Epub/Epub/Page.h
+1
View File
@@ -2,6 +2,7 @@
#include <HalStorage.h>
#include <algorithm>
#include <string>
#include <utility>
#include <vector>
lib/Epub/Epub/ParsedText.cpp
+18 -26
View File
@@ -101,20 +101,19 @@ void ParsedText::layoutAndExtractLines(const GfxRenderer& renderer, const int fo
applyParagraphIndent();
const int pageWidth = viewportWidth;
const int spaceWidth = renderer.getSpaceWidth(fontId, EpdFontFamily::REGULAR);
auto wordWidths = calculateWordWidths(renderer, fontId);
std::vector<size_t> lineBreakIndices;
if (hyphenationEnabled) {
// Use greedy layout that can split words mid-loop when a hyphenated prefix fits.
lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths, wordContinues);
lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues);
} else {
lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths, wordContinues);
lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues);
}
const size_t lineCount = includeLastLine ? lineBreakIndices.size() : lineBreakIndices.size() - 1;
for (size_t i = 0; i < lineCount; ++i) {
extractLine(i, pageWidth, spaceWidth, wordWidths, wordContinues, lineBreakIndices, processLine, renderer, fontId);
extractLine(i, pageWidth, wordWidths, wordContinues, lineBreakIndices, processLine, renderer, fontId);
}
// Remove consumed words so size() reflects only remaining words
@@ -138,8 +137,7 @@ std::vector<uint16_t> ParsedText::calculateWordWidths(const GfxRenderer& rendere
}
std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, const int fontId, const int pageWidth,
const int spaceWidth, std::vector<uint16_t>& wordWidths,
std::vector<bool>& continuesVec) {
std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec) {
if (words.empty()) {
return {};
}
@@ -187,9 +185,8 @@ std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, c
// Add space before word j, unless it's the first word on the line or a continuation
int gap = 0;
if (j > static_cast<size_t>(i) && !continuesVec[j]) {
gap = spaceWidth;
gap += renderer.getSpaceKernAdjust(fontId, lastCodepoint(words[j - 1]), firstCodepoint(words[j]),
wordStyles[j - 1]);
gap =
renderer.getSpaceAdvance(fontId, lastCodepoint(words[j - 1]), firstCodepoint(words[j]), wordStyles[j - 1]);
} else if (j > static_cast<size_t>(i) && continuesVec[j]) {
// Cross-boundary kerning for continuation words (e.g. nonbreaking spaces, attached punctuation)
gap = renderer.getKerning(fontId, lastCodepoint(words[j - 1]), firstCodepoint(words[j]), wordStyles[j - 1]);
@@ -275,8 +272,7 @@ void ParsedText::applyParagraphIndent() {
// Builds break indices while opportunistically splitting the word that would overflow the current line.
std::vector<size_t> ParsedText::computeHyphenatedLineBreaks(const GfxRenderer& renderer, const int fontId,
const int pageWidth, const int spaceWidth,
std::vector<uint16_t>& wordWidths,
const int pageWidth, std::vector<uint16_t>& wordWidths,
std::vector<bool>& continuesVec) {
// Calculate first line indent (only for left/justified text).
// Positive text-indent (paragraph indent) is suppressed when extraParagraphSpacing is on.
@@ -304,9 +300,8 @@ std::vector<size_t> ParsedText::computeHyphenatedLineBreaks(const GfxRenderer& r
const bool isFirstWord = currentIndex == lineStart;
int spacing = 0;
if (!isFirstWord && !continuesVec[currentIndex]) {
spacing = spaceWidth;
spacing += renderer.getSpaceKernAdjust(fontId, lastCodepoint(words[currentIndex - 1]),
firstCodepoint(words[currentIndex]), wordStyles[currentIndex - 1]);
spacing = renderer.getSpaceAdvance(fontId, lastCodepoint(words[currentIndex - 1]),
firstCodepoint(words[currentIndex]), wordStyles[currentIndex - 1]);
} else if (!isFirstWord && continuesVec[currentIndex]) {
// Cross-boundary kerning for continuation words (e.g. nonbreaking spaces, attached punctuation)
spacing = renderer.getKerning(fontId, lastCodepoint(words[currentIndex - 1]),
@@ -440,9 +435,8 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
return true;
}
void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const int spaceWidth,
const std::vector<uint16_t>& wordWidths, const std::vector<bool>& continuesVec,
const std::vector<size_t>& lineBreakIndices,
void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const std::vector<uint16_t>& wordWidths,
const std::vector<bool>& continuesVec, const std::vector<size_t>& lineBreakIndices,
const std::function<void(std::shared_ptr<TextBlock>)>& processLine,
const GfxRenderer& renderer, const int fontId) {
const size_t lineBreak = lineBreakIndices[breakIndex];
@@ -471,11 +465,9 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
// Count gaps: each word after the first creates a gap, unless it's a continuation
if (wordIdx > 0 && !continuesVec[lastBreakAt + wordIdx]) {
actualGapCount++;
int naturalGap = spaceWidth;
naturalGap += renderer.getSpaceKernAdjust(fontId, lastCodepoint(words[lastBreakAt + wordIdx - 1]),
firstCodepoint(words[lastBreakAt + wordIdx]),
wordStyles[lastBreakAt + wordIdx - 1]);
totalNaturalGaps += naturalGap;
totalNaturalGaps +=
renderer.getSpaceAdvance(fontId, lastCodepoint(words[lastBreakAt + wordIdx - 1]),
firstCodepoint(words[lastBreakAt + wordIdx]), wordStyles[lastBreakAt + wordIdx - 1]);
} else if (wordIdx > 0 && continuesVec[lastBreakAt + wordIdx]) {
// Cross-boundary kerning for continuation words (e.g. nonbreaking spaces, attached punctuation)
totalNaturalGaps +=
@@ -520,11 +512,11 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
firstCodepoint(words[lastBreakAt + wordIdx + 1]), wordStyles[lastBreakAt + wordIdx]);
xpos += advance;
} else {
int gap = spaceWidth;
int gap = 0;
if (wordIdx + 1 < lineWordCount) {
gap += renderer.getSpaceKernAdjust(fontId, lastCodepoint(words[lastBreakAt + wordIdx]),
firstCodepoint(words[lastBreakAt + wordIdx + 1]),
wordStyles[lastBreakAt + wordIdx]);
gap = renderer.getSpaceAdvance(fontId, lastCodepoint(words[lastBreakAt + wordIdx]),
firstCodepoint(words[lastBreakAt + wordIdx + 1]),
wordStyles[lastBreakAt + wordIdx]);
}
if (blockStyle.alignment == CssTextAlign::Justify && !isLastLine) {
gap += justifyExtra;
lib/Epub/Epub/ParsedText.h
+3 -4
View File
@@ -21,14 +21,13 @@ class ParsedText {
bool hyphenationEnabled;
void applyParagraphIndent();
std::vector<size_t> computeLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth, int spaceWidth,
std::vector<size_t> computeLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth,
std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec);
std::vector<size_t> computeHyphenatedLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth,
int spaceWidth, std::vector<uint16_t>& wordWidths,
std::vector<bool>& continuesVec);
std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec);
bool hyphenateWordAtIndex(size_t wordIndex, int availableWidth, const GfxRenderer& renderer, int fontId,
std::vector<uint16_t>& wordWidths, bool allowFallbackBreaks);
void extractLine(size_t breakIndex, int pageWidth, int spaceWidth, const std::vector<uint16_t>& wordWidths,
void extractLine(size_t breakIndex, int pageWidth, const std::vector<uint16_t>& wordWidths,
const std::vector<bool>& continuesVec, const std::vector<size_t>& lineBreakIndices,
const std::function<void(std::shared_ptr<TextBlock>)>& processLine, const GfxRenderer& renderer,
int fontId);
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
+34 -3
View File
@@ -4,6 +4,7 @@
#include <GfxRenderer.h>
#include <HalStorage.h>
#include <Logging.h>
#include <Utf8.h>
#include <expat.h>
#include "../../Epub.h"
@@ -758,9 +759,30 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
}
}
// If we're about to run out of space, then cut the word off and start a new one
// If we're about to run out of space, then cut the word off and start a new one.
// For CJK text (no spaces), this is the primary word-breaking mechanism.
// We must avoid splitting multi-byte UTF-8 sequences across word boundaries,
// otherwise the trailing bytes become orphaned continuation bytes that the
// decoder can't interpret.
if (self->partWordBufferIndex >= MAX_WORD_SIZE) {
self->flushPartWordBuffer();
int safeLen = utf8SafeTruncateBuffer(self->partWordBuffer, self->partWordBufferIndex);
if (safeLen < self->partWordBufferIndex && safeLen > 0) {
// Incomplete UTF-8 sequence at the end — save it before flushing
int overflow = self->partWordBufferIndex - safeLen;
char saved[4];
for (int j = 0; j < overflow; j++) {
saved[j] = self->partWordBuffer[safeLen + j];
}
self->partWordBufferIndex = safeLen;
self->flushPartWordBuffer();
for (int j = 0; j < overflow; j++) {
self->partWordBuffer[j] = saved[j];
}
self->partWordBufferIndex = overflow;
} else {
self->flushPartWordBuffer();
}
}
self->partWordBuffer[self->partWordBufferIndex++] = s[i];
@@ -772,8 +794,12 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
// Spotted when reading Intermezzo, there are some really long text blocks in there.
if (self->currentTextBlock->size() > 750) {
LOG_DBG("EHP", "Text block too long, splitting into multiple pages");
const int horizontalInset = self->currentTextBlock->getBlockStyle().totalHorizontalInset();
const uint16_t effectiveWidth = (horizontalInset < self->viewportWidth)
? static_cast<uint16_t>(self->viewportWidth - horizontalInset)
: self->viewportWidth;
self->currentTextBlock->layoutAndExtractLines(
self->renderer, self->fontId, self->viewportWidth,
self->renderer, self->fontId, effectiveWidth,
[self](const std::shared_ptr<TextBlock>& textBlock) { self->addLineToPage(textBlock); }, false);
}
}
@@ -1020,6 +1046,11 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
void ChapterHtmlSlimParser::addLineToPage(std::shared_ptr<TextBlock> line) {
const int lineHeight = renderer.getLineHeight(fontId) * lineCompression;
if (!currentPage) {
currentPage.reset(new Page());
currentPageNextY = 0;
}
if (currentPageNextY + lineHeight > viewportHeight) {
completePageFn(std::move(currentPage));
completedPageCount++;