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

Merge pull request #123 from jpirnay/fix-indexing-on-toc-pagebreak

Browse Source 
fix: Fix reindexing loop on toc-page-break
This commit is contained in:
jpirnay
2026-04-23 16:34:07 +02:00
committed by GitHub
parent d9d6e32359 e0e3bd4251
commit 1d4748d20c
2 changed files with 20 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
+16 -21
View File
@@ -170,6 +170,17 @@ void ChapterHtmlSlimParser::flushPartWordBuffer() {
nextWordContinues = false;
}
// Emit the current page, keeping paragraphLutPerPage and completedPageCount in lockstep.
// Callers must ensure currentPage is non-null and carries content; the helper resets
// currentPage to a fresh Page and zeroes currentPageNextY so the caller can keep building.
void ChapterHtmlSlimParser::emitPage(uint32_t xhtmlByteOffset) {
paragraphLutPerPage.push_back({xhtmlByteOffset, xpathParagraphIndex});
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
currentPageNextY = 0;
}
// start a new text block if needed
void ChapterHtmlSlimParser::startNewTextBlock(const BlockStyle& blockStyle) {
nextWordContinues = false; // New block = new paragraph, no continuation
@@ -198,10 +209,7 @@ void ChapterHtmlSlimParser::startNewTextBlock(const BlockStyle& blockStyle) {
if (!pendingAnchorId.empty()) {
if (std::find(tocAnchors.begin(), tocAnchors.end(), pendingAnchorId) != tocAnchors.end()) {
if (currentPage && !currentPage->elements.empty()) {
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
currentPageNextY = 0;
emitPage(lastBodyChildByteOffset);
}
}
anchorData.push_back({std::move(pendingAnchorId), static_cast<uint16_t>(completedPageCount)});
@@ -218,10 +226,7 @@ void ChapterHtmlSlimParser::startNewTextBlock(const BlockStyle& blockStyle) {
if (!pendingAnchorId.empty() &&
std::find(tocAnchors.begin(), tocAnchors.end(), pendingAnchorId) != tocAnchors.end()) {
if (currentPage && !currentPage->elements.empty()) {
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
currentPageNextY = 0;
emitPage(lastBodyChildByteOffset);
}
}
// Record deferred anchor after previous block is flushed (and any TOC page break)
@@ -593,15 +598,11 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
(self->currentPageNextY + totalImageHeightWithSpacing > self->viewportHeight)) {
LOG_DBG("EHP", "Image page break: currentY=%d needed=%d viewportH=%d", self->currentPageNextY,
totalImageHeightWithSpacing, self->viewportHeight);
self->paragraphLutPerPage.push_back({self->lastBodyChildByteOffset, self->xpathParagraphIndex});
self->completePageFn(std::move(self->currentPage));
self->completedPageCount++;
self->currentPage.reset(new Page());
self->emitPage(self->lastBodyChildByteOffset);
if (!self->currentPage) {
LOG_ERR("EHP", "Failed to create new page");
return;
}
self->currentPageNextY = 0;
} else if (!self->currentPage) {
self->currentPage.reset(new Page());
if (!self->currentPage) {
@@ -1423,9 +1424,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
anchorData.push_back({std::move(pendingAnchorId), static_cast<uint16_t>(completedPageCount)});
pendingAnchorId.clear();
}
paragraphLutPerPage.push_back({0u, xpathParagraphIndex}); // post-parse: no byte offset available
completePageFn(std::move(currentPage));
completedPageCount++;
emitPage(0u); // post-parse: no byte offset available
currentPage.reset();
currentTextBlock.reset();
}
@@ -1444,11 +1443,7 @@ ParsedText::LineProcessResult ChapterHtmlSlimParser::addLineToPage(std::shared_p
}
if (currentPageNextY + lineHeight > viewportHeight) {
paragraphLutPerPage.push_back({lastBodyChildByteOffset, xpathParagraphIndex});
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
currentPageNextY = 0;
emitPage(lastBodyChildByteOffset);
}
const bool noRoomForAnotherLine =
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.h
+4
View File
@@ -127,6 +127,10 @@ class ChapterHtmlSlimParser {
void startNewTextBlock(const BlockStyle& blockStyle);
void flushPartWordBuffer();
void makePages();
// Emit currentPage to the consumer while keeping paragraphLutPerPage and completedPageCount
// in lockstep. Every page break MUST go through this helper; open-coded completePageFn
// calls risk desynchronising paragraphLutPerPage and failing the size check in Section.cpp.
void emitPage(uint32_t xhtmlByteOffset);
// XML callbacks
static void XMLCALL startElement(void* userData, const XML_Char* name, const XML_Char** atts);
static void XMLCALL characterData(void* userData, const XML_Char* s, int len);