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

Picking up some itsthisjutin ideas

Browse Source
This commit is contained in:
jpirnay
2026-04-19 19:03:43 +02:00
parent 174a08831d
commit d6292920d9
18 changed files with 337 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
+11 -3
View File
@@ -593,7 +593,9 @@ 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->paragraphIndexPerPage.push_back(self->xpathParagraphIndex);
const uint32_t byteOff =
self->activeParser ? static_cast<uint32_t>(XML_GetCurrentByteIndex(self->activeParser)) : 0;
self->paragraphLutPerPage.push_back({byteOff, self->xpathParagraphIndex});
self->completePageFn(std::move(self->currentPage));
self->completedPageCount++;
self->currentPage.reset(new Page());
@@ -1344,6 +1346,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
XML_SetUserData(parser, this);
XML_SetElementHandler(parser, startElement, endElement);
XML_SetCharacterDataHandler(parser, characterData);
activeParser = parser;
// Compute the time taken to parse and build pages
const uint32_t chapterStartTime = millis();
@@ -1354,6 +1357,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
XML_StopParser(parser, XML_FALSE); // Stop any pending processing
XML_SetElementHandler(parser, nullptr, nullptr); // Clear callbacks
XML_SetCharacterDataHandler(parser, nullptr);
activeParser = nullptr;
XML_ParserFree(parser);
file.close();
return false;
@@ -1376,6 +1380,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
XML_StopParser(parser, XML_FALSE); // Stop any pending processing
XML_SetElementHandler(parser, nullptr, nullptr); // Clear callbacks
XML_SetCharacterDataHandler(parser, nullptr);
activeParser = nullptr;
XML_ParserFree(parser);
file.close();
return false;
@@ -1389,6 +1394,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
XML_StopParser(parser, XML_FALSE); // Stop any pending processing
XML_SetElementHandler(parser, nullptr, nullptr); // Clear callbacks
XML_SetCharacterDataHandler(parser, nullptr);
activeParser = nullptr;
XML_ParserFree(parser);
file.close();
return false;
@@ -1400,6 +1406,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
XML_StopParser(parser, XML_FALSE); // Stop any pending processing
XML_SetElementHandler(parser, nullptr, nullptr); // Clear callbacks
XML_SetCharacterDataHandler(parser, nullptr);
activeParser = nullptr;
XML_ParserFree(parser);
file.close();
@@ -1410,7 +1417,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
anchorData.push_back({std::move(pendingAnchorId), static_cast<uint16_t>(completedPageCount)});
pendingAnchorId.clear();
}
paragraphIndexPerPage.push_back(xpathParagraphIndex);
paragraphLutPerPage.push_back({0u, xpathParagraphIndex}); // post-parse: no byte offset available
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset();
@@ -1431,7 +1438,8 @@ ParsedText::LineProcessResult ChapterHtmlSlimParser::addLineToPage(std::shared_p
}
if (currentPageNextY + lineHeight > viewportHeight) {
paragraphIndexPerPage.push_back(xpathParagraphIndex);
const uint32_t byteOff = activeParser ? static_cast<uint32_t>(XML_GetCurrentByteIndex(activeParser)) : 0;
paragraphLutPerPage.push_back({byteOff, xpathParagraphIndex});
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.h
+14 -4
View File
@@ -90,9 +90,19 @@ class ChapterHtmlSlimParser {
// Counts <p> sibling indices (1-based, matching XPath convention) during page building.
// Stored per page in the section cache so that XPath p[N] can be resolved to a page
// without reparsing, and current page can generate an XPath without reparsing.
uint16_t xpathParagraphIndex = 0; // current <p> sibling index (1-based)
int xpathBodyDepth = -1; // depth of the <body> element (-1 = not yet seen)
std::vector<uint16_t> paragraphIndexPerPage; // <p> index at each page completion
uint16_t xpathParagraphIndex = 0; // current <p> sibling index (1-based)
int xpathBodyDepth = -1; // depth of the <body> element (-1 = not yet seen)
struct ParagraphLutEntry {
uint32_t xhtmlByteOffset; // Expat byte offset at page break — used to seek near target paragraph
uint16_t paragraphIndex; // 1-based <p> index at page completion
};
std::vector<ParagraphLutEntry> paragraphLutPerPage; // deep LUT: one entry per page
// Active parser handle during parseAndBuildPages(), nullptr otherwise.
// Stored as a member so page-break sites (addLineToPage, image breaks) can call
// XML_GetCurrentByteIndex without needing the parser threaded through every call.
XML_Parser activeParser = nullptr;
// Footnote link tracking
bool insideFootnoteLink = false;
@@ -154,5 +164,5 @@ class ChapterHtmlSlimParser {
ParsedText::LineProcessResult addLineToPage(std::shared_ptr<TextBlock> line, bool lineEndsWithHyphenatedWord,
bool suppressHyphenationRetry);
const std::vector<std::pair<std::string, uint16_t>>& getAnchors() const { return anchorData; }
const std::vector<uint16_t>& getParagraphIndexPerPage() const { return paragraphIndexPerPage; }
const std::vector<ParagraphLutEntry>& getParagraphLutPerPage() const { return paragraphLutPerPage; }
};