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

Add paragraph index LUT for accurate KOReader position sync

Browse Source 
Store per-page paragraph indices in section cache to enable precise
XPath-to-page and page-to-XPath mapping without reparsing XHTML.

Forward path (upload): generates XPath directly from paragraph LUT
instead of byte-offset estimation, eliminating drift in chapters
with non-uniform content density.

Reverse path (download): resolves incoming KOReader XPath p[N] to
the exact page via paragraph LUT lookup.

Paragraph counter counts all <p> elements including display:none
to match ChapterXPathIndexer and crengine's standard XPath counting.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
jpirnay
2026-03-22 12:29:26 +01:00
co-authored by Claude Opus 4.6
parent dccb82642d
commit b625b8bd26
17 changed files with 354 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
+15
View File
@@ -491,6 +491,19 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
}
}
// Track body element depth for paragraph index counting
if (strcmp(name, "body") == 0 && self->xpathBodyDepth < 0) {
self->xpathBodyDepth = self->depth;
}
// Count <p> sibling indices at body-child level. Must happen BEFORE the display:none
// check so that hidden <p> elements are still counted, matching ChapterXPathIndexer's
// counting (pure XML, no CSS). This ensures paragraph indices in the section cache LUT
// align with KOReader's crengine XPath indices.
if (self->xpathBodyDepth >= 0 && self->depth == self->xpathBodyDepth + 1 && strcmp(name, "p") == 0) {
self->xpathParagraphIndex++;
}
if (matches(name, SKIP_TAGS, NUM_SKIP_TAGS)) {
// start skip
self->skipUntilDepth = self->depth;
@@ -1062,6 +1075,7 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
anchorData.push_back({std::move(pendingAnchorId), static_cast<uint16_t>(completedPageCount)});
pendingAnchorId.clear();
}
paragraphIndexPerPage.push_back(xpathParagraphIndex);
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset();
@@ -1080,6 +1094,7 @@ void ChapterHtmlSlimParser::addLineToPage(std::shared_ptr<TextBlock> line) {
}
if (currentPageNextY + lineHeight > viewportHeight) {
paragraphIndexPerPage.push_back(xpathParagraphIndex);
completePageFn(std::move(currentPage));
completedPageCount++;
currentPage.reset(new Page());
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.h
+9
View File
@@ -75,6 +75,14 @@ class ChapterHtmlSlimParser {
std::vector<std::pair<std::string, uint16_t>> anchorData;
std::string pendingAnchorId; // deferred until after previous text block is flushed
// Paragraph index tracking for XPath-to-page lookup table.
// 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
// Footnote link tracking
bool insideFootnoteLink = false;
int footnoteLinkDepth = -1;
@@ -126,4 +134,5 @@ class ChapterHtmlSlimParser {
bool parseAndBuildPages();
void addLineToPage(std::shared_ptr<TextBlock> line);
const std::vector<std::pair<std::string, uint16_t>>& getAnchors() const { return anchorData; }
const std::vector<uint16_t>& getParagraphIndexPerPage() const { return paragraphIndexPerPage; }
};