feat: footnote anchor navigation (#1245)
## Summary: Enable footnote anchor navigation in EPUB reader This PR extracts the core anchor-to-page mapping mechanism from PR #1143 (TOC fragment navigation) to provide immediate footnote navigation support. By merging this focused subset first, users get a complete footnote experience now while simplifying the eventual review and merge of the full #1143 PR. --- ## What this extracts from PR #1143 PR #1143 implements comprehensive TOC fragment navigation for EPUBs with multi-chapter spine files. This PR takes only the anchor resolution infrastructure: - Anchor-to-page mapping in section cache: During page layout, ChapterHtmlSlimParser records which page each HTML id attribute lands on, serializing the map into the .bin cache file. - Anchor resolution in `EpubReaderActivity`: When navigating to a footnote link with a fragment (e.g., `chapter2.xhtml#note1`), the reader resolves the anchor to a page number and jumps directly to it. - Section file format change: Bumped to version 15, adds anchor map offset in header. --- ## Simplified scope vs. PR #1143 To minimize conflicts and complexity, this PR differs from #1143 in key ways: * **Anchors tracked** * **Origin:** Only TOC anchors (passed via `std::set`) * **This branch:** All `id` attributes * **Page breaks** * **Origin**: Forces new page at TOC chapter boundaries * **This branch:** None — natural flow * **TOC integration** * **Origin**: `tocBoundaries`, `getTocIndexForPage()`, chapter skip * **This branch:** None — just footnote links * **Bug fix** * **This branch:** Fixed anchor page off-by-1/2 bug The anchor recording bug (recording page number before `makePages()` flushes previous block) was identified and fixed during this extraction. The fix uses a deferred `pendingAnchorId` pattern that records the anchor after page completion. --- ## Positioning for future merge Changes are structured to minimize conflicts when #1143 eventually merges: - `ChapterHtmlSlimParser.cpp` `startElement()`: Both branches rewrite the same if `(!idAttr.empty())` block. The merged version will combine both approaches (TOC anchors get page breaks + immediate recording; footnote anchors get deferred recording). - `EpubReaderActivity.cpp` `render()`: The `pendingAnchor` resolution block is positioned at the exact same insertion point where #1143 places its `pendingTocIndex` block (line 596, right after `nextPageNumber` assignment). During merge, both blocks will sit side-by-side. --- ## Why merge separately? 1. Immediate user value: Footnote navigation works now without waiting for the full TOC overhaul 2. Easier review: ~100 lines vs. 500+ lines in #1143 3. Bug fix included: The page recording bug is fixed here and will carry into #1143 4. Minimal conflicts: Structured for clean merge — both PRs touch the same files but in complementary ways --- ### AI Usage Did you use AI tools to help write this code? _**< YES >**_ Done by Claude Opus 4.6
This commit is contained in:
Uri Tauber
@@ -10,10 +10,10 @@
|
||||
#include "parsers/ChapterHtmlSlimParser.h"
|
||||
|
||||
namespace {
|
||||
constexpr uint8_t SECTION_FILE_VERSION = 17;
|
||||
constexpr uint8_t SECTION_FILE_VERSION = 18;
|
||||
constexpr uint32_t HEADER_SIZE = sizeof(uint8_t) + sizeof(int) + sizeof(float) + sizeof(bool) + sizeof(uint8_t) +
|
||||
sizeof(uint16_t) + sizeof(uint16_t) + sizeof(uint16_t) + sizeof(bool) + sizeof(bool) +
|
||||
sizeof(uint8_t) + sizeof(uint32_t);
|
||||
sizeof(uint8_t) + sizeof(uint32_t) + sizeof(uint32_t);
|
||||
} // namespace
|
||||
|
||||
uint32_t Section::onPageComplete(std::unique_ptr<Page> page) {
|
||||
@@ -44,7 +44,7 @@ void Section::writeSectionFileHeader(const int fontId, const float lineCompressi
|
||||
static_assert(HEADER_SIZE == sizeof(SECTION_FILE_VERSION) + sizeof(fontId) + sizeof(lineCompression) +
|
||||
sizeof(extraParagraphSpacing) + sizeof(paragraphAlignment) + sizeof(viewportWidth) +
|
||||
sizeof(viewportHeight) + sizeof(pageCount) + sizeof(hyphenationEnabled) +
|
||||
sizeof(embeddedStyle) + sizeof(imageRendering) + sizeof(uint32_t),
|
||||
sizeof(embeddedStyle) + sizeof(imageRendering) + sizeof(uint32_t) + sizeof(uint32_t),
|
||||
"Header size mismatch");
|
||||
serialization::writePod(file, SECTION_FILE_VERSION);
|
||||
serialization::writePod(file, fontId);
|
||||
@@ -56,8 +56,9 @@ void Section::writeSectionFileHeader(const int fontId, const float lineCompressi
|
||||
serialization::writePod(file, hyphenationEnabled);
|
||||
serialization::writePod(file, embeddedStyle);
|
||||
serialization::writePod(file, imageRendering);
|
||||
serialization::writePod(file, pageCount); // Placeholder for page count (will be initially 0 when written)
|
||||
serialization::writePod(file, static_cast<uint32_t>(0)); // Placeholder for LUT offset
|
||||
serialization::writePod(file, pageCount); // Placeholder for page count (will be initially 0, patched later)
|
||||
serialization::writePod(file, static_cast<uint32_t>(0)); // Placeholder for LUT offset (patched later)
|
||||
serialization::writePod(file, static_cast<uint32_t>(0)); // Placeholder for anchor map offset (patched later)
|
||||
}
|
||||
|
||||
bool Section::loadSectionFile(const int fontId, const float lineCompression, const bool extraParagraphSpacing,
|
||||
@@ -239,10 +240,20 @@ bool Section::createSectionFile(const int fontId, const float lineCompression, c
|
||||
return false;
|
||||
}
|
||||
|
||||
// Go back and write LUT offset
|
||||
file.seek(HEADER_SIZE - sizeof(uint32_t) - sizeof(pageCount));
|
||||
// Write anchor-to-page map for fragment navigation (e.g. footnote targets)
|
||||
const uint32_t anchorMapOffset = file.position();
|
||||
const auto& anchors = visitor.getAnchors();
|
||||
serialization::writePod(file, static_cast<uint16_t>(anchors.size()));
|
||||
for (const auto& [anchor, page] : anchors) {
|
||||
serialization::writeString(file, anchor);
|
||||
serialization::writePod(file, page);
|
||||
}
|
||||
|
||||
// Patch header with final pageCount, lutOffset, and anchorMapOffset
|
||||
file.seek(HEADER_SIZE - sizeof(uint32_t) * 2 - sizeof(pageCount));
|
||||
serialization::writePod(file, pageCount);
|
||||
serialization::writePod(file, lutOffset);
|
||||
serialization::writePod(file, anchorMapOffset);
|
||||
file.close();
|
||||
if (cssParser) {
|
||||
cssParser->clear();
|
||||
@@ -255,7 +266,7 @@ std::unique_ptr<Page> Section::loadPageFromSectionFile() {
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
file.seek(HEADER_SIZE - sizeof(uint32_t));
|
||||
file.seek(HEADER_SIZE - sizeof(uint32_t) * 2);
|
||||
uint32_t lutOffset;
|
||||
serialization::readPod(file, lutOffset);
|
||||
file.seek(lutOffset + sizeof(uint32_t) * currentPage);
|
||||
@@ -267,3 +278,36 @@ std::unique_ptr<Page> Section::loadPageFromSectionFile() {
|
||||
file.close();
|
||||
return page;
|
||||
}
|
||||
|
||||
std::optional<uint16_t> Section::getPageForAnchor(const std::string& anchor) const {
|
||||
FsFile f;
|
||||
if (!Storage.openFileForRead("SCT", filePath, f)) {
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
const uint32_t fileSize = f.size();
|
||||
f.seek(HEADER_SIZE - sizeof(uint32_t));
|
||||
uint32_t anchorMapOffset;
|
||||
serialization::readPod(f, anchorMapOffset);
|
||||
if (anchorMapOffset == 0 || anchorMapOffset >= fileSize) {
|
||||
f.close();
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
f.seek(anchorMapOffset);
|
||||
uint16_t count;
|
||||
serialization::readPod(f, count);
|
||||
for (uint16_t i = 0; i < count; i++) {
|
||||
std::string key;
|
||||
uint16_t page;
|
||||
serialization::readString(f, key);
|
||||
serialization::readPod(f, page);
|
||||
if (key == anchor) {
|
||||
f.close();
|
||||
return page;
|
||||
}
|
||||
}
|
||||
|
||||
f.close();
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user