feat: Lazy incremental EPUB section indexing (#2452)

Co-authored-by: Uri Tauber <uritaube@gmail.com> Co-authored-by: Julia Nguyen <julia@uxj.io>
2026-07-04 21:21:24 +03:00
parent 79b4d63ee2
commit 685d4e88f9
14 changed files with 1055 additions and 262 deletions
@@ -2,6 +2,7 @@

 #include <HalStorage.h>
 #include <Logging.h>
+#include <Memory.h>
 #include <Serialization.h>

 #include "Epub/css/CssParser.h"
@@ -12,32 +13,57 @@
 namespace {
 // v28: text decoration bits now include line-through in serialized wordStyles.
 constexpr uint8_t SECTION_FILE_VERSION = 28;
+// Written into the version field while a build is in progress; patched to
+// SECTION_FILE_VERSION only when the build is finalized. An abandoned /
+// crash-interrupted .bin therefore carries version 0, which loadSectionFile rejects
+// as unknown and clears -- so an incomplete file is never mistaken for a valid one.
+constexpr uint8_t SECTION_FILE_INCOMPLETE_VERSION = 0;
+// Written when a build is suspended partway (reader exited or device slept mid-build).
+// The file carries valid pages 0..pageCount-1, all LUTs, and a trailer with the parse
+// watermark (bytesConsumed, totalBytes) appended after the li LUT. loadSectionFile
+// accepts it so a resume shows those pages instantly; the reader extends it by
+// rebuilding in the background. Uses the same header layout as SECTION_FILE_VERSION,
+// so finalized files are untouched by this feature; older firmware treats the sentinel
+// as an unknown version and rebuilds, which is a safe downgrade.
+constexpr uint8_t SECTION_FILE_PARTIAL_VERSION = 0xFE;
 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(bool) + sizeof(uint32_t) + sizeof(uint32_t) +
                                 sizeof(uint32_t) + sizeof(uint32_t);
-
-struct PageLutEntry {
-  uint32_t fileOffset;
-  uint16_t paragraphIndex;
-  uint16_t listItemIndex;
-};
 }  // namespace

+// Out-of-line so the unique_ptr<ChapterHtmlSlimParser> in BuildContext can be
+// constructed/destroyed where the parser's full definition is visible.
+Section::Section(const std::shared_ptr<Epub>& epub, const int spineIndex, GfxRenderer& renderer)
+    : epub(epub),
+      spineIndex(spineIndex),
+      renderer(renderer),
+      filePath(epub->getCachePath() + "/sections/" + std::to_string(spineIndex) + ".bin") {}
+
+// Suspend any in-progress build so every section.reset() / navigation / sleep path
+// persists the pages already laid out as a partial .bin instead of discarding them
+// (no-op once a build has completed or never started).
+Section::~Section() { suspendBuild(); }
+
 uint32_t Section::onPageComplete(std::unique_ptr<Page> page) {
  if (!file) {
-    LOG_ERR("SCT", "File not open for writing page %d", pageCount);
+    LOG_ERR("SCT", "File not open for writing page %d", builtPageCount_);
    return 0;
  }

  const uint32_t position = file.position();
  if (!page->serialize(file)) {
-    LOG_ERR("SCT", "Failed to serialize page %d", pageCount);
+    LOG_ERR("SCT", "Failed to serialize page %d", builtPageCount_);
    return 0;
  }
-  LOG_DBG("SCT", "Page %d processed", pageCount);
+  LOG_DBG("SCT", "Page %d processed", builtPageCount_);

-  pageCount++;
+  builtPageCount_++;
+  // pageCount is the pages available to read: a rebuild over a partial only raises it
+  // once it has laid out more pages than the partial already covers.
+  if (builtPageCount_ > pageCount) {
+    pageCount = builtPageCount_;
+  }
  return position;
 }

@@ -56,7 +82,9 @@ void Section::writeSectionFileHeader(const int fontId, const float lineCompressi
                                   sizeof(embeddedStyle) + sizeof(imageRendering) + sizeof(focusReadingEnabled) +
                                   sizeof(uint32_t) + sizeof(uint32_t) + sizeof(uint32_t) + sizeof(uint32_t),
                "Header size mismatch");
-  serialization::writePod(file, SECTION_FILE_VERSION);
+  // Written as the incomplete sentinel; finalizeBuild() patches it to
+  // SECTION_FILE_VERSION as the last step, committing the file.
+  serialization::writePod(file, SECTION_FILE_INCOMPLETE_VERSION);
  serialization::writePod(file, fontId);
  serialization::writePod(file, lineCompression);
  serialization::writePod(file, extraParagraphSpacing);
@@ -83,16 +111,18 @@ bool Section::loadSectionFile(const int fontId, const float lineCompression, con
  }

  // Match parameters
+  bool filePartial = false;
  {
    uint8_t version;
    serialization::readPod(file, version);
-    if (version != SECTION_FILE_VERSION) {
+    if (version != SECTION_FILE_VERSION && version != SECTION_FILE_PARTIAL_VERSION) {
      // Explicit close() required: member variable persists beyond function scope
      file.close();
      LOG_ERR("SCT", "Deserialization failed: Unknown version %u", version);
      clearCache();
      return false;
    }
+    filePartial = (version == SECTION_FILE_PARTIAL_VERSION);

    int fileFontId;
    uint16_t fileViewportWidth, fileViewportHeight;
@@ -127,14 +157,42 @@ bool Section::loadSectionFile(const int fontId, const float lineCompression, con
  }

  serialization::readPod(file, pageCount);
+
+  if (filePartial) {
+    // A partial's pageCount is the watermark of a suspended build. Read the watermark
+    // trailer (appended after the li LUT) so estimatedTotalPages can extrapolate.
+    uint32_t liLutOffset = 0;
+    file.seek(HEADER_SIZE - sizeof(uint32_t));
+    serialization::readPod(file, liLutOffset);
+    const uint32_t trailerOffset = liLutOffset + static_cast<uint32_t>(pageCount) * sizeof(uint16_t);
+    const bool trailerValid =
+        pageCount > 0 && liLutOffset >= HEADER_SIZE && trailerOffset + 2 * sizeof(uint32_t) <= file.size();
+    if (!trailerValid) {
+      file.close();
+      LOG_ERR("SCT", "Deserialization failed: malformed partial section");
+      clearCache();
+      pageCount = 0;
+      return false;
+    }
+    file.seek(trailerOffset);
+    serialization::readPod(file, partialBytesConsumed_);
+    serialization::readPod(file, partialTotalBytes_);
+    partial_ = true;
+    partialPageCount_ = pageCount;
+  }
+
  // Explicit close() required: member variable persists beyond function scope
  file.close();
-  LOG_DBG("SCT", "Deserialization succeeded: %d pages", pageCount);
+  LOG_DBG("SCT", "Deserialization succeeded: %d pages%s", pageCount, filePartial ? " (partial)" : "");
  return true;
 }

 // Your updated class method (assuming you are using the 'SD' object, which is a wrapper for a specific filesystem)
 bool Section::clearCache() const {
+  const std::string tmpBin = binTmpPath();
+  if (Storage.exists(tmpBin.c_str())) {
+    Storage.remove(tmpBin.c_str());
+  }
  if (!Storage.exists(filePath.c_str())) {
    LOG_DBG("SCT", "Cache does not exist, no action needed");
    return true;
@@ -154,8 +212,43 @@ bool Section::createSectionFile(const int fontId, const float lineCompression, c
                                const uint16_t viewportHeight, const bool hyphenationEnabled, const bool embeddedStyle,
                                const uint8_t imageRendering, const bool focusReadingEnabled,
                                const std::function<void()>& popupFn) {
+  // One-shot build: start, then lay out the whole section in a single pass.
+  if (!startBuild(fontId, lineCompression, extraParagraphSpacing, paragraphAlignment, viewportWidth, viewportHeight,
+                  hyphenationEnabled, embeddedStyle, imageRendering, focusReadingEnabled, popupFn)) {
+    return false;
+  }
+  if (!buildSomeMore(0)) {  // 0 = build to completion
+    return false;
+  }
+  return buildComplete_;
+}
+
+bool Section::startBuild(const int fontId, const float lineCompression, const bool extraParagraphSpacing,
+                         const uint8_t paragraphAlignment, const uint16_t viewportWidth, const uint16_t viewportHeight,
+                         const bool hyphenationEnabled, const bool embeddedStyle, const uint8_t imageRendering,
+                         const bool focusReadingEnabled, const std::function<void()>& popupFn) {
+  if (build_) {
+    LOG_ERR("SCT", "startBuild called while a build is already active");
+    return false;
+  }
+  buildComplete_ = false;
+  builtPageCount_ = 0;
+  // Pages from a loaded partial stay readable (from filePath) while this build writes
+  // to the tmp .bin, so availability never drops below the partial's watermark.
+  pageCount = partial_ ? partialPageCount_ : 0;
+
+  // Remove a stale tmp .bin from a crash-interrupted build; this build recreates it.
+  {
+    const std::string staleTmp = binTmpPath();
+    if (Storage.exists(staleTmp.c_str())) {
+      Storage.remove(staleTmp.c_str());
+    }
+  }
+
  const auto localPath = epub->getSpineItem(spineIndex).href;
-  const auto tmpHtmlPath = epub->getCachePath() + "/.tmp_" + std::to_string(spineIndex) + ".html";
+  const auto htmlDir = epub->getCachePath() + "/html";
+  const auto htmlPath = htmlDir + "/" + std::to_string(spineIndex) + ".html";
+  const auto tmpHtmlPath = htmlDir + "/.tmp_" + std::to_string(spineIndex) + ".html";

  // Create cache directory if it doesn't exist
  {
@@ -163,62 +256,101 @@ bool Section::createSectionFile(const int fontId, const float lineCompression, c
    Storage.mkdir(sectionsDir.c_str());
  }

-  // Retry logic for SD card timing issues
-  bool success = false;
-  uint32_t fileSize = 0;
-  for (int attempt = 0; attempt < 3 && !success; attempt++) {
-    if (attempt > 0) {
-      LOG_DBG("SCT", "Retrying stream (attempt %d)...", attempt + 1);
-      delay(50);  // Brief delay before retry
+  // Reuse the previously unzipped HTML if we already have it. The unzipped HTML is keyed only on the
+  // book (it lives in the per-book cache dir), not on render settings, so it survives the invalidation
+  // that wipes the layout (.bin) caches when font/margin/orientation change -- rebuilds then skip zip
+  // inflation entirely. It's promoted by an atomic rename as soon as the inflate succeeds (below), so
+  // even a window-only giant spine -- whose .bin never finalizes -- still caches its HTML, letting a
+  // reopen skip the multi-second inflate. If htmlPath exists it is known-complete.
+  const bool reusedHtml = Storage.exists(htmlPath.c_str());
+  bool htmlCached = reusedHtml;
+  if (reusedHtml) {
+    LOG_DBG("SCT", "Reusing cached HTML %s", htmlPath.c_str());
+  } else {
+    Storage.mkdir(htmlDir.c_str());
+
+    // Retry logic for SD card timing issues
+    bool streamed = false;
+    uint32_t fileSize = 0;
+    for (int attempt = 0; attempt < 3 && !streamed; attempt++) {
+      if (attempt > 0) {
+        LOG_DBG("SCT", "Retrying stream (attempt %d)...", attempt + 1);
+        delay(50);  // Brief delay before retry
+      }
+
+      // Remove any incomplete file from previous attempt before retrying
+      if (Storage.exists(tmpHtmlPath.c_str())) {
+        Storage.remove(tmpHtmlPath.c_str());
+      }
+
+      HalFile tmpHtml;
+      if (!Storage.openFileForWrite("SCT", tmpHtmlPath, tmpHtml)) {
+        continue;
+      }
+      // Larger chunks mean far fewer SD writes inflating the HTML; a 1KB chunk turned a 584KB
+      // single-spine novel into ~570 tiny writes (multi-second). 8KB keeps the transient buffers
+      // small while cutting the write count 8x.
+      streamed = epub->readItemContentsToStream(localPath, tmpHtml, 8192);
+      fileSize = tmpHtml.size();
+      // Explicitly close() file before calling Storage.remove()
+      tmpHtml.close();
+
+      // If streaming failed, remove the incomplete file immediately
+      if (!streamed && Storage.exists(tmpHtmlPath.c_str())) {
+        Storage.remove(tmpHtmlPath.c_str());
+        LOG_DBG("SCT", "Removed incomplete temp file after failed attempt");
+      }
    }

-    // Remove any incomplete file from previous attempt before retrying
-    if (Storage.exists(tmpHtmlPath.c_str())) {
-      Storage.remove(tmpHtmlPath.c_str());
+    if (!streamed) {
+      LOG_ERR("SCT", "Failed to stream item contents to temp file after retries");
+      return false;
    }

-    HalFile tmpHtml;
-    if (!Storage.openFileForWrite("SCT", tmpHtmlPath, tmpHtml)) {
-      continue;
-    }
-    success = epub->readItemContentsToStream(localPath, tmpHtml, 1024);
-    fileSize = tmpHtml.size();
-    // Explicitly close() file before calling Storage.remove()
-    tmpHtml.close();
+    LOG_DBG("SCT", "Streamed temp HTML to %s (%d bytes)", tmpHtmlPath.c_str(), fileSize);

-    // If streaming failed, remove the incomplete file immediately
-    if (!success && Storage.exists(tmpHtmlPath.c_str())) {
-      Storage.remove(tmpHtmlPath.c_str());
-      LOG_DBG("SCT", "Removed incomplete temp file after failed attempt");
+    // Promote to the persistent HTML cache immediately -- the inflate is complete and the bytes are
+    // valid regardless of whether the layout build finishes, so reopening (even a window-only spine
+    // that never finalizes its .bin) skips re-inflation. If the rename fails we just parse the temp.
+    if (Storage.rename(tmpHtmlPath.c_str(), htmlPath.c_str())) {
+      htmlCached = true;
+    } else {
+      LOG_DBG("SCT", "Failed to promote HTML cache; parsing from temp");
    }
  }

-  if (!success) {
-    LOG_ERR("SCT", "Failed to stream item contents to temp file after retries");
-    return false;
-  }
-
-  LOG_DBG("SCT", "Streamed temp HTML to %s (%d bytes)", tmpHtmlPath.c_str(), fileSize);
-
-  if (!Storage.openFileForWrite("SCT", filePath, file)) {
+  if (!Storage.openFileForWrite("SCT", binTmpPath(), file)) {
+    if (!reusedHtml) Storage.remove(tmpHtmlPath.c_str());
    return false;
  }
+  // Header is written with the incomplete-version sentinel; finalizeBuild() commits it.
  writeSectionFileHeader(fontId, lineCompression, extraParagraphSpacing, paragraphAlignment, viewportWidth,
                         viewportHeight, hyphenationEnabled, embeddedStyle, imageRendering, focusReadingEnabled);
-  std::vector<PageLutEntry> lut = {};
+
+  auto ctx = makeUniqueNoThrow<BuildContext>();
+  if (!ctx) {
+    LOG_ERR("SCT", "OOM: BuildContext");
+    file.close();
+    Storage.remove(binTmpPath().c_str());
+    if (!reusedHtml) Storage.remove(tmpHtmlPath.c_str());
+    return false;
+  }
+  // htmlCached == "htmlPath is the live cache" (reused, or just promoted). finalizeBuild/abandonBuild
+  // then leave the cached HTML alone; only an un-promoted temp (rename failed) is theirs to clean up.
+  ctx->reusedHtml = htmlCached;
+  ctx->htmlPath = htmlPath;
+  ctx->tmpHtmlPath = tmpHtmlPath;
+  ctx->parsePath = htmlCached ? htmlPath : tmpHtmlPath;

  // Derive the content base directory and image cache path prefix for the parser
-  size_t lastSlash = localPath.find_last_of('/');
-  std::string contentBase = (lastSlash != std::string::npos) ? localPath.substr(0, lastSlash + 1) : "";
-  std::string imageBasePath = epub->getCachePath() + "/img_" + std::to_string(spineIndex) + "_";
+  const size_t lastSlash = localPath.find_last_of('/');
+  ctx->contentBase = (lastSlash != std::string::npos) ? localPath.substr(0, lastSlash + 1) : "";
+  ctx->imageBasePath = epub->getCachePath() + "/img_" + std::to_string(spineIndex) + "_";

-  CssParser* cssParser = nullptr;
  if (embeddedStyle) {
-    cssParser = epub->getCssParser();
-    if (cssParser) {
-      if (!cssParser->loadFromCache()) {
-        LOG_ERR("SCT", "Failed to load CSS from cache");
-      }
+    ctx->cssParser = epub->getCssParser();
+    if (ctx->cssParser && !ctx->cssParser->loadFromCache()) {
+      LOG_ERR("SCT", "Failed to load CSS from cache");
    }
  }

@@ -235,104 +367,367 @@ bool Section::createSectionFile(const int fontId, const float lineCompression, c
    }
  }

-  ChapterHtmlSlimParser visitor(
-      epub, tmpHtmlPath, renderer, fontId, lineCompression, extraParagraphSpacing, paragraphAlignment, viewportWidth,
-      viewportHeight, hyphenationEnabled, focusReadingEnabled,
-      [this, &lut](std::unique_ptr<Page> page, const uint16_t paragraphIndex, const uint16_t listItemIndex) {
-        lut.push_back({this->onPageComplete(std::move(page)), paragraphIndex, listItemIndex});
+  // The parser stores the path/contentBase/imageBasePath by reference, so they must
+  // live in the BuildContext (which outlives the parser). The page-complete callback
+  // captures the BuildContext pointer to append to its in-RAM LUT; build_ owns the
+  // context for the parser's whole lifetime.
+  BuildContext* ctxPtr = ctx.get();
+  ctx->parser = makeUniqueNoThrow<ChapterHtmlSlimParser>(
+      epub, ctxPtr->parsePath, renderer, fontId, lineCompression, extraParagraphSpacing, paragraphAlignment,
+      viewportWidth, viewportHeight, hyphenationEnabled, focusReadingEnabled,
+      [this, ctxPtr](std::unique_ptr<Page> page, const uint16_t paragraphIndex, const uint16_t listItemIndex) {
+        ctxPtr->lut.push_back({this->onPageComplete(std::move(page)), paragraphIndex, listItemIndex});
      },
-      embeddedStyle, contentBase, imageBasePath, imageRendering, std::move(tocAnchors), popupFn, cssParser);
-  Hyphenator::setPreferredLanguage(epub->getLanguage());
-  success = visitor.parseAndBuildPages();
-
-  Storage.remove(tmpHtmlPath.c_str());
-  if (!success) {
-    LOG_ERR("SCT", "Failed to parse XML and build pages");
-    // Explicitly close() file before calling Storage.remove()
+      embeddedStyle, ctxPtr->contentBase, ctxPtr->imageBasePath, imageRendering, std::move(tocAnchors), popupFn,
+      ctxPtr->cssParser);
+  if (!ctx->parser) {
+    LOG_ERR("SCT", "OOM: ChapterHtmlSlimParser");
+    if (ctx->cssParser) ctx->cssParser->clear();
    file.close();
-    Storage.remove(filePath.c_str());
-    if (cssParser) {
-      cssParser->clear();
-    }
+    Storage.remove(binTmpPath().c_str());
+    if (!reusedHtml) Storage.remove(tmpHtmlPath.c_str());
    return false;
  }

+  Hyphenator::setPreferredLanguage(epub->getLanguage());
+  build_ = std::move(ctx);
+
+  if (!build_->parser->beginParse()) {
+    LOG_ERR("SCT", "Failed to begin parse");
+    abandonBuild();
+    return false;
+  }
+  build_->totalBytes = build_->parser->parseTotalBytes();
+  return true;
+}
+
+bool Section::buildSomeMore(const int maxPages) {
+  if (!build_ || !build_->parser) {
+    LOG_ERR("SCT", "buildSomeMore with no active build");
+    return false;
+  }
+  // Pace on pages laid out by THIS build, not pageCount: during a rebuild over a partial,
+  // pageCount stays pinned at the partial's watermark until the build passes it, which
+  // would otherwise turn one "small" chunk into a blocking rebuild of the whole watermark.
+  const int startCount = builtPageCount_;
+  for (;;) {
+    const auto status = build_->parser->parseStep();
+    if (status == ChapterHtmlSlimParser::ParseStatus::Error) {
+      LOG_ERR("SCT", "Parse error during incremental build");
+      abandonBuild();
+      return false;
+    }
+    if (status == ChapterHtmlSlimParser::ParseStatus::Done) {
+      return finalizeBuild();
+    }
+    // ParseStatus::More: yield once we've laid out the requested number of pages.
+    if (maxPages > 0 && (builtPageCount_ - startCount) >= maxPages) {
+      build_->bytesConsumed = build_->parser->parseBytesConsumed();
+      return true;
+    }
+  }
+}
+
+bool Section::hasHtmlCache() const {
+  const std::string htmlPath = epub->getCachePath() + "/html/" + std::to_string(spineIndex) + ".html";
+  return Storage.exists(htmlPath.c_str());
+}
+
+std::optional<uint16_t> Section::findAnchorDuringBuild(const std::string& anchor) const {
+  if (!build_ || !build_->parser) return std::nullopt;
+  for (const auto& [key, page] : build_->parser->getAnchors()) {
+    if (key == anchor) return page;
+  }
+  return std::nullopt;
+}
+
+std::optional<uint16_t> Section::findAnchor(const std::string& anchor) const {
+  if (const auto page = findAnchorDuringBuild(anchor)) {
+    return page;
+  }
+  // Fall back to the on-disk anchor map: a finalized section, or a partial whose map
+  // covers everything up to its watermark (nullopt past it -- build further and retry).
+  return getPageForAnchor(anchor);
+}
+
+uint16_t Section::estimatedTotalPages() const {
+  // Extrapolation from a suspended session's watermark trailer. A static snapshot, so no EMA
+  // damping is needed. Also the best guess while a rebuild is running but hasn't laid out
+  // enough pages yet to extrapolate from its own progress.
+  const auto partialEstimate = [this]() -> uint16_t {
+    if (!partial_ || partialBytesConsumed_ == 0 || partialTotalBytes_ <= partialBytesConsumed_) {
+      return pageCount;
+    }
+    const uint64_t est = static_cast<uint64_t>(partialPageCount_) * partialTotalBytes_ / partialBytesConsumed_;
+    if (est <= pageCount) return pageCount;
+    return est > 60000 ? 60000 : static_cast<uint16_t>(est);
+  };
+
+  if (!build_) {
+    return partial_ ? partialEstimate() : pageCount;  // partial -> extrapolate, finalized -> exact
+  }
+  const uint32_t consumed = build_->bytesConsumed;
+  const uint32_t total = build_->totalBytes;
+  if (builtPageCount_ == 0 || consumed == 0 || total <= consumed) return partialEstimate();
+
+  // Raw extrapolation: scale the pages built so far by the fraction of HTML still unparsed. This
+  // re-derives from a growing, non-uniform sample, so it jitters up and down as the build crosses
+  // dense vs sparse regions of the chapter.
+  const uint64_t raw = static_cast<uint64_t>(builtPageCount_) * total / consumed;
+
+  // Damp that jitter with an exponential moving average. Step it once per build advance (keyed on
+  // bytesConsumed) rather than per status-bar redraw, so the smoothing rate doesn't depend on how
+  // often we repaint. As the build nears the end, consumed -> total and raw -> the built count, so
+  // the average settles onto the true count (and finalizeBuild then returns the exact pageCount).
+  constexpr float ALPHA = 0.25f;  // weight of each new sample; lower = steadier but slower to settle
+  if (build_->smoothedEstimate <= 0) {
+    build_->smoothedEstimate = static_cast<float>(raw);  // seed on the first estimate
+  } else if (consumed != build_->smoothedAtConsumed) {
+    build_->smoothedEstimate += ALPHA * (static_cast<float>(raw) - build_->smoothedEstimate);
+  }
+  build_->smoothedAtConsumed = consumed;
+
+  const uint64_t est = static_cast<uint64_t>(build_->smoothedEstimate + 0.5f);
+  if (est <= pageCount) return pageCount;  // never fewer than the pages already available
+  return est > 60000 ? 60000 : static_cast<uint16_t>(est);
+}
+
+// Write the LUTs and anchor map into the open tmp .bin, patch the header with the built
+// page count and table offsets, stamp `version` as the commit point, then swap the tmp
+// file over filePath. For SECTION_FILE_PARTIAL_VERSION a watermark trailer
+// (bytesConsumed, totalBytes) is appended after the li LUT so a later open can estimate
+// the total page count. The parser must still be alive (anchors are read from it).
+// On failure the tmp is removed and any pre-existing file at filePath is left intact.
+bool Section::commitBuildFile(const uint8_t version, const uint32_t bytesConsumed, const uint32_t totalBytes) {
+  const bool asPartial = (version == SECTION_FILE_PARTIAL_VERSION);
+
+  const auto failCommit = [this]() {
+    // Explicit close() required before remove (member variable, O_RDWR handle).
+    file.close();
+    Storage.remove(binTmpPath().c_str());
+    return false;
+  };
+
  const uint32_t lutOffset = file.position();
-  bool hasFailedLutRecords = false;
-  // Write LUT
-  for (const auto& entry : lut) {
+  for (const auto& entry : build_->lut) {
    if (entry.fileOffset == 0) {
-      hasFailedLutRecords = true;
-      break;
+      LOG_ERR("SCT", "Failed to write LUT due to invalid page positions");
+      return failCommit();
    }
    serialization::writePod(file, entry.fileOffset);
  }

-  if (hasFailedLutRecords) {
-    LOG_ERR("SCT", "Failed to write LUT due to invalid page positions");
-    // Explicitly close() file before calling Storage.remove()
-    file.close();
-    Storage.remove(filePath.c_str());
-    return false;
-  }
-
-  // Write anchor-to-page map for fragment navigation (e.g. footnote targets)
+  // Write anchor-to-page map for fragment navigation (e.g. footnote targets). For a
+  // partial, skip anchors that landed on the incomplete trailing page the suspend drops.
  const uint32_t anchorMapOffset = file.position();
-  const auto& anchors = visitor.getAnchors();
-  serialization::writePod(file, static_cast<uint16_t>(anchors.size()));
+  const auto& anchors = build_->parser->getAnchors();
+  uint16_t anchorCount = 0;
  for (const auto& [anchor, page] : anchors) {
+    if (!asPartial || page < builtPageCount_) anchorCount++;
+  }
+  serialization::writePod(file, anchorCount);
+  for (const auto& [anchor, page] : anchors) {
+    if (asPartial && page >= builtPageCount_) continue;
    serialization::writeString(file, anchor);
    serialization::writePod(file, page);
  }

  const uint32_t paragraphLutOffset = file.position();
-  serialization::writePod(file, static_cast<uint16_t>(lut.size()));
-  for (const auto& entry : lut) {
+  serialization::writePod(file, static_cast<uint16_t>(build_->lut.size()));
+  for (const auto& entry : build_->lut) {
    serialization::writePod(file, entry.paragraphIndex);
  }

  const uint32_t liLutFileOffset = static_cast<uint32_t>(file.position());
-  for (const auto& entry : lut) {
+  for (const auto& entry : build_->lut) {
    serialization::writePod(file, entry.listItemIndex);
  }

-  // Patch header with final pageCount, lutOffset, anchorMapOffset, paragraphLutOffset, and liLutOffset
-  file.seek(HEADER_SIZE - sizeof(uint32_t) * 4 - sizeof(pageCount));
-  serialization::writePod(file, pageCount);
+  if (asPartial) {
+    // Watermark trailer, located on load as liLutOffset + pageCount * sizeof(uint16_t).
+    serialization::writePod(file, bytesConsumed);
+    serialization::writePod(file, totalBytes);
+  }
+
+  // Patch header with the built page count and section offsets...
+  file.seek(HEADER_SIZE - sizeof(uint32_t) * 4 - sizeof(builtPageCount_));
+  serialization::writePod(file, builtPageCount_);
  serialization::writePod(file, lutOffset);
  serialization::writePod(file, anchorMapOffset);
  serialization::writePod(file, paragraphLutOffset);
  serialization::writePod(file, liLutFileOffset);
+  // ...then commit by overwriting the sentinel version with the real one. Writing the
+  // version last makes it the commit point: a crash before here leaves version 0.
+  file.seek(0);
+  serialization::writePod(file, version);
  // Explicit close() required: member variable persists beyond function scope
  file.close();
-  if (cssParser) {
-    cssParser->clear();
+
+  // Swap into place. A crash between remove and rename loses the old file but keeps a
+  // fully-committed tmp; the next build just removes it and rebuilds.
+  if (Storage.exists(filePath.c_str())) {
+    Storage.remove(filePath.c_str());
+  }
+  if (!Storage.rename(binTmpPath().c_str(), filePath.c_str())) {
+    LOG_ERR("SCT", "Failed to move built section into place");
+    Storage.remove(binTmpPath().c_str());
+    return false;
  }
  return true;
 }

-std::unique_ptr<Page> Section::loadPageFromSectionFile() {
-  if (!Storage.openFileForRead("SCT", filePath, file)) {
+bool Section::finalizeBuild() {
+  // Flush the trailing page (emits the last page via the completePageFn into the LUT).
+  build_->parser->finishParse();
+
+  if (!build_->reusedHtml) {
+    // Parse succeeded: promote the freshly unzipped HTML to the persistent cache so future
+    // rebuilds skip zip inflation. If promotion fails, drop the temp -- the build still succeeded.
+    if (!Storage.rename(build_->tmpHtmlPath.c_str(), build_->htmlPath.c_str())) {
+      LOG_DBG("SCT", "Failed to promote HTML cache, removing temp");
+      Storage.remove(build_->tmpHtmlPath.c_str());
+    }
+  }
+
+  const bool committed = commitBuildFile(SECTION_FILE_VERSION, 0, 0);
+  if (build_->cssParser) build_->cssParser->clear();
+  build_.reset();
+  if (!committed) {
+    // commitBuildFile removed filePath before the failed swap, so nothing valid remains.
+    partial_ = false;
+    partialPageCount_ = 0;
+    pageCount = 0;
+    builtPageCount_ = 0;
+    return false;
+  }
+  buildComplete_ = true;
+  partial_ = false;
+  partialPageCount_ = 0;
+  pageCount = builtPageCount_;
+  return true;
+}
+
+void Section::suspendBuild() {
+  if (!build_) return;
+
+  // Only worth persisting if this build produced pages a pre-existing partial doesn't
+  // already cover; otherwise keep the older (bigger) partial and just drop the tmp.
+  const bool worthKeeping = builtPageCount_ > 0 && (!partial_ || builtPageCount_ > partialPageCount_);
+
+  bool committed = false;
+  if (worthKeeping) {
+    // Capture the parse watermark and commit before tearing the parser down (the anchor
+    // map is read from it). The incomplete trailing page is intentionally not flushed:
+    // only fully laid-out pages are persisted, and the rebuild re-derives the rest.
+    const uint32_t consumed = static_cast<uint32_t>(build_->parser->parseBytesConsumed());
+    committed = commitBuildFile(SECTION_FILE_PARTIAL_VERSION, consumed, build_->totalBytes);
+    if (committed) {
+      partial_ = true;
+      partialPageCount_ = builtPageCount_;
+      partialBytesConsumed_ = consumed;
+      partialTotalBytes_ = build_->totalBytes;
+      LOG_INF("SCT", "Suspended build: %u pages persisted", builtPageCount_);
+    }
+  }
+
+  if (build_->parser) build_->parser->abortParse();
+  if (build_->cssParser) build_->cssParser->clear();
+  if (!committed && file) {
+    // Explicit close() required before remove (member variable, O_RDWR handle).
+    file.close();
+    Storage.remove(binTmpPath().c_str());
+  }
+  if (!build_->reusedHtml && Storage.exists(build_->tmpHtmlPath.c_str())) {
+    Storage.remove(build_->tmpHtmlPath.c_str());
+  }
+  build_.reset();
+  buildComplete_ = false;
+  pageCount = partial_ ? partialPageCount_ : 0;
+  builtPageCount_ = 0;
+}
+
+void Section::abandonBuild() {
+  if (!build_) return;
+  if (build_->parser) build_->parser->abortParse();
+  if (build_->cssParser) build_->cssParser->clear();
+  if (file) {
+    // Explicit close() required before remove (member variable, O_RDWR handle).
+    file.close();
+    Storage.remove(binTmpPath().c_str());
+  }
+  // A parse error would recur against the same HTML, so drop any partial too -- resuming
+  // from it would just re-enter the failing build every open.
+  if (Storage.exists(filePath.c_str())) {
+    Storage.remove(filePath.c_str());
+  }
+  if (!build_->reusedHtml && Storage.exists(build_->tmpHtmlPath.c_str())) {
+    Storage.remove(build_->tmpHtmlPath.c_str());
+  }
+  build_.reset();
+  buildComplete_ = false;
+  partial_ = false;
+  partialPageCount_ = 0;
+  pageCount = 0;
+  builtPageCount_ = 0;
+}
+
+std::unique_ptr<Page> Section::loadPageDuringBuild(const int page) {
+  if (!build_ || page < 0 || page >= static_cast<int>(build_->lut.size()) || !file) {
+    return nullptr;
+  }
+  const uint32_t pos = build_->lut[page].fileOffset;
+  if (pos == 0) {
+    return nullptr;
+  }
+  // The .bin is open O_RDWR for the build. Read the already-written page, then restore
+  // the write cursor so the next onPageComplete keeps appending where it left off.
+  const uint32_t writePos = file.position();
+  file.seek(pos);
+  auto p = Page::deserialize(file);
+  file.seek(writePos);
+  return p;
+}
+
+// Read a page from the committed file at filePath (finalized section or partial from a
+// previous session). Uses a local handle so it is safe while a build holds the member
+// `file` open on the tmp .bin.
+std::unique_ptr<Page> Section::loadPageAt(const int page) const {
+  HalFile f;
+  if (!Storage.openFileForRead("SCT", filePath, f)) {
    return nullptr;
  }

-  file.seek(HEADER_SIZE - sizeof(uint32_t) * 4);
+  f.seek(HEADER_SIZE - sizeof(uint32_t) * 4);
  uint32_t lutOffset;
-  serialization::readPod(file, lutOffset);
-  file.seek(lutOffset + sizeof(uint32_t) * currentPage);
+  serialization::readPod(f, lutOffset);
+  f.seek(lutOffset + sizeof(uint32_t) * page);
  uint32_t pagePos;
-  serialization::readPod(file, pagePos);
-  file.seek(pagePos);
+  serialization::readPod(f, pagePos);
+  f.seek(pagePos);

-  auto page = Page::deserialize(file);
-  // Explicit close() required: member variable persists beyond function scope
-  file.close();
-  return page;
+  return Page::deserialize(f);
+  // No f.close() needed -- DESTRUCTOR_CLOSES_FILE=1 handles it at scope exit
+}
+
+std::unique_ptr<Page> Section::loadPage(const int page) {
+  if (page < 0) {
+    return nullptr;
+  }
+  if (build_ && page < static_cast<int>(build_->lut.size())) {
+    return loadPageDuringBuild(page);
+  }
+  // Not (yet) in the active build: serve from the file on disk -- a finalized section,
+  // or a partial from a previous session whose pages the rebuild hasn't reached again.
+  const int onDisk = partial_ ? partialPageCount_ : (build_ ? 0 : pageCount);
+  if (page >= onDisk) {
+    return nullptr;
+  }
+  return loadPageAt(page);
 }

 std::string Section::getTextFromSectionFile() {
  std::string fullText;
-  auto p = this->loadPageFromSectionFile();
+  auto p = loadPage(currentPage);
  if (p) {
    for (const auto& el : p->elements) {
      if (el->getTag() == TAG_PageLine) {
@@ -361,6 +756,15 @@ std::optional<uint16_t> Section::getCachedPageCount() const {
    return std::nullopt;
  }

+  // Only a finalized section's count is the chapter total; a partial's count is just the
+  // suspended build's watermark, which would skew progress mapping. Callers fall back to
+  // their own estimates.
+  uint8_t version;
+  serialization::readPod(f, version);
+  if (version != SECTION_FILE_VERSION) {
+    return std::nullopt;
+  }
+
  f.seek(HEADER_SIZE - sizeof(uint32_t) * 4 - sizeof(uint16_t));
  uint16_t count;
  serialization::readPod(f, count);
@@ -3,11 +3,14 @@
 #include <memory>
 #include <optional>
 #include <string>
+#include <vector>

 #include "Epub.h"

 class Page;
 class GfxRenderer;
+class ChapterHtmlSlimParser;
+class CssParser;

 class Section {
  std::shared_ptr<Epub> epub;
@@ -21,16 +24,67 @@ class Section {
                              bool embeddedStyle, uint8_t imageRendering, bool focusReadingEnabled);
  uint32_t onPageComplete(std::unique_ptr<Page> page);

+  // Page-offset table entry, kept in RAM while an incremental build is running so
+  // already-built pages can be located in the partially-written .bin.
+  struct PageLutEntry {
+    uint32_t fileOffset;
+    uint16_t paragraphIndex;
+    uint16_t listItemIndex;
+  };
+  // Held only while an incremental build is in progress (see startBuild). Carries the
+  // live parser plus the strings it references (the parser stores them by reference)
+  // and the in-RAM page-offset table.
+  struct BuildContext {
+    std::unique_ptr<ChapterHtmlSlimParser> parser;
+    std::vector<PageLutEntry> lut;
+    std::string parsePath;
+    std::string contentBase;
+    std::string imageBasePath;
+    std::string htmlPath;
+    std::string tmpHtmlPath;
+    bool reusedHtml = false;
+    CssParser* cssParser = nullptr;
+    // HTML byte progress, for estimating the section's total page count while it's still building.
+    uint32_t bytesConsumed = 0;
+    uint32_t totalBytes = 0;
+    // Exponentially-smoothed page-count estimate (0 = not yet seeded) and the bytesConsumed at its
+    // last update. The raw byte-ratio estimate jitters as the build crosses dense/sparse regions;
+    // the EMA is stepped once per build advance (not per redraw) to damp that wobble.
+    float smoothedEstimate = 0;
+    uint32_t smoothedAtConsumed = 0;
+  };
+  std::unique_ptr<BuildContext> build_;
+  bool buildComplete_ = false;
+  // Pages laid out by the active build (== build_->lut.size()). Distinct from pageCount,
+  // which is the pages *available to read* and also counts a loaded partial file's pages.
+  uint16_t builtPageCount_ = 0;
+  // A partial section file (suspended build from a previous session) is loaded at filePath.
+  // Its pages 0..partialPageCount_-1 are readable while a rebuild extends past them.
+  bool partial_ = false;
+  uint16_t partialPageCount_ = 0;
+  // Parse watermark from the partial's trailer, for estimating the total page count.
+  uint32_t partialBytesConsumed_ = 0;
+  uint32_t partialTotalBytes_ = 0;
+  bool finalizeBuild();
+  // Write the LUTs/anchor map (and, for a partial, the watermark trailer), patch the
+  // header, stamp the version byte, and swap the tmp .bin over filePath.
+  bool commitBuildFile(uint8_t version, uint32_t bytesConsumed, uint32_t totalBytes);
+  // Builds write here and are swapped over filePath only on commit, so a prior
+  // partial/finalized file stays readable while a rebuild is in progress.
+  std::string binTmpPath() const { return filePath + ".part"; }
+  std::unique_ptr<Page> loadPageAt(int page) const;
+  // Read a page already laid out by the in-progress build (page < build LUT size), from
+  // the partially-written tmp .bin without disturbing the build's write cursor.
+  std::unique_ptr<Page> loadPageDuringBuild(int page);
+
 public:
  uint16_t pageCount = 0;
  int currentPage = 0;

-  explicit Section(const std::shared_ptr<Epub>& epub, const int spineIndex, GfxRenderer& renderer)
-      : epub(epub),
-        spineIndex(spineIndex),
-        renderer(renderer),
-        filePath(epub->getCachePath() + "/sections/" + std::to_string(spineIndex) + ".bin") {}
-  ~Section() = default;
+  // Constructor and destructor are out-of-line: BuildContext holds a unique_ptr to the
+  // forward-declared ChapterHtmlSlimParser, whose full definition is only visible in the .cpp.
+  explicit Section(const std::shared_ptr<Epub>& epub, int spineIndex, GfxRenderer& renderer);
+  ~Section();
  bool loadSectionFile(int fontId, float lineCompression, bool extraParagraphSpacing, uint8_t paragraphAlignment,
                       uint16_t viewportWidth, uint16_t viewportHeight, bool hyphenationEnabled, bool embeddedStyle,
                       uint8_t imageRendering, bool focusReadingEnabled);
@@ -39,12 +93,56 @@ class Section {
                         uint16_t viewportWidth, uint16_t viewportHeight, bool hyphenationEnabled, bool embeddedStyle,
                         uint8_t imageRendering, bool focusReadingEnabled,
                         const std::function<void()>& popupFn = nullptr);
-  std::unique_ptr<Page> loadPageFromSectionFile();
+
+  // Incremental build: lay out the section a few pages at a time so a large chapter
+  // can show its first page immediately and keep the UI responsive while the rest
+  // builds. createSectionFile() above is the one-shot wrapper over these.
+  //   if (!startBuild(...)) fail;
+  //   each tick: buildSomeMore(N); render up to pageCount; when isBuildComplete() stop.
+  bool startBuild(int fontId, float lineCompression, bool extraParagraphSpacing, uint8_t paragraphAlignment,
+                  uint16_t viewportWidth, uint16_t viewportHeight, bool hyphenationEnabled, bool embeddedStyle,
+                  uint8_t imageRendering, bool focusReadingEnabled, const std::function<void()>& popupFn = nullptr);
+  // Lay out up to maxPages more pages (maxPages <= 0 = build to completion). Returns
+  // false on error (the build is abandoned). Sets isBuildComplete() when finished.
+  bool buildSomeMore(int maxPages);
+  bool isBuilding() const { return static_cast<bool>(build_); }
+  bool isBuildComplete() const { return buildComplete_; }
+  // Best-known total page count: the exact pageCount once finalized, or a smoothed byte-based
+  // estimate (pages so far scaled by totalBytes/bytesConsumed, damped by an EMA) while a giant spine
+  // is still building, so "page X of Y" / progress don't read off the small build watermark.
+  uint16_t estimatedTotalPages() const;
+  void abandonBuild();
+  // Persist an in-progress build as a partial section file (version sentinel + LUTs +
+  // watermark trailer) instead of discarding it, so the next open of this spine can show
+  // its pages instantly and only rebuild in the background. Called by the destructor, so
+  // any teardown path (exit, sleep, navigation) keeps the work already done. Keeps a
+  // pre-existing partial when it covers more pages than this build reached.
+  void suspendBuild();
+  // True when a partial file was loaded: pageCount is a watermark, not the chapter total.
+  bool isPartial() const { return partial_; }
+
+  // Unified page read: from the active build if it has reached the page, otherwise from
+  // the on-disk file (finalized section, or a partial the rebuild hasn't caught up to).
+  std::unique_ptr<Page> loadPage(int page);
+
  std::string getTextFromSectionFile();

+  // Resolve an anchor from the in-progress build first, then the on-disk anchor map
+  // (covers finalized sections and partials from a previous session).
+  std::optional<uint16_t> findAnchor(const std::string& anchor) const;
+
+  // True if this spine's unzipped HTML is already cached, so a build won't pay the (multi-second on a
+  // giant spine) zip inflation. Lets the reader skip the indexing popup on a fast reopen/rebuild.
+  bool hasHtmlCache() const;
+
  // Look up the page number for an anchor id from the section cache file.
  std::optional<uint16_t> getPageForAnchor(const std::string& anchor) const;

+  // Look up an anchor among the pages built so far by the in-progress build, so an anchor jump
+  // (TOC / chapter select, usually the chapter top = page 0) can resolve without laying out the
+  // whole chapter. Returns nullopt if the anchor hasn't been reached yet (build more) or no build.
+  std::optional<uint16_t> findAnchorDuringBuild(const std::string& anchor) const;
+
  // Get the page count from the section cache file without fully loading it.
  std::optional<uint16_t> getCachedPageCount() const;

@@ -1275,7 +1275,9 @@ void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* n
  }
 }

-bool ChapterHtmlSlimParser::parseAndBuildPages() {
+ChapterHtmlSlimParser::~ChapterHtmlSlimParser() { abortParse(); }
+
+bool ChapterHtmlSlimParser::beginParse() {
  // Initialize block style stack with a root entry representing "no ancestor block elements".
  // The user's paragraph alignment is set as the default so child elements without explicit
  // text-align inherit it correctly through getCombinedBlockStyle.
@@ -1293,67 +1295,78 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
  paragraphAlignmentBlockStyle.alignment = align;
  startNewTextBlock(paragraphAlignmentBlockStyle);

-  XML_Parser parser = XML_ParserCreate(nullptr);
-  int done;
-
-  if (!parser) {
+  xmlParser_ = XML_ParserCreate(nullptr);
+  if (!xmlParser_) {
    LOG_ERR("EHP", "Couldn't allocate memory for parser");
    return false;
  }

  // Handle HTML entities (like &nbsp;) that aren't in XML spec or DTD
  // Using DefaultHandlerExpand preserves normal entity expansion from DOCTYPE
-  XML_SetDefaultHandlerExpand(parser, defaultHandlerExpand);
+  XML_SetDefaultHandlerExpand(xmlParser_, defaultHandlerExpand);

-  HalFile file;
-  if (!Storage.openFileForRead("EHP", filepath, file)) {
-    destroyXmlParser(parser);
+  if (!Storage.openFileForRead("EHP", filepath, parseFile_)) {
+    destroyXmlParser(xmlParser_);
+    xmlParser_ = nullptr;
    return false;
  }

  // Get file size to decide whether to show indexing popup.
-  if (popupFn && file.size() >= MIN_SIZE_FOR_POPUP) {
+  if (popupFn && parseFile_.size() >= MIN_SIZE_FOR_POPUP) {
    popupFn();
  }

-  XML_SetUserData(parser, this);
-  XML_SetElementHandler(parser, startElement, endElement);
-  XML_SetCharacterDataHandler(parser, characterData);
+  XML_SetUserData(xmlParser_, this);
+  XML_SetElementHandler(xmlParser_, startElement, endElement);
+  XML_SetCharacterDataHandler(xmlParser_, characterData);

-  // Compute the time taken to parse and build pages
-  const uint32_t chapterStartTime = millis();
-  do {
-    void* const buf = XML_GetBuffer(parser, PARSE_BUFFER_SIZE);
-    if (!buf) {
-      LOG_ERR("EHP", "Couldn't allocate memory for buffer");
-      destroyXmlParser(parser);
-      file.close();
-      return false;
-    }
+  parseStartTime_ = millis();
+  return true;
+}

-    const size_t len = file.read(buf, PARSE_BUFFER_SIZE);
+ChapterHtmlSlimParser::ParseStatus ChapterHtmlSlimParser::parseStep() {
+  void* const buf = XML_GetBuffer(xmlParser_, PARSE_BUFFER_SIZE);
+  if (!buf) {
+    LOG_ERR("EHP", "Couldn't allocate memory for buffer");
+    return ParseStatus::Error;
+  }

-    if (len == 0 && file.available() > 0) {
-      LOG_ERR("EHP", "File read error");
-      destroyXmlParser(parser);
-      file.close();
-      return false;
-    }
+  const size_t len = parseFile_.read(buf, PARSE_BUFFER_SIZE);

-    done = file.available() == 0;
+  if (len == 0 && parseFile_.available() > 0) {
+    LOG_ERR("EHP", "File read error");
+    return ParseStatus::Error;
+  }

-    if (XML_ParseBuffer(parser, static_cast<int>(len), done) == XML_STATUS_ERROR) {
-      LOG_ERR("EHP", "Parse error at line %lu:\n%s", XML_GetCurrentLineNumber(parser),
-              XML_ErrorString(XML_GetErrorCode(parser)));
-      destroyXmlParser(parser);
-      file.close();
-      return false;
-    }
-  } while (!done);
-  LOG_DBG("EHP", "Time to parse and build pages: %lu ms", millis() - chapterStartTime);
+  const int done = parseFile_.available() == 0;

-  destroyXmlParser(parser);
-  file.close();
+  if (XML_ParseBuffer(xmlParser_, static_cast<int>(len), done) == XML_STATUS_ERROR) {
+    LOG_ERR("EHP", "Parse error at line %lu:\n%s", XML_GetCurrentLineNumber(xmlParser_),
+            XML_ErrorString(XML_GetErrorCode(xmlParser_)));
+    return ParseStatus::Error;
+  }
+
+  return done ? ParseStatus::Done : ParseStatus::More;
+}
+
+void ChapterHtmlSlimParser::abortParse() {
+  if (xmlParser_) {
+    destroyXmlParser(xmlParser_);
+    xmlParser_ = nullptr;
+  }
+  // Only close the file if it was successfully opened in beginParse()
+  if (parseFile_.isOpen()) {
+    parseFile_.close();
+  }
+}
+
+bool ChapterHtmlSlimParser::finishParse() {
+  if (xmlParser_) {
+    LOG_DBG("EHP", "Time to parse and build pages: %lu ms", millis() - parseStartTime_);
+    destroyXmlParser(xmlParser_);
+    xmlParser_ = nullptr;
+  }
+  parseFile_.close();

  // Process last page if there is still text
  if (currentTextBlock) {
@@ -1371,6 +1384,23 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
  return true;
 }

+bool ChapterHtmlSlimParser::parseAndBuildPages() {
+  if (!beginParse()) {
+    return false;
+  }
+  for (;;) {
+    const ParseStatus status = parseStep();
+    if (status == ParseStatus::Error) {
+      abortParse();
+      return false;
+    }
+    if (status == ParseStatus::Done) {
+      break;
+    }
+  }
+  return finishParse();
+}
+
 void ChapterHtmlSlimParser::addLineToPage(std::shared_ptr<TextBlock> line) {
  const int lineHeight = renderer.getLineHeight(fontId) * lineCompression;

@@ -1,5 +1,6 @@
 #pragma once

+#include <HalStorage.h>
 #include <expat.h>

 #include <climits>
@@ -96,6 +97,16 @@ class ChapterHtmlSlimParser {
  std::vector<std::pair<int, FootnoteEntry>> pendingFootnotes;  // <wordIndex, entry>
  int wordsExtractedInBlock = 0;

+  // Resumable parse state. The one-shot parseAndBuildPages() drives these
+  // internally; the incremental section builder drives them across render ticks
+  // so a large single chapter can yield between pages instead of blocking the UI
+  // until the whole thing is laid out. parseFile_ and the expat parser stay alive
+  // for the lifetime of the parse so it can be paused and resumed at buffer
+  // boundaries.
+  XML_Parser xmlParser_ = nullptr;
+  HalFile parseFile_;
+  uint32_t parseStartTime_ = 0;
+
  void updateEffectiveInlineStyle();
  void startNewTextBlock(const BlockStyle& blockStyle);
  void flushPendingAnchor();
@@ -144,8 +155,28 @@ class ChapterHtmlSlimParser {
        imageBasePath(imageBasePath),
        tocAnchors(std::move(tocAnchors)) {}

-  ~ChapterHtmlSlimParser() = default;
+  ~ChapterHtmlSlimParser();
+
+  // One-shot parse: builds every page before returning (begin + step* + finish).
  bool parseAndBuildPages();
+
+  // Resumable parse, for the incremental section builder. Drive as:
+  //   if (!beginParse()) fail;
+  //   loop: switch (parseStep()) { More: keep going / yield; Done: finishParse(); Error: abortParse(); }
+  // Pages are emitted via completePageFn as they complete during parseStep(), so
+  // the caller can stop once enough pages are built and resume on a later tick.
+  enum class ParseStatus { More, Done, Error };
+  bool beginParse();
+  ParseStatus parseStep();
+  bool finishParse();  // flush the trailing page and tear down; returns true
+  void abortParse();   // tear down without flushing (error / abandon)
+
  void addLineToPage(std::shared_ptr<TextBlock> line);
  const std::vector<std::pair<std::string, uint16_t>>& getAnchors() const { return anchorData; }
+
+  // Byte progress of the in-flight parse, used to estimate a still-building section's total page
+  // count (a giant single-spine book never fully lays out, so its real count is unknown). Valid
+  // between beginParse() and finishParse()/abortParse().
+  size_t parseBytesConsumed() { return parseFile_ ? parseFile_.position() : 0; }
+  size_t parseTotalBytes() { return parseFile_ ? parseFile_.size() : 0; }
 };
@@ -278,13 +278,18 @@ class XPathParagraphResolver final : public Print {
    path.push_back({name, siblingIndex});
    parentStates.emplace_back();

+    // Count both <p> and <li> as paragraph-like positions, matching how the section
+    // layout tracks them (xpathParagraphIndex and xpathListItemIndex). This ensures
+    // KOReader progress in list items maps to the correct XPath.
    if (name == "p") {
      paragraphCount++;
-      if (paragraphCount == targetParagraph) {
-        xpath = buildParagraphXPath(spineIndex, path, 0, 0);
-        stopped = true;
-        XML_StopParser(parser, XML_FALSE);
-      }
+    } else if (name == "li") {
+      paragraphCount++;
+    }
+    if (paragraphCount == targetParagraph) {
+      xpath = buildParagraphXPath(spineIndex, path, 0, 0);
+      stopped = true;
+      XML_StopParser(parser, XML_FALSE);
    }

    depth++;
@@ -709,12 +709,13 @@ SavedProgressPosition ProgressMapper::toSavedProgress(const std::shared_ptr<Epub
  float intra =
      (pos.totalPages > 1) ? static_cast<float>(pos.pageNumber) / static_cast<float>(pos.totalPages - 1) : 0.0f;
  result.percentage = epub->calculateProgress(pos.spineIndex, intra);
-  // Progress-based XPath correctly handles both <p> and <li> positions.
-  result.xpath = ChapterXPathResolver::findXPathForProgress(epub, pos.spineIndex, intra);
-  // Fall back to paragraph-index lookup when progress-based resolution fails.
-  if (result.xpath.empty() && pos.hasParagraphIndex && pos.paragraphIndex > 0) {
+  if (pos.hasParagraphIndex && pos.paragraphIndex > 0) {
    result.xpath = ChapterXPathResolver::findXPathForParagraph(epub, pos.spineIndex, pos.paragraphIndex);
  }
+  // Fall back to progress-based XPath, then synthetic progress mapping.
+  if (result.xpath.empty()) {
+    result.xpath = ChapterXPathResolver::findXPathForProgress(epub, pos.spineIndex, intra);
+  }
  if (result.xpath.empty()) {
    result.xpath = generateXPath(epub, pos.spineIndex, intra);
  }