crosspoint-reader-mod/lib/Epub/Epub/Section.cpp

#include "Section.h"

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

#include <algorithm>
#include <set>

#include "Epub/css/CssParser.h"
#include "Page.h"
#include "hyphenation/Hyphenator.h"
#include "parsers/ChapterHtmlSlimParser.h"

namespace {
constexpr uint8_t SECTION_FILE_VERSION = 19;
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(uint32_t);
}  // namespace

uint32_t Section::onPageComplete(std::unique_ptr<Page> page) {
  if (!file) {
    LOG_ERR("SCT", "File not open for writing page %d", pageCount);
    return 0;
  }

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

  pageCount++;
  return position;
}

void Section::writeSectionFileHeader(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) {
  if (!file) {
    LOG_DBG("SCT", "File not open for writing header");
    return;
  }
  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(uint32_t),
                "Header size mismatch");
  serialization::writePod(file, SECTION_FILE_VERSION);
  serialization::writePod(file, fontId);
  serialization::writePod(file, lineCompression);
  serialization::writePod(file, extraParagraphSpacing);
  serialization::writePod(file, paragraphAlignment);
  serialization::writePod(file, viewportWidth);
  serialization::writePod(file, viewportHeight);
  serialization::writePod(file, hyphenationEnabled);
  serialization::writePod(file, embeddedStyle);
  serialization::writePod(file, imageRendering);
  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,
                              const uint8_t paragraphAlignment, const uint16_t viewportWidth,
                              const uint16_t viewportHeight, const bool hyphenationEnabled, const bool embeddedStyle,
                              const uint8_t imageRendering) {
  if (!Storage.openFileForRead("SCT", filePath, file)) {
    return false;
  }

  // Match parameters
  {
    uint8_t version;
    serialization::readPod(file, version);
    if (version != SECTION_FILE_VERSION) {
      file.close();
      LOG_ERR("SCT", "Deserialization failed: Unknown version %u", version);
      clearCache();
      return false;
    }

    int fileFontId;
    uint16_t fileViewportWidth, fileViewportHeight;
    float fileLineCompression;
    bool fileExtraParagraphSpacing;
    uint8_t fileParagraphAlignment;
    bool fileHyphenationEnabled;
    bool fileEmbeddedStyle;
    uint8_t fileImageRendering;
    serialization::readPod(file, fileFontId);
    serialization::readPod(file, fileLineCompression);
    serialization::readPod(file, fileExtraParagraphSpacing);
    serialization::readPod(file, fileParagraphAlignment);
    serialization::readPod(file, fileViewportWidth);
    serialization::readPod(file, fileViewportHeight);
    serialization::readPod(file, fileHyphenationEnabled);
    serialization::readPod(file, fileEmbeddedStyle);
    serialization::readPod(file, fileImageRendering);

    if (fontId != fileFontId || lineCompression != fileLineCompression ||
        extraParagraphSpacing != fileExtraParagraphSpacing || paragraphAlignment != fileParagraphAlignment ||
        viewportWidth != fileViewportWidth || viewportHeight != fileViewportHeight ||
        hyphenationEnabled != fileHyphenationEnabled || embeddedStyle != fileEmbeddedStyle ||
        imageRendering != fileImageRendering) {
      file.close();
      LOG_ERR("SCT", "Deserialization failed: Parameters do not match");
      clearCache();
      return false;
    }
  }

  serialization::readPod(file, pageCount);
  file.close();
  LOG_DBG("SCT", "Deserialization succeeded: %d pages", pageCount);
  buildTocBoundaries(readAnchorMap(filePath));
  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 {
  if (!Storage.exists(filePath.c_str())) {
    LOG_DBG("SCT", "Cache does not exist, no action needed");
    return true;
  }

  if (!Storage.remove(filePath.c_str())) {
    LOG_ERR("SCT", "Failed to clear cache");
    return false;
  }

  LOG_DBG("SCT", "Cache cleared successfully");
  return true;
}

bool Section::createSectionFile(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 std::function<void()>& popupFn) {
  const auto localPath = epub->getSpineItem(spineIndex).href;
  const auto tmpHtmlPath = epub->getCachePath() + "/.tmp_" + std::to_string(spineIndex) + ".html";

  // Create cache directory if it doesn't exist
  {
    const auto sectionsDir = epub->getCachePath() + "/sections";
    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
    }

    // Remove any incomplete file from previous attempt before retrying
    if (Storage.exists(tmpHtmlPath.c_str())) {
      Storage.remove(tmpHtmlPath.c_str());
    }

    FsFile tmpHtml;
    if (!Storage.openFileForWrite("SCT", tmpHtmlPath, tmpHtml)) {
      continue;
    }
    success = epub->readItemContentsToStream(localPath, tmpHtml, 1024);
    fileSize = tmpHtml.size();
    tmpHtml.close();

    // 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");
    }
  }

  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)) {
    return false;
  }
  writeSectionFileHeader(fontId, lineCompression, extraParagraphSpacing, paragraphAlignment, viewportWidth,
                         viewportHeight, hyphenationEnabled, embeddedStyle, imageRendering);
  std::vector<uint32_t> lut = {};

  // 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) + "_";

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

  // Collect TOC anchors for this spine so the parser can insert page breaks at chapter boundaries
  std::set<std::string> tocAnchors;
  const int startTocIndex = epub->getTocIndexForSpineIndex(spineIndex);
  if (startTocIndex >= 0) {
    for (int i = startTocIndex; i < epub->getTocItemsCount(); i++) {
      auto entry = epub->getTocItem(i);
      if (entry.spineIndex != spineIndex) break;
      if (!entry.anchor.empty()) {
        tocAnchors.insert(std::move(entry.anchor));
      }
    }
  }

  ChapterHtmlSlimParser visitor(
      epub, tmpHtmlPath, renderer, fontId, lineCompression, extraParagraphSpacing, paragraphAlignment, viewportWidth,
      viewportHeight, hyphenationEnabled,
      [this, &lut](std::unique_ptr<Page> page) { lut.emplace_back(this->onPageComplete(std::move(page))); },
      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");
    file.close();
    Storage.remove(filePath.c_str());
    if (cssParser) {
      cssParser->clear();
    }
    return false;
  }

  const uint32_t lutOffset = file.position();
  bool hasFailedLutRecords = false;
  // Write LUT
  for (const uint32_t& pos : lut) {
    if (pos == 0) {
      hasFailedLutRecords = true;
      break;
    }
    serialization::writePod(file, pos);
  }

  if (hasFailedLutRecords) {
    LOG_ERR("SCT", "Failed to write LUT due to invalid page positions");
    file.close();
    Storage.remove(filePath.c_str());
    return false;
  }

  // Write anchor-to-page map for fragment navigation (footnotes + TOC)
  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();
  }

  // Convert anchor vector to map for buildTocBoundaries
  std::map<std::string, uint16_t> anchorMap;
  for (const auto& [a, p] : anchors) {
    anchorMap.emplace(a, p);
  }
  buildTocBoundaries(anchorMap);
  return true;
}

std::unique_ptr<Page> Section::loadPageFromSectionFile() {
  if (!Storage.openFileForRead("SCT", filePath, file)) {
    return nullptr;
  }

  file.seek(HEADER_SIZE - sizeof(uint32_t) * 2);
  uint32_t lutOffset;
  serialization::readPod(file, lutOffset);
  file.seek(lutOffset + sizeof(uint32_t) * currentPage);
  uint32_t pagePos;
  serialization::readPod(file, pagePos);
  file.seek(pagePos);

  auto page = Page::deserialize(file);
  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;
    if (!serialization::readString(f, key)) break;
    serialization::readPod(f, page);
    if (key == anchor) {
      f.close();
      return page;
    }
  }

  f.close();
  return std::nullopt;
}

std::map<std::string, uint16_t> Section::readAnchorMap(const std::string& sectionPath) {
  FsFile f;
  if (!Storage.openFileForRead("SCT", sectionPath, f)) {
    return {};
  }

  f.seek(HEADER_SIZE - sizeof(uint32_t));
  uint32_t anchorMapOffset;
  serialization::readPod(f, anchorMapOffset);
  if (anchorMapOffset == 0) {
    f.close();
    return {};
  }

  f.seek(anchorMapOffset);
  uint16_t count;
  serialization::readPod(f, count);
  std::map<std::string, uint16_t> result;
  for (uint16_t i = 0; i < count; i++) {
    std::string key;
    uint16_t page;
    if (!serialization::readString(f, key)) break;
    serialization::readPod(f, page);
    result.emplace(std::move(key), page);
  }

  f.close();
  return result;
}

void Section::buildTocBoundaries(const std::map<std::string, uint16_t>& anchorMap) {
  tocBoundaries.clear();
  const int startTocIndex = epub->getTocIndexForSpineIndex(spineIndex);
  if (startTocIndex < 0) return;

  const int tocCount = epub->getTocItemsCount();
  for (int i = startTocIndex; i < tocCount; i++) {
    const auto entry = epub->getTocItem(i);
    if (entry.spineIndex != spineIndex) break;
    uint16_t page = 0;
    if (!entry.anchor.empty()) {
      auto it = anchorMap.find(entry.anchor);
      if (it != anchorMap.end()) page = it->second;
    }
    tocBoundaries.push_back({i, page});
  }
  std::sort(tocBoundaries.begin(), tocBoundaries.end(),
            [](const TocBoundary& a, const TocBoundary& b) { return a.startPage < b.startPage; });
}

int Section::getTocIndexForPage(const int page) const {
  if (tocBoundaries.empty()) {
    return epub->getTocIndexForSpineIndex(spineIndex);
  }

  auto it = std::upper_bound(tocBoundaries.begin(), tocBoundaries.end(), static_cast<uint16_t>(page),
                             [](uint16_t p, const TocBoundary& boundary) { return p < boundary.startPage; });
  if (it == tocBoundaries.begin()) {
    return tocBoundaries[0].tocIndex;
  }
  return std::prev(it)->tocIndex;
}

std::optional<int> Section::getPageForTocIndex(const int tocIndex) const {
  for (const auto& boundary : tocBoundaries) {
    if (boundary.tocIndex == tocIndex) {
      return boundary.startPage;
    }
  }
  return std::nullopt;
}

std::optional<Section::TocPageRange> Section::getPageRangeForTocIndex(const int tocIndex) const {
  for (size_t i = 0; i < tocBoundaries.size(); i++) {
    if (tocBoundaries[i].tocIndex == tocIndex) {
      const int startPage = tocBoundaries[i].startPage;
      const int endPage = (i + 1 < tocBoundaries.size()) ? static_cast<int>(tocBoundaries[i + 1].startPage) : pageCount;
      return TocPageRange{startPage, endPage};
    }
  }
  return std::nullopt;
}

std::optional<uint16_t> Section::readCachedPageCount(const std::string& cachePath, const int spineIndex,
                                                     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 std::string path = cachePath + "/sections/" + std::to_string(spineIndex) + ".bin";
  FsFile f;
  if (!Storage.openFileForRead("SCT", path, f)) {
    return std::nullopt;
  }

  uint8_t version;
  serialization::readPod(f, version);
  if (version != SECTION_FILE_VERSION) {
    f.close();
    return std::nullopt;
  }

  int fileFontId;
  float fileLineCompression;
  bool fileExtraParagraphSpacing;
  uint8_t fileParagraphAlignment;
  uint16_t fileViewportWidth, fileViewportHeight;
  bool fileHyphenationEnabled, fileEmbeddedStyle;
  uint8_t fileImageRendering;
  serialization::readPod(f, fileFontId);
  serialization::readPod(f, fileLineCompression);
  serialization::readPod(f, fileExtraParagraphSpacing);
  serialization::readPod(f, fileParagraphAlignment);
  serialization::readPod(f, fileViewportWidth);
  serialization::readPod(f, fileViewportHeight);
  serialization::readPod(f, fileHyphenationEnabled);
  serialization::readPod(f, fileEmbeddedStyle);
  serialization::readPod(f, fileImageRendering);

  if (fontId != fileFontId || lineCompression != fileLineCompression ||
      extraParagraphSpacing != fileExtraParagraphSpacing || paragraphAlignment != fileParagraphAlignment ||
      viewportWidth != fileViewportWidth || viewportHeight != fileViewportHeight ||
      hyphenationEnabled != fileHyphenationEnabled || embeddedStyle != fileEmbeddedStyle ||
      imageRendering != fileImageRendering) {
    f.close();
    return std::nullopt;
  }

  uint16_t count;
  serialization::readPod(f, count);
  f.close();
  return count;
}