Xteink-X4-crosspoint-reader/lib/Epub/Epub/ParsedText.cpp

#include "ParsedText.h"

#include <GfxRenderer.h>

#include <algorithm>
#include <cmath>
#include <functional>
#include <iterator>
#include <limits>
#include <vector>

#include "hyphenation/Hyphenator.h"

constexpr int MAX_COST = std::numeric_limits<int>::max();

namespace {

// Soft hyphen byte pattern used throughout EPUBs (UTF-8 for U+00AD).
constexpr char SOFT_HYPHEN_UTF8[] = "\xC2\xAD";
constexpr size_t SOFT_HYPHEN_BYTES = 2;

bool containsSoftHyphen(const std::string& word) { return word.find(SOFT_HYPHEN_UTF8) != std::string::npos; }

// Removes every soft hyphen in-place so rendered glyphs match measured widths.
void stripSoftHyphensInPlace(std::string& word) {
  size_t pos = 0;
  while ((pos = word.find(SOFT_HYPHEN_UTF8, pos)) != std::string::npos) {
    word.erase(pos, SOFT_HYPHEN_BYTES);
  }
}

// Returns the rendered width for a word while ignoring soft hyphen glyphs and optionally appending a visible hyphen.
uint16_t measureWordWidth(const GfxRenderer& renderer, const int fontId, const std::string& word,
                          const EpdFontFamily::Style style, const bool appendHyphen = false) {
  const bool hasSoftHyphen = containsSoftHyphen(word);
  if (!hasSoftHyphen && !appendHyphen) {
    return renderer.getTextWidth(fontId, word.c_str(), style);
  }

  std::string sanitized = word;
  if (hasSoftHyphen) {
    stripSoftHyphensInPlace(sanitized);
  }
  if (appendHyphen) {
    sanitized.push_back('-');
  }
  return renderer.getTextWidth(fontId, sanitized.c_str(), style);
}

}  // namespace

void ParsedText::addWord(std::string word, const EpdFontFamily::Style style, const bool underline) {
  if (word.empty()) return;

  words.push_back(std::move(word));
  EpdFontFamily::Style combinedStyle = style;
  if (underline) {
    combinedStyle = static_cast<EpdFontFamily::Style>(combinedStyle | EpdFontFamily::UNDERLINE);
  }
  wordStyles.push_back(combinedStyle);
}

// Consumes data to minimize memory usage
void ParsedText::layoutAndExtractLines(const GfxRenderer& renderer, const int fontId, const uint16_t viewportWidth,
                                       const std::function<void(std::shared_ptr<TextBlock>)>& processLine,
                                       const bool includeLastLine) {
  if (words.empty()) {
    return;
  }

  // Apply fixed transforms before any per-line layout work.
  applyParagraphIndent();

  const int pageWidth = viewportWidth;
  const int spaceWidth = renderer.getSpaceWidth(fontId);
  auto wordWidths = calculateWordWidths(renderer, fontId);
  std::vector<size_t> lineBreakIndices;
  if (hyphenationEnabled) {
    // Use greedy layout that can split words mid-loop when a hyphenated prefix fits.
    lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths);
  } else {
    lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths);
  }
  const size_t lineCount = includeLastLine ? lineBreakIndices.size() : lineBreakIndices.size() - 1;

  for (size_t i = 0; i < lineCount; ++i) {
    extractLine(i, pageWidth, spaceWidth, wordWidths, lineBreakIndices, processLine);
  }
}

std::vector<uint16_t> ParsedText::calculateWordWidths(const GfxRenderer& renderer, const int fontId) {
  const size_t totalWordCount = words.size();

  std::vector<uint16_t> wordWidths;
  wordWidths.reserve(totalWordCount);

  auto wordsIt = words.begin();
  auto wordStylesIt = wordStyles.begin();

  while (wordsIt != words.end()) {
    wordWidths.push_back(measureWordWidth(renderer, fontId, *wordsIt, *wordStylesIt));

    std::advance(wordsIt, 1);
    std::advance(wordStylesIt, 1);
  }

  return wordWidths;
}

std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, const int fontId, const int pageWidth,
                                                  const int spaceWidth, std::vector<uint16_t>& wordWidths) {
  if (words.empty()) {
    return {};
  }

  // Calculate first line indent (only for left/justified text without extra paragraph spacing)
  const int firstLineIndent =
      blockStyle.textIndent > 0 && !extraParagraphSpacing &&
              (blockStyle.alignment == CssTextAlign::Justify || blockStyle.alignment == CssTextAlign::Left)
          ? blockStyle.textIndent
          : 0;

  // Ensure any word that would overflow even as the first entry on a line is split using fallback hyphenation.
  for (size_t i = 0; i < wordWidths.size(); ++i) {
    // First word needs to fit in reduced width if there's an indent
    const int effectiveWidth = i == 0 ? pageWidth - firstLineIndent : pageWidth;
    while (wordWidths[i] > effectiveWidth) {
      if (!hyphenateWordAtIndex(i, effectiveWidth, renderer, fontId, wordWidths, /*allowFallbackBreaks=*/true)) {
        break;
      }
    }
  }

  const size_t totalWordCount = words.size();

  // DP table to store the minimum badness (cost) of lines starting at index i
  std::vector<int> dp(totalWordCount);
  // 'ans[i]' stores the index 'j' of the *last word* in the optimal line starting at 'i'
  std::vector<size_t> ans(totalWordCount);

  // Base Case
  dp[totalWordCount - 1] = 0;
  ans[totalWordCount - 1] = totalWordCount - 1;

  for (int i = totalWordCount - 2; i >= 0; --i) {
    int currlen = -spaceWidth;
    dp[i] = MAX_COST;

    // First line has reduced width due to text-indent
    const int effectivePageWidth = i == 0 ? pageWidth - firstLineIndent : pageWidth;

    for (size_t j = i; j < totalWordCount; ++j) {
      // Current line length: previous width + space + current word width
      currlen += wordWidths[j] + spaceWidth;

      if (currlen > effectivePageWidth) {
        break;
      }

      int cost;
      if (j == totalWordCount - 1) {
        cost = 0;  // Last line
      } else {
        const int remainingSpace = effectivePageWidth - currlen;
        // Use long long for the square to prevent overflow
        const long long cost_ll = static_cast<long long>(remainingSpace) * remainingSpace + dp[j + 1];

        if (cost_ll > MAX_COST) {
          cost = MAX_COST;
        } else {
          cost = static_cast<int>(cost_ll);
        }
      }

      if (cost < dp[i]) {
        dp[i] = cost;
        ans[i] = j;  // j is the index of the last word in this optimal line
      }
    }

    // Handle oversized word: if no valid configuration found, force single-word line
    // This prevents cascade failure where one oversized word breaks all preceding words
    if (dp[i] == MAX_COST) {
      ans[i] = i;  // Just this word on its own line
      // Inherit cost from next word to allow subsequent words to find valid configurations
      if (i + 1 < static_cast<int>(totalWordCount)) {
        dp[i] = dp[i + 1];
      } else {
        dp[i] = 0;
      }
    }
  }

  // Stores the index of the word that starts the next line (last_word_index + 1)
  std::vector<size_t> lineBreakIndices;
  size_t currentWordIndex = 0;

  while (currentWordIndex < totalWordCount) {
    size_t nextBreakIndex = ans[currentWordIndex] + 1;

    // Safety check: prevent infinite loop if nextBreakIndex doesn't advance
    if (nextBreakIndex <= currentWordIndex) {
      // Force advance by at least one word to avoid infinite loop
      nextBreakIndex = currentWordIndex + 1;
    }

    lineBreakIndices.push_back(nextBreakIndex);
    currentWordIndex = nextBreakIndex;
  }

  return lineBreakIndices;
}

void ParsedText::applyParagraphIndent() {
  if (extraParagraphSpacing || words.empty()) {
    return;
  }

  if (blockStyle.textIndentDefined) {
    // CSS text-indent is explicitly set (even if 0) - don't use fallback EmSpace
    // The actual indent positioning is handled in extractLine()
  } else if (blockStyle.alignment == CssTextAlign::Justify || blockStyle.alignment == CssTextAlign::Left) {
    // No CSS text-indent defined - use EmSpace fallback for visual indent
    words.front().insert(0, "\xe2\x80\x83");
  }
}

// Builds break indices while opportunistically splitting the word that would overflow the current line.
std::vector<size_t> ParsedText::computeHyphenatedLineBreaks(const GfxRenderer& renderer, const int fontId,
                                                            const int pageWidth, const int spaceWidth,
                                                            std::vector<uint16_t>& wordWidths) {
  // Calculate first line indent (only for left/justified text without extra paragraph spacing)
  const int firstLineIndent =
      blockStyle.textIndent > 0 && !extraParagraphSpacing &&
              (blockStyle.alignment == CssTextAlign::Justify || blockStyle.alignment == CssTextAlign::Left)
          ? blockStyle.textIndent
          : 0;

  std::vector<size_t> lineBreakIndices;
  size_t currentIndex = 0;
  bool isFirstLine = true;

  while (currentIndex < wordWidths.size()) {
    const size_t lineStart = currentIndex;
    int lineWidth = 0;

    // First line has reduced width due to text-indent
    const int effectivePageWidth = isFirstLine ? pageWidth - firstLineIndent : pageWidth;

    // Consume as many words as possible for current line, splitting when prefixes fit
    while (currentIndex < wordWidths.size()) {
      const bool isFirstWord = currentIndex == lineStart;
      const int spacing = isFirstWord ? 0 : spaceWidth;
      const int candidateWidth = spacing + wordWidths[currentIndex];

      // Word fits on current line
      if (lineWidth + candidateWidth <= effectivePageWidth) {
        lineWidth += candidateWidth;
        ++currentIndex;
        continue;
      }

      // Word would overflow — try to split based on hyphenation points
      const int availableWidth = effectivePageWidth - lineWidth - spacing;
      const bool allowFallbackBreaks = isFirstWord;  // Only for first word on line

      if (availableWidth > 0 &&
          hyphenateWordAtIndex(currentIndex, availableWidth, renderer, fontId, wordWidths, allowFallbackBreaks)) {
        // Prefix now fits; append it to this line and move to next line
        lineWidth += spacing + wordWidths[currentIndex];
        ++currentIndex;
        break;
      }

      // Could not split: force at least one word per line to avoid infinite loop
      if (currentIndex == lineStart) {
        lineWidth += candidateWidth;
        ++currentIndex;
      }
      break;
    }

    lineBreakIndices.push_back(currentIndex);
    isFirstLine = false;
  }

  return lineBreakIndices;
}

// Splits words[wordIndex] into prefix (adding a hyphen only when needed) and remainder when a legal breakpoint fits the
// available width.
bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availableWidth, const GfxRenderer& renderer,
                                      const int fontId, std::vector<uint16_t>& wordWidths,
                                      const bool allowFallbackBreaks) {
  // Guard against invalid indices or zero available width before attempting to split.
  if (availableWidth <= 0 || wordIndex >= words.size()) {
    return false;
  }

  // Get iterators to target word and style.
  auto wordIt = words.begin();
  auto styleIt = wordStyles.begin();
  std::advance(wordIt, wordIndex);
  std::advance(styleIt, wordIndex);

  const std::string& word = *wordIt;
  const auto style = *styleIt;

  // Collect candidate breakpoints (byte offsets and hyphen requirements).
  auto breakInfos = Hyphenator::breakOffsets(word, allowFallbackBreaks);
  if (breakInfos.empty()) {
    return false;
  }

  size_t chosenOffset = 0;
  int chosenWidth = -1;
  bool chosenNeedsHyphen = true;

  // Iterate over each legal breakpoint and retain the widest prefix that still fits.
  for (const auto& info : breakInfos) {
    const size_t offset = info.byteOffset;
    if (offset == 0 || offset >= word.size()) {
      continue;
    }

    const bool needsHyphen = info.requiresInsertedHyphen;
    const int prefixWidth = measureWordWidth(renderer, fontId, word.substr(0, offset), style, needsHyphen);
    if (prefixWidth > availableWidth || prefixWidth <= chosenWidth) {
      continue;  // Skip if too wide or not an improvement
    }

    chosenWidth = prefixWidth;
    chosenOffset = offset;
    chosenNeedsHyphen = needsHyphen;
  }

  if (chosenWidth < 0) {
    // No hyphenation point produced a prefix that fits in the remaining space.
    return false;
  }

  // Split the word at the selected breakpoint and append a hyphen if required.
  std::string remainder = word.substr(chosenOffset);
  wordIt->resize(chosenOffset);
  if (chosenNeedsHyphen) {
    wordIt->push_back('-');
  }

  // Insert the remainder word (with matching style) directly after the prefix.
  auto insertWordIt = std::next(wordIt);
  auto insertStyleIt = std::next(styleIt);
  words.insert(insertWordIt, remainder);
  wordStyles.insert(insertStyleIt, style);

  // Update cached widths to reflect the new prefix/remainder pairing.
  wordWidths[wordIndex] = static_cast<uint16_t>(chosenWidth);
  const uint16_t remainderWidth = measureWordWidth(renderer, fontId, remainder, style);
  wordWidths.insert(wordWidths.begin() + wordIndex + 1, remainderWidth);
  return true;
}

void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const int spaceWidth,
                             const std::vector<uint16_t>& wordWidths, const std::vector<size_t>& lineBreakIndices,
                             const std::function<void(std::shared_ptr<TextBlock>)>& processLine) {
  const size_t lineBreak = lineBreakIndices[breakIndex];
  const size_t lastBreakAt = breakIndex > 0 ? lineBreakIndices[breakIndex - 1] : 0;
  const size_t lineWordCount = lineBreak - lastBreakAt;

  // Calculate first line indent (only for left/justified text without extra paragraph spacing)
  const bool isFirstLine = breakIndex == 0;
  const int firstLineIndent =
      isFirstLine && blockStyle.textIndent > 0 && !extraParagraphSpacing &&
              (blockStyle.alignment == CssTextAlign::Justify || blockStyle.alignment == CssTextAlign::Left)
          ? blockStyle.textIndent
          : 0;

  // Calculate total word width for this line
  int lineWordWidthSum = 0;
  for (size_t i = lastBreakAt; i < lineBreak; i++) {
    lineWordWidthSum += wordWidths[i];
  }

  // Calculate spacing (account for indent reducing effective page width on first line)
  const int effectivePageWidth = pageWidth - firstLineIndent;
  const int spareSpace = effectivePageWidth - lineWordWidthSum;

  int spacing = spaceWidth;
  const bool isLastLine = breakIndex == lineBreakIndices.size() - 1;

  if (blockStyle.alignment == CssTextAlign::Justify && !isLastLine && lineWordCount >= 2) {
    spacing = spareSpace / (lineWordCount - 1);
  }

  // Calculate initial x position (first line starts at indent for left/justified text)
  auto xpos = static_cast<uint16_t>(firstLineIndent);
  if (blockStyle.alignment == CssTextAlign::Right) {
    xpos = spareSpace - (lineWordCount - 1) * spaceWidth;
  } else if (blockStyle.alignment == CssTextAlign::Center) {
    xpos = (spareSpace - (lineWordCount - 1) * spaceWidth) / 2;
  }

  // Pre-calculate X positions for words
  std::list<uint16_t> lineXPos;
  for (size_t i = lastBreakAt; i < lineBreak; i++) {
    const uint16_t currentWordWidth = wordWidths[i];
    lineXPos.push_back(xpos);
    xpos += currentWordWidth + spacing;
  }

  // Iterators always start at the beginning as we are moving content with splice below
  auto wordEndIt = words.begin();
  auto wordStyleEndIt = wordStyles.begin();
  std::advance(wordEndIt, lineWordCount);
  std::advance(wordStyleEndIt, lineWordCount);

  // *** CRITICAL STEP: CONSUME DATA USING SPLICE ***
  std::list<std::string> lineWords;
  lineWords.splice(lineWords.begin(), words, words.begin(), wordEndIt);
  std::list<EpdFontFamily::Style> lineWordStyles;
  lineWordStyles.splice(lineWordStyles.begin(), wordStyles, wordStyles.begin(), wordStyleEndIt);

  for (auto& word : lineWords) {
    if (containsSoftHyphen(word)) {
      stripSoftHyphensInPlace(word);
    }
  }

  processLine(
      std::make_shared<TextBlock>(std::move(lineWords), std::move(lineXPos), std::move(lineWordStyles), blockStyle));
}