Method addWord

lib/Epub/Epub/ParsedText.cpp:253–448

}  // namespace

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

  // The device fonts carry no combining-mark positioning, so EPUB text stored in NFD
  // (a base letter followed by separate combining accents -- common for Vietnamese,
  // and used for many EPUB <h1> chapter headings) renders with the marks detached or
  // misplaced. Compose to NFC here, the single funnel every word passes through, so a
  // precomposed glyph is used instead. This runs once per word at layout time (the
  // result is cached in the section file) and is a cheap no-op for mark-free text.
  word = utf8ComposeNfc(word);

  EpdFontFamily::Style baseStyle = fontStyle;
  if (underline) {
    baseStyle = static_cast<EpdFontFamily::Style>(baseStyle | EpdFontFamily::UNDERLINE);
  }
  const bool wordStartsRtl = !hasRtlWord && mayContainRtlBytes(word.c_str()) &&
                             BidiUtils::startsWithRtl(word.c_str(), RTL_PER_WORD_PROBE_DEPTH);

  const auto pushToken = [&](std::string token, const bool continues, const bool noSpaceBefore,
                             const bool isFocusSuffix) {
    words.push_back(std::move(token));
    wordStyles.push_back(baseStyle);
    wordContinues.push_back(continues);
    wordNoSpaceBefore.push_back(noSpaceBefore);
    wordIsFocusSuffix.push_back(isFocusSuffix);
  };

  bool effectiveAttachToPrevious = attachToPrevious;
  bool effectiveNoSpaceBefore = false;
  if (attachToPrevious && !words.empty() &&
      hasCjkBreakOpportunityBetween(lastCodepoint(words.back()), firstCodepoint(word))) {
    effectiveAttachToPrevious = false;
    effectiveNoSpaceBefore = true;
  }

  if (auto breakOffsets = cjkCharacterBreakByteOffsets(word); !breakOffsets.empty()) {
    bool firstToken = true;
    size_t tokenStart = 0;
    for (const size_t breakOffset : breakOffsets) {
      if (breakOffset <= tokenStart || breakOffset > word.size()) continue;
      pushToken(word.substr(tokenStart, breakOffset - tokenStart), firstToken ? effectiveAttachToPrevious : false,
                firstToken ? effectiveNoSpaceBefore : true, false);
      firstToken = false;
      tokenStart = breakOffset;
    }
    if (tokenStart < word.size()) {
      pushToken(word.substr(tokenStart), firstToken ? effectiveAttachToPrevious : false,
                firstToken ? effectiveNoSpaceBefore : true, false);
    }
    if (wordStartsRtl) {
      hasRtlWord = true;
    }
    return;
  }

  if (containsCjkBreakableCodepoint(word)) {
    pushToken(std::move(word), effectiveAttachToPrevious, effectiveNoSpaceBefore, false);