Function firstCodepoint

lib/Epub/Epub/ParsedText.cpp:38–45

Returns the first rendered codepoint of a word (skipping leading soft hyphens).

// Returns the first rendered codepoint of a word (skipping leading soft hyphens).
uint32_t firstCodepoint(const std::string& word) {
  const auto* ptr = reinterpret_cast<const unsigned char*>(word.c_str());
  while (true) {
    const uint32_t cp = utf8NextCodepoint(&ptr);
    if (cp == 0) return 0;
    if (cp != 0x00AD) return cp;  // skip soft hyphens
  }
}

// Returns the last codepoint of a word by scanning backward for the start of the last UTF-8 sequence.
uint32_t lastCodepoint(const std::string& word) {