#include <iostream>
#include <memory>

#include "simdutf.cpp"
#include "simdutf.h"

int main(int argc, char *argv[]) {
  const char *source = "1234";
  // 4 == strlen(source)
  bool validutf8 = simdutf::validate_utf8(source, 4);
  if (validutf8) {
    std::cout << "valid UTF-8" << std::endl;
  } else {
    std::cerr << "invalid UTF-8" << std::endl;
    return EXIT_FAILURE;
  }
  // We need a buffer of size where to write the UTF-16LE code units.
  size_t expected_utf16words = simdutf::utf16_length_from_utf8(source, 4);
  std::unique_ptr<char16_t[]> utf16_output{new char16_t[expected_utf16words]};
  // convert to UTF-16LE
  size_t utf16words =
      simdutf::convert_utf8_to_utf16le(source, 4, utf16_output.get());
  std::cout << "wrote " << utf16words << " UTF-16LE code units." << std::endl;
  // It wrote utf16words * sizeof(char16_t) bytes.
  bool validutf16 = simdutf::validate_utf16le(utf16_output.get(), utf16words);
  if (validutf16) {
    std::cout << "valid UTF-16LE" << std::endl;
  } else {
    std::cerr << "invalid UTF-16LE" << std::endl;
    return EXIT_FAILURE;
  }
  // convert it back:
  // We need a buffer of size where to write the UTF-8 code units.
  size_t expected_utf8words =
      simdutf::utf8_length_from_utf16le(utf16_output.get(), utf16words);
  std::unique_ptr<char[]> utf8_output{new char[expected_utf8words]};
  // convert to UTF-8
  size_t utf8words = simdutf::convert_utf16le_to_utf8(
      utf16_output.get(), utf16words, utf8_output.get());
  std::cout << "wrote " << utf8words << " UTF-8 code units." << std::endl;
  std::string final_string(utf8_output.get(), utf8words);
  std::cout << final_string << std::endl;
  if (final_string != source) {
    std::cerr << "bad conversion" << std::endl;
    return EXIT_FAILURE;
  } else {
    std::cerr << "perfect round trip" << std::endl;
  }
  return EXIT_SUCCESS;
}

enum encoding_type {
        UTF8 = 1,       // BOM 0xef 0xbb 0xbf
        UTF16_LE = 2,   // BOM 0xff 0xfe
        UTF16_BE = 4,   // BOM 0xfe 0xff
        UTF32_LE = 8,   // BOM 0xff 0xfe 0x00 0x00
        UTF32_BE = 16,   // BOM 0x00 0x00 0xfe 0xff

        unspecified = 0
};

/**
 * Autodetect the encoding of the input, a single encoding is recommended.
 * E.g., the function might return simdutf::encoding_type::UTF8,
 * simdutf::encoding_type::UTF16_LE, simdutf::encoding_type::UTF16_BE, or
 * simdutf::encoding_type::UTF32_LE.
 *
 * @param input the string to analyze.
 * @param length the length of the string in bytes.
 * @return the detected encoding type
 */
simdutf_warn_unused simdutf::encoding_type autodetect_encoding(const char * input, size_t length) noexcept;

/**
 * Autodetect the possible encodings of the input in one pass.
 * E.g., if the input might be UTF-16LE or UTF-8, this function returns
 * the value (simdutf::encoding_type::UTF8 | simdutf::encoding_type::UTF16_LE).
 *
 * Overridden by each implementation.
 *
 * @param input the string to analyze.
 * @param length the length of the string in bytes.
 * @return the detected encoding type
 */
simdutf_warn_unused int detect_encodings(const char * input, size_t length) noexcept;

struct result {
  error_code error; // see `struct error_code`.
  size_t count; // In case of error, indicates the position of the error in the input in code units.
  // In case of success, indicates the number of code units validated/written.
};

enum error_code {
  SUCCESS = 0,
  HEADER_BITS,  // Any byte must have fewer than 5 header bits.
  TOO_SHORT,    // The leading byte must be followed by N-1 continuation bytes, where N is the UTF-8 character length
                // This is also the error when the input is truncated.
  TOO_LONG,     // We either have too many consecutive continuation bytes or the string starts with a continuation byte.
  OVERLONG,     // The decoded character must be above U+7F for two-byte characters, U+7FF for three-byte characters,
                // and U+FFFF for four-byte characters.
  TOO_LARGE,    // The decoded character must be less than or equal to U+10FFFF,less than or equal than U+7F for ASCII OR less than equal than U+FF for Latin1
  SURROGATE,    // The decoded character must not be in U+D800...DFFF (UTF-8 or UTF-32) OR
                // a high surrogate must be followed by a low surrogate and a low surrogate must be preceded by a high surrogate (UTF-16) OR
                // there must be no surrogate at all (Latin1)
  OTHER         // Not related to validation/transcoding.
};

  std::string bad_ascii = "\x20\x20\x20\x20\x20\xff\x20\x20\x20";
  simdutf::result res = implementation.validate_ascii_with_errors(bad_ascii.data(), bad_ascii.size());
  if(res.error != simdutf::error_code::SUCCESS) {
    std::cerr << "error at index " << res.count << std::endl;
  }

  std::string bad_utf8 = "\xc3\xa9\xc3\xa9\x20\xff\xc3\xa9";
  simdutf::result res = implementation.validate_utf8_with_errors(bad_utf8.data(), bad_utf8.size());
  if(res.error != simdutf::error_code::SUCCESS) {
    std::cerr << "error at index " << res.count << std::endl;
  }
  res = implementation.validate_utf8_with_errors(bad_utf8.data(), res.count);
  // will be successful in this case
  if(res.error == simdutf::error_code::SUCCESS) {
    std::cerr << "we have " << res.count << "valid bytes" << std::endl;
  }

/**
 * Validate the ASCII string.
 *
 * Overridden by each implementation.
 *
 * @param buf the ASCII string to validate.
 * @param len the length of the string in bytes.
 * @return true if and only if the string is valid ASCII.
 */
simdutf_warn_unused bool validate_ascii(const char *buf, size_t len) noexcept;

/**
 * Validate the ASCII string and stop on error.
 *
 * Overridden by each implementation.
 *
 * @param buf the ASCII string to validate.
 * @param len the length of the string in bytes.
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_ascii_with_errors(const char *buf, size_t len) noexcept;

/**
 * Validate the UTF-8 string. This function may be best when you expect
 * the input to be almost always valid. Otherwise, consider using
 * validate_utf8_with_errors.
 *
 * Overridden by each implementation.
 *
 * @param buf the UTF-8 string to validate.
 * @param len the length of the string in bytes.
 * @return true if and only if the string is valid UTF-8.
 */
simdutf_warn_unused bool validate_utf8(const char *buf, size_t len) noexcept;

/**
 * Validate the UTF-8 string and stop on error. It might be faster than
 * validate_utf8 when an error is expected to occur early.
 *
 * Overridden by each implementation.
 *
 * @param buf the UTF-8 string to validate.
 * @param len the length of the string in bytes.
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_utf8_with_errors(const char *buf, size_t len) noexcept;

/**
 * Using native endianness; Validate the UTF-16 string.
 * This function may be best when you expect the input to be almost always valid.
 * Otherwise, consider using validate_utf16_with_errors.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16 string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return true if and only if the string is valid UTF-16.
 */
simdutf_warn_unused bool validate_utf16(const char16_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-16LE string. This function may be best when you expect
 * the input to be almost always valid. Otherwise, consider using
 * validate_utf16le_with_errors.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16LE string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return true if and only if the string is valid UTF-16LE.
 */
simdutf_warn_unused bool validate_utf16le(const char16_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-16BE string. This function may be best when you expect
 * the input to be almost always valid. Otherwise, consider using
 * validate_utf16be_with_errors.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16BE string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return true if and only if the string is valid UTF-16BE.
 */
simdutf_warn_unused bool validate_utf16be(const char16_t *buf, size_t len) noexcept;

/**
 * Using native endianness; Validate the UTF-16 string and stop on error.
 * It might be faster than validate_utf16 when an error is expected to occur early.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16 string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_utf16_with_errors(const char16_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-16LE string and stop on error. It might be faster than
 * validate_utf16le when an error is expected to occur early.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16LE string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_utf16le_with_errors(const char16_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-16BE string and stop on error. It might be faster than
 * validate_utf16be when an error is expected to occur early.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-16BE string to validate.
 * @param len the length of the string in number of 2-byte code units (char16_t).
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_utf16be_with_errors(const char16_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-32 string.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-32 string to validate.
 * @param len the length of the string in number of 4-byte code units (char32_t).
 * @return true if and only if the string is valid UTF-32.
 */
simdutf_warn_unused bool validate_utf32(const char32_t *buf, size_t len) noexcept;

/**
 * Validate the UTF-32 string and stop on error.
 *
 * Overridden by each implementation.
 *
 * This function is not BOM-aware.
 *
 * @param buf the UTF-32 string to validate.
 * @param len the length of the string in number of 4-byte code units (char32_t).
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result validate_utf32_with_errors(const char32_t *buf, size_t len) noexcept;

/**
 * Count the number of code points (characters) in the string assuming that
 * it is valid.
 *
 * This function assumes that the input string is valid UTF-16 (native endianness).
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to process
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return number of code points
 */
simdutf_warn_unused size_t count_utf16(const char16_t * input, size_t length) noexcept;

/**
 * Count the number of code points (characters) in the string assuming that
 * it is valid.
 *
 * This function assumes that the input string is valid UTF-16LE.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to process
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return number of code points
 */
simdutf_warn_unused size_t count_utf16le(const char16_t * input, size_t length) noexcept;

/**
 * Count the number of code points (characters) in the string assuming that
 * it is valid.
 *
 * This function assumes that the input string is valid UTF-16BE.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to process
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return number of code points
 */
simdutf_warn_unused size_t count_utf16be(const char16_t * input, size_t length) noexcept;

/**
 * Count the number of code points (characters) in the string assuming that
 * it is valid.
 *
 * This function assumes that the input string is valid UTF-8.
 *
 * @param input         the UTF-8 string to process
 * @param length        the length of the string in bytes
 * @return number of code points
 */
simdutf_warn_unused size_t count_utf8(const char * input, size_t length) noexcept;

/**
 * Return the number of bytes that this Latin1 string would require in UTF-8 format.
 *
 * @param input         the Latin1 string to convert
 * @param length        the length of the string bytes
 * @return the number of bytes required to encode the Latin1 string as UTF-8
 */
simdutf_warn_unused size_t utf8_length_from_latin1(const char * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-8 string would require in Latin1 format.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in byte
 * @return the number of bytes required to encode the UTF-8 string as Latin1
 */
simdutf_warn_unused size_t latin1_length_from_utf8(const char * input, size_t length) noexcept;

/*
 * Compute the number of bytes that this UTF-16LE/BE string would require in Latin1 format.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16LE string as Latin1
 */
simdutf_warn_unused size_t latin1_length_from_utf16(size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-32 string would require in Latin1 format.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @return the number of bytes required to encode the UTF-32 string as Latin1
 */
simdutf_warn_unused size_t latin1_length_from_utf32(size_t length) noexcept;

/**
 * Compute the number of 2-byte code units that this UTF-8 string would require in UTF-16 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-8 string to process
 * @param length        the length of the string in bytes
 * @return the number of char16_t code units required to encode the UTF-8 string as UTF-16
 */
simdutf_warn_unused size_t utf16_length_from_utf8(const char * input, size_t length) noexcept;


/**
 * Compute the number of 4-byte code units that this UTF-8 string would require in UTF-32 format.
 *
 * This function is equivalent to count_utf8
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-8 string to process
 * @param length        the length of the string in bytes
 * @return the number of char32_t code units required to encode the UTF-8 string as UTF-32
 */
simdutf_warn_unused size_t utf32_length_from_utf8(const char * input, size_t length) noexcept;

/**
 * Using native endianness; Compute the number of bytes that this UTF-16
 * string would require in UTF-8 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16LE string as UTF-8
 */
simdutf_warn_unused size_t utf8_length_from_utf16(const char16_t * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-16LE string would require in UTF-8 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16LE string as UTF-8
 */
simdutf_warn_unused size_t utf8_length_from_utf16le(const char16_t * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-16BE string would require in UTF-8 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16BE string as UTF-8
 */
simdutf_warn_unused size_t utf8_length_from_utf16be(const char16_t * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-32 string would require in UTF-8 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @return the number of bytes required to encode the UTF-32 string as UTF-8
 */
simdutf_warn_unused size_t utf8_length_from_utf32(const char32_t * input, size_t length) noexcept;

/**
 * Compute the number of two-byte code units that this UTF-32 string would require in UTF-16 format.
 *
 * This function does not validate the input.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @return the number of bytes required to encode the UTF-32 string as UTF-16
 */
simdutf_warn_unused size_t utf16_length_from_utf32(const char32_t * input, size_t length) noexcept;

/**
 * Using native endianness; Compute the number of bytes that this UTF-16
 * string would require in UTF-32 format.
 *
 * This function is equivalent to count_utf16.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16LE string as UTF-32
 */
simdutf_warn_unused size_t utf32_length_from_utf16(const char16_t * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-16LE string would require in UTF-32 format.
 *
 * This function is equivalent to count_utf16le.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16LE string as UTF-32
 */
simdutf_warn_unused size_t utf32_length_from_utf16le(const char16_t * input, size_t length) noexcept;

/**
 * Compute the number of bytes that this UTF-16BE string would require in UTF-32 format.
 *
 * This function is equivalent to count_utf16be.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @return the number of bytes required to encode the UTF-16BE string as UTF-32
 */
simdutf_warn_unused size_t utf32_length_from_utf16be(const char16_t * input, size_t length) noexcept;

/**
 * Convert Latin1 string into UTF8 string.
 *
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the Latin1 string to convert
 * @param length        the length of the string in bytes
 * @param latin1_output  the pointer to buffer that can hold conversion result
 * @return the number of written char; 0 if conversion is not possible
 */
simdutf_warn_unused size_t convert_latin1_to_utf8(const char * input, size_t length, char* utf8_output) noexcept;

/**
 * Using native endianness, convert a Latin1 string into a UTF-16 string.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t.
 */
simdutf_warn_unused size_t convert_latin1_to_utf16(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly Latin1 string into UTF-16LE string.
 *
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the Latin1  string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t; 0 if conversion is not possible
 */
simdutf_warn_unused size_t convert_latin1_to_utf16le(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert Latin1 string into UTF-16BE string.
 *
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the Latin1 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t; 0 if conversion is not possible
 */
simdutf_warn_unused size_t convert_latin1_to_utf16be(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert Latin1 string into UTF-32 string.
 *
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the Latin1 string to convert
 * @param length        the length of the string in bytes
 * @param utf32_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char32_t; 0 if conversion is not possible
 */
simdutf_warn_unused size_t convert_latin1_to_utf32(const char * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Convert possibly broken UTF-8 string into latin1 string.
 * If the string cannot be represented as Latin1, an error
 * code is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param latin1_output  the pointer to buffer that can hold conversion result
 * @return the number of written char; 0 if the input was not valid UTF-8 string or if it cannot be represented as Latin1
 */
simdutf_warn_unused size_t convert_utf8_to_latin1(const char * input, size_t length, char* latin1_output) noexcept;

/**
 * Using native endianness; Convert possibly broken UTF-8 string into a UTF-16 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t; 0 if the input was not valid UTF-8 string
 */
simdutf_warn_unused size_t convert_utf8_to_utf16(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-16LE string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t; 0 if the input was not valid UTF-8 string
 */
simdutf_warn_unused size_t convert_utf8_to_utf16le(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-16BE string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char16_t; 0 if the input was not valid UTF-8 string
 */
simdutf_warn_unused size_t convert_utf8_to_utf16be(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-32 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf32_buffer  the pointer to buffer that can hold conversion result
 * @return the number of written char32_t; 0 if the input was not valid UTF-8 string
 */
simdutf_warn_unused size_t convert_utf8_to_utf32(const char * input, size_t length, char32_t* utf32_output) noexcept;


/**
 * Using native endianness, convert possibly broken UTF-16 string into Latin1 string.
 * If the string cannot be represented as Latin1, an error
 * is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16 string or if it cannot be represented as Latin1
 */
simdutf_warn_unused size_t convert_utf16_to_latin1(const char16_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Convert possibly broken UTF-16LE string into Latin1 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string or if it cannot be represented as Latin1
 */
simdutf_warn_unused size_t convert_utf16le_to_latin1(const char16_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into Latin1 string.
 * If the string cannot be represented as Latin1, an error
 * is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16BE string or if it cannot be represented as Latin1
 */
simdutf_warn_unused size_t convert_utf16be_to_latin1(const char16_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Convert possibly broken UTF-16LE string into UTF-8 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string
 */
simdutf_warn_unused size_t convert_utf16le_to_utf8(const char16_t * input, size_t length, char* utf8_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into UTF-8 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string
 */
simdutf_warn_unused size_t convert_utf16be_to_utf8(const char16_t * input, size_t length, char* utf8_buffer) noexcept;


/**
 * Convert possibly broken UTF-32 string into Latin1 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-32 string or if it cannot be represented as Latin1
 */
simdutf_warn_unused size_t convert_utf32_to_latin1(const char32_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Convert possibly broken UTF-32 string into UTF-8 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-32 string
 */
simdutf_warn_unused size_t convert_utf32_to_utf8(const char32_t * input, size_t length, char* utf8_buffer) noexcept;

/**
 * Using native endianness; Convert possibly broken UTF-32 string into a UTF-16 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-32 string
 */
simdutf_warn_unused size_t convert_utf32_to_utf16(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Convert possibly broken UTF-32 string into UTF-16LE string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-32 string
 */
simdutf_warn_unused size_t convert_utf32_to_utf16le(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Convert possibly broken UTF-32 string into UTF-16BE string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-32 string
 */
simdutf_warn_unused size_t convert_utf32_to_utf16be(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Using native endianness; Convert possibly broken UTF-16 string into UTF-32 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string
 */
simdutf_warn_unused size_t convert_utf16_to_utf32(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Convert possibly broken UTF-16LE string into UTF-32 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string
 */
simdutf_warn_unused size_t convert_utf16le_to_utf32(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into UTF-32 string.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return number of written code units; 0 if input is not a valid UTF-16LE string
 */
simdutf_warn_unused size_t convert_utf16be_to_utf32(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Given a valid UTF-8 string having a possibly truncated last character,
 * this function checks the end of string. If the last character is truncated (or partial),
 * then it returns a shorter length (shorter by 1 to 3 bytes) so that the short UTF-8
 * strings only contain complete characters. If there is no truncated character,
 * the original length is returned.
 *
 * This function assumes that the input string is valid UTF-8, but possibly truncated.
 *
 * @param input         the UTF-8 string to process
 * @param length        the length of the string in bytes
 * @return the length of the string in bytes, possibly shorter by 1 to 3 bytes
 */
simdutf_warn_unused size_t trim_partial_utf8(const char *input, size_t length);

/**
 * Given a valid UTF-16BE string having a possibly truncated last character,
 * this function checks the end of string. If the last character is truncated (or partial),
 * then it returns a shorter length (shorter by 1 unit) so that the short UTF-16BE
 * strings only contain complete characters. If there is no truncated character,
 * the original length is returned.
 *
 * This function assumes that the input string is valid UTF-16BE, but possibly truncated.
 *
 * @param input         the UTF-16BE string to process
 * @param length        the length of the string in bytes
 * @return the length of the string in bytes, possibly shorter by 1 unit
 */
simdutf_warn_unused size_t trim_partial_utf16be(const char16_t* input, size_t length);

/**
 * Given a valid UTF-16LE string having a possibly truncated last character,
 * this function checks the end of string. If the last character is truncated (or partial),
 * then it returns a shorter length (shorter by 1 unit) so that the short UTF-16LE
 * strings only contain complete characters. If there is no truncated character,
 * the original length is returned.
 *
 * This function assumes that the input string is valid UTF-16LE, but possibly truncated.
 *
 * @param input         the UTF-16LE string to process
 * @param length        the length of the string in bytes
 * @return the length of the string in unit, possibly shorter by 1 unit
 */
simdutf_warn_unused size_t trim_partial_utf16le(const char16_t* input, size_t length);


/**
 * Given a valid UTF-16 string having a possibly truncated last character,
 * this function checks the end of string. If the last character is truncated (or partial),
 * then it returns a shorter length (shorter by 1 unit) so that the short UTF-16
 * strings only contain complete characters. If there is no truncated character,
 * the original length is returned.
 *
 * This function assumes that the input string is valid UTF-16, but possibly truncated.
 * We use the native endianness.
 *
 * @param input         the UTF-16 string to process
 * @param length        the length of the string in bytes
 * @return the length of the string in unit, possibly shorter by 1 unit
 */
simdutf_warn_unused size_t trim_partial_utf16(const char16_t* input, size_t length);

  const char unicode[] = "\xc3\xa9\x63ole d'\xc3\xa9t\xc3\xa9";
  // suppose you want to decode only the start of this string.
  size_t length = 10;
  // Picking 10 bytes is problematic because we might end up in the middle of a
  // code point. But we can rewind to the previous code point.
  length = simdutf::trim_partial_utf8(unicode, length);
  // Now we can transcode safely
  size_t budget_utf16 = simdutf::utf16_length_from_utf8(unicode, length);
  std::unique_ptr<char16_t[]> utf16{new char16_t[budget_utf16]};
  size_t utf16words =
      simdutf::convert_utf8_to_utf16le(unicode, length, utf16.get());
  // We can then transcode the next batch
  const char * next = unicode + length;
  size_t next_length = sizeof(unicode) - length;
  size_t next_budget_utf16 = simdutf::utf16_length_from_utf8(next, next_length);
  std::unique_ptr<char16_t[]> next_utf16{new char16_t[next_budget_utf16]};
  size_t next_utf16words =
      simdutf::convert_utf8_to_utf16le(next, next_length, next_utf16.get());

  const char16_t unicode[] = u"\x3cd8\x10df\x3cd8\x10df\x3cd8\x10df";
  // suppose you want to decode only the start of this string.
  size_t length = 3;
  // Picking 3 units is problematic because we might end up in the middle of a
  // surrogate pair. But we can rewind to the previous code point.
  length = simdutf::trim_partial_utf16(unicode, length);
  // Now we can transcode safely
  size_t budget_utf8 = simdutf::utf8_length_from_utf16(unicode, length);
  std::unique_ptr<char[]> utf8{new char[budget_utf8]};
  size_t utf8words =
      simdutf::convert_utf16_to_utf8(unicode, length, utf8.get());
  // We can then transcode the next batch
  const char16_t * next = unicode + length;
  size_t next_length = 6 - length;
  size_t next_budget_utf8 = simdutf::utf8_length_from_utf16(next, next_length);
  std::unique_ptr<char[]> next_utf8{new char[next_budget_utf8]};
  size_t next_utf8words =
      simdutf::convert_utf16_to_utf8(next, next_length, next_utf8.get());

  // this UTF-8 string has a bad byte at index 5
  std::string bad_utf8 = "\xc3\xa9\xc3\xa9\x20\xff\xc3\xa9";
  size_t budget_utf16 = simdutf::utf16_length_from_utf8(bad_utf8.data(), bad_utf8.size());
  std::unique_ptr<char16_t[]> utf16{new char16_t[budget_utf16]};
  simdutf::result res = simdutf::convert_utf8_to_utf16_with_errors(bad_utf8.data(), bad_utf8.size(), utf16.get());
  if(res.error != simdutf::error_code::SUCCESS) {
    std::cerr << "error at index " << res.count << std::endl;
  }
  // the following will be successful
  res = simdutf::convert_utf8_to_utf16_with_errors(bad_utf8.data(), res.count, utf16.get());
  if(res.error == simdutf::error_code::SUCCESS) {
    std::cerr << "we have transcoded " << res.count << " characters" << std::endl;
  }

/**
 * Convert possibly broken UTF-8 string into latin1 string with errors.
 * If the string cannot be represented as Latin1, an error
 * code is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param latin1_output  the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.
 */
simdutf_warn_unused result convert_utf8_to_latin1_with_errors(const char * input, size_t length, char* latin1_output) noexcept;

/**
 * Convert possibly broken UTF-16LE string into Latin1 string.
 * If the string cannot be represented as Latin1, an error
 * is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf16le_to_latin1_with_errors(const char16_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into Latin1 string.
 * If the string cannot be represented as Latin1, an error
 * is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf16be_to_latin1_with_errors(const char16_t * input, size_t length, char* latin1_buffer) noexcept;

/**
 * Using native endianness, convert possibly broken UTF-16 string into Latin1 string.
 * If the string cannot be represented as Latin1, an error
 * is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf16_to_latin1_with_errors(const char16_t * input, size_t length, char* latin1_buffer) noexcept;


/**
 * Using native endianness; Convert possibly broken UTF-8 string into UTF-16
 * string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf8_to_utf16_with_errors(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-16LE string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf8_to_utf16le_with_errors(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-16BE string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf16_buffer  the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf8_to_utf16be_with_errors(const char * input, size_t length, char16_t* utf16_output) noexcept;

/**
 * Convert possibly broken UTF-8 string into UTF-32 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * @param input         the UTF-8 string to convert
 * @param length        the length of the string in bytes
 * @param utf32_buffer  the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char32_t written if successful.
 */
simdutf_warn_unused result convert_utf8_to_utf32_with_errors(const char * input, size_t length, char32_t* utf32_output) noexcept;


/**
 * Convert possibly broken UTF-16LE string into UTF-8 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf16le_to_utf8_with_errors(const char16_t * input, size_t length, char* utf8_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into UTF-8 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf16be_to_utf8_with_errors(const char16_t * input, size_t length, char* utf8_buffer) noexcept;


/**
 * Convert possibly broken UTF-32 string into Latin1 string and stop on error.
 * If the string cannot be represented as Latin1, an error is returned.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param latin1_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf32_to_latin1_with_errors(const char32_t * input, size_t length, char* latin1_buffer) noexcept;


/**
 * Convert possibly broken UTF-32 string into UTF-8 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf8_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.
 */
simdutf_warn_unused result convert_utf32_to_utf8_with_errors(const char32_t * input, size_t length, char* utf8_buffer) noexcept;

/**
 * Using native endianness; Convert possibly broken UTF-32 string into UTF-16
 * string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf32_to_utf16_with_errors(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Convert possibly broken UTF-32 string into UTF-16LE string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf32_to_utf16le_with_errors(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Convert possibly broken UTF-32 string into UTF-16BE string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-32 string to convert
 * @param length        the length of the string in 4-byte code units (char32_t)
 * @param utf16_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char16_t written if successful.
 */
simdutf_warn_unused result convert_utf32_to_utf16be_with_errors(const char32_t * input, size_t length, char16_t* utf16_buffer) noexcept;

/**
 * Using native endianness; Convert possibly broken UTF-16 string into
 * UTF-32 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char32_t written if successful.
 */
simdutf_warn_unused result convert_utf16_to_utf32_with_errors(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Convert possibly broken UTF-16LE string into UTF-32 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16LE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char32_t written if successful.
 */
simdutf_warn_unused result convert_utf16le_to_utf32_with_errors(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Convert possibly broken UTF-16BE string into UTF-32 string and stop on error.
 *
 * During the conversion also validation of the input string is done.
 * This function is suitable to work with inputs from untrusted sources.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16BE string to convert
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param utf32_buffer   the pointer to buffer that can hold conversion result
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char32_t written if successful.
 */
simdutf_warn_unused result convert_utf16be_to_utf32_with_errors(const char16_t * input, size_t length, char32_t* utf32_buffer) noexcept;

/**
 * Change the endianness of the input. Can be used to go from UTF-16LE to UTF-16BE or
 * from UTF-16BE to UTF-16LE.
 *
 * This function does not validate the input.
 *
 * This function is not BOM-aware.
 *
 * @param input         the UTF-16 string to process
 * @param length        the length of the string in 2-byte code units (char16_t)
 * @param output        the pointer to buffer that can hold the conversion result
 */
void change_endianness_utf16(const char16_t * input, size_t length, char16_t * output) noexcept;

std::vector<char> buffer(simdutf::base64_length_from_binary(source.size()));
simdutf::binary_to_base64(source.data(), source.size(), buffer.data());

std::vector<char> buffer(simdutf::maximal_binary_length_from_base64(base64.data(), base64.size()));
simdutf::result r = simdutf::base64_to_binary(base64.data(), base64.size(), buffer.data());
if(r.error) {
  // We have some error, r.count tells you where the error was encountered in the input if
  // the error is INVALID_BASE64_CHARACTER. If the error is BASE64_INPUT_REMAINDER, then
  // a single valid base64 remained, and r.count contains the number of bytes decoded.
} else {
  buffer.resize(r.count); // resize the buffer according to actual number of bytes
}

  size_t len = 72; // for simplicity we chose len divisible by 3
  std::vector<char> base64(len, 'a'); // we want to decode 'aaaaa....'
  std::vector<char> back((len + 3) / 4 * 3);
  size_t limited_length = back.size() / 2; // Intentionally too small
  // We proceed to decode half:
  simdutf::result r = simdutf::base64_to_binary_safe(
            base64.data(), base64.size(), back.data(), limited_length);
  assert(r.error == simdutf::error_code::OUTPUT_BUFFER_TOO_SMALL);
  // We decoded r.count base64 8-bit units to limited_length bytes
  // Now let us decode the rest !!!
  //
  // We have read up to r.count in the input buffer and we have
  // produced limited_length bytes.
  //
  size_t input_index = r.count;
  size_t limited_length2 = back.size();
  r = simdutf::base64_to_binary_safe(base64.data() + input_index,
                                           base64.size() - input_index,
                                           back.data(), limited_length2);
  assert(r.error == simdutf::error_code::SUCCESS);
  // We decoded r.count base64 8-bit units to limited_length2 bytes
  // We are done
  assert(limited_length2 + limited_length == (len + 3) / 4 * 3);

// base64_options are used to specify the base64 encoding options.
using base64_options = uint64_t;
enum : base64_options {
  base64_default = 0, /* standard base64 format */
  base64_url = 1 /* base64url format*/
};

/**
 * Provide the maximal binary length in bytes given the base64 input.
 * In general, if the input contains ASCII spaces, the result will be less than
 * the maximum length.
 *
 * @param input         the base64 input to process
 * @param length        the length of the base64 input in bytes
 * @return maximal number of binary bytes
 */
simdutf_warn_unused size_t maximal_binary_length_from_base64(const char * input, size_t length) noexcept;

/**
 * Provide the maximal binary length in bytes given the base64 input.
 * In general, if the input contains ASCII spaces, the result will be less than
 * the maximum length.
 *
 * @param input         the base64 input to process, in ASCII stored as 16-bit units
 * @param length        the length of the base64 input in 16-bit units
 * @return maximal number of binary bytes
 */
simdutf_warn_unused size_t maximal_binary_length_from_base64(const char16_t * input, size_t length) noexcept;

/**
 * Convert a base64 input to a binary ouput.
 *
 * This function follows the WHATWG forgiving-base64 format, which means that it will
 * ignore any ASCII spaces in the input. You may provide a padded input (with one or two
 * equal signs at the end) or an unpadded input (without any equal signs at the end).
 *
 * See https://infra.spec.whatwg.org/#forgiving-base64-decode
 *
 * This function will fail in case of invalid input. There are two possible reasons for
 * failure: the input contains a number of base64 characters that when divided by 4, leaves
 * a single remainder character (BASE64_INPUT_REMAINDER), or the input contains a character
 * that is not a valid base64 character (INVALID_BASE64_CHARACTER).
 *
 * The INVALID_BASE64_CHARACTER cases are considered fatal and you are expected to discard
 * the output.
 *
 * When the error is INVALID_BASE64_CHARACTER, r.count contains the index in the input
 * where the invalid character was found. When the error is BASE64_INPUT_REMAINDER, then
 * r.count contains the number of bytes decoded.
 *
 * You should call this function with a buffer that is at least maximal_binary_length_from_base64(input, length) bytes long.
 * If you fail to provide that much space, the function may cause a buffer overflow.
 *
 * @param input         the base64 string to process
 * @param length        the length of the string in bytes
 * @param output        the pointer to buffer that can hold the conversion result (should be at least maximal_binary_length_from_base64(input, length) bytes long).
 * @param options       the base64 options to use, can be base64_default or base64_url, is base64_default by default.
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the error (in the input in bytes) if any, or the number of bytes written if successful.
 */
simdutf_warn_unused result base64_to_binary(const char * input, size_t length, char* output, base64_options options = base64_default) noexcept;

  /**
   * Provide the base64 length in bytes given the length of a binary input.
   *
   * @param length        the length of the input in bytes
   * @parem options       the base64 options to use, can be base64_default or base64_url, is base64_default by default.
   * @return number of base64 bytes
   */
  simdutf_warn_unused size_t base64_length_from_binary(size_t length, base64_options options = base64_default) noexcept;


/**
 * Convert a binary input to a base64 ouput. The output is always padded with equal signs so that it is
 * a multiple of 4 bytes long.
 *
 * This function always succeeds.
 *
 * @param input         the binary to process
 * @param length        the length of the input in bytes
 * @param output        the pointer to buffer that can hold the conversion result (should be at least base64_length_from_binary(length) bytes long)
 * @param options       the base64 options to use, can be base64_default or base64_url, is base64_default by default.
 * @return number of written bytes, will be equal to base64_length_from_binary(length)
 */
size_t binary_to_base64(const char * input, size_t length, char* output, base64_options options = base64_default) noexcept;

/**
 * Convert a base64 input to a binary ouput.
 *
 * This function follows the WHATWG forgiving-base64 format, which means that it will
 * ignore any ASCII spaces in the input. You may provide a padded input (with one or two
 * equal signs at the end) or an unpadded input (without any equal signs at the end).
 *
 * See https://infra.spec.whatwg.org/#forgiving-base64-decode
 *
 * This function will fail in case of invalid input. There are two possible reasons for
 * failure: the input contains a number of base64 characters that when divided by 4, leaves
 * a single remainder character (BASE64_INPUT_REMAINDER), or the input contains a character
 * that is not a valid base64 character (INVALID_BASE64_CHARACTER).
 *
 * When the error is INVALID_BASE64_CHARACTER, r.count contains the index in the input
 * where the invalid character was found. When the error is BASE64_INPUT_REMAINDER, then
 * r.count contains the number of bytes decoded.
 *
 * You should call this function with a buffer that is at least maximal_binary_length_from_utf6_base64(input, length) bytes long.
 * If you fail to provide that much space, the function may cause a buffer overflow.
 *
 * @param input         the base64 string to process, in ASCII stored as 16-bit units
 * @param length        the length of the string in 16-bit units
 * @param output        the pointer to buffer that can hold the conversion result (should be at least maximal_binary_length_from_base64(input, length) bytes long).
 * @param options       the base64 options to use, can be base64_default or base64_url, is base64_default by default.
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and either position of the INVALID_BASE64_CHARACTER error (in the input in units) if any, or the number of bytes written if successful.
 */
simdutf_warn_unused result base64_to_binary(const char16_t * input, size_t length, char* output, base64_options options = base64_default)  noexcept;

/**
 * Convert a base64 input to a binary ouput.
 *
 * This function follows the WHATWG forgiving-base64 format, which means that it will
 * ignore any ASCII spaces in the input. You may provide a padded input (with one or two
 * equal signs at the end) or an unpadded input (without any equal signs at the end).
 *
 * See https://infra.spec.whatwg.org/#forgiving-base64-decode
 *
 * This function will fail in case of invalid input. There are three possible reasons for
 * failure: the input contains a number of base64 characters that when divided by 4, leaves
 * a single remainder character (BASE64_INPUT_REMAINDER), the input contains a character
 * that is not a valid base64 character (INVALID_BASE64_CHARACTER), or the output buffer
 * is too small (OUTPUT_BUFFER_TOO_SMALL).
 *
 * When OUTPUT_BUFFER_TOO_SMALL, we return both the number of bytes written
 * and the number of units processed, see description of the parameters and returned value.
 *
 * When the error is INVALID_BASE64_CHARACTER, r.count contains the index in the input
 * where the invalid character was found. When the error is BASE64_INPUT_REMAINDER, then
 * r.count contains the number of bytes decoded.
 *
 * The INVALID_BASE64_CHARACTER cases are considered fatal and you are expected to discard
 * the output.
 *
 * @param input         the base64 string to process, in ASCII stored as 8-bit or 16-bit units
 * @param length        the length of the string in 8-bit or 16-bit units.
 * @param output        the pointer to buffer that can hold the conversion result.
 * @param outlen        the number of bytes that can be written in the output buffer. Upon return, it is modified to reflect how many bytes were written.
 * @param options       the base64 options to use, can be base64_default or base64_url, is base64_default by default.
 * @return a result pair struct (of type simdutf::error containing the two fields error and count) with an error code and position of the INVALID_BASE64_CHARACTER error (in the input in units) if any, or the number of units processed if successful.
 */
simdutf_warn_unused result base64_to_binary_safe(const char * input, size_t length, char* output, size_t& outlen, base64_options options = base64_default) noexcept;
simdutf_warn_unused result base64_to_binary_safe(const char16_t * input, size_t length, char* output, size_t& outlen, base64_options options = base64_default) noexcept;

#include "simdutf.h"
#include <cstdlib>
#include <iostream>
#include <string>

int main() {
  // This is just a demonstration, not actual testing required.
  std::string source = "La vie est belle.";
  std::string chosen_implementation;
  for (auto &implementation : simdutf::get_available_implementations()) {
    if (!implementation->supported_by_runtime_system()) {
      continue;
    }
    bool validutf8 = implementation->validate_utf8(source.c_str(), source.size());
    if (!validutf8) {
      return EXIT_FAILURE;
    }
    std::cout << implementation->name() << ": " << implementation->description()
              << std::endl;
    chosen_implementation = implementation->name();
  }
  auto my_implementation =
      simdutf::get_available_implementations()[chosen_implementation];
  if (!my_implementation) {
    return EXIT_FAILURE;
  }
  if (!my_implementation->supported_by_runtime_system()) {
    return EXIT_FAILURE;
  }
  simdutf::get_active_implementation() = my_implementation;
  bool validutf8 = simdutf::validate_utf8(source.c_str(), source.size());
  if (!validutf8) {
    return EXIT_FAILURE;
  }
  if (simdutf::get_active_implementation()->name() != chosen_implementation) {
    return EXIT_FAILURE;
  }
  std::cout << "I have manually selected: " << simdutf::get_active_implementation()->name() << std::endl;
  return EXIT_SUCCESS;
}