view release on metacpan or  search on metacpan

source/myhtml/api.h  view on Meta::CPAN

/**
 * Convert Unicode Codepoint to UTF-16LE
 *
 * I advise not to use UTF-16! Use UTF-8 and be happy!
 *
 * @param[in] Codepoint
 * @param[in] Data to set characters. Data length is 2 or 4 bytes
 *   data length must be always available 4 bytes
 *
 * @return size character set
 */
size_t
myhtml_encoding_codepoint_to_ascii_utf_16(size_t codepoint, char *data);

/**
 * Detect character encoding
 *
 * Now available for detect UTF-8, UTF-16LE, UTF-16BE
 * and Russians: windows-1251,  koi8-r, iso-8859-5, x-mac-cyrillic, ibm866
 * Other in progress
 *
 * @param[in]  text
 * @param[in]  text length
 * @param[out] detected encoding
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_detect(const char *text, size_t length, myhtml_encoding_t *encoding);

/**
 * Detect Russian character encoding
 *
 * Now available for detect windows-1251,  koi8-r, iso-8859-5, x-mac-cyrillic, ibm866
 *
 * @param[in]  text
 * @param[in]  text length
 * @param[out] detected encoding
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_detect_russian(const char *text, size_t length, myhtml_encoding_t *encoding);

/**
 * Detect Unicode character encoding
 *
 * Now available for detect UTF-8, UTF-16LE, UTF-16BE
 *
 * @param[in]  text
 * @param[in]  text length
 * @param[out] detected encoding
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_detect_unicode(const char *text, size_t length, myhtml_encoding_t *encoding);

/**
 * Detect Unicode character encoding by BOM
 *
 * Now available for detect UTF-8, UTF-16LE, UTF-16BE
 *
 * @param[in]  text
 * @param[in]  text length
 * @param[out] detected encoding
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_detect_bom(const char *text, size_t length, myhtml_encoding_t *encoding);

/**
 * Detect Unicode character encoding by BOM. Cut BOM if will be found
 *
 * Now available for detect UTF-8, UTF-16LE, UTF-16BE
 *
 * @param[in]  text
 * @param[in]  text length
 * @param[out] detected encoding
 * @param[out] new text position
 * @param[out] new size position
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_detect_and_cut_bom(const char *text, size_t length, myhtml_encoding_t *encoding,
                                   const char **new_text, size_t *new_size);

/**
 * Detect encoding by name
 * Names like: windows-1258 return MyHTML_ENCODING_WINDOWS_1258
 *             cp1251 or windows-1251 return MyHTML_ENCODING_WINDOWS_1251
 *
 * See https://encoding.spec.whatwg.org/#names-and-labels
 *
 * @param[in]  name
 * @param[in]  name length
 * @param[out] detected encoding
 *
 * @return true if encoding found, otherwise false
 */
bool
myhtml_encoding_by_name(const char *name, size_t length, myhtml_encoding_t *encoding);

/***********************************************************************************
 *
 * MyHTML_STRING
 *
 ***********************************************************************************/

/**
 * Init myhtml_string_t structure
 *
 * @param[in] mchar_async_t*. It can be obtained from myhtml_tree_t object
 *  (see myhtml_tree_get_mchar function) or create manualy
 *  For each Tree creates its object, I recommend to use it (myhtml_tree_get_mchar).
 *
 * @param[in] node_id. For all threads (and Main thread) identifier that is unique.
 *  if created mchar_async_t object manually you know it, if not then take from the Tree 
 *  (see myhtml_tree_get_mchar_node_id)
 *
 * @param[in] myhtml_string_t*. It can be obtained from myhtml_tree_node_t object
 *  (see myhtml_node_string function) or create manualy
 *
 * @param[in] data size. Set the size you want for char*
 *
 * @return char* of the size if successful, otherwise a NULL value
 */
char*
myhtml_string_init(mchar_async_t *mchar, size_t node_id,
                   myhtml_string_t* str, size_t size);

/**