comparison src/coding.c @ 88438:3a34b722dd71

(encode_coding_utf_8): Initialize produced_chars to 0. (decode_coding_utf_16): Fix converting high and low bytes to code-point. (encode_coding_utf_16): Substitute coding->default_char for non-Unicode characters. (decode_coding): Don't call record_insert here. (setup_coding_system): Initialize `surrogate' of coding->spec.utf_16 to 0. (EMIT_ONE_BYTE): Fix for multibyte case.

88437:ffec838ec027

/*** 0. General comments ***


CODING SYSTEM

  Coding system is an encoding mechanism of one or more character
  sets.  Here's a list of coding system types supported by Emacs.
  When we say "decode", it means converting a text encoded by some
  coding system into Emacs' internal format (emacs-utf-8), and when we
  say "encode", it means converting a text of emacs-utf-8 to some
  other coding system.

  Emacs represents a coding system by a Lisp symbol.  Each symbol is a
  key to the hash table Vcharset_hash_table.  This hash table
  associates the symbol to the corresponding detailed specifications.

  Before using a coding system for decoding and encoding, we setup a
  structure of type `struct coding_system'.  This structure keeps
  various information about a specific code conversion (e.g.  the
  location of source and destination data).

  Coding systems are classified into the following types by how to
  represent a character in a byte sequence.  Here's a brief descrition
  about type.

  o Emacs' internal format (emacs-utf-8)

  The extended UTF-8 which allows eight-bit raw bytes mixed with
  character codes.  Emacs holds characters in buffers and strings by
  this format.

  o UTF-8

  o UTF-16

  `carriage-return'.

  Since text characters encoding and end-of-line encoding are
  independent, any coding system described above can take any format
  of end-of-line (except for no-conversion).

*/

/* COMMON MACROS */

  } while (0)


/* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2.  */

#define EMIT_TWO_BYTES(c1, c2)			\
  do {						\
    produced_chars += 2;			\
    if (multibytep)				\
      {						\
	CHAR_STRING_ADVANCE ((int) (c1), dst);	\
	CHAR_STRING_ADVANCE ((int) (c2), dst);	\
      }						\
    else					\
      {						\
	*dst++ = (c1);				\
	*dst++ = (c2);				\
      }						\
  } while (0)


#define EMIT_THREE_BYTES(c1, c2, c3)	\
  do {					\

    {
      if (coding->src_pos < 0)
	coding->source = GAP_END_ADDR + coding->src_pos_byte;
      else
	{
	  if (coding->src_pos < GPT
	      && coding->src_pos + coding->src_chars >= GPT)
	    move_gap_both (coding->src_pos, coding->src_pos_byte);
	  coding->source = BYTE_POS_ADDR (coding->src_pos_byte);
	}
    }
  else if (STRINGP (coding->src_object))
    {
      coding->source = (XSTRING (coding->src_object)->data

  int multibytep = coding->dst_multibyte;
  int *charbuf = coding->charbuf;
  int *charbuf_end = charbuf + coding->charbuf_used;
  unsigned char *dst = coding->destination + coding->produced;
  unsigned char *dst_end = coding->destination + coding->dst_bytes;
  int produced_chars;
  int c;

  if (multibytep)
    {
      int safe_room = MAX_MULTIBYTE_LENGTH * 2;

      int c, c1, c2;

      src_base = src;
      ONE_MORE_BYTE (c1);
      ONE_MORE_BYTE (c2);
      c = (c1 << 16) | c2;
      if (bom == utf_16_with_bom)
	{
	  if (endian == utf_16_big_endian
	      ? c != 0xFFFE : c != 0xFEFF)
	    {

	break;

      ONE_MORE_BYTE (c1);
      ONE_MORE_BYTE (c2);
      c = (endian == utf_16_big_endian
	   ? ((c1 << 16) | c2) : ((c2 << 16) | c1));
      if (surrogate)
	{
	  if (! UTF_16_LOW_SURROGATE_P (c))
	    {
	      if (endian == utf_16_big_endian)

  while (charbuf < charbuf_end)
    {
      ASSURE_DESTINATION (safe_room);
      c = *charbuf++;
      if (c >= 0x110000)
	c = 0xFFFF;

      if (c < 0x10000)
	{
	  if (big_endian)
	    EMIT_TWO_BYTES (c >> 8, c & 0xFF);

				    : EQ (val, Qt) ? utf_16_with_bom
				    : utf_16_without_bom);
      val = AREF (attrs, coding_attr_utf_16_endian);
      CODING_UTF_16_ENDIAN (coding) = (NILP (val) ? utf_16_big_endian
				       : utf_16_little_endian);
      coding->detector = detect_coding_utf_16;
      coding->decoder = decode_coding_utf_16;
      coding->encoder = encode_coding_utf_16;
      coding->common_flags
	|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);

	  coding->carryover_bytes = nbytes;
	  while (nbytes-- > 0)
	    *p++ = *src++;
	}
      coding->consumed = coding->src_bytes;
    }

  if (BUFFERP (coding->dst_object))
    {
      record_insert (coding->dst_pos, coding->produced_char);
    }

  return coding->result;
}

88438:3a34b722dd71

/*** 0. General comments ***


CODING SYSTEM

  Coding system is an object for a encoding mechanism that contains
  information about how to convert byte sequence to character
  sequences and vice versa.  When we say "decode", it means converting
  a byte sequence of a specific coding system into a character
  sequence that is represented by Emacs' internal coding system
  `emacs-utf-8', and when we say "encode", it means converting a
  character sequence of emacs-utf-8 to a byte sequence of a specific
  coding system.

  In Emacs Lisp, a coding system is represented by a Lisp symbol.  In
  C level, a coding system is represented by a vector of attributes
  stored in the hash table Vcharset_hash_table.  The conversion from a
  coding system symbol to attributes vector is done by looking up
  Vcharset_hash_table by the symbol.

  Coding systems are classified into the following types depending on
  the mechanism of encoding.  Here's a brief descrition about type.

  o UTF-8

  o UTF-16

  `carriage-return'.

  Since text characters encoding and end-of-line encoding are
  independent, any coding system described above can take any format
  of end-of-line (except for no-conversion).

STRUCT CODING_SYSTEM

  Before using a coding system for code conversion (i.e. decoding and
  encoding), we setup a structure of type `struct coding_system'.
  This structure keeps various information about a specific code
  conversion (e.g.  the location of source and destination data).

*/

/* COMMON MACROS */

  } while (0)


/* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2.  */

#define EMIT_TWO_BYTES(c1, c2)		\
  do {					\
    produced_chars += 2;		\
    if (multibytep)			\
      {					\
	int ch;				\
					\
	ch = (c1);			\
	if (ch >= 0x80)			\
	  ch = BYTE8_TO_CHAR (ch);	\
	CHAR_STRING_ADVANCE (ch, dst);	\
	ch = (c2);			\
	if (ch >= 0x80)			\
	  ch = BYTE8_TO_CHAR (ch);	\
	CHAR_STRING_ADVANCE (ch, dst);	\
      }					\
    else				\
      {					\
	*dst++ = (c1);			\
	*dst++ = (c2);			\
      }					\
  } while (0)


#define EMIT_THREE_BYTES(c1, c2, c3)	\
  do {					\

    {
      if (coding->src_pos < 0)
	coding->source = GAP_END_ADDR + coding->src_pos_byte;
      else
	{
	  struct buffer *buf = XBUFFER (coding->src_object);
	  EMACS_INT beg_byte = BUF_BEG_BYTE (buf);
	  EMACS_INT gpt_byte = BUF_GPT_BYTE (buf);
	  unsigned char *beg_addr = BUF_BEG_ADDR (buf);

	  coding->source = beg_addr + coding->src_pos_byte - 1;
	  if (coding->src_pos_byte >= gpt_byte)
	    coding->source += BUF_GAP_SIZE (buf);
	}
    }
  else if (STRINGP (coding->src_object))
    {
      coding->source = (XSTRING (coding->src_object)->data

  int multibytep = coding->dst_multibyte;
  int *charbuf = coding->charbuf;
  int *charbuf_end = charbuf + coding->charbuf_used;
  unsigned char *dst = coding->destination + coding->produced;
  unsigned char *dst_end = coding->destination + coding->dst_bytes;
  int produced_chars = 0;
  int c;

  if (multibytep)
    {
      int safe_room = MAX_MULTIBYTE_LENGTH * 2;

      int c, c1, c2;

      src_base = src;
      ONE_MORE_BYTE (c1);
      ONE_MORE_BYTE (c2);
      c = (c1 << 8) | c2;
      if (bom == utf_16_with_bom)
	{
	  if (endian == utf_16_big_endian
	      ? c != 0xFFFE : c != 0xFEFF)
	    {

	break;

      ONE_MORE_BYTE (c1);
      ONE_MORE_BYTE (c2);
      c = (endian == utf_16_big_endian
	   ? ((c1 << 8) | c2) : ((c2 << 8) | c1));
      if (surrogate)
	{
	  if (! UTF_16_LOW_SURROGATE_P (c))
	    {
	      if (endian == utf_16_big_endian)

  while (charbuf < charbuf_end)
    {
      ASSURE_DESTINATION (safe_room);
      c = *charbuf++;
      if (c >= MAX_UNICODE_CHAR)
	c = coding->default_char;

      if (c < 0x10000)
	{
	  if (big_endian)
	    EMIT_TWO_BYTES (c >> 8, c & 0xFF);

				    : EQ (val, Qt) ? utf_16_with_bom
				    : utf_16_without_bom);
      val = AREF (attrs, coding_attr_utf_16_endian);
      CODING_UTF_16_ENDIAN (coding) = (NILP (val) ? utf_16_big_endian
				       : utf_16_little_endian);
      CODING_UTF_16_SURROGATE (coding) = 0;
      coding->detector = detect_coding_utf_16;
      coding->decoder = decode_coding_utf_16;
      coding->encoder = encode_coding_utf_16;
      coding->common_flags
	|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);

	  coding->carryover_bytes = nbytes;
	  while (nbytes-- > 0)
	    *p++ = *src++;
	}
      coding->consumed = coding->src_bytes;
    }

  return coding->result;
}