X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/d37478d0d7bf30c941bd5accd922a54dea0f49c8..2a0bd758b7c45138c8343f8a591ab8c77401b52b:/src/charset.c diff --git a/src/charset.c b/src/charset.c index 118d5fed9b..e7b6897ea9 100644 --- a/src/charset.c +++ b/src/charset.c @@ -1,7 +1,7 @@ /* Basic multilingual character support. Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. Licensed to the Free Software Foundation. - Copyright (C) 2001 Free Software Foundation, Inc. + Copyright (C) 2001, 2004 Free Software Foundation, Inc. This file is part of GNU Emacs. @@ -17,8 +17,8 @@ GNU General Public License for more details. You should have received a copy of the GNU General Public License along with GNU Emacs; see the file COPYING. If not, write to -the Free Software Foundation, Inc., 59 Temple Place - Suite 330, -Boston, MA 02111-1307, USA. */ +the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, +Boston, MA 02110-1301, USA. */ /* At first, see the document in `charset.h' to understand the code in this file. */ @@ -210,7 +210,7 @@ char_to_string_1 (c, str) /* If C still has any modifier bits, just ignore it. */ c &= ~CHAR_MODIFIER_MASK; } - + if (SINGLE_BYTE_CHAR_P (c)) { if (ASCII_BYTE_P (c) || c >= 0xA0) @@ -345,7 +345,7 @@ char_printable_p (c) return 0; else if (c >= MAX_CHAR) return 0; - + SPLIT_CHAR (c, charset, c1, c2); if (! CHARSET_DEFINED_P (charset)) return 0; @@ -700,14 +700,14 @@ DESCRIPTION (string) is the description string of the charset. */) || !STRINGP (vec[7]) || !STRINGP (vec[8])) error ("Invalid info-vector argument for defining charset %s", - XSYMBOL (charset_symbol)->name->data); + SDATA (SYMBOL_NAME (charset_symbol))); if (NILP (charset_id)) { charset_id = get_new_private_charset_id (XINT (vec[0]), XINT (vec[2])); if (XINT (charset_id) == 0) error ("There's no room for a new private charset %s", - XSYMBOL (charset_symbol)->name->data); + SDATA (SYMBOL_NAME (charset_symbol))); } update_charset_table (charset_id, vec[0], vec[1], vec[2], vec[3], @@ -730,7 +730,7 @@ It includes a generic character for a charset not yet defined. */) DEFUN ("get-unused-iso-final-char", Fget_unused_iso_final_char, Sget_unused_iso_final_char, 2, 2, 0, - doc: /* Return an unsed ISO's final char for a charset of DIMENISION and CHARS. + doc: /* Return an unused ISO's final char for a charset of DIMENSION and CHARS. DIMENSION is the number of bytes to represent a character: 1 or 2. CHARS is the number of characters in a dimension: 94 or 96. @@ -760,17 +760,20 @@ return nil. */) DEFUN ("declare-equiv-charset", Fdeclare_equiv_charset, Sdeclare_equiv_charset, 4, 4, 0, - doc: /* Declare a charset of DIMENSION, CHARS, FINAL-CHAR is the same as CHARSET. -CHARSET should be defined by `defined-charset' in advance. */) - (dimension, chars, final_char, charset_symbol) - Lisp_Object dimension, chars, final_char, charset_symbol; + doc: /* Declare an equivalent charset for ISO-2022 decoding. + +On decoding by an ISO-2022 base coding system, when a charset +specified by DIMENSION, CHARS, and FINAL-CHAR is designated, behave as +if CHARSET is designated instead. */) + (dimension, chars, final_char, charset) + Lisp_Object dimension, chars, final_char, charset; { - int charset; + int charset_id; CHECK_NUMBER (dimension); CHECK_NUMBER (chars); CHECK_NUMBER (final_char); - CHECK_SYMBOL (charset_symbol); + CHECK_SYMBOL (charset); if (XINT (dimension) != 1 && XINT (dimension) != 2) error ("Invalid DIMENSION %d, it should be 1 or 2", XINT (dimension)); @@ -778,10 +781,10 @@ CHARSET should be defined by `defined-charset' in advance. */) error ("Invalid CHARS %d, it should be 94 or 96", XINT (chars)); if (XINT (final_char) < '0' || XFASTINT (final_char) > '~') error ("Invalid FINAL-CHAR %c, it should be `0'..`~'", XINT (chars)); - if ((charset = get_charset_id (charset_symbol)) < 0) - error ("Invalid charset %s", XSYMBOL (charset_symbol)->name->data); + if ((charset_id = get_charset_id (charset)) < 0) + error ("Invalid charset %s", SDATA (SYMBOL_NAME (charset))); - ISO_CHARSET_TABLE (dimension, chars, final_char) = charset; + ISO_CHARSET_TABLE (dimension, chars, final_char) = charset_id; return Qnil; } @@ -802,7 +805,7 @@ CHARSET should be defined by `defined-charset' in advance. */) int find_charset_in_text (ptr, nchars, nbytes, charsets, table) - unsigned char *ptr; + const unsigned char *ptr; int nchars, nbytes, *charsets; Lisp_Object table; { @@ -810,14 +813,14 @@ find_charset_in_text (ptr, nchars, nbytes, charsets, table) { if (charsets && nbytes > 0) { - unsigned char *endp = ptr + nbytes; + const unsigned char *endp = ptr + nbytes; int maskbits = 0; while (ptr < endp && maskbits != 7) { maskbits |= (*ptr < 0x80 ? 1 : *ptr < 0xA0 ? 2 : 4); ptr++; - } + } if (maskbits & 1) charsets[CHARSET_ASCII] = 1; @@ -943,8 +946,8 @@ only `ascii', `eight-bit-control', and `eight-bit-graphic'. */) CHECK_STRING (str); bzero (charsets, (MAX_CHARSET + 1) * sizeof (int)); - find_charset_in_text (XSTRING (str)->data, XSTRING (str)->size, - STRING_BYTES (XSTRING (str)), charsets, table); + find_charset_in_text (SDATA (str), SCHARS (str), + SBYTES (str), charsets, table); val = Qnil; if (charsets[1]) @@ -1025,9 +1028,9 @@ Internal use only. */) } DEFUN ("split-char", Fsplit_char, Ssplit_char, 1, 1, 0, - doc: /* Return list of charset and one or two position-codes of CHAR. -If CHAR is invalid as a character code, -return a list of symbol `unknown' and CHAR. */) + doc: /* Return list of charset and one or two position-codes of CH. +If CH is invalid as a character code, +return a list of symbol `unknown' and CH. */) (ch) Lisp_Object ch; { @@ -1045,7 +1048,7 @@ return a list of symbol `unknown' and CHAR. */) } DEFUN ("char-charset", Fchar_charset, Schar_charset, 1, 1, 0, - doc: /* Return charset of CHAR. */) + doc: /* Return charset of CH. */) (ch) Lisp_Object ch; { @@ -1176,8 +1179,7 @@ The conversion is done based on `nonascii-translation-table' (which see) } DEFUN ("char-bytes", Fchar_bytes, Schar_bytes, 1, 1, 0, - doc: /* Return 1 regardless of the argument CHAR. -This is now an obsolete function. We keep it just for backward compatibility. */) + doc: /* Return 1 regardless of the argument CH. */) (ch) Lisp_Object ch; { @@ -1221,7 +1223,7 @@ char_bytes (c) : 4)))) DEFUN ("char-width", Fchar_width, Schar_width, 1, 1, 0, - doc: /* Return width of CHAR when displayed in the current buffer. + doc: /* Return width of CH when displayed in the current buffer. The width is measured by how many columns it occupies on the screen. Tab is taken to occupy `tab-width' columns. */) (ch) @@ -1272,8 +1274,8 @@ strwidth (str, len) int c_string_width (str, len, precision, nchars, nbytes) - unsigned char *str; - int precision, *nchars, *nbytes; + const unsigned char *str; + int len, precision, *nchars, *nbytes; { int i = 0, i_byte = 0; int width = 0; @@ -1336,9 +1338,9 @@ lisp_string_width (string, precision, nchars, nbytes) Lisp_Object string; int precision, *nchars, *nbytes; { - int len = XSTRING (string)->size; - int len_byte = STRING_BYTES (XSTRING (string)); - unsigned char *str = XSTRING (string)->data; + int len = SCHARS (string); + int len_byte = SBYTES (string); + const unsigned char *str = SDATA (string); int i = 0, i_byte = 0; int width = 0; struct Lisp_Char_Table *dp = buffer_display_table (); @@ -1404,18 +1406,18 @@ When calculating width of a multibyte character in STRING, only the base leading-code is considered; the validity of the following bytes is not checked. Tabs in STRING are always taken to occupy `tab-width' columns. */) - (str) - Lisp_Object str; + (string) + Lisp_Object string; { Lisp_Object val; - CHECK_STRING (str); - XSETFASTINT (val, lisp_string_width (str, -1, NULL, NULL)); + CHECK_STRING (string); + XSETFASTINT (val, lisp_string_width (string, -1, NULL, NULL)); return val; } DEFUN ("char-direction", Fchar_direction, Schar_direction, 1, 1, 0, - doc: /* Return the direction of CHAR. + doc: /* Return the direction of CH. The returned value is 0 for left-to-right and 1 for right-to-left. */) (ch) Lisp_Object ch; @@ -1429,22 +1431,6 @@ The returned value is 0 for left-to-right and 1 for right-to-left. */) return CHARSET_TABLE_INFO (charset, CHARSET_DIRECTION_IDX); } -DEFUN ("chars-in-region", Fchars_in_region, Schars_in_region, 2, 2, 0, - doc: /* Return number of characters between BEG and END. */) - (beg, end) - Lisp_Object beg, end; -{ - int from, to; - - CHECK_NUMBER_COERCE_MARKER (beg); - CHECK_NUMBER_COERCE_MARKER (end); - - from = min (XFASTINT (beg), XFASTINT (end)); - to = max (XFASTINT (beg), XFASTINT (end)); - - return make_number (to - from); -} - /* Return the number of characters in the NBYTES bytes at PTR. This works by looking at the contents and checking for multibyte sequences. However, if the current buffer has enable-multibyte-characters = nil, @@ -1452,7 +1438,7 @@ DEFUN ("chars-in-region", Fchars_in_region, Schars_in_region, 2, 2, 0, int chars_in_text (ptr, nbytes) - unsigned char *ptr; + const unsigned char *ptr; int nbytes; { /* current_buffer is null at early stages of Emacs initialization. */ @@ -1469,10 +1455,10 @@ chars_in_text (ptr, nbytes) int multibyte_chars_in_text (ptr, nbytes) - unsigned char *ptr; + const unsigned char *ptr; int nbytes; { - unsigned char *endp; + const unsigned char *endp; int chars, bytes; endp = ptr + nbytes; @@ -1494,10 +1480,10 @@ multibyte_chars_in_text (ptr, nbytes) 0x80..0x9F are represented by 2 bytes in multibyte text. */ void parse_str_as_multibyte (str, len, nchars, nbytes) - unsigned char *str; + const unsigned char *str; int len, *nchars, *nbytes; { - unsigned char *endp = str + len; + const unsigned char *endp = str + len; int n, chars = 0, bytes = 0; while (str < endp) @@ -1549,7 +1535,7 @@ str_as_multibyte (str, len, nbytes, nchars) { while (n--) *to++ = *p++; - } + } else { *to++ = LEADING_CODE_8_BIT_CONTROL; @@ -1601,7 +1587,7 @@ str_to_multibyte (str, len, bytes) endp = str + len; safe_bcopy (p, endp - bytes, bytes); p = endp - bytes; - while (p < endp) + while (p < endp) { if (*p < 0x80 || *p >= 0xA0) *to++ = *p++; @@ -1625,7 +1611,7 @@ str_as_unibyte (str, bytes) while (p < endp && *p != LEADING_CODE_8_BIT_CONTROL) p++; to = p; - while (p < endp) + while (p < endp) { if (*p == LEADING_CODE_8_BIT_CONTROL) *to++ = *(p + 1) - 0x20, p += 2; @@ -1643,11 +1629,16 @@ usage: (string &rest CHARACTERS) */) int n; Lisp_Object *args; { - int i; - unsigned char *buf = (unsigned char *) alloca (MAX_MULTIBYTE_LENGTH * n); - unsigned char *p = buf; + int i, bufsize; + unsigned char *buf, *p; int c; int multibyte = 0; + Lisp_Object ret; + USE_SAFE_ALLOCA; + + bufsize = MAX_MULTIBYTE_LENGTH * n; + SAFE_ALLOCA (buf, unsigned char *, bufsize); + p = buf; for (i = 0; i < n; i++) { @@ -1665,7 +1656,10 @@ usage: (string &rest CHARACTERS) */) *p++ = c; } - return make_string_from_bytes (buf, n, p - buf); + ret = make_string_from_bytes (buf, n, p - buf); + SAFE_FREE (); + + return ret; } #endif /* emacs */ @@ -1845,7 +1839,6 @@ syms_of_charset () defsubr (&Schar_width); defsubr (&Sstring_width); defsubr (&Schar_direction); - defsubr (&Schars_in_region); defsubr (&Sstring); defsubr (&Ssetup_special_charsets); @@ -1909,3 +1902,6 @@ Such characters have value t in this table. */); } #endif /* emacs */ + +/* arch-tag: 66a89b8d-4c28-47d3-9ca1-56f78440d69f + (do not change this comment) */