Remove spurious semicolons.

[bpt/emacs.git] / src / character.c

diff --git a/src/character.c b/src/character.c
index ede99cf..50ca652 100644 (file)
--- a/src/character.c
+++ b/src/character.c
@@ -1,9 +1,9 @@
 /* Basic character support.
    Copyright (C) 1995, 1997, 1998, 2001 Electrotechnical Laboratory, JAPAN.
      Licensed to the Free Software Foundation.
-   Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
+   Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
      Free Software Foundation, Inc.
-   Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008
+   Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009
      National Institute of Advanced Industrial Science and Technology (AIST)
      Registration Number H13PRO009
 
@@ -59,7 +59,7 @@ Lisp_Object Vauto_fill_chars;
 Lisp_Object Qauto_fill_chars;
 
 /* Char-table of information about which character to unify to which
-   Unicode character.  */
+   Unicode character.  Mainly used by the macro MAYBE_UNIFY_CHAR.  */
 Lisp_Object Vchar_unify_table;
 
 /* A char-table.  An element is non-nil iff the corresponding
@@ -85,6 +85,8 @@ Lisp_Object Vscript_representative_chars;
 
 static Lisp_Object Qchar_script_table;
 
+Lisp_Object Vunicode_category_table;
+
 /* Mapping table from unibyte chars to multibyte chars.  */
 int unibyte_to_multibyte_table[256];
 
@@ -409,9 +411,7 @@ usage: (char-width CHAR)  */)
    respectively.  */
 
 int
-c_string_width (str, len, precision, nchars, nbytes)
-     const unsigned char *str;
-     int precision, *nchars, *nbytes;
+c_string_width (const unsigned char *str, int len, int precision, int *nchars, int *nbytes)
 {
   int i = 0, i_byte = 0;
   int width = 0;
@@ -1009,12 +1009,12 @@ usage: (unibyte-string &rest BYTES)  */)
   return make_string_from_bytes ((char *) buf, n, p - buf);
 }
 
-DEFUN ("char-resolve-modifers", Fchar_resolve_modifiers,
+DEFUN ("char-resolve-modifiers", Fchar_resolve_modifiers,
        Schar_resolve_modifiers, 1, 1, 0,
        doc: /* Resolve modifiers in the character CHAR.
 The value is a character with modifiers resolved into the character
 code.  Unresolved modifiers are kept in the value.
-usage: (char-resolve-modifers CHAR)  */)
+usage: (char-resolve-modifiers CHAR)  */)
      (character)
      Lisp_Object character;
 {
@@ -1025,6 +1025,67 @@ usage: (char-resolve-modifers CHAR)  */)
   return make_number (char_resolve_modifier_mask (c));
 }
 
+DEFUN ("get-byte", Fget_byte, Sget_byte, 0, 2, 0,
+       doc: /* Return a byte value of a character at point.
+Optional 1st arg POSITION, if non-nil, is a position of a character to get
+a byte value.
+Optional 2nd arg STRING, if non-nil, is a string of which first
+character is a target to get a byte value.  In this case, POSITION, if
+non-nil, is an index of a target character in the string.
+
+If the current buffer (or STRING) is multibyte, and the target
+character is not ASCII nor 8-bit character, an error is signalled.  */)
+     (position, string)
+     Lisp_Object position, string;
+{
+  int c;
+  EMACS_INT pos;
+  unsigned char *p;
+
+  if (NILP (string))
+    {
+      if (NILP (position))
+       {
+         p = PT_ADDR;
+       }
+      else
+       {
+         CHECK_NUMBER_COERCE_MARKER (position);
+         if (XINT (position) < BEGV || XINT (position) >= ZV)
+           args_out_of_range_3 (position, make_number (BEGV), make_number (ZV));
+         pos = XFASTINT (position);
+         p = CHAR_POS_ADDR (pos);
+       }
+      if (NILP (current_buffer->enable_multibyte_characters))
+       return make_number (*p);
+    }
+  else
+    {
+      CHECK_STRING (string);
+      if (NILP (position))
+       {
+         p = SDATA (string);
+       }
+      else
+       {
+         CHECK_NATNUM (position);
+         if (XINT (position) >= SCHARS (string))
+           args_out_of_range (string, position);
+         pos = XFASTINT (position);
+         p = SDATA (string) + string_char_to_byte (string, pos);
+       }
+      if (! STRING_MULTIBYTE (string))
+       return make_number (*p);
+    }
+  c = STRING_CHAR (p, 0);
+  if (CHAR_BYTE8_P (c))
+    c = CHAR_TO_BYTE8 (c);
+  else if (! ASCII_CHAR_P (c))
+    error ("Not an ASCII nor an 8-bit character: %d", c);
+  return make_number (c);
+}
+
+
 void
 init_character_once ()
 {
@@ -1052,6 +1113,7 @@ syms_of_character ()
   defsubr (&Sstring);
   defsubr (&Sunibyte_string);
   defsubr (&Schar_resolve_modifiers);
+  defsubr (&Sget_byte);
 
   DEFVAR_LISP ("translation-table-vector",  &Vtranslation_table_vector,
               doc: /*
@@ -1102,8 +1164,23 @@ It has one extra slot whose value is a list of script symbols.  */);
   Vchar_script_table = Fmake_char_table (Qchar_script_table, Qnil);
 
   DEFVAR_LISP ("script-representative-chars", &Vscript_representative_chars,
-              doc: /* Alist of scripts vs the representative characters.  */);
+              doc: /* Alist of scripts vs the representative characters.
+Each element is a cons (SCRIPT . CHARS).
+SCRIPT is a symbol representing a script or a subgroup of a script.
+CHARS is a list or a vector of characters.
+If it is a list, all characters in the list are necessary for supporting SCRIPT.
+If it is a vector, one of the characters in the vector is necessary.
+This variable is used to find a font for a specific script.  */);
   Vscript_representative_chars = Qnil;
+
+  DEFVAR_LISP ("unicode-category-table", &Vunicode_category_table,
+              doc: /* Char table of Unicode's "General Category".
+All Unicode characters have one of the following values (symbol):
+  Lu, Ll, Lt, Lm, Lo, Mn, Mc, Me, Nd, Nl, No, Pc, Pd, Ps, Pe, Pi, Pf, Po,
+  Sm, Sc, Sk, So, Zs, Zl, Zp, Cc, Cf, Cs, Co, Cn
+See The Unicode Standard for the meaning of those values.  */);
+  /* The correct char-table is setup in characters.el.  */
+  Vunicode_category_table = Qnil;
 }
 
 #endif /* emacs */