* sysdep.c (LC_COLLATE, LC_COLLATE_MASK): Give individual defaults.

[gnu-emacs] / src / character.c

diff --git a/src/character.c b/src/character.c
index 5a06c7f4d6cfe0082c947022190f4bb1ded65b71..a8e48dfd774231eabd94c3fa7b22054ca1b08745 100644 (file)
--- a/src/character.c
+++ b/src/character.c
@@ -1,6 +1,6 @@
 /* Basic character support.
 
-Copyright (C) 2001-2013 Free Software Foundation, Inc.
+Copyright (C) 2001-2014 Free Software Foundation, Inc.
 Copyright (C) 1995, 1997, 1998, 2001 Electrotechnical Laboratory, JAPAN.
   Licensed to the Free Software Foundation.
 Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
@@ -29,8 +29,6 @@ along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
 #include <config.h>
 #endif
 
-#define CHARACTER_INLINE EXTERN_INLINE
-
 #include <stdio.h>
 
 #ifdef emacs
@@ -174,11 +172,14 @@ string_char (const unsigned char *p, const unsigned char **advanced, int *len)
 
   if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10))
     {
+      /* 1-, 2-, and 3-byte sequences can be handled by the macro.  */
       c = STRING_CHAR_ADVANCE (p);
     }
   else if (! (*p & 0x08))
     {
-      c = ((((p)[0] & 0xF) << 18)
+      /* A 4-byte sequence of this form:
+        11110xxx 10xxxxxx 10xxxxxx 10xxxxxx  */
+      c = ((((p)[0] & 0x7) << 18)
           | (((p)[1] & 0x3F) << 12)
           | (((p)[2] & 0x3F) << 6)
           | ((p)[3] & 0x3F));
@@ -186,7 +187,14 @@ string_char (const unsigned char *p, const unsigned char **advanced, int *len)
     }
   else
     {
-      c = ((((p)[1] & 0x3F) << 18)
+      /* A 5-byte sequence of this form:
+
+        111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+
+        Note that the top 4 `x's are always 0, so shifting p[1] can
+        never exceed the maximum valid character codepoint. */
+      c = (/* (((p)[0] & 0x3) << 24) ... always 0, so no need to shift. */
+          (((p)[1] & 0x3F) << 18)
           | (((p)[2] & 0x3F) << 12)
           | (((p)[3] & 0x3F) << 6)
           | ((p)[4] & 0x3F));
@@ -225,32 +233,6 @@ translate_char (Lisp_Object table, int c)
   return c;
 }
 
-/* Convert ASCII or 8-bit character C to unibyte.  If C is none of
-   them, return (C & 0xFF).  */
-
-int
-multibyte_char_to_unibyte (int c)
-{
-  if (c < 0x80)
-    return c;
-  if (CHAR_BYTE8_P (c))
-    return CHAR_TO_BYTE8 (c);
-  return (c & 0xFF);
-}
-
-/* Like multibyte_char_to_unibyte, but return -1 if C is not supported
-   by charset_unibyte.  */
-
-int
-multibyte_char_to_unibyte_safe (int c)
-{
-  if (c < 0x80)
-    return c;
-  if (CHAR_BYTE8_P (c))
-    return CHAR_TO_BYTE8 (c);
-  return -1;
-}
-
 DEFUN ("characterp", Fcharacterp, Scharacterp, 1, 2, 0,
        doc: /* Return non-nil if OBJECT is a character.
 In Emacs Lisp, characters are represented by character codes, which
@@ -833,8 +815,8 @@ string_escape_byte8 (Lisp_Object string)
 
   if (multibyte)
     {
-      if (byte8_count > (MOST_POSITIVE_FIXNUM - nchars) / 3
-         || byte8_count > (STRING_BYTES_BOUND - nbytes) / 2)
+      if ((MOST_POSITIVE_FIXNUM - nchars) / 3 < byte8_count
+         || (STRING_BYTES_BOUND - nbytes) / 2 < byte8_count)
        string_overflow ();
 
       /* Convert 2-byte sequence of byte8 chars to 4-byte octal.  */
@@ -843,7 +825,7 @@ string_escape_byte8 (Lisp_Object string)
     }
   else
     {
-      if (byte8_count > (STRING_BYTES_BOUND - nbytes) / 3)
+      if ((STRING_BYTES_BOUND - nbytes) / 3 < byte8_count)
        string_overflow ();
 
       /* Convert 1-byte sequence of byte8 chars to 4-byte octal.  */
@@ -1062,10 +1044,6 @@ A char-table for width (columns) of each character.  */);
               doc: /* Char table of script symbols.
 It has one extra slot whose value is a list of script symbols.  */);
 
-  /* Intern this now in case it isn't already done.
-     Setting this variable twice is harmless.
-     But don't staticpro it here--that is done in alloc.c.  */
-  Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots");
   DEFSYM (Qchar_script_table, "char-script-table");
   Fput (Qchar_script_table, Qchar_table_extra_slots, make_number (1));
   Vchar_script_table = Fmake_char_table (Qchar_script_table, Qnil);