X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/f15c8583198c3d6c26ca0c0a5b6fb019f98d6c3c..02ca5db040b57ca4a36c317fcb3fb56f43ab371e:/src/character.h

diff --git a/src/character.h b/src/character.h
index 7d902952db..586f330fba 100644
--- a/src/character.h
+++ b/src/character.h
@@ -9,8 +9,8 @@ This file is part of GNU Emacs.
 
 GNU Emacs is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
+the Free Software Foundation, either version 3 of the License, or (at
+your option) any later version.
 
 GNU Emacs is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -24,6 +24,7 @@ along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
 #define EMACS_CHARACTER_H
 
 #include <verify.h>
+#include "lisp.h"
 
 INLINE_HEADER_BEGIN
 
@@ -59,6 +60,30 @@ INLINE_HEADER_BEGIN
 /* Maximum leading code of multibyte characters.  */
 #define MAX_MULTIBYTE_LEADING_CODE 0xF8
 
+/* Unicode character values.  */
+enum
+{
+  NO_BREAK_SPACE = 0x00A0,
+  SOFT_HYPHEN = 0x00AD,
+  ZERO_WIDTH_NON_JOINER = 0x200C,
+  ZERO_WIDTH_JOINER = 0x200D,
+  HYPHEN = 0x2010,
+  NON_BREAKING_HYPHEN = 0x2011,
+  LEFT_SINGLE_QUOTATION_MARK = 0x2018,
+  RIGHT_SINGLE_QUOTATION_MARK = 0x2019,
+  PARAGRAPH_SEPARATOR = 0x2029,
+  LEFT_POINTING_ANGLE_BRACKET = 0x2329,
+  RIGHT_POINTING_ANGLE_BRACKET = 0x232A,
+  LEFT_ANGLE_BRACKET = 0x3008,
+  RIGHT_ANGLE_BRACKET = 0x3009,
+  OBJECT_REPLACEMENT_CHARACTER = 0xFFFC,
+};
+
+/* UTF-8 encodings.  Use \x escapes, so they are portable to pre-C11
+   compilers and can be concatenated with ordinary string literals.  */
+#define uLSQM "\xE2\x80\x98" /* U+2018 LEFT SINGLE QUOTATION MARK */
+#define uRSQM "\xE2\x80\x99" /* U+2019 RIGHT SINGLE QUOTATION MARK */
+
 /* Nonzero iff C is a character that corresponds to a raw 8-bit
    byte.  */
 #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)
@@ -110,14 +135,12 @@ INLINE_HEADER_BEGIN
   do {					\
     Lisp_Object tmp = XCAR (x);		\
     CHECK_CHARACTER (tmp);		\
-    XSETCAR ((x), tmp);			\
   } while (false)
 
 #define CHECK_CHARACTER_CDR(x) \
   do {					\
     Lisp_Object tmp = XCDR (x);		\
     CHECK_CHARACTER (tmp);		\
-    XSETCDR ((x), tmp);			\
   } while (false)
 
 /* Nonzero iff C is a character of code less than 0x100.  */
@@ -589,14 +612,13 @@ sanitize_char_width (EMACS_INT width)
    : (c) <= 0xE01EF ? (c) - 0xE0100 + 17	\
    : 0)
 
-/* If C is a high surrogate, return 1.  If C is a low surrogate,
-   return 2.  Otherwise, return 0.  */
+/* Return true if C is a surrogate.  */
 
-#define CHAR_SURROGATE_PAIR_P(c)	\
-  ((c) < 0xD800 ? 0			\
-   : (c) <= 0xDBFF ? 1			\
-   : (c) <= 0xDFFF ? 2			\
-   : 0)
+INLINE bool
+char_surrogate_p (int c)
+{
+  return 0xD800 <= c && c <= 0xDFFF;
+}
 
 /* Data type for Unicode general category.
 
@@ -662,6 +684,8 @@ extern Lisp_Object string_escape_byte8 (Lisp_Object);
 
 extern bool alphabeticp (int);
 extern bool decimalnump (int);
+extern bool graphicp (int);
+extern bool printablep (int);
 
 /* Return a translation table of id number ID.  */
 #define GET_TRANSLATION_TABLE(id) \