Removed references to buck2obj.h and obj2buck.h.

[libucw.git] / charset / unicode.h

diff --git a/charset/unicode.h b/charset/unicode.h
index 3246f1346162a33c996a4abd8c08323d4a3b2162..7bc6f235812ef3c5529dac1de956e768924eea7f 100644 (file)
--- a/charset/unicode.h
+++ b/charset/unicode.h
@@ -42,14 +42,14 @@ static inline uns Uunaccent(uns x)
 extern const word *Uexpand_lig(uns x);
 
 enum unicode_char_type {
 extern const word *Uexpand_lig(uns x);
 
 enum unicode_char_type {

-  _U_LETTER,                   /* Letters */
-  _U_UPPER,                    /* Upper-case letters */
-  _U_LOWER,                    /* Lower-case letters */
-  _U_CTRL,                     /* Control characters */
-  _U_DIGIT,                    /* Digits */
-  _U_XDIGIT,                   /* Hexadecimal digits */
-  _U_SPACE,                    /* White spaces (spaces, tabs, newlines) */
-  _U_LIGATURE,                 /* Compatibility ligature (to be expanded) */
+  _U_LETTER = 1,               /* Letters */
+  _U_UPPER = 2,                        /* Upper-case letters */
+  _U_LOWER = 4,                        /* Lower-case letters */
+  _U_CTRL = 8,                 /* Control characters */
+  _U_DIGIT = 16,               /* Digits */
+  _U_XDIGIT = 32,              /* Hexadecimal digits */
+  _U_SPACE = 64,               /* White spaces (spaces, tabs, newlines) */
+  _U_LIGATURE = 128,           /* Compatibility ligature (to be expanded) */

 };
 
 #define _U_LUPPER (_U_LETTER | _U_UPPER)
 };
 
 #define _U_LUPPER (_U_LETTER | _U_UPPER)


@@ -124,6 +124,8 @@ enum unicode_char_type {
         p++, c <<= 1;                                  \
   } while (0)
 
         p++, c <<= 1;                                  \
   } while (0)
 

+#define UTF8_SKIP_BWD(p) while ((--*(p) & 0xc0) == 0x80)
+

 #define UTF8_SPACE(u) ((u) < 0x80 ? 1 : (u) < 0x800 ? 2 : 3)
 
 uns ucs2_to_utf8(byte *, word *);
 #define UTF8_SPACE(u) ((u) < 0x80 ? 1 : (u) < 0x800 ? 2 : 3)
 
 uns ucs2_to_utf8(byte *, word *);