Use CMake

[linenoise.git] / utf8.h

diff --git a/utf8.h b/utf8.h
index 564d64e45d989aa9ec5b1801831fb3c7926acf97..dd9c94ec7e383ff0617e02322ea4ac92dfacda0e 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,34 +1,46 @@
 #ifndef UTF8_UTIL_H
 #define UTF8_UTIL_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /**
  * UTF-8 utility functions
  *
- * (c) 2010 Steve Bennett <steveb@workware.net.au>
+ * (c) 2010-2019 Steve Bennett <steveb@workware.net.au>
  *
- * See LICENCE for licence details.
+ * See utf8.c for licence details.
  */
 
 #ifndef USE_UTF8
 #include <ctype.h>
 
+#define MAX_UTF8_LEN 1
+
 /* No utf-8 support. 1 byte = 1 char */
-#define utf8_strlen(S, B) (B) < 0 ? (int)strlen(S) : (B)
-#define utf8_tounicode(S, CP) (*(CP) = *(S), 1)
+#define utf8_strlen(S, B) ((B) < 0 ? (int)strlen(S) : (B))
+#define utf8_strwidth(S, B) utf8_strlen((S), (B))
+#define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
 #define utf8_index(C, I) (I)
 #define utf8_charlen(C) 1
+ #define utf8_width(C) 1
 
 #else
+
+#define MAX_UTF8_LEN 4
+
 /**
- * Converts the given unicode codepoint (0 - 0xffff) to utf-8
+ * Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
  * and stores the result at 'p'.
- * 
- * Returns the number of utf-8 characters (1-3).
+ *
+ * Returns the number of utf-8 characters
  */
-int utf8_fromunicode(char *p, unsigned short uc);
+int utf8_fromunicode(char *p, unsigned uc);
 
 /**
  * Returns the length of the utf-8 sequence starting with 'c'.
- * 
+ *
  * Returns 1-4, or -1 if this is not a valid start byte.
  *
  * Note that charlen=4 is not supported by the rest of the API.
@@ -36,7 +48,7 @@ int utf8_fromunicode(char *p, unsigned short uc);
 int utf8_charlen(int c);
 
 /**
- * Returns the number of characters in the utf-8 
+ * Returns the number of characters in the utf-8
  * string of the given byte length.
  *
  * Any bytes which are not part of an valid utf-8
@@ -44,13 +56,19 @@ int utf8_charlen(int c);
  *
  * The string *must* be null terminated.
  *
- * Does not support unicode code points > \uffff
+ * Does not support unicode code points > \u1fffff
  */
 int utf8_strlen(const char *str, int bytelen);
 
+/**
+ * Calculates the display width of the first 'charlen' characters in 'str'.
+ * See utf8_width()
+ */
+int utf8_strwidth(const char *str, int charlen);
+
 /**
  * Returns the byte index of the given character in the utf-8 string.
- * 
+ *
  * The string *must* be null terminated.
  *
  * This will return the byte length of a utf-8 string
@@ -61,7 +79,7 @@ int utf8_index(const char *str, int charindex);
 /**
  * Returns the unicode codepoint corresponding to the
  * utf-8 sequence 'str'.
- * 
+ *
  * Stores the result in *uc and returns the number of bytes
  * consumed.
  *
@@ -70,10 +88,20 @@ int utf8_index(const char *str, int charindex);
  *
  * If it is not null terminated, the length *must* be checked first.
  *
- * Does not support unicode code points > \uffff
+ * Does not support unicode code points > \u1fffff
  */
 int utf8_tounicode(const char *str, int *uc);
 
+/**
+ * Returns the width (in characters) of the given unicode codepoint.
+ * This is 1 for normal letters and 0 for combining characters and 2 for wide characters.
+ */
+int utf8_width(int ch);
+
+#endif
+
+#ifdef __cplusplus
+}
 #endif
 
 #endif