utf8: pick_one_utf8_char()

utf8_width() function was doing two different things.  To pick a
valid character from UTF-8 stream, and compute the display width of
that character.  This splits the former to a separate function
pick_one_utf8_char().

Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/utf8.c b/utf8.c
index 9efcdb9c09970127ebe37923879274b95efd526c..24d2ec696afac26c2b5e31c0994025005837470d 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -3,8 +3,6 @@
 
 /* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
 
-typedef unsigned int ucs_char_t;  /* assuming 32bit int */
-
 struct interval {
   int first;
   int last;
@@ -153,11 +151,14 @@ static int git_wcwidth(ucs_char_t ch)
 }
 
 /*
- * This function returns the number of columns occupied by the character
- * pointed to by the variable start. The pointer is updated to point at
- * the next character. If it was not valid UTF-8, the pointer is set to NULL.
+ * Pick one ucs character starting from the location *start points at,
+ * and return it, while updating the *start pointer to point at the
+ * end of that character.
+ *
+ * If the string was not a valid UTF-8, *start pointer is set to NULL
+ * and the return value is undefined.
  */
-int utf8_width(const char **start)
+ucs_char_t pick_one_utf8_char(const char **start)
 {
        unsigned char *s = (unsigned char *)*start;
        ucs_char_t ch;
@@ -208,6 +209,20 @@ invalid:
                return 0;
        }
 
+       return ch;
+}
+
+/*
+ * This function returns the number of columns occupied by the character
+ * pointed to by the variable start. The pointer is updated to point at
+ * the next character.  If it was not valid UTF-8, the pointer is set to
+ * NULL.
+ */
+int utf8_width(const char **start)
+{
+       ucs_char_t ch = pick_one_utf8_char(start);
+       if (!*start)
+               return 0;
        return git_wcwidth(ch);
 }
 

diff --git a/utf8.h b/utf8.h
index 15db6f1f27ef7a1f056d5b6adca901f092036f82..4a7f0464c4321864f96eb9ce96eaccfead3ad935 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,9 @@
 #ifndef GIT_UTF8_H
 #define GIT_UTF8_H
 
+typedef unsigned int ucs_char_t;  /* assuming 32bit int */
+
+ucs_char_t pick_one_utf8_char(const char **start);
 int utf8_width(const char **start);
 int is_utf8(const char *text);
 int is_encoding_utf8(const char *name);