STR 2822: function to count bytes in a UTF-8 string

2 files changed, 25 insertions, 0 deletions

diff --git a/FL/fl_utf8.h b/FL/fl_utf8.h
index 7a7489b38..41e59c648 100644
--- a/FL/fl_utf8.h
+++ b/FL/fl_utf8.h
@@ -56,6 +56,9 @@ FL_EXPORT int fl_utf8len(char c);
 /* OD: returns the byte length of the first UTF-8 char sequence (returns +1 if not valid) */
 FL_EXPORT int fl_utf8len1(char c);
 
+/* OD: returns the byte length of a UTF-8 text */
+FL_EXPORT int fl_utf8strlen(const char *text, int len=-1);
+
 /* OD: returns the number of Unicode chars in the UTF-8 string */
 FL_EXPORT int fl_utf_nb_char(const unsigned char *buf, int len);
 
diff --git a/src/fl_utf8.cxx b/src/fl_utf8.cxx
index 72589c8e7..2ca9d6b2f 100644
--- a/src/fl_utf8.cxx
+++ b/src/fl_utf8.cxx
@@ -119,7 +119,29 @@ int fl_utf8len1(char c)
 
 
 /**
+ Return the length in bytes of a UTF-8 string.
+ \param[in] text encoded in UTF-8
+ \param[in] len number of Unicode characters, -1 to test until the end of text
+ \return number of bytes that make up the Unicode string
+ \see fl_utf_nb_char(const unsigned char *buf, int len)
+ */
+int fl_utf8strlen(const char *text, int len)
+{
+  if (len == -1) return (int)strlen(text);
+  int i, n = 0;
+  for (i=len; i>0; i--) {
+    if (*text == 0) return n; // end of string
+    int nc = fl_utf8len1(*text);
+    n += nc;
+    text += nc;
+  }
+  return n;
+}
+
+
+/**
   Returns the number of Unicode chars in the UTF-8 string.
+ \see fl_utf8strlen(const char *text, int len)
 */
 int
 fl_utf_nb_char(