From: Peter Verthez <Peter.Verthez@advalvas.be>
Date: Sat, 1 Feb 2003 16:50:51 +0000 (+0000)
Subject: New functions next_utf8_char and nth_utf8_char.
X-Git-Url: https://git.dlugolecki.net.pl/?a=commitdiff_plain;h=8f6712fc64a6d02770442f0c9c2142a8c4e38b9c;p=gedcom-parse.git

New functions next_utf8_char and nth_utf8_char.
---

diff --git a/utf8/ChangeLog b/utf8/ChangeLog
index 3420dab..d23aad3 100644
--- a/utf8/ChangeLog
+++ b/utf8/ChangeLog
@@ -1,3 +1,7 @@
+2003-02-01  Peter Verthez  <Peter.Verthez@advalvas.be>
+
+	* utf8tools.h, utf8.c: New functions next_utf8_char and nth_utf8_char.
+
 2002-12-30  Peter Verthez  <Peter.Verthez@advalvas.be>
 
 	* release 0.1.0
diff --git a/utf8/utf8.c b/utf8/utf8.c
index e3809b9..6c5f5be 100644
--- a/utf8/utf8.c
+++ b/utf8/utf8.c
@@ -21,6 +21,7 @@
 /* $Name$ */
 
 #include "utf8tools.h"
+#include <string.h>
 
 int is_utf8_string(const char* str)
 {
@@ -78,11 +79,37 @@ int utf8_strlen(const char* str)
   if (!str) return 0;
   
   while (*str) {
-    if ((*str & 0x80) == 0 || (*str & 0xC0) == 0xC0)
-      num_char++;
+    if ((*str & 0xC0) != 0xC0) num_char++;
     str++;
   }
   
   return num_char;
 }
 
+char* next_utf8_char(char* str)
+{
+  if (!str) return NULL;
+
+  if (*str) {
+    str++;
+    while (*str && (*str & 0xC0) == 0x80)
+      str++;
+  }
+  return str;
+}
+
+char* nth_utf8_char(char* str, int n)
+{
+  int num_char = 0;
+  if (!str) return NULL;
+
+  if (*str) {
+    str++;
+    while (*str) {
+      if ((*str & 0xC0) != 0x80) num_char++;
+      if (num_char == n) break;
+      str++;
+    }
+  }
+  return str;
+}
diff --git a/utf8/utf8tools.h b/utf8/utf8tools.h
index 0eca7da..d2e4e98 100644
--- a/utf8/utf8tools.h
+++ b/utf8/utf8tools.h
@@ -41,6 +41,12 @@ int   utf8_strlen(const char* input);
   /* Returns 1 if string is valid UTF-8 string, 0 otherwise */
 int   is_utf8_string(const char* input);
 
+  /* Returns respectively a pointer to the next or the nth UTF-8 character.
+     The value n = 0 is the first character of the input, i.e.
+     next_utf8_char(input) is the same as nth_utf8_char(input, 1) */
+char* next_utf8_char(char* input);
+char* nth_utf8_char(char* input, int n);
+
   /* Functions for creating and freeing conversion buffers yourself */
 conv_buffer_t create_conv_buffer(int size);
 void free_conv_buffer(conv_buffer_t buf);