From b254663a41a4da7bc4c9039f89411f4b3bd0b8a7 Mon Sep 17 00:00:00 2001
From: Peter Verthez <Peter.Verthez@advalvas.be>
Date: Fri, 22 Nov 2002 20:53:51 +0000
Subject: [PATCH] Renamed utf8-locale.h to utf8.h. Added functions
 is_utf8_string and utf8_strlen.

---
 utf8/utf8.c                    | 77 ++++++++++++++++++++++++++++++++++
 utf8/{utf8-locale.h => utf8.h} | 15 +++++--
 2 files changed, 88 insertions(+), 4 deletions(-)
 create mode 100644 utf8/utf8.c
 rename utf8/{utf8-locale.h => utf8.h} (58%)

diff --git a/utf8/utf8.c b/utf8/utf8.c
new file mode 100644
index 0000000..443fcfc
--- /dev/null
+++ b/utf8/utf8.c
@@ -0,0 +1,77 @@
+/* Utility functions for UTF-8
+   Copyright (C) 2001, 2002 Peter Verthez
+
+   Permission granted to do anything with this file that you want, as long
+   as the above copyright is retained in all copies.
+   THERE IS NO WARRANTY - USE AT YOUR OWN RISK
+*/
+
+/* $Id$ */
+/* $Name$ */
+
+#include "utf8.h"
+
+int is_utf8_string(const char* str)
+{
+  int expect_bytes = 0;
+
+  if (!str) return 0;
+  
+  while (*str) {
+    if ((*str & 0x80) == 0) {
+      /* Looks like an ASCII character */
+      if (expect_bytes)
+	/* byte of UTF-8 character expected */
+	return 0;
+      else {
+	/* OK, ASCII character expected */
+	str++;
+      }
+    }
+    else {
+      /* Looks like byte of an UTF-8 character */
+      if (expect_bytes) {
+	/* expect_bytes already set: first byte of UTF-8 char already seen */
+	if ((*str & 0xC0) == 0x80) {
+	  /* OK, next byte of UTF-8 character */
+	  /* Decrement number of expected bytes */
+	  expect_bytes--;
+	  str++;
+	}
+	else {
+	  /* again first byte ?!?! */
+	  return 0;
+	}
+      }
+      else {
+	/* First byte of the UTF-8 character */
+	/* count initial one bits and set expect_bytes to 1 less */
+	char ch = *str;
+	while (ch & 0x80) {
+	  expect_bytes++;
+	  ch = (ch & 0x7f) << 1;
+	}
+	expect_bytes--;
+	str++;
+      }
+    }
+  }
+
+  return (expect_bytes == 0);
+}
+
+int utf8_strlen(const char* str)
+{
+  int num_char = 0;
+  
+  if (!str) return 0;
+  
+  while (*str) {
+    if ((*str & 0x80) == 0 || (*str & 0xC0) == 0xC0)
+      num_char++;
+    str++;
+  }
+  
+  return num_char;
+}
+
diff --git a/utf8/utf8-locale.h b/utf8/utf8.h
similarity index 58%
rename from utf8/utf8-locale.h
rename to utf8/utf8.h
index b8a752b..79836dd 100644
--- a/utf8/utf8-locale.h
+++ b/utf8/utf8.h
@@ -1,4 +1,4 @@
-/* Encoding utility from UTF-8 to locale and vice versa
+/* Header file for UTF-8 functions
    Copyright (C) 2001, 2002 Peter Verthez
 
    Permission granted to do anything with this file that you want, as long
@@ -9,13 +9,20 @@
 /* $Id$ */
 /* $Name$ */
 
-#ifndef __UTF8_LOCALE_H
-#define __UTF8_LOCALE_H
+#ifndef __UTF8_H
+#define __UTF8_H
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+  /* Returns -1 if the string is not a valid UTF-8 string, returns its
+     string length otherwise */
+int   utf8_strlen(const char* input);
+
+  /* Returns 1 if string is valid UTF-8 string, 0 otherwise */
+int   is_utf8_string(const char* input);
+  
 void  convert_set_unknown(const char* unknown);
 char* convert_utf8_to_locale(const char* input, int *conv_fails);
 char* convert_locale_to_utf8(const char* input);
@@ -24,4 +31,4 @@ char* convert_locale_to_utf8(const char* input);
 }
 #endif
 
-#endif /* __UTF8_LOCALE_H */
+#endif /* __UTF8_H */
-- 
2.30.2