Merge branch '1.1'

[jansson.git] / src / utf.c

diff --git a/src/utf.c b/src/utf.c
index 092959d..dda80f0 100644 (file)
--- a/src/utf.c
+++ b/src/utf.c
@@ -1,4 +1,48 @@
+/*
+ * Copyright (c) 2009 Petri Lehtinen <petri@digip.org>
+ *
+ * Jansson is free software; you can redistribute it and/or modify
+ * it under the terms of the MIT license. See LICENSE for details.
+ */
+
 #include <string.h>
+#include <stdint.h>
+
+int utf8_encode(int32_t codepoint, char *buffer, int *size)
+{
+    if(codepoint < 0)
+        return -1;
+    else if(codepoint < 0x80)
+    {
+        buffer[0] = (char)codepoint;
+        *size = 1;
+    }
+    else if(codepoint < 0x800)
+    {
+        buffer[0] = 0xC0 + ((codepoint & 0x7C0) >> 6);
+        buffer[1] = 0x80 + ((codepoint & 0x03F));
+        *size = 2;
+    }
+    else if(codepoint < 0x10000)
+    {
+        buffer[0] = 0xE0 + ((codepoint & 0xF000) >> 12);
+        buffer[1] = 0x80 + ((codepoint & 0x0FC0) >> 6);
+        buffer[2] = 0x80 + ((codepoint & 0x003F));
+        *size = 3;
+    }
+    else if(codepoint <= 0x10FFFF)
+    {
+        buffer[0] = 0xF0 + ((codepoint & 0x1C0000) >> 18);
+        buffer[1] = 0x80 + ((codepoint & 0x03F000) >> 12);
+        buffer[2] = 0x80 + ((codepoint & 0x000FC0) >> 6);
+        buffer[3] = 0x80 + ((codepoint & 0x00003F));
+        *size = 4;
+    }
+    else
+        return -1;
+
+    return 0;
+}
 
 int utf8_check_first(char byte)
 {
@@ -36,9 +80,10 @@ int utf8_check_first(char byte)
     }
 }
 
-int utf8_check_full(const char *buffer, int size)
+int utf8_check_full(const char *buffer, int size, int32_t *codepoint)
 {
-    int i, value = 0;
+    int i;
+    int32_t value = 0;
     unsigned char u = (unsigned char)buffer[0];
 
     if(size == 2)
@@ -85,9 +130,38 @@ int utf8_check_full(const char *buffer, int size)
         return 0;
     }
 
+    if(codepoint)
+        *codepoint = value;
+
     return 1;
 }
 
+const char *utf8_iterate(const char *buffer, int32_t *codepoint)
+{
+    int count;
+    int32_t value;
+
+    if(!*buffer)
+        return buffer;
+
+    count = utf8_check_first(buffer[0]);
+    if(count <= 0)
+        return NULL;
+
+    if(count == 1)
+        value = (unsigned char)buffer[0];
+    else
+    {
+        if(!utf8_check_full(buffer, count, &value))
+            return NULL;
+    }
+
+    if(codepoint)
+        *codepoint = value;
+
+    return buffer + count;
+}
+
 int utf8_check_string(const char *string, int length)
 {
     int i;
@@ -105,7 +179,7 @@ int utf8_check_string(const char *string, int length)
             if(i + count > length)
                 return 0;
 
-            if(!utf8_check_full(&string[i], count))
+            if(!utf8_check_full(&string[i], count, NULL))
                 return 0;
 
             i += count - 1;