[unicode] Add _cairo_utf8_get_char_validated()

1 files changed, 40 insertions, 2 deletions

diff --git a/src/cairo-unicode.c b/src/cairo-unicode.c
index 973ef5767..39d37b8e8 100644
--- a/src/cairo-unicode.c
+++ b/src/cairo-unicode.c
@@ -196,6 +196,40 @@ _utf8_get_char_extended (const unsigned char *p,
 }
 
 /**
+ * _cairo_utf8_get_char_validated:
+ * @p: a UTF-8 string
+ * @unicode: location to store one Unicode character
+ *
+ * Decodes the first character of a valid UTF-8 string, and returns
+ * the number of bytes consumed.
+ *
+ * Note that the string should be valid.  Do not use this without
+ * validating the string first.
+ *
+ * Returns: the number of bytes forming the character returned.
+ **/
+int
+_cairo_utf8_get_char_validated (const char *p,
+				uint32_t   *unicode)
+{
+    int i, mask = 0, len;
+    uint32_t result;
+    unsigned char c = (unsigned char) *p;
+
+    UTF8_COMPUTE (c, mask, len);
+    if (len == -1) {
+	if (unicode)
+	    *unicode = (uint32_t)-1;
+	return 1;
+    }
+    UTF8_GET (result, p, i, mask, len);
+
+    if (unicode)
+	*unicode = result;
+    return len;
+}
+
+/**
  * _cairo_utf8_to_utf32:
  * @str: an UTF-8 string
  * @len: length of @str in bytes, or -1 if it is nul-terminated.
@@ -266,7 +300,7 @@ _cairo_utf8_to_ucs4 (const char *str,
  * _cairo_ucs4_to_utf8:
  * @unicode: a UCS-4 character
  * @utf8: buffer to write utf8 string into. Must have at least 4 bytes
- * space available.
+ * space available. Or %NULL.
  *
  * Return value: Number of bytes in the utf8 string or 0 if an invalid
  * unicode character
@@ -279,7 +313,8 @@ _cairo_ucs4_to_utf8 (uint32_t  unicode,
     char *p;
 
     if (unicode < 0x80) {
-	*utf8 = unicode;
+	if (utf8)
+	    *utf8 = unicode;
 	return 1;
     } else if (unicode < 0x800) {
 	bytes = 2;
@@ -291,6 +326,9 @@ _cairo_ucs4_to_utf8 (uint32_t  unicode,
 	return 0;
     }
 
+    if (!utf8)
+	return bytes;
+
     p = utf8 + bytes;
     while (p > utf8) {
 	*--p = 0x80 | (unicode & 0x3f);