Replicate the semantics of the libunicode utf8 functions by returning NULL

2001-05-14  Jon Trowbridge  <trow@ximian.com>

        * camel-search-private.c (utf8_get): Replicate the semantics of
        the libunicode utf8 functions by returning NULL in the arg
        on invalid utf8.

        * camel-pgp-context.c (pgp_verify): Check for valid utf8,
        terminate loop if something looks wrong.

        * camel-mime-utils.c (header_encode_phrase_get_words): Properly
        check for invalid utf8.
        (header_encode_string): Properly check for invalid utf8.

        * camel-charset-map.c (camel_charset_step): Properly check for
        invalid utf8.

2001-05-14  Jon Trowbridge  <trow@ximian.com>

        * e-html-utils.c (is_citation): Check for bad utf8.

svn path=/trunk/; revision=9798

7 files changed, 36 insertions, 10 deletions

diff --git a/camel/ChangeLog b/camel/ChangeLog
index 5a42731323..41e78c0129 100644
--- a/camel/ChangeLog
+++ b/camel/ChangeLog
@@ -1,3 +1,19 @@
+2001-05-14  Jon Trowbridge  <trow@ximian.com>
+
+	* camel-search-private.c (utf8_get): Replicate the semantics of
+	the libunicode utf8 functions by returning NULL in the arg
+	on invalid utf8.
+
+	* camel-pgp-context.c (pgp_verify): Check for valid utf8,
+	terminate loop if something looks wrong.
+
+	* camel-mime-utils.c (header_encode_phrase_get_words): Properly
+	check for invalid utf8.
+	(header_encode_string): Properly check for invalid utf8.
+
+	* camel-charset-map.c (camel_charset_step): Properly check for
+	invalid utf8.
+
 2001-05-14  Jeffrey Stedfast  <fejj@ximian.com>
 
 	* tests/folder/test9.c: 
diff --git a/camel/camel-charset-map.c b/camel/camel-charset-map.c
index d7aa8763dd..f33c8082dd 100644
--- a/camel/camel-charset-map.c
+++ b/camel/camel-charset-map.c
@@ -227,11 +227,12 @@ camel_charset_step(CamelCharset *c, const char *in, int len)
 		gunichar c;
 		const char *newinptr;
 		newinptr = g_utf8_next_char(inptr);
-		if (newinptr == NULL) {
+		c = g_utf8_get_char(inptr);
+		if (newinptr == NULL || !g_unichar_validate (c)) {
 			inptr++;
 			continue;
 		}
-		c = g_utf8_get_char(inptr);
+
 		inptr = newinptr;
 		if (c<=0xffff) {
 			mask &= charset_mask(c);
diff --git a/camel/camel-mime-utils.c b/camel/camel-mime-utils.c
index fbfbb3e5be..3d915be1f7 100644
--- a/camel/camel-mime-utils.c
+++ b/camel/camel-mime-utils.c
@@ -1255,6 +1255,8 @@ header_encode_string (const unsigned char *in)
 	int encoding;
 	GString *out;
 	char *outstr;
+
+	g_return_val_if_fail (g_utf8_validate (in, -1, NULL), NULL);
 	
 	if (in == NULL)
 		return NULL;
@@ -1281,13 +1283,14 @@ header_encode_string (const unsigned char *in)
 		const char *newinptr;
 		
 		newinptr = g_utf8_next_char (inptr);
-		if (newinptr == NULL) {
+		c = g_utf8_get_char (inptr);
+		if (newinptr == NULL || !g_unichar_validate (c)) {
 			w(g_warning ("Invalid UTF-8 sequence encountered (pos %d, char '%c'): %s",
 				     (inptr-in), inptr[0], in));
 			inptr++;
 			continue;
 		}
-		c = g_utf8_get_char (inptr);
+
 		
 		if (g_unichar_isspace (c) && !last_was_space) {
 			/* we've reached the end of a 'word' */
@@ -1427,13 +1430,15 @@ header_encode_phrase_get_words (const unsigned char *in)
 		const char *newinptr;
 		
 		newinptr = g_utf8_next_char (inptr);
-		if (newinptr == NULL) {
+		c = g_utf8_get_char (inptr);
+
+		if (!g_unichar_validate (c)) {
 			w(g_warning ("Invalid UTF-8 sequence encountered (pos %d, char '%c'): %s",
 				     (inptr - in), inptr[0], in));
 			inptr++;
 			continue;
 		}
-		c = g_utf8_get_char (inptr);
+
 		
 		inptr = newinptr;
 		if (g_unichar_isspace (c)) {
diff --git a/camel/camel-pgp-context.c b/camel/camel-pgp-context.c
index c2e361ce40..c19756a135 100644
--- a/camel/camel-pgp-context.c
+++ b/camel/camel-pgp-context.c
@@ -992,7 +992,7 @@ pgp_verify (CamelCipherContext *ctx, CamelStream *istream,
 			inptr = diagnostics;
 			inend = inptr + inlen;
 			
-			while (inptr && inptr < inend) {
+			while (inptr && inptr < inend && g_unichar_validate (g_utf8_get_char (inptr))) {
 				*outbuf++ = g_utf8_get_char (inptr) & 0xff;
 				inptr = g_utf8_next_char (inptr);
 			}
diff --git a/camel/camel-search-private.c b/camel/camel-search-private.c
index e46cc29cc8..65f6c17ff9 100644
--- a/camel/camel-search-private.c
+++ b/camel/camel-search-private.c
@@ -200,7 +200,7 @@ utf8_get (const char **inp)
 	g_return_val_if_fail (p != NULL, 0);
 	
 	c = g_utf8_get_char (p);
-	*inp = g_utf8_next_char (p);
+	*inp = g_unichar_validate (c) ? g_utf8_next_char (p) : NULL;
 	
 	return c;
 }
diff --git a/e-util/ChangeLog b/e-util/ChangeLog
index abf4fcc7ee..d0cf6a5369 100644
--- a/e-util/ChangeLog
+++ b/e-util/ChangeLog
@@ -1,3 +1,7 @@
+2001-05-14  Jon Trowbridge  <trow@ximian.com>
+
+	* e-html-utils.c (is_citation): Check for bad utf8.
+
 2001-05-08  Dan Winship  <danw@ximian.com>
 
 	* e-path.c (e_path_find_folders): Walk a hierarchy using the
diff --git a/e-util/e-html-utils.c b/e-util/e-html-utils.c
index 1561492454..e79d5e2192 100644
--- a/e-util/e-html-utils.c
+++ b/e-util/e-html-utils.c
@@ -145,7 +145,7 @@ is_citation (const unsigned char *c, gboolean saw_citation)
 	}
 
 	/* Check for "Rupert> " and the like... */
-	for (i = 0; c && *c && *c != '\n' && i < 10; i ++, c = g_utf8_next_char (c)) {
+	for (i = 0; c && *c && g_unichar_validate (g_utf8_get_char (c)) && *c != '\n' && i < 10; i ++, c = g_utf8_next_char (c)) {
 		u = g_utf8_get_char (c);
 		if (u == '>')
 			return TRUE;
@@ -304,7 +304,7 @@ e_text_to_html_full (const char *input, unsigned int flags, guint32 color)
 			}
 		}
 
-		if (u == (gunichar)-1) {
+		if (!g_unichar_validate (u)) {
 			/* Sigh. Someone sent undeclared 8-bit data.
 			 * Assume it's iso-8859-1.
 			 */