encoder test.

1999-08-06  Robert Brady  <rwb197@ecs.soton.ac.uk>

	* tests/test6.c: encoder test.

	* camel/gmime-rfc2047.c: Fixed decoder bug : sequence
	?= is not always the terminator for an encoded-string.

svn path=/trunk/; revision=1091

3 files changed, 80 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index 861b4a7b09..caf152633a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+1999-08-06  Robert Brady  <rwb197@ecs.soton.ac.uk>
+
+	* tests/test6.c: encoder test.
+
+	* camel/gmime-rfc2047.c: Fixed decoder bug : sequence
+	?= is not always the terminator for an encoded-string.
+
 1999-08-06  bertrand  <Bertrand.Guiheneuf@aful.org>
 
 	* camel/providers/MH/camel-mh-folder.c (_list_subfolders): 
diff --git a/camel/gmime-rfc2047.c b/camel/gmime-rfc2047.c
index 2a44a20dd6..ecb75d519d 100644
--- a/camel/gmime-rfc2047.c
+++ b/camel/gmime-rfc2047.c
@@ -160,6 +160,7 @@ rfc2047_decode_word (const gchar *data, const gchar *into_what)
 		int b_len = 4096;
 		iconv_t i;
 		strncpy(q, charset, c - charset);
+		q[c - charset] = 0;
 		i = unicode_iconv_open(into_what, q);
 		if (!i) {
 			g_free(q);
@@ -167,11 +168,29 @@ rfc2047_decode_word (const gchar *data, const gchar *into_what)
 		}
 		unicode_iconv(i, &cook_2, &cook_len, &b, &b_len);
 		unicode_iconv_close(i);
+		*b = 0;
 	}
 
 	return g_strdup(buffer);
 }
 
+static gchar *
+find_end_of_encoded_word(const gchar *data) {
+	/* We can't just search for ?=,
+           because of the case :
+           "=?charset?q?=ff?=" :( */
+	if (!data) return NULL;
+	data = strstr(data, "=?");
+	if (!data) return NULL;
+	data = strchr(data+2, '?');
+	if (!data) return NULL;
+	data = strchr(data+1, '?');
+	if (!data) return NULL;
+	data = strstr(data+1, "?=");
+	if (!data) return NULL;
+	return data + 2;
+}
+
 gchar *
 gmime_rfc2047_decode (const gchar *data, const gchar *into_what) 
 {
@@ -185,6 +204,7 @@ gmime_rfc2047_decode (const gchar *data, const gchar *into_what)
 		char *word_start = strstr(data, "=?"), *decoded;
 		if (!word_start) {
 			strcpy(b, data);
+			b[strlen(data)] = 0;
 			return buffer;
 		}
 		if (word_start != data) {
@@ -192,14 +212,16 @@ gmime_rfc2047_decode (const gchar *data, const gchar *into_what)
 			if (strspn(data, " \t\n\r") != (word_start - data)) {
 				strncpy(b, data, word_start - data);
 				b += word_start - data;
+				*b = 0;
 			}
 		}
 		decoded = rfc2047_decode_word(word_start, into_what);
 		strcpy(b, decoded);
 		b += strlen(decoded);
+		*b = 0;
 		g_free(decoded);
 
-		data = strstr(data, "?=") + 2;
+		data = find_end_of_encoded_word(data);
 	}
 
 	*b = 0;
diff --git a/tests/test6.c b/tests/test6.c
new file mode 100644
index 0000000000..ead8312c52
--- /dev/null
+++ b/tests/test6.c
@@ -0,0 +1,50 @@
+/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
+
+/* test for the RFC 2047 encoder */
+
+#include <string.h>
+#include <unicode.h>
+
+#include "gmime-utils.h"
+#include "stdio.h"
+#include "camel-log.h"
+#include "camel-mime-message.h"
+#include "camel-mime-part.h"
+#include "camel-stream.h"
+#include "camel-stream-fs.h"
+#include "camel.h"
+#include "gmime-rfc2047.h"
+
+#define TERMINAL_CHARSET "UTF-8"
+
+/* 
+ * Info on many unicode issues, including, utf-8 xterms from :
+ * 
+ *   http://www.cl.cam.ac.uk/~mgk25/unicode.html
+ *
+ */
+
+const char *tests[] = 
+{ 
+  "�is is a test", "ISO-8859-1",
+  "I�t�r��ti�n�l��ation", "ISO-8859-1",
+  "Καλημέρα κόσμε", "UTF-8",
+  "コンニチハ", "UTF-8",
+  "ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn", "UTF-8",
+  NULL
+};
+  
+
+int
+main (int argc, char**argv)
+{      
+	const char **b = tests;
+	while (*b) {
+		char *e = gmime_rfc2047_encode(b[0], b[1]);
+		printf("%s\t%s\n", e, gmime_rfc2047_decode(e, TERMINAL_CHARSET));
+		b+=2;
+	}
+
+	return 0;
+
+}