* Fix url parser (get regexp from our mail system)

* Add some more tests to url testcase

2 files changed, 62 insertions, 14 deletions

diff --git a/test/rspamd_test_suite.c b/test/rspamd_test_suite.c
index d9d7f63fe..7b699f40b 100644
--- a/test/rspamd_test_suite.c
+++ b/test/rspamd_test_suite.c
@@ -16,10 +16,13 @@
 int
 main (int argc, char **argv)
 {
+	g_mem_set_vtable(glib_mem_profiler_table);
+
 	g_test_init (&argc, &argv, NULL);
 
 	g_test_add_func ("/rspamd/url", rspamd_url_test_func);
 
 	g_test_run ();
-
+	
+	g_mem_profile ();
 }
diff --git a/test/rspamd_url_test.c b/test/rspamd_url_test.c
index 5a4d9e5ba..0db5084bf 100644
--- a/test/rspamd_url_test.c
+++ b/test/rspamd_url_test.c
@@ -17,8 +17,54 @@
 #include "../url.h"
 #include "tests.h"
 
-const char *test_text = "This is test file with http://TesT%45.com/././ url";
-const char *test_html = "<some_tag>This is test file with <a href=\"http://microsoft.com\">http://TesT%45.com/././ url</a></some_tag>";
+const char *test_text =
+"www.schemeless.ru\n"
+"www.schemeless.rus\n"
+" as ftp.schemeless.ru dasd \n"
+"ftp12.schemeless.ru\n"
+"ftpsearch.schemeless.ru\n"
+"schemeless.ru\n"
+"www.schemeless.microsoft\n"
+"1.2.3.4\n"
+"1.2.3.4/a\n"
+"1.2.3\n"
+"1.2.3.4.5\n"
+"www.schemeless.ru,\n"
+"www.schemeless.ru.\n"
+"http://www.schemed.ru.\n"
+"http://www.schemed.ru.\n"
+"http://www.bolinfest.com/targetalert/'\n"
+"http://www.bolinfest.com/targetalert/'';\n"
+"https://www.schemed.ru.\n"
+"ufps://www.schemed.ru.\n"
+"http://ported.ru:8080\n"
+"http://ported.ru:8080\n"
+"http://1.2.3.4\n"
+"http://1.2.3.4:80\n"
+"1.2.3.4:80\n"
+"www.a9.com\n"
+"www.a-9.com\n"
+"http://www.schemed.ru/a.txt:\n"
+"http://www.schemed.ru/a.txt'\n"
+"http://www.schemed.ru/a.txt\"\n"
+"http://www.schemed.ru/a.txt>\n"
+"http://www.schemed.ru/a=3&b=4\n"
+"http://spam.ru/bad=user@domain.com\n"
+"http://spam.ru/bad=user@domain.com\n"
+"http://spam.ru user@domain.com\n"
+"http://a.foto.radikal.ru/0604/de7793c6ca62.jpg\n"
+"http://a.foto.radikal.ru/0604/de7793c6ca62.jpg\n"
+"schemeless.gz\n"
+"schemeless.jp\n"
+"schemeless.ua\n"
+"schemeless.gz/a\n"
+"mysql.so\n"
+"http://mysql.so\n"
+"3com.com\n"
+"lj-user.livejournal.com\n"
+"http://lj-user.livejournal.com\n"
+"http://vsem.ru?action;\n";
+const char *test_html = "<some_tag>This is test file with <a href=\"http://microsoft.com\">http://TesT.com/././?%45%46%20 url</a></some_tag>";
 
 /* Function for using in glib test suite */
 void
@@ -39,12 +85,12 @@ rspamd_url_test_func ()
 	TAILQ_INIT (&task.urls);
 	
 	g_test_timer_start ();
-	g_test_message ("* Testing text URL regexp parser *");
-	g_test_message ("Passing string: %s", test_text);
+	g_test_message ("Testing text URL regexp parser");
+	msg_debug ("Passing string: %s", test_text);
 	url_parse_text (&task, text);
 
 	TAILQ_FOREACH (url, &task.urls, next) {
-		g_test_message ("Found url: %s, hostname: %s, data: %s", struri (url), url->host, url->data);
+		msg_debug ("Found url: %s, hostname: %s, data: %s", struri (url), url->host, url->data);
 		i ++;
 	}
 
@@ -54,18 +100,17 @@ rspamd_url_test_func ()
 		g_free (url->string);
 		g_free (url);
 	}
-	g_assert (i == 1);
-
-	g_test_message ("Time elapsed: %.2f", g_test_timer_elapsed ());
+	g_assert (i == 39);
 
+	msg_debug ("Time elapsed: %.2f", g_test_timer_elapsed ());
 	i = 0;
 	g_test_timer_start ();
-	g_test_message ("* Testing html URL regexp parser *");
-	g_test_message ("Passing string: %s", test_html);
+	g_test_message ("Testing html URL regexp parser");
+	msg_debug ("Passing string: %s", test_html);
 	url_parse_html (&task, html);
 
 	TAILQ_FOREACH (url, &task.urls, next) {
-		g_test_message ("Found url: %s, hostname: %s, data: %s", struri (url), url->host, url->data);
+		msg_debug ("Found url: %s, hostname: %s, data: %s", struri (url), url->host, url->data);
 		i ++;
 	}
 
@@ -75,6 +120,6 @@ rspamd_url_test_func ()
 		g_free (url->string);
 		g_free (url);
 	}
-	g_assert (i == 2);
-	g_test_message ("Time elapsed: %.2f", g_test_timer_elapsed ());
+	g_assert (i == 1);
+	msg_debug ("Time elapsed: %.2f", g_test_timer_elapsed ());
 }