From 4c4b91d3e365f2db75433fd8059a94b7bfc966d6 Mon Sep 17 00:00:00 2001
From: henoheno <henoheno>
Date: Sun, 24 Jun 2007 00:21:32 +0900
Subject: [PATCH] whois_responsibility() related, and uri_pickup()

---
 spam/SpamTest.php | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 spam/spam.php     | 16 +++++++++----
 2 files changed, 79 insertions(+), 5 deletions(-)

diff --git a/spam/SpamTest.php b/spam/SpamTest.php
index 7acb360..20171a4 100644
--- a/spam/SpamTest.php
+++ b/spam/SpamTest.php
@@ -1,5 +1,5 @@
 <?php
-// $Id: SpamTest.php,v 1.16 2007/06/23 14:11:10 henoheno Exp $
+// $Id: SpamTest.php,v 1.17 2007/06/23 15:21:32 henoheno Exp $
 // Copyright (C) 2007 heno
 //
 // Design test case for spam.php (called from runner.php)
@@ -301,6 +301,36 @@ EOF;
 		$test_string = ' http://192.168.0.1/fobar.html ';
 		$results = uri_pickup_normalize(uri_pickup($test_string));
 		$this->assertEquals('192.168.0.1',    $results[0]['host']);
+
+		// Host: Starts
+		$test_string = ' http://_sss/foo.html ';
+		$results = uri_pickup_normalize(uri_pickup($test_string));
+		$this->assertEquals('_sss',           $results[0]['host']);
+		$this->assertEquals('foo.html',       $results[0]['file']);
+
+		// Host: Ends
+		$test_string = ' http://sss_/foo.html ';
+		$results = uri_pickup_normalize(uri_pickup($test_string));
+		$this->assertEquals('sss_',           $results[0]['host']);
+		$this->assertEquals('foo.html',       $results[0]['file']);
+
+
+		// Specific tests ---- Fails
+
+		// Divider: Colon only (Too sensitive to capture)
+		$test_string = ' http:colon.org ';
+		$results = uri_pickup_normalize(uri_pickup($test_string));
+		$this->assertEquals(0, count($results));
+
+		// Host: Too short
+		$test_string = ' http://s/foo.html http://ss/foo.html ';
+		$results = uri_pickup_normalize(uri_pickup($test_string));
+		$this->assertEquals(0, count($results));
+
+		$test_string = ' http://sss/foo.html ';
+		$results = uri_pickup_normalize(uri_pickup($test_string));
+		$this->assertEquals('sss',            $results[0]['host']);
+		$this->assertEquals('foo.html',       $results[0]['file']);
 	}
 
 	function testFunc_scheme_normalize()
@@ -586,6 +616,42 @@ EOF;
 		$array = get_blocklist('goodhost');
 		$this->assertTrue(isset($array['IANA-examples']));
 	}
+
+
+	function testFunc_whois_responsibility()
+	{
+		// 1st argument: Null
+		foreach($this->setup_string_null() as $key => $value){
+			$this->assertEquals('',        whois_responsibility($value), $key);
+		}
+
+		// 'act.edu.au' is known as 3rd level domain
+		$this->AssertEquals('bar.act.edu.au', whois_responsibility('foo.bar.act.edu.au'));
+		$this->AssertEquals('bar.act.edu.au', whois_responsibility('bar.act.edu.au'));
+		$this->AssertEquals('act.edu.au',  whois_responsibility('act.edu.au'));
+		$this->AssertEquals('edu.au',      whois_responsibility('edu.au'));
+		$this->AssertEquals('au',          whois_responsibility('au'));
+
+		// 'co.uk' is known as 2nd level domain
+		$this->AssertEquals('bar.co.uk',   whois_responsibility('foo.bar.co.uk'));
+		$this->AssertEquals('bar.co.uk',   whois_responsibility('bar.co.uk'));
+		$this->AssertEquals('co.uk',       whois_responsibility('co.uk'));
+		$this->AssertEquals('uk',          whois_responsibility('uk'));
+
+		// 'bar.uk' is not 2nd level (implicit responsibility)
+		$this->AssertEquals('bar.uk',      whois_responsibility('foo.bar.uk'));
+		$this->AssertEquals('bar.uk',      whois_responsibility('bar.uk'));
+
+		// IPv4
+		$this->AssertEquals('192.168.0.1', whois_responsibility('192.168.0.1'));
+
+		// Invalid Top-Level Domain (With implicit)
+		$this->AssertEquals('bar.local',  whois_responsibility('foo.bar.local'));	// Implicit responsibility
+		$this->AssertEquals('bar.local',  whois_responsibility('bar.local'));
+		$this->AssertEquals('local',      whois_responsibility('local'));
+		$this->AssertEquals('localhost',  whois_responsibility('localhost'));
+		$this->AssertEquals('s',          whois_responsibility('s'));
+	}
 }
 
 ?>
diff --git a/spam/spam.php b/spam/spam.php
index 3383326..ea35012 100644
--- a/spam/spam.php
+++ b/spam/spam.php
@@ -1,5 +1,5 @@
 <?php
-// $Id: spam.php,v 1.189 2007/06/23 14:11:10 henoheno Exp $
+// $Id: spam.php,v 1.190 2007/06/23 15:21:10 henoheno Exp $
 // Copyright (C) 2006-2007 PukiWiki Developers Team
 // License: GPL v2 or (at your option) any later version
 //
@@ -189,7 +189,7 @@ function uri_pickup($string = '')
 			// 3: Host
 			'\[[0-9a-f:.]+\]' . '|' .				// IPv6([colon-hex and dot]): RFC2732
 			'(?:[0-9]{1,3}\.){3}[0-9]{1,3}' . '|' .	// IPv4(dot-decimal): 001.22.3.44
-			'[a-z0-9][a-z0-9_.-]+[a-z0-9]' . 		// hostname(FQDN) : foo.example.org
+			'[a-z0-9_-][a-z0-9_.-]+[a-z0-9_-]' . 		// hostname(FQDN) : foo.example.org
 		')' .
 		'(?::([0-9]*))?' .					// 4: Port
 		'((?:/+[^\s<>"\'\[\]/\#]+)*/+)?' .	// 5: Directory path or path-info
@@ -1526,7 +1526,13 @@ function summarize_detail_newtral($progress = array())
 	foreach($progress['hosts'] as $value) {
 		// 'A.foo.bar.example.com'
 		$resp = whois_responsibility($value);	// 'example.com'
-		$rest = rtrim(substr($value, 0, - strlen($resp)), '.');	// 'A.foo.bar'
+		if (empty($resp)) {
+			// One or more test, or do nothing here
+			$resp = strval($value);
+			$rest = '';
+		} else {
+			$rest = rtrim(substr($value, 0, - strlen($resp)), '.');	// 'A.foo.bar'
+		}
 		$trie = array_merge_recursive($trie, array($resp => array($rest => NULL)));
 	}
 
@@ -2038,13 +2044,15 @@ function whois_responsibility($fqdn = 'foo.bar.example.com', $parent = FALSE, $i
 		),
 	);
 
-	if (is_ip($fqdn) || ! is_string($fqdn)) return $fqdn;
+	if (! is_string($fqdn)) return '';
+	if (is_ip($fqdn))       return $fqdn;
 
 	$result  = array();
 	$dcursor = & $domain;
 	$array   = array_reverse(explode('.', $fqdn));
 	$i = 0;
 	while(TRUE) {
+		if (! isset($array[$i])) break;
 		$acursor = $array[$i];
 		if (is_array($dcursor) && isset($dcursor[$acursor])) {
 			$result[] = & $array[$i];
-- 
2.11.0