Added LinkExtractor.matches test and fixed bug in that same method

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40457

scrapy/trunk/scrapy/link/extractors.py

@@ -78,6 +78,6 @@ class RegexLinkExtractor(LinkExtractor):
         if self.deny_domains and url_is_from_any_domain(url, self.deny_domains):
             return False
             
-        allowed = [regex.search(url) for regex in self.allow_res]
-        denied = [regex.search(url) for regex in self.deny_res]
-        return any(allowed) and not any(denied)
+        allowed = [regex.search(url) for regex in self.allow_res] if self.allow_res else [True]
+        denied = [regex.search(url) for regex in self.deny_res] if self.deny_res else []
+        return True if any(allowed) and not any(denied) else False

scrapy/trunk/scrapy/tests/test_link.py

@@ -2,6 +2,7 @@ import unittest
 
 from scrapy.http import Response
 from scrapy.link import LinkExtractor, Link
+from scrapy.link.extractors import RegexLinkExtractor
 
 class LinkExtractorTestCase(unittest.TestCase):
     def test_basic(self):
@@ -31,5 +32,36 @@ class LinkExtractorTestCase(unittest.TestCase):
         self.assertEqual(lx.extract_urls(response), 
                          [Link(url='http://otherdomain.com/base/item/12.html', text='Item 12')])
 
+    def test_matches(self):
+        url1 = 'http://lotsofstuff.com/stuff1/index'
+        url2 = 'http://evenmorestuff.com/uglystuff/index'
+
+        lx = LinkExtractor()
+        self.assertEqual(lx.matches(url1), True)
+        self.assertEqual(lx.matches(url2), True)
+
+        lx = RegexLinkExtractor(allow=(r'stuff1', ))
+        self.assertEqual(lx.matches(url1), True)
+        self.assertEqual(lx.matches(url2), False)
+
+        lx = RegexLinkExtractor(deny=(r'uglystuff', ))
+        self.assertEqual(lx.matches(url1), True)
+        self.assertEqual(lx.matches(url2), False)
+
+        lx = RegexLinkExtractor(allow_domains=('evenmorestuff.com', ))
+        self.assertEqual(lx.matches(url1), False)
+        self.assertEqual(lx.matches(url2), True)
+
+        lx = RegexLinkExtractor(deny_domains=('lotsofstuff.com', ))
+        self.assertEqual(lx.matches(url1), False)
+        self.assertEqual(lx.matches(url2), True)
+
+        lx = RegexLinkExtractor(allow=('blah1', ), deny=('blah2', ),
+            allow_domains=('blah1.com', ), deny_domains=('blah2.com', ))
+        self.assertEqual(lx.matches('http://blah1.com/blah1'), True)
+        self.assertEqual(lx.matches('http://blah1.com/blah2'), False)
+        self.assertEqual(lx.matches('http://blah2.com/blah1'), False)
+        self.assertEqual(lx.matches('http://blah2.com/blah2'), False)
+
 if __name__ == "__main__":
     unittest.main()