InvalidLinkBear: Add ignore_regex setting

To ignore all urls that matches the regex

bears/general/InvalidLinkBear.py

@@ -33,18 +33,22 @@ def get_status_code(url, timeout):
             pass
 
     @staticmethod
-    def find_links_in_file(file, timeout):
+    def find_links_in_file(file, timeout, ignore_regex):
+        ignore_regex = re.compile(ignore_regex)
         regex = re.compile(
             r'((ftp|http)s?:\/\/\S+\.(?:[^\s\(\)\'\"\>\|]+|'
             r'\([^\s\(\)]*\))*)(?<!\.)(?<!\,)')
         for line_number, line in enumerate(file):
             match = regex.search(line)
             if match:
                 link = match.group()
-                code = InvalidLinkBear.get_status_code(link, timeout)
-                yield line_number + 1, link, code
+                if not ignore_regex.search(link):
+                    code = InvalidLinkBear.get_status_code(link, timeout)
+                    yield line_number + 1, link, code
 
-    def run(self, filename, file, timeout: int=DEFAULT_TIMEOUT):
+    def run(self, filename, file,
+            timeout: int=DEFAULT_TIMEOUT,
+            ignore_regex: str="[.\/]example\.com"):
         """
         Find links in any text file and check if they are valid.
 
@@ -53,10 +57,11 @@ def run(self, filename, file, timeout: int=DEFAULT_TIMEOUT):
         This bear can automatically fix redirects, but ignores redirect
         URLs that have a huge difference with the original URL.
 
-        :param timeout: Request timeout period.
+        :param timeout:      Request timeout period.
+        :param ignore_regex: A regex for urls to ignore.
         """
         for line_number, link, code in InvalidLinkBear.find_links_in_file(
-                file, timeout):
+                file, timeout, ignore_regex):
             if code is None:
                 yield Result.from_values(
                     origin=self,

tests/general/InvalidLinkBearTest.py

@@ -5,6 +5,7 @@
 
 from bears.general.InvalidLinkBear import InvalidLinkBear
 from coalib.settings.Section import Section
+from coalib.settings.Setting import Setting
 
 
 def custom_matcher(request):
@@ -38,10 +39,12 @@ class InvalidLinkBearTest(unittest.TestCase):
     def setUp(self):
         self.section = Section("")
 
-    def assertResult(self, valid_file=None, invalid_file=None):
+    def assertResult(self, valid_file=None, invalid_file=None, settings={}):
         with requests_mock.Mocker() as m:
             InvalidLinkBear.check_prerequisites = lambda *args: True
             uut = InvalidLinkBear(self.section, Queue())
+            for name, value in settings.items():
+                self.section.append(Setting(name, value))
             m.add_matcher(custom_matcher)
             if valid_file:
                 out = uut.execute("valid", valid_file)
@@ -141,3 +144,29 @@ def test_redirect_threshold(self):
 
         self.assertResult(valid_file=long_url_redirect,
                           invalid_file=short_url_redirect)
+
+    def test_ignore_regex(self):
+
+        ignored_URLs = """
+        http://sub.example.com
+        http://sub.example.com/something
+        """.splitlines()
+
+        not_ignored_URLs = """
+        http://www.notexample.com
+        http://exampe.com
+        http://example.co.in
+        """.splitlines()
+
+        self.assertResult(valid_file=ignored_URLs,
+                          invalid_file=not_ignored_URLs)
+
+        valid_file = """
+        http://httpbin.org/status/524
+        """.splitlines()
+        invalid_file = """
+        http://httpbin.org/status/503
+        """.splitlines()
+        self.assertResult(valid_file=valid_file,
+                          invalid_file=invalid_file,
+                          settings={'ignore_regex': '[1-9]{2}$'})