Fix assertion checking external links; fix tests

doc/changelog.txt

@@ -2,13 +2,17 @@
 
 Features:
 - checking: Support parsing of sitemap and sitemap index XML files.
-- checking: Fix URL result caching.
 - logging: Support arbitrary encodings in CSV output.
   Closes: GH bug #467
 
+Changes:
+- checking: Ignored URLs are reported earlier now.
+
 Fixes:
 - checking: Fix internal errors in debug output.
   Closes: GH bug #472
+- checking: Fix URL result caching.
+- checking: Fix assertion in external link checking.
 
 
 9.0 "The Wolf of Wall Street" (released 3.3.2014)

linkcheck/checker/urlbase.py

@@ -118,6 +118,11 @@ class UrlBase (object):
         if recursion_level == 0:
             self.add_intern_pattern()
         self.set_extern(self.url)
+        if self.extern[0] and self.extern[1]:
+            self.add_info(_("The URL is outside of the domain "
+                          "filter, checked only syntax."))
+            if not self.has_result:
+                self.set_result(_("filtered"))
 
     def init (self, base_ref, base_url, parent_url, recursion_level,
               aggregate, line, column, name, url_encoding, extern):
@@ -594,11 +599,6 @@ class UrlBase (object):
             self.extern = (1, 0)
         else:
             self.extern = (1, 1)
-        if self.extern[0] and self.extern[1]:
-            self.add_info(_("The URL is outside of the domain "
-                          "filter, checked only syntax."))
-            if not self.has_result:
-                self.set_result(_("filtered"))
 
     def set_content_type (self):
         """Set content MIME type.

tests/checker/data/file.html.result

@@ -4,15 +4,15 @@ real url file://%(curdir)s/%(datadir)s/file.html
 name %(datadir)s/file.html
 valid
 
-url file.html
-cache key file://%(curdir)s/%(datadir)s/file.html
-real url file://%(curdir)s/%(datadir)s/file.html
-name relative url
-valid
-
 url javascript:loadthis()
 cache key javascript:loadthis()
 real url javascript:loadthis()
 name javascript url
 info Javascript URL ignored.
 valid
+
+url file.html
+cache key file://%(curdir)s/%(datadir)s/file.html
+real url file://%(curdir)s/%(datadir)s/file.html
+name relative url
+valid

tests/checker/data/file.php.result

@@ -4,10 +4,11 @@ real url file://%(curdir)s/%(datadir)s/file.php
 name %(datadir)s/file.php
 valid
 
-url anchor.html
-cache key file://%(curdir)s/%(datadir)s/anchor.html
-real url file://%(curdir)s/%(datadir)s/anchor.html
-name Bla
+url test_<?php echo $module ?>
+cache key file://%(curdir)s/%(datadir)s/test_%%3C?php%%20echo%%20%%24module%%20?%%3E
+real url file://%(curdir)s/%(datadir)s/test_%%3C?php%%20echo%%20%%24module%%20?%%3E
+name PHP 2
+info File URL ignored.
 valid
 
 url test_<? echo $module ?>
@@ -17,9 +18,8 @@ name PHP 1
 info File URL ignored.
 valid
 
-url test_<?php echo $module ?>
-cache key file://%(curdir)s/%(datadir)s/test_%%3C?php%%20echo%%20%%24module%%20?%%3E
-real url file://%(curdir)s/%(datadir)s/test_%%3C?php%%20echo%%20%%24module%%20?%%3E
-name PHP 2
-info File URL ignored.
+url anchor.html
+cache key file://%(curdir)s/%(datadir)s/anchor.html
+real url file://%(curdir)s/%(datadir)s/anchor.html
+name Bla
 valid

tests/checker/data/http.html.result

@@ -3,6 +3,12 @@ cache key http://localhost:%(port)d/%(datadir)s/http.html
 real url http://localhost:%(port)d/%(datadir)s/http.html
 valid
 
+url clsid:12345-67890
+cache key clsid:12345-67890
+real url clsid:12345-67890
+info Clsid URL ignored.
+valid
+
 url 
 cache key http://localhost:%(port)d/%(datadir)s/http.html
 real url http://localhost:%(port)d/%(datadir)s/http.html
@@ -64,12 +70,6 @@ real url http://localhost:%(port)d/tests/checker/data/file.txt
 name CSS urls
 valid
 
-url clsid:12345-67890
-cache key clsid:12345-67890
-real url clsid:12345-67890
-info Clsid URL ignored.
-valid
-
 url http://example.org/foo/ #a=1,2,3
 cache key http://example.org/foo/%%20
 real url http://example.org/foo/%%20#a%%3D1%%2C2%%2C3

tests/checker/data/misc.html.result

@@ -7,6 +7,7 @@ valid
 url 
 cache key None
 real url 
+info The URL is outside of the domain filter, checked only syntax.
 error
 
 url http://www.example.com/

tests/checker/data/urllist.txt.result

@@ -4,13 +4,13 @@ real url file://%(curdir)s/%(datadir)s/urllist.txt
 name %(datadir)s/urllist.txt
 valid
 
-url file.html
-cache key file://%(curdir)s/%(datadir)s/file.html
-real url file://%(curdir)s/%(datadir)s/file.html
-valid
-
 url javascript:loadthis()
 cache key javascript:loadthis()
 real url javascript:loadthis()
 info Javascript URL ignored.
 valid
+
+url file.html
+cache key file://%(curdir)s/%(datadir)s/file.html
+real url file://%(curdir)s/%(datadir)s/file.html
+valid

tests/checker/test_news.py

@@ -17,6 +17,7 @@
 """
 Test news checking.
 """
+import pytest
 from tests import need_newsserver, limit_time
 from . import LinkCheckTest
 
@@ -30,7 +31,8 @@ NNTP_INFO = u"200 news.uni-stuttgart.de InterNetNews NNRP server " \
 NNTP_TIMEOUT_SECS = 30
 
 # disabled for now until some stable news server comes up
-class _TestNews (LinkCheckTest):
+@pytest.mark.skipif("True")
+class TestNews (LinkCheckTest):
     """Test nntp: and news: link checking."""
 
     def newstest (self, url, resultlines):