From c5334fb68367708294fe3382979a190292893074 Mon Sep 17 00:00:00 2001
From: Jimmy <jimmy@spalge.com>
Date: Tue, 3 Apr 2018 20:29:31 +1200
Subject: [PATCH] Greasemonkey: use UrlPatterns for match directives

The greasemonkey `@match` directive is used to match urls against
chromium url patterns (as opposed to `@include` which treats its
argument as a glob expression). I was using fnmatch for both here
because I am lazy and knew someone else was going to implement chromium
url patterns for me eventually. Now it is done and I should switch to
using them instead. The most common failing case that this will fix is
something matching on `*://*.domain.com/*` because it wouldn't match
the url with no subdomain.

This codepath is only used on webengine 5.7.1 and webkit backends.
---
 qutebrowser/browser/greasemonkey.py        | 16 ++++++++++++----
 tests/unit/javascript/test_greasemonkey.py |  4 ++--
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/qutebrowser/browser/greasemonkey.py b/qutebrowser/browser/greasemonkey.py
index a43644bf6..55a2e7356 100644
--- a/qutebrowser/browser/greasemonkey.py
+++ b/qutebrowser/browser/greasemonkey.py
@@ -32,6 +32,7 @@ from PyQt5.QtCore import pyqtSignal, QObject, QUrl
 
 from qutebrowser.utils import (log, standarddir, jinja, objreg, utils,
                                javascript)
+from qutebrowser.utils.urlmatch import UrlPattern
 from qutebrowser.commands import cmdutils
 from qutebrowser.browser import downloads
 
@@ -48,6 +49,7 @@ class GreasemonkeyScript:
     def __init__(self, properties, code):
         self._code = code
         self.includes = []
+        self.matches = []
         self.excludes = []
         self.requires = []
         self.description = None
@@ -63,8 +65,10 @@ class GreasemonkeyScript:
                 self.namespace = value
             elif name == 'description':
                 self.description = value
-            elif name in ['include', 'match']:
+            elif name == 'include':
                 self.includes.append(value)
+            elif name == 'match':
+                self.matches.append(value)
             elif name in ['exclude', 'exclude_match']:
                 self.excludes.append(value)
             elif name == 'run-at':
@@ -92,7 +96,7 @@ class GreasemonkeyScript:
             props = ""
         script = cls(re.findall(cls.PROPS_REGEX, props), source)
         script.script_meta = props
-        if not script.includes:
+        if not script.includes and not script.matches:
             script.includes = ['*']
         return script
 
@@ -117,7 +121,7 @@ class GreasemonkeyScript:
         return json.dumps({
             'name': self.name,
             'description': self.description,
-            'matches': self.includes,
+            'matches': self.matches,
             'includes': self.includes,
             'excludes': self.excludes,
             'run-at': self.run_at,
@@ -324,8 +328,12 @@ class GreasemonkeyManager(QObject):
             # Otherwise they are glob expressions.
             return fnmatch.fnmatch(string_url, pattern)
 
+        def _chromium_match(pattern):
+            return UrlPattern(pattern).matches(url)
+
         tester = (lambda script:
-                  any(_match(pat) for pat in script.includes) and
+                  (any(_match(pat) for pat in script.includes) or
+                   any(_chromium_match(pat) for pat in script.matches)) and
                   not any(_match(pat) for pat in script.excludes))
 
         return MatchingScripts(
diff --git a/tests/unit/javascript/test_greasemonkey.py b/tests/unit/javascript/test_greasemonkey.py
index 7759f5d18..8701e8170 100644
--- a/tests/unit/javascript/test_greasemonkey.py
+++ b/tests/unit/javascript/test_greasemonkey.py
@@ -32,7 +32,7 @@ test_gm_script = r"""
 // @name qutebrowser test userscript
 // @namespace invalid.org
 // @include http://localhost:*/data/title.html
-// @match http://trolol*
+// @match http://*.trolol.com/*
 // @exclude https://badhost.xxx/*
 // @run-at document-start
 // ==/UserScript==
@@ -60,7 +60,7 @@ def test_all():
 
 @pytest.mark.parametrize("url, expected_matches", [
     # included
-    ('http://trololololololo.com/', 1),
+    ('http://trolol.com/', 1),
     # neither included nor excluded
     ('http://aaaaaaaaaa.com/', 0),
     # excluded