Issue 5141 - [emscripten] Convert filter matcher to C++

test/matcher.js

Index: test/matcher.js
===================================================================
new file mode 100644
--- /dev/null
+++ b/test/matcher.js
@@ -0,0 +1,160 @@
+/*
+ * This file is part of Adblock Plus <https://adblockplus.org/>,
+ * Copyright (C) 2006-present eyeo GmbH
+ *
+ * Adblock Plus is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 3 as
+ * published by the Free Software Foundation.
+ *
+ * Adblock Plus is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+"use strict";

[Wladimir Palant, 2017/10/17 12:51:22]

This test has been taken from the master branch and adapted slightly:

* Testing internals (keywords and caching) has been removed.
* checkMatch() function has been adapted to API changes and rewritten somewhat
to be more concise.
* Some of the tests had multiple potentially matching filters and relied on
internals to determine which one will actually match. These internals are no
longer valid, the matching filter depends in particular on the blacklisting vs.
whitelisting scenario. So I had to adjust these tests to remove the ambiguity.

+
+const {createSandbox} = require("./_common");
+
+let Filter = null;
+let RegExpFilter = null;
+let Matcher = null;
+let defaultMatcher = null;
+
+exports.setUp = function(callback)
+{
+  let sandboxedRequire = createSandbox();
+  (
+    {Filter, RegExpFilter} = sandboxedRequire("../lib/filterClasses"),
+    {defaultMatcher, Matcher} = sandboxedRequire("../lib/matcher")

[sergei, 2017/10/18 10:58:44]

What about deletion of defaultMatcher in tearDown?

+  );
+
+  callback();
+};
+
+function checkMatch(test, filters, location, contentType, docDomain, thirdParty, sitekey, specificOnly, expected)
+{
+  for (let prefix of ["", "@@"])
+  {
+    // Generic whitelisting rules can match for specificOnly searches, so we
+    // can't easily know which rule will match for these whitelisting tests
+    if (prefix == "@@" && specificOnly)
+      continue;
+
+    let matcher = Matcher.create();

[sergei, 2017/10/18 10:58:43]

matcher is not deleted.

+    let actualFilters = [];
+    for (let text of filters)
+    {
+      if (prefix && !text.startsWith(prefix))
+        text = prefix + text;
+      actualFilters.push(text);
+
+      let filter = Filter.fromText(text);
+      matcher.add(filter);
+      filter.delete();
+    }
+
+    let result = matcher.matchesAny(location, RegExpFilter.typeMap[contentType], docDomain, thirdParty, sitekey, specificOnly);
+    if (result)
+    {
+      let tmp = result.text;
+      result.delete();
+      result = tmp;
+    }
+
+    let actualExpected = expected;
+    if (actualExpected && prefix && !expected.startsWith(prefix))
+      actualExpected = prefix + actualExpected;
+    test.equal(result, actualExpected,
+        `match(${location}, ${contentType}, ${docDomain},
+        ${thirdParty ? "third-party" : "first-party"},
+        ${sitekey || "no-sitekey"},
+        ${specificOnly ? "specificOnly" : "not-specificOnly"})
+        with: ${actualFilters.join(" ")}`.replace(/\s+/g, " "));
+  }
+}
+
+exports.testMatcherClassDefinitions = function(test)
+{
+  test.equal(typeof Matcher, "function", "typeof Matcher");
+  test.equal(typeof defaultMatcher, "object", "typeof defaultMatcher");
+  test.ok(defaultMatcher instanceof Matcher, "defaultMatcher is a Matcher instance");
+
+  test.done();
+};
+
+exports.testFilterMatching = function(test)
+{
+  checkMatch(test, [], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["abc"], "http://abc/def", "IMAGE", null, false, null, false, "abc");
+  checkMatch(test, ["abc", "ddd"], "http://abc/def", "IMAGE", null, false, null, false, "abc");
+  checkMatch(test, ["ddd", "abc"], "http://abc/def", "IMAGE", null, false, null, false, "abc");
+  checkMatch(test, ["ddd", "abd"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["://abc/d"], "http://abc/def", "IMAGE", null, false, null, false, "://abc/d");
+  checkMatch(test, ["|http://"], "http://abc/def", "IMAGE", null, false, null, false, "|http://");
+  checkMatch(test, ["|http://abc"], "http://abc/def", "IMAGE", null, false, null, false, "|http://abc");
+  checkMatch(test, ["|abc"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["|/abc/def"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["/def|"], "http://abc/def", "IMAGE", null, false, null, false, "/def|");
+  checkMatch(test, ["/abc/def|"], "http://abc/def", "IMAGE", null, false, null, false, "/abc/def|");
+  checkMatch(test, ["/abc/|"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["http://abc/|"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["|http://abc/def|"], "http://abc/def", "IMAGE", null, false, null, false, "|http://abc/def|");
+  checkMatch(test, ["|/abc/def|"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["|http://abc/|"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["|/abc/|"], "http://abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["||example.com/abc"], "http://example.com/abc/def", "IMAGE", null, false, null, false, "||example.com/abc");
+  checkMatch(test, ["||com/abc/def"], "http://example.com/abc/def", "IMAGE", null, false, null, false, "||com/abc/def");
+  checkMatch(test, ["||com/abc"], "http://example.com/abc/def", "IMAGE", null, false, null, false, "||com/abc");
+  checkMatch(test, ["||mple.com/abc"], "http://example.com/abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["||.com/abc/def"], "http://example.com/abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["||http://example.com/"], "http://example.com/abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["||example.com/abc/def|"], "http://example.com/abc/def", "IMAGE", null, false, null, false, "||example.com/abc/def|");
+  checkMatch(test, ["||com/abc/def|"], "http://example.com/abc/def", "IMAGE", null, false, null, false, "||com/abc/def|");
+  checkMatch(test, ["||example.com/abc|"], "http://example.com/abc/def", "IMAGE", null, false, null, false, null);
+  checkMatch(test, ["://abc/d", "asdf1234"], "http://abc/def", "IMAGE", null, false, null, false, "://abc/d");
+  checkMatch(test, ["foo*://abc/d", "foo*//abc/de", "://abc/de", "asdf1234"], "http://abc/def", "IMAGE", null, false, null, false, "://abc/de");
+  checkMatch(test, ["abc$third-party", "abc$~third-party", "ddd"], "http://abc/def", "IMAGE", null, false, null, false, "abc$~third-party");
+  checkMatch(test, ["abc$third-party", "abc$~third-party", "ddd"], "http://abc/def", "IMAGE", null, true, null, false, "abc$third-party");
+  checkMatch(test, ["//abc/def$third-party", "//abc/def$~third-party", "//abc_def"], "http://abc/def", "IMAGE", null, false, null, false, "//abc/def$~third-party");
+  checkMatch(test, ["//abc/def$third-party", "//abc/def$~third-party", "//abc_def"], "http://abc/def", "IMAGE", null, true, null, false, "//abc/def$third-party");
+  checkMatch(test, ["abc$~third-party", "//abc/def"], "http://abc/def", "IMAGE", null, true, null, false, "//abc/def");
+  checkMatch(test, ["abc$~third-party", "//abc/def$third-party"], "http://abc/def", "IMAGE", null, true, null, false, "//abc/def$third-party");
+  checkMatch(test, ["abc$third-party", "abc$~third-party", "//abc/def$third-party"], "http://abc/def", "IMAGE", null, false, null, false, "abc$~third-party");
+  checkMatch(test, ["abc$third-party", "abc$~third-party", "//abc/def$~third-party"], "http://abc/def", "IMAGE", null, true, null, false, "abc$third-party");
+  checkMatch(test, ["abc$image", "abc$script", "abc$~image"], "http://abc/def", "IMAGE", null, false, null, false, "abc$image");
+  checkMatch(test, ["abc$image", "abc$script", "abc$~script"], "http://abc/def", "SCRIPT", null, false, null, false, "abc$script");
+  checkMatch(test, ["abc$image", "abc$script", "abc$~image"], "http://abc/def", "OTHER", null, false, null, false, "abc$~image");
+  checkMatch(test, ["//abc/def$image", "//abc/def$script", "//abc/def$~image"], "http://abc/def", "IMAGE", null, false, null, false, "//abc/def$image");
+  checkMatch(test, ["//abc/def$image", "//abc/def$script", "//abc/def$~script"], "http://abc/def", "SCRIPT", null, false, null, false, "//abc/def$script");
+  checkMatch(test, ["//abc/def$image", "//abc/def$script", "//abc/def$~image"], "http://abc/def", "OTHER", null, false, null, false, "//abc/def$~image");
+  checkMatch(test, ["abc$~image", "//abc/def"], "http://abc/def", "IMAGE", null, false, null, false, "//abc/def");
+  checkMatch(test, ["abc$~image", "//abc/def$image"], "http://abc/def", "IMAGE", null, false, null, false, "//abc/def$image");
+  checkMatch(test, ["abc$image", "abc$~image", "//abc/def$script"], "http://abc/def", "IMAGE", null, false, null, false, "abc$image");
+  checkMatch(test, ["abc$domain=foo.com", "abc$domain=bar.com", "abc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "foo.com", false, null, false, "abc$domain=foo.com");

[Wladimir Palant, 2017/10/17 12:51:22]

This test and a few similar ones are currently failing. I still need to
investigate this, the failure might be caused by code not touched here.

[sergei, 2017/11/20 16:30:49]

I think it is because of mutable docDomain. docDomain is passed by reference and
when it checks whether the data matches the second filter its value gets "com",
so when it reaches the third filter it matches too. I think Hubert meant or
observed the same in
https://codereview.adblockplus.org/29594607/diff/29594608/compiled/ElemHideEm....

I would propose to consider passing of DependentString by value, though bindings
generator should be aware about it.

PS: I have to say that debugging is not trivial at all, we should discuss it
separately.

+  checkMatch(test, ["abc$domain=foo.com", "abc$domain=bar.com", "abc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "bar.com", false, null, false, "abc$domain=bar.com");
+  checkMatch(test, ["abc$domain=foo.com", "abc$domain=bar.com", "abc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "baz.com", false, null, false, "abc$domain=~foo.com|~bar.com");
+  checkMatch(test, ["abc$domain=foo.com", "cba$domain=bar.com", "ccc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "foo.com", false, null, false, "abc$domain=foo.com");
+  checkMatch(test, ["abc$domain=foo.com", "cba$domain=bar.com", "ccc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "bar.com", false, null, false, null);
+  checkMatch(test, ["abc$domain=foo.com", "cba$domain=bar.com", "ccc$domain=~foo.com|~bar.com"], "http://abc/def", "IMAGE", "baz.com", false, null, false, null);
+  checkMatch(test, ["abc$domain=foo.com", "cba$domain=bar.com", "ccc$domain=~foo.com|~bar.com"], "http://ccc/def", "IMAGE", "baz.com", false, null, false, "ccc$domain=~foo.com|~bar.com");
+  checkMatch(test, ["abc$sitekey=foo-publickey", "abc$sitekey=bar-publickey"], "http://abc/def", "IMAGE", "foo.com", false, "foo-publickey", false, "abc$sitekey=foo-publickey");
+  checkMatch(test, ["abc$sitekey=foo-publickey", "abc$sitekey=bar-publickey"], "http://abc/def", "IMAGE", "bar.com", false, "bar-publickey", false, "abc$sitekey=bar-publickey");
+  checkMatch(test, ["abc$sitekey=foo-publickey", "cba$sitekey=bar-publickey"], "http://abc/def", "IMAGE", "bar.com", false, "bar-publickey", false, null);
+  checkMatch(test, ["abc$sitekey=foo-publickey", "cba$sitekey=bar-publickey"], "http://abc/def", "IMAGE", "baz.com", false, null, false, null);
+  checkMatch(test, ["abc$sitekey=foo-publickey,domain=foo.com", "abc$sitekey=bar-publickey,domain=bar.com"], "http://abc/def", "IMAGE", "foo.com", false, "foo-publickey", false, "abc$sitekey=foo-publickey,domain=foo.com");
+  checkMatch(test, ["abc$sitekey=foo-publickey,domain=foo.com", "abc$sitekey=bar-publickey,domain=bar.com"], "http://abc/def", "IMAGE", "foo.com", false, "bar-publickey", false, null);
+  checkMatch(test, ["abc$sitekey=foo-publickey,domain=foo.com", "abc$sitekey=bar-publickey,domain=bar.com"], "http://abc/def", "IMAGE", "bar.com", false, "foo-publickey", false, null);
+  checkMatch(test, ["abc$sitekey=foo-publickey,domain=foo.com", "abc$sitekey=bar-publickey,domain=bar.com"], "http://abc/def", "IMAGE", "bar.com", false, "bar-publickey", false, "abc$sitekey=bar-publickey,domain=bar.com");
+  checkMatch(test, ["@@foo.com$generichide"], "http://foo.com/bar", "GENERICHIDE", "foo.com", false, null, false, "@@foo.com$generichide");
+  checkMatch(test, ["@@foo.com$genericblock"], "http://foo.com/bar", "GENERICBLOCK", "foo.com", false, null, false, "@@foo.com$genericblock");
+  checkMatch(test, ["@@bar.com$generichide"], "http://foo.com/bar", "GENERICHIDE", "foo.com", false, null, false, null);
+  checkMatch(test, ["@@bar.com$genericblock"], "http://foo.com/bar", "GENERICBLOCK", "foo.com", false, null, false, null);
+  checkMatch(test, ["/bar"], "http://foo.com/bar", "IMAGE", "foo.com", false, null, true, null);
+  checkMatch(test, ["/bar$domain=foo.com"], "http://foo.com/bar", "IMAGE", "foo.com", false, null, true, "/bar$domain=foo.com");
+
+  test.done();
+};