Implementation of a Matching strategy for URLs in the Declarative WebRequest API.

chrome/browser/extensions/api/declarative/url_component_patterns_unittest.cc

+// Copyright (c) 2012 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "chrome/browser/extensions/api/declarative/url_component_patterns.h"
+
+#include <set>
+#include <string>
+#include <vector>
+
+#include "base/string_util.h"
+#include "googleurl/src/gurl.h"
+#include "testing/gtest/include/gtest/gtest.h"
+
+using namespace extensions;
+
+namespace {
+
+bool Matches(const SubstringPattern& pattern, std::string text) {
+  return text.find(pattern.pattern()) != std::string::npos;
+}
+
+}  // namespace
+
+TEST(UrlComponentPatternsTest, GURLCharacterSet) {
+  // GURL guarantees that neither domain, nor path, nor query may contain
+  // non ASCII-7 characters. We test this here, because a change to this
+  // guarantee breaks this implementation horribly.
+  GURL url("http://www.föö.com/föö?föö#föö");
+  EXPECT_TRUE(IsStringASCII(url.host()));
+  EXPECT_TRUE(IsStringASCII(url.path()));
+  EXPECT_TRUE(IsStringASCII(url.query()));
+  EXPECT_FALSE(IsStringASCII(url.ref()));
+}
+
+// Basic tests of SubstringPattern objects
+TEST(UrlComponentPatternsTest, TestSingletonProperty) {
+  UrlComponentPatterns matcher;
+  SubstringPattern p1 = matcher.CreateHostEqualsPattern("www.google.com");
+  SubstringPattern p2 = matcher.CreateHostEqualsPattern("www.google.com");
+  EXPECT_EQ(p1, p2);
+  SubstringPattern p3 = matcher.CreateHostEqualsPattern("www.google.de");
+  EXPECT_NE(p2.id(), p3.id());
+  EXPECT_NE(p2.pattern(), p3.pattern());
+}
+
+TEST(UrlComponentPatternsTest, TestComponentSearches) {
+  GURL gurl("https://www.google.com/webhp?sourceid=chrome-instant&ie=UTF-8"
+      "&ion=1#hl=en&output=search&sclient=psy-ab&q=chrome%20is%20awesome");
+  UrlComponentPatterns matcher;
+  std::string url = matcher.CanonlicalizeURLForComponentSearches(gurl);
+
+  // Test host component.
+  EXPECT_TRUE(Matches(matcher.CreateHostPrefixPattern(""), url));

[Matt Perry, 2012/02/14 01:38:34]

nit: take a look at EXPECT_PRED2, which I believe will output the parameters in
the event of a failure. Example:
http://code.google.com/codesearch#OAMlx_jo-ck/src/ui/base/clipboard/clipboard...

[battre, 2012/02/14 19:32:21]

It does, but:
- It is one character longer per line.
- There is no equivalent to EXPECT_FALSE.
- It requires a std::basic_ostream::operator<<(const SubstringPattern*)

I am not sure whether this change would be a net win.

+  EXPECT_TRUE(Matches(matcher.CreateHostPrefixPattern("www.goog"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostPrefixPattern("www.google.com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostPrefixPattern(".www.google.com"), url));
+  EXPECT_FALSE(
+      Matches(matcher.CreateHostPrefixPattern("www.google.com/"), url));
+  EXPECT_FALSE(Matches(matcher.CreateHostPrefixPattern("webhp"), url));

[Matt Perry, 2012/02/14 01:38:34]

Test that "google.com" does not match. In general, you could use more tests that
verify the URL component markers are being respected (e.g. below,
host_suffix("www") and path_prefix("webhp") do not match).

[battre, 2012/02/14 19:32:21]

Done.

+
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPattern("com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPattern(".com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPattern("www.google.com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPattern(".www.google.com"), url));
+  EXPECT_FALSE(
+      Matches(matcher.CreateHostSuffixPattern("www.google.com/"), url));
+  EXPECT_FALSE(Matches(matcher.CreateHostSuffixPattern("webhp"), url));
+
+  EXPECT_FALSE(Matches(matcher.CreateHostEqualsPattern(""), url));
+  EXPECT_FALSE(Matches(matcher.CreateHostEqualsPattern("www"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostEqualsPattern("www.google.com"), url));
+  EXPECT_FALSE(
+      Matches(matcher.CreateHostEqualsPattern("www.google.com/"), url));
+
+
+  // Test path component.
+  EXPECT_TRUE(Matches(matcher.CreatePathPrefixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreatePathPrefixPattern("/web"), url));
+  EXPECT_TRUE(Matches(matcher.CreatePathPrefixPattern("/webhp"), url));
+  EXPECT_FALSE(Matches(matcher.CreatePathPrefixPattern("/webhp?"), url));
+
+  EXPECT_TRUE(Matches(matcher.CreatePathSuffixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreatePathSuffixPattern("webhp"), url));
+  EXPECT_TRUE(Matches(matcher.CreatePathSuffixPattern("/webhp"), url));
+  EXPECT_FALSE(Matches(matcher.CreatePathSuffixPattern("/webhp?"), url));
+
+  EXPECT_TRUE(Matches(matcher.CreatePathEqualsPattern("/webhp"), url));
+  EXPECT_FALSE(Matches(matcher.CreatePathEqualsPattern("/webhp?"), url));
+  EXPECT_FALSE(Matches(matcher.CreatePathEqualsPattern("www.google.com"), url));
+
+
+  // Test query component.
+  EXPECT_TRUE(Matches(matcher.CreateQueryPrefixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateQueryPrefixPattern("?sourceid"), url));
+  EXPECT_FALSE(Matches(matcher.CreatePathPrefixPattern("sourceid"), url));
+
+  EXPECT_TRUE(Matches(matcher.CreateQuerySuffixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateQuerySuffixPattern("ion=1"), url));
+  EXPECT_FALSE(Matches(matcher.CreateQuerySuffixPattern("www"), url));
+
+  EXPECT_TRUE(Matches(matcher.CreateQueryEqualsPattern(
+      "?sourceid=chrome-instant&ie=UTF-8&ion=1"), url));
+  EXPECT_FALSE(
+      Matches(matcher.CreateQueryEqualsPattern("www.google.com"), url));
+
+
+  // Test adjacent components
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPathPrefixPattern(
+      "google.com", "/webhp"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPathPrefixPattern(
+        "", "/webhp"), url));
+  EXPECT_TRUE(Matches(matcher.CreateHostSuffixPathPrefixPattern(
+        "google.com", ""), url));
+  EXPECT_FALSE(Matches(matcher.CreateHostSuffixPathPrefixPattern(
+        "www", ""), url));
+}
+
+TEST(UrlComponentPatternsTest, TestFullSearches) {
+  GURL gurl("https://www.google.com/webhp?sourceid=chrome-instant&ie=UTF-8"
+      "&ion=1#hl=en&output=search&sclient=psy-ab&q=chrome%20is%20awesome");
+  UrlComponentPatterns matcher;
+  std::string url = matcher.CanonlicalizeURLForFullSearches(gurl);
+
+  EXPECT_TRUE(Matches(matcher.CreateURLPrefixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLPrefixPattern("www.goog"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLPrefixPattern("www.google.com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLPrefixPattern(".www.google.com"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLPrefixPattern("www.google.com/"), url));
+  EXPECT_FALSE(Matches(matcher.CreateHostPrefixPattern("webhp"), url));

[Matt Perry, 2012/02/14 01:38:34]

did you mean CreateURLPrefixPattern?

[battre, 2012/02/14 19:32:21]

Done.

+
+  EXPECT_TRUE(Matches(matcher.CreateURLSuffixPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLSuffixPattern("ion=1"), url));
+  EXPECT_FALSE(Matches(matcher.CreateURLSuffixPattern("www"), url));
+
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern(""), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern("www.goog"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern(".www.goog"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern("webhp"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern("?"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern("sourceid"), url));
+  EXPECT_TRUE(Matches(matcher.CreateURLContainsPattern("ion=1"), url));
+  EXPECT_FALSE(Matches(matcher.CreateURLSuffixPattern("foobar"), url));

[Matt Perry, 2012/02/14 01:38:34]

also test that url_contains("search") does not match (to verify #ref part is
stripped).

[battre, 2012/02/14 19:32:21]

Done.

+
+  EXPECT_TRUE(Matches(matcher.CreateURLEqualsPattern(
+      "www.google.com/webhp?sourceid=chrome-instant&ie=UTF-8&ion=1"), url));
+  EXPECT_FALSE(Matches(matcher.CreateURLEqualsPattern("www.google.com"), url));
+
+}